Ship mooring drift state prediction method, device, terminal and storage medium

Abstract

The present invention is applicable to the field of mooring data prediction technology and provides a method, device, terminal, and storage medium for predicting the mooring drift state of a ship. The method comprises: obtaining ship size data and historical mooring data, including historical data on the ship's movement distance and movement angle, for each ship moored at a dock, and obtaining historical environmental data affecting the safety of the ship's mooring during the same period; training a ship mooring drift prediction model using the ship size data and historical environmental data as input and the historical mooring data as output; obtaining predicted movement distance data and predicted movement angle data of the target ship during the prediction period based on the ship mooring drift prediction model; and determining whether the mooring drift state of the target ship is safe based on the predicted movement distance data and the predicted movement angle data. The present invention can comprehensively evaluate the drift motion of a moored ship from two aspects, namely, movement distance and movement angle, to accurately provide mooring safety warnings under various working conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of mooring data prediction, and in particular to a method, device, terminal and storage medium for predicting the mooring drift state of a ship. Background Art

[0002] Ship mooring refers to the process of anchoring a vessel at a dock or berth, secured to shore or buoys by cables. Large vessels can drift offshore due to external influences such as wind, waves, and currents during mooring operations. In extreme cases, this can cause cable breakage, instantly threatening the lives of nearby workers. This breakage can also affect the stability of the mooring, potentially causing the vessel to drift from its berth, collide with dock facilities, or collide with surrounding vessels. Therefore, predicting ship mooring drift is crucial for safe harbor operations.

[0003] However, the inventors discovered that current methods for predicting mooring drift typically rely on the relative distance between the ship and the dock or the mooring force. However, in some cases, this approach fails to accurately provide mooring safety warnings. For example, in some operating conditions, even if the relative distance between the ship and the dock does not reach the warning threshold, the mooring line may break, compromising mooring safety. Summary of the Invention

[0004] The embodiments of the present invention provide a method, device, terminal and storage medium for predicting the mooring drift state of a ship, so as to solve the problem that the current method for predicting the mooring drift state of a ship cannot accurately provide a mooring safety warning.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting a ship mooring drift state, comprising:

[0006] Obtaining ship size data and historical mooring data of each ship moored at the pier, and obtaining historical environmental data affecting ship mooring safety during the same period; wherein the historical mooring data includes historical data on the movement distance and movement angle of the ship;

[0007] Using the ship size data and the historical environmental data as input and the historical mooring data as output, a ship mooring drift prediction model is trained;

[0008] Inputting target ship size data of a target ship moored at a pier and predicted environmental data of a prediction period into the ship mooring drift prediction model to obtain movement distance prediction data and movement angle prediction data of the target ship during the prediction period;

[0009] Whether the mooring drift state of the target ship is safe is determined according to the movement distance prediction data and the movement angle prediction data.

[0010] In one possible implementation, the process of acquiring the predicted environmental data for the prediction period includes:

[0011] Build a numerical model of the dynamic environment at the dock location;

[0012] Simulating environmental data of the terminal during the forecast period according to the numerical model to obtain initial environmental data;

[0013] Simulating environmental data of the dock during a historical period according to the numerical model to obtain historical simulated environmental data;

[0014] Perform fitting based on the historical simulation environment data and the historical environment data corresponding to the historical period to obtain a correction function;

[0015] The initial environmental data is corrected according to the correction function to obtain predicted environmental data for the prediction period.

[0016] In a possible implementation, the movement distance prediction data includes relative distance prediction data between the target ship and the dock, and the movement angle prediction data includes turning angle prediction data of the target ship;

[0017] Determining whether the mooring drift state of the target ship is safe according to the movement distance prediction data and the movement angle prediction data includes:

[0018] Correcting the relative distance prediction data according to the rotation angle prediction data and the target ship size data to obtain actual relative distance prediction data of the mooring position of the target ship;

[0019] The actual relative distance prediction data is compared with a preset drift distance warning value, and whether the mooring drift state of the target ship is safe is determined based on the comparison result.

[0020] In a possible implementation, after obtaining the ship size data and historical mooring data of each ship moored at the pier, and obtaining historical environmental data affecting ship mooring safety during the same period, the following is further included:

[0021] Calculate the correlation between each historical environmental data and each historical mooring data, and determine the strongly correlated historical environmental data corresponding to each historical mooring data;

[0022] The ship mooring drift prediction optimization model is obtained by training the historical environmental data and the ship size data corresponding to each type of historical mooring data as input and the historical mooring data corresponding to the historical environmental data as output;

[0023] Inputting target ship size data of a target ship moored at a pier and predicted environmental data of a predicted period into the ship mooring drift prediction optimization model to obtain optimized movement distance data and optimized movement angle data of the target ship during the predicted period;

[0024] Determining whether the mooring drift state of the target ship is safe according to the movement distance prediction data and the movement angle prediction data includes:

[0025] Whether the mooring drift state of the target ship is safe is determined according to the movement distance prediction data, the movement distance optimization data, the movement angle prediction data and the movement angle optimization data.

[0026] In one possible implementation, determining whether the mooring drift state of the target ship is safe according to the movement distance prediction data, the movement distance optimization data, the movement angle prediction data, and the movement angle optimization data includes:

[0027] Acquire the actual movement distance data and the actual movement angle data of the target ship in the period before the prediction period;

[0028] Calculating a difference between the movement distance prediction data and the movement distance actual measurement data, which is recorded as a first distance difference, and calculating a difference between the movement distance optimization data and the movement distance actual measurement data, which is recorded as a second distance difference;

[0029] Calculating a difference between the motion angle prediction data and the motion angle measured data, which is recorded as a first angle difference, and calculating a difference between the motion angle optimization data and the motion angle measured data, which is recorded as a second angle difference;

[0030] Correcting the movement distance prediction data and the movement distance optimization data according to the first distance difference and the second distance difference to obtain movement distance correction data;

[0031] Correcting the motion angle prediction data and the motion angle optimization data according to the first angle difference and the second angle difference to obtain motion angle correction data;

[0032] Whether the mooring drift state of the target ship is safe is determined according to the movement distance correction data and the movement angle correction data.

[0033] In a possible implementation, correcting the movement distance prediction data and the movement distance optimization data according to the first distance difference and the second distance difference to obtain movement distance correction data includes:

[0034] determining a first distance correction coefficient for the movement distance prediction data and a second distance correction coefficient for the movement distance optimization data according to the first distance difference and the second distance difference;

[0035] Performing a weighted summation on the movement distance prediction data and the movement distance optimization data according to the first distance correction coefficient and the second distance correction coefficient to obtain movement distance correction data;

[0036] Correcting the motion angle prediction data and the motion angle optimization data according to the first angle difference and the second angle difference to obtain motion angle correction data includes:

[0037] Determining a first angle correction coefficient of the motion angle prediction data and a second angle correction coefficient of the motion angle optimization data according to the first angle difference and the second angle difference;

[0038] A weighted sum is performed on the motion angle prediction data and the motion angle optimization data according to the first angle correction coefficient and the second angle correction coefficient to obtain motion angle correction data.

[0039] In a possible implementation, the calculating the correlation between each type of historical environmental data and each type of historical mooring data includes:

[0040] Calculate the derivative of each historical environmental data, record it as the first derivative sequence, calculate the derivative of each historical mooring data, record it as the second derivative sequence;

[0041] Calculating a distance matrix between each type of historical environmental data and each type of historical mooring data according to the first derivative sequence and the second derivative sequence;

[0042] Based on the distance matrix, a dynamic time warping (DTW) algorithm is used to obtain the minimum cumulative distance between each historical environmental data and each historical mooring data, which is used as the correlation between each historical environmental data and each historical mooring data.

[0043] In a second aspect, an embodiment of the present invention provides a device for predicting a mooring drift state of a ship, comprising:

[0044] An acquisition module is used to acquire ship size data and historical mooring data of each ship moored at the pier, and to acquire historical environmental data affecting the safety of ship mooring during the same period; wherein the historical mooring data includes historical data of movement distance and movement angle of the ship;

[0045] a training module, configured to use the ship size data and the historical environmental data as input and the historical mooring data as output to train a ship mooring drift prediction model;

[0046] A prediction module, configured to input target ship size data of a target ship moored at a pier and predicted environmental data of a prediction period into the ship mooring drift prediction model, and obtain predicted movement distance data and predicted movement angle data of the target ship during the prediction period;

[0047] An evaluation module is used to determine whether the mooring drift state of the target ship is safe based on the movement distance prediction data and the movement angle prediction data.

[0048] In a third aspect, an embodiment of the present invention provides a terminal comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0049] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0050] Embodiments of the present invention provide a ship mooring drift state prediction method, device, terminal, and storage medium. The method obtains ship size data and historical mooring data for each ship moored at a dock, as well as historical environmental data affecting ship mooring safety during the same period. The historical mooring data includes historical ship motion distance and motion angle data. A ship mooring drift prediction model is trained using the ship size data and historical environmental data as input and the historical mooring data as output. The target ship size data and predicted environmental data for a predicted period of time are then input into the ship mooring drift prediction model to obtain predicted motion distance and motion angle data for the target ship during the predicted period. The predicted motion distance and motion angle data are then used to determine whether the target ship's mooring drift state is safe. The method then comprehensively evaluates various drift movements of the moored ship, including lateral, longitudinal, and vertical, that may affect mooring safety, from both the motion distance and motion angle perspectives. This allows accurate mooring safety warnings to be issued based on the predicted drift state of the moored ship under various operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 This is a flow chart of an implementation method for predicting a ship mooring drift state provided by an embodiment of the present invention;

[0053] Figure 2 is a schematic diagram of a moored vessel according to an embodiment of the present invention when it turns;

[0054] Figure 3 1 is a schematic structural diagram of a device for predicting a ship mooring drift state provided by an embodiment of the present invention;

[0055] Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0057] Currently, the prediction of a ship's mooring drift state typically involves estimating the relative distance between the ship and the dock or the mooring force. However, in some cases, this approach cannot accurately provide a mooring safety warning. For example, in some operating conditions, even if the relative distance between the ship and the dock does not reach the warning threshold, the mooring line may break, compromising mooring safety. Therefore, the present invention proposes a method for predicting the ship's mooring drift state.

[0058] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0059] See also Figure 1 , which shows a flow chart of the implementation of the ship mooring drift state prediction method provided by an embodiment of the present invention, and is described in detail as follows:

[0060] In step 101, the ship size data and historical mooring data of each ship moored at the pier are obtained, and the historical environmental data affecting the ship mooring safety during the same period are obtained; wherein the historical mooring data includes the historical data of the movement distance and the historical data of the movement angle of the ship.

[0061] For example, historical mooring data can be obtained by deploying lidar sensors at appropriate locations on the dock (for example, on cranes used for loading and unloading operations), and wind, wave and current monitoring equipment can be deployed to collect real-time wind, wave and current monitoring data in the front operating area of ​​the dock as historical environmental data that affects the safety of ship mooring.

[0062] Among them, the terminal front operating area is the land operating area in front of the terminal and the waters for ship mooring operations. The monitoring points of the wind, wave and current monitoring equipment can be set according to actual conditions. There is no fixed boundary range and location requirement. It only needs to reflect the data characteristics of the wind, wave and current monitoring elements of the terminal front operating area.

[0063] For example, considering the impact of wind, wave and current monitoring data on mooring safety, when obtaining historical environmental data, characteristic data such as wind speed and direction, flow speed and direction (layered acquisition, for example, a layer of flow speed and direction can be obtained every 1m to 2m), wave height, wave direction, and wave period can be obtained.

[0064] Considering that when a ship is moored, it may produce a certain turning angle or inclination angle due to the influence of wind, waves and currents, and may also produce a certain degree of heave depth changes due to loading and unloading. It may also produce a certain drift distance under the influence of wind, waves and currents. Whether it is the movement distance data such as drift distance and heave depth change, or the movement angle data such as turning angle or inclination angle, it may cause changes in the mooring force when the ship is moored, thereby posing a risk of breaking the mooring rope when the ship is moored. Therefore, when obtaining historical mooring data, it is possible to obtain historical movement distance data such as the drift distance between the ship and the dock shore, the ship's heave depth, as well as the ship's movement angle data such as the ship's turning angle, roll, and pitch, so as to fully reflect the relative position of the moored ship and the dock shore and the motion posture information of the moored ship.

[0065] For example, in order to make the ship mooring drift prediction model obtained by subsequent training more universal, the influence of different ship sizes on the drift of moored ships is also considered, and the ship size data of each ship moored at the dock is obtained, such as the length, width, draft, etc. of each ship.

[0066] In step 102, a ship mooring drift prediction model is trained using ship size data and historical environmental data as input and historical mooring data as output.

[0067] In this embodiment, based on the data preparation in step 101, a ship mooring drift prediction model based on ship size and dock environment data can be established. Considering that both historical mooring data and historical environment data are time series data, a deep learning model that processes time series dependencies can be used when training the ship mooring drift prediction model. For example, a recurrent neural network (RNN) or a long short-term memory (LSTM) network can be used to more accurately and effectively train the impact of different ships and different environments on the drift state of moored ships. This allows the ship to obtain a ship mooring drift prediction model that predicts the drift distance between the ship and the dock shore, the ship's heave depth, the ship's turning angle, roll, and pitch based on the ship's length, width, draft, wind speed and direction, current speed and direction, wave height, wave direction, and wave period.

[0068] In step 103, the target ship size data of the target ship moored at the pier and the predicted environmental data of the predicted period are input into the ship mooring drift prediction model to obtain the movement distance prediction data and movement angle prediction data of the target ship in the predicted period.

[0069] In this embodiment, after the ship mooring drift prediction model is trained, the ship mooring drift prediction model can be used to perform mooring safety early warning.

[0070] For example, in order to apply the ship mooring drift prediction model, a wind-wave and current simulation system can be established in front of the dock through the use of wind-wave and current numerical simulation methods, and corrections can be made through wind-wave and current monitoring data to obtain short-term high-precision wind-wave and current forecast data, which are input into the ship mooring drift prediction model as the predicted environmental data for the prediction period.

[0071] Specifically, the process of obtaining the predicted environmental data for the prediction period may include:

[0072] Establish a numerical model of the dynamic environment at the terminal's location; simulate the terminal's environmental data during the forecast period based on the numerical model to obtain initial environmental data; simulate the terminal's environmental data during the historical period based on the numerical model to obtain historical simulated environmental data; fit the historical simulated environmental data with the historical environmental data corresponding to the historical period to obtain a correction function; correct the initial environmental data based on the correction function to obtain predicted environmental data for the forecast period.

[0073] The dynamic environment refers to wind, waves, and tides. A numerical model of the dynamic environment at the dock location is established, that is, a numerical model of the wind, a numerical model of the waves, and a numerical model of the tide at the dock location is established.

[0074] For example, assuming that the current time is June 21 of a certain year, to predict the ship's mooring drift state from June 22 to June 24, it is necessary to first obtain the predicted environmental data from June 22 to June 24. When obtaining the predicted environmental data from June 22 to June 24, the wind, wave and current simulation values ​​from June 20 to June 24 (i.e., including historical simulated environmental data and initial environmental data) can be first simulated using a numerical model. The wind, wave and current simulation values ​​from June 20 to June 21 are then compared and fitted with the wind, wave and current measured values ​​from June 20 to June 21 (i.e., the historical environmental data corresponding to the historical period) to obtain a correction function. The wind, wave and current simulation values ​​from June 22 to June 24 are then corrected based on this correction function, thereby improving the forecast accuracy of the predicted environmental data from June 22 to June 24.

[0075] After obtaining the predicted environmental data for the forecast period, the target vessel's dimensions and predicted environmental data are input into the ship mooring drift prediction model to obtain the predicted drift state of the target vessel moored at the pier in the short term. This means the predicted distance and angle of motion of the target vessel moored at the pier in the short term.

[0076] Optionally, after obtaining the target ship's movement distance prediction data and movement angle prediction data during the prediction period, when the target ship's movement distance measured data and movement angle measured data during the prediction period can be obtained subsequently, the target ship's movement distance prediction data and movement angle prediction data during the prediction period and the target ship's movement distance measured data and movement angle measured data during the prediction period can also be used as incremental data to perform evolutionary training on the ship mooring drift prediction model, so as to continuously optimize the prediction accuracy of the ship mooring drift prediction model.

[0077] In step 104, it is determined whether the mooring drift state of the target ship is safe based on the movement distance prediction data and the movement angle prediction data.

[0078] For example, in combination with the description in step 101, the motion distance prediction data may include the drift distance prediction data between the target ship and the dock shore (i.e., the relative distance prediction data between the target ship and the dock), the heave depth prediction data of the target ship, and the motion angle prediction data may include the turning angle prediction data, roll prediction data, and pitch prediction data of the target ship.

[0079] When determining whether the mooring drift state of the target ship is safe based on the motion distance prediction data and the motion angle prediction data, considering that the turning angle of the target ship will affect the drift distance between the target ship and the dock shore, the relative distance prediction data can be corrected according to the turning angle prediction data and the target ship size data to obtain the actual relative distance prediction data of the mooring position of the target ship, and then the actual relative distance prediction data is compared with the preset drift distance warning value, and whether the mooring drift state of the target ship is safe is determined based on the comparison result.

[0080] Among them, a suitable drift distance can be selected from the situations where cable breakage or significant drift occurred in the historical records of terminal operations as the preset drift distance warning value.

[0081] like Figure 2 As shown, when the lidar sensor acquires historical mooring data, it is generally fixed at a certain position on the ship. The historical mooring data acquired is only the historical data of the movement distance and movement angle at a certain position on the ship. When assessing whether the drift state of a moored ship is safe, it is generally necessary to assess whether the drift distance between the mooring positions at both ends of the ship and the dock shore exceeds the preset drift distance warning value. The ship's turning angle refers to the ship's rotation angle in the horizontal plane. When the ship has a turning angle, the drift distance between the mooring positions at both ends of the ship and the dock shore will change. Therefore, the drift distance can be corrected based on trigonometric functions using the turning angle and the size of the target ship to obtain the actual drift distance of the target ship's mooring position. Based on the actual drift distance of the target ship's mooring position, it is determined whether the target ship's mooring drift state is safe.

[0082] For example, in addition to setting a preset drift distance warning value, a preset heave depth warning value, a preset rotation angle warning value, a preset roll warning value, a preset pitch warning value, etc. can also be set accordingly, so that after obtaining the target ship's movement distance prediction data and movement angle prediction data, a comprehensive assessment can be made of whether the mooring drift state of the target ship is safe based on the corresponding warning values.

[0083] Optionally, for different ships, a comparison table of typical ship sizes and various warning values ​​can be set to be compatible with various types of ships.

[0084] For example, when it is determined based on the movement distance prediction data and the movement angle prediction data that the mooring drift state of the target ship exceeds the corresponding warning value, the warning terminal equipment can be used to prompt the relevant personnel with warning information through sound, light, voice, etc., so that effective measures can be taken in time to prevent the risk of cable breakage.

[0085] For example, the early warning terminal device may include but is not limited to the following forms:

[0086] 1. Set up a display screen and buzzer on site to send warning messages through light and sound broadcasting.

[0087] 2. Mobile App: Send warning messages through WeChat mini-program app.

[0088] 3. Wearable devices used for positioning and warning dock workers have integrated positioning and voice broadcasting devices. The devices will automatically report the personnel's location information and integrate and display it in the system. Management can understand the situation of dock workers in real time, and when they enter a dangerous area, warning information will be automatically pushed to the workers.

[0089] The present invention obtains ship size data and historical mooring data for each ship moored at a pier, as well as historical environmental data affecting ship mooring safety during the same period. The historical mooring data includes historical ship movement distance and movement angle data. A ship mooring drift prediction model is then trained using the ship size data and historical environmental data as input and the historical mooring data as output. The target ship size data and predicted environmental data for a predicted period of time are then input into the ship mooring drift prediction model to obtain predicted movement distance and movement angle data for the target ship during the predicted period. The target ship's mooring drift state is then determined based on the predicted movement distance and movement angle data to determine whether the target ship's mooring drift state is safe. Furthermore, the system comprehensively assesses the various drift movements of the moored ship, including lateral, longitudinal, and vertical, that may affect mooring safety, from the perspectives of movement distance and movement angle. This allows accurate mooring safety warnings to be issued based on the prediction of the moored ship's drift state under various working conditions.

[0090] In one embodiment, in order to further improve the accuracy of mooring safety warning, after obtaining the ship size data and historical mooring data of each ship moored at the pier, and obtaining historical environmental data affecting ship mooring safety during the same period, the following steps may also be performed:

[0091] The correlation between each historical environmental data and each historical mooring data is calculated, and the strongly correlated historical environmental data corresponding to each historical mooring data is determined.

[0092] The ship mooring drift prediction optimization model is trained by taking the strongly correlated historical environmental data and ship size data corresponding to each type of historical mooring data as input and the historical mooring data corresponding to the strongly correlated historical environmental data as output.

[0093] The target ship size data of the target ship moored at the dock and the predicted environmental data of the prediction period are input into the ship mooring drift prediction optimization model to obtain the movement distance optimization data and movement angle optimization data of the target ship in the prediction period.

[0094] Accordingly, determining whether the mooring drift state of the target ship is safe based on the motion distance prediction data and the motion angle prediction data may include:

[0095] Whether the mooring drift state of the target ship is safe is determined based on the movement distance prediction data, the movement distance optimization data, the movement angle prediction data and the movement angle optimization data.

[0096] In this embodiment, considering the potential for errors in predicting the target ship's mooring drift state based solely on the ship mooring drift prediction model, a ship mooring drift prediction optimization model is trained in addition to the ship mooring drift prediction model, taking into account the impact of different historical environmental data on different historical mooring data. This allows for a subsequent comprehensive assessment of whether the target ship's mooring drift state is safe by combining the prediction results of the ship mooring drift prediction model with those of the ship mooring drift prediction optimization model.

[0097] In one embodiment, calculating the correlation between each type of historical environmental data and each type of historical mooring data may include:

[0098] The derivative of each historical environmental data is calculated and recorded as the first derivative sequence, and the derivative of each historical mooring data is calculated and recorded as the second derivative sequence.

[0099] According to the first derivative sequence and the second derivative sequence, a distance matrix between each historical environmental data and each historical mooring data is calculated.

[0100] Based on the distance matrix, the dynamic time warping algorithm is used to obtain the minimum cumulative distance between each historical environmental data and each historical mooring data, which is used as the correlation between each historical environmental data and each historical mooring data.

[0101] When calculating the correlation between each type of historical environmental data and each type of historical mooring data, this embodiment takes into account that the dynamic time warping algorithm DTW is a similarity measure directly based on the sum of the distances between the points in the two time series. However, when the overall trends of the two time series are similar but there is local noise or amplitude changes, the alignment path is prone to instability and the overall trend cannot be accurately captured. Therefore, by aligning the derivatives of the time series to ignore local noise or amplitude changes, the overall trend of change can be more accurately captured, thereby more accurately measuring the correlation between each type of historical environmental data and each type of historical mooring data, so that a more accurate ship mooring drift prediction optimization model can be obtained through subsequent training.

[0102] Optionally, determining whether the mooring drift state of the target ship is safe based on the movement distance prediction data, the movement distance optimization data, the movement angle prediction data, and the movement angle optimization data may include:

[0103] Obtain the actual movement distance data and movement angle data of the target ship in the period before the prediction period.

[0104] The difference between the movement distance prediction data and the movement distance measured data is calculated and recorded as the first distance difference, and the difference between the movement distance optimization data and the movement distance measured data is calculated and recorded as the second distance difference.

[0105] The difference between the motion angle prediction data and the motion angle measured data is calculated and recorded as the first angle difference, and the difference between the motion angle optimization data and the motion angle measured data is calculated and recorded as the second angle difference.

[0106] The movement distance prediction data and the movement distance optimization data are corrected according to the first distance difference and the second distance difference to obtain movement distance correction data.

[0107] The motion angle prediction data and the motion angle optimization data are corrected according to the first angle difference and the second angle difference to obtain motion angle correction data.

[0108] Whether the mooring drift state of the target ship is safe is determined based on the motion distance correction data and the motion angle correction data.

[0109] Optionally, correcting the movement distance prediction data and the movement distance optimization data according to the first distance difference and the second distance difference to obtain the movement distance correction data may include:

[0110] A first distance correction coefficient of the movement distance prediction data and a second distance correction coefficient of the movement distance optimization data are determined according to the first distance difference and the second distance difference.

[0111] A weighted sum is performed on the movement distance prediction data and the movement distance optimization data according to the first distance correction coefficient and the second distance correction coefficient to obtain movement distance correction data.

[0112] Similarly, correcting the motion angle prediction data and the motion angle optimization data according to the first angle difference and the second angle difference to obtain the motion angle correction data may include:

[0113] A first angle correction coefficient of the motion angle prediction data and a second angle correction coefficient of the motion angle optimization data are determined according to the first angle difference and the second angle difference.

[0114] The motion angle prediction data and the motion angle optimization data are weightedly summed according to the first angle correction coefficient and the second angle correction coefficient to obtain motion angle correction data.

[0115] In this embodiment, it is considered that the drift state of a moored ship generally changes continuously. Therefore, when comprehensively utilizing the prediction results of the ship mooring drift prediction optimization model and the prediction results of the ship mooring drift prediction model to determine whether the mooring drift state of the target ship is safe, the difference between the prediction results of the ship mooring drift prediction optimization model and the mooring measured data of the target ship in the period before the prediction period, as well as the difference between the prediction results of the ship mooring drift prediction model and the mooring measured data of the target ship in the period before the prediction period can be calculated respectively, and then a larger weight is given to the prediction result with a smaller difference, and a smaller weight is given to the prediction result with a larger difference, so that a more accurate corrected prediction result can be obtained through weighted summation.

[0116] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0117] The following are device embodiments of the present invention. For details not fully described therein, reference may be made to the corresponding method embodiments described above.

[0118] Figure 3 The following is a schematic diagram showing the structure of a device for predicting a ship mooring drift state according to an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0119] like Figure 3 As shown, the ship mooring drift state prediction device includes: an acquisition module 31, a training module 32, a prediction module 33 and an evaluation module 34.

[0120] The acquisition module 31 is used to obtain the ship size data and historical mooring data of each ship moored at the dock, and obtain historical environmental data affecting the ship's mooring safety during the same period; wherein the historical mooring data includes the ship's movement distance history data and movement angle history data.

[0121] The training module 32 is used to train a ship mooring drift prediction model using ship size data and historical environmental data as input and historical mooring data as output.

[0122] The prediction module 33 is used to input the target ship size data of the target ship moored at the dock and the predicted environmental data of the prediction period into the ship mooring drift prediction model to obtain the movement distance prediction data and movement angle prediction data of the target ship in the prediction period.

[0123] The evaluation module 34 is used to determine whether the mooring drift state of the target ship is safe based on the movement distance prediction data and the movement angle prediction data.

[0124] The present invention obtains ship size data and historical mooring data for each ship moored at a pier, as well as historical environmental data affecting ship mooring safety during the same period. The historical mooring data includes historical ship movement distance and movement angle data. A ship mooring drift prediction model is then trained using the ship size data and historical environmental data as input and the historical mooring data as output. The target ship size data and predicted environmental data for a predicted period of time are then input into the ship mooring drift prediction model to obtain predicted movement distance and movement angle data for the target ship during the predicted period. The target ship's mooring drift state is then determined based on the predicted movement distance and movement angle data to determine whether the target ship's mooring drift state is safe. Furthermore, the system comprehensively assesses the various drift movements of the moored ship, including lateral, longitudinal, and vertical, that may affect mooring safety, from the perspectives of movement distance and movement angle. This allows accurate mooring safety warnings to be issued based on the prediction of the moored ship's drift state under various working conditions.

[0125] In one possible implementation, the prediction module 33 can be used to establish a numerical model of the dynamic environment at the location of the terminal; simulate the environmental data of the terminal in the prediction period according to the numerical model to obtain initial environmental data; simulate the environmental data of the terminal in the historical period according to the numerical model to obtain historical simulated environmental data; fit the historical simulated environmental data and the historical environmental data corresponding to the historical period to obtain a correction function; correct the initial environmental data according to the correction function to obtain predicted environmental data for the prediction period.

[0126] In one possible implementation, the motion distance prediction data includes the relative distance prediction data between the target ship and the dock, and the motion angle prediction data includes the rotation angle prediction data of the target ship; the evaluation module 34 can be used to correct the relative distance prediction data based on the rotation angle prediction data and the target ship size data to obtain the actual relative distance prediction data of the mooring position of the target ship; the actual relative distance prediction data is compared with the preset drift distance warning value, and whether the mooring drift state of the target ship is safe is determined based on the comparison result.

[0127] In one possible implementation, the training module 32 can also be used to calculate the correlation between each type of historical environmental data and each type of historical mooring data, and determine the strongly correlated historical environmental data corresponding to each type of historical mooring data; using the strongly correlated historical environmental data and ship size data corresponding to each type of historical mooring data as input, and the historical mooring data corresponding to the strongly correlated historical environmental data as output, a ship mooring drift prediction optimization model is trained; the prediction module 33 can also be used to input the target ship size data of the target ship moored at the dock and the predicted environmental data of the prediction period into the ship mooring drift prediction optimization model, and obtain the movement distance optimization data and movement angle optimization data of the target ship in the prediction period; the evaluation module 34 can be used to determine whether the mooring drift state of the target ship is safe based on the movement distance prediction data, the movement distance optimization data, the movement angle prediction data and the movement angle optimization data.

[0128] In one possible implementation, the evaluation module 34 can be used to obtain the target ship's actual movement distance data and movement angle data in a period before the prediction period; calculate the difference between the movement distance prediction data and the movement distance measurement data, recorded as a first distance difference, and calculate the difference between the movement distance optimization data and the movement distance measurement data, recorded as a second distance difference; calculate the difference between the movement angle prediction data and the movement angle measurement data, recorded as a first angle difference, and calculate the difference between the movement angle optimization data and the movement angle measurement data, recorded as a second angle difference; correct the movement distance prediction data and the movement distance optimization data according to the first distance difference and the second distance difference to obtain movement distance correction data; correct the movement angle prediction data and the movement angle optimization data according to the first angle difference and the second angle difference to obtain movement angle correction data; determine whether the mooring drift state of the target ship is safe based on the movement distance correction data and the movement angle correction data.

[0129] In one possible implementation, the evaluation module 34 can be used to determine a first distance correction coefficient of the motion distance prediction data and a second distance correction coefficient of the motion distance optimization data based on the first distance difference and the second distance difference; perform weighted summation on the motion distance prediction data and the motion distance optimization data according to the first distance correction coefficient and the second distance correction coefficient to obtain motion distance correction data; correct the motion angle prediction data and the motion angle optimization data according to the first angle difference and the second angle difference to obtain motion angle correction data, including: determining a first angle correction coefficient of the motion angle prediction data and a second angle correction coefficient of the motion angle optimization data according to the first angle difference and the second angle difference; perform weighted summation on the motion angle prediction data and the motion angle optimization data according to the first angle correction coefficient and the second angle correction coefficient to obtain motion angle correction data.

[0130] In one possible implementation, the training module 32 can be used to calculate the derivative of each historical environmental data, recorded as the first derivative sequence, and calculate the derivative of each historical mooring data, recorded as the second derivative sequence; based on the first derivative sequence and the second derivative sequence, calculate the distance matrix between each historical environmental data and each historical mooring data; based on the distance matrix, use the dynamic time warping algorithm to obtain the minimum cumulative distance between each historical environmental data and each historical mooring data, as the correlation between each historical environmental data and each historical mooring data.

[0131] Figure 4 Schematic diagram of a terminal provided by an embodiment of the present invention. Figure 4 As shown, the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned various ship mooring drift state prediction method embodiments are implemented, such as Figure 1 Steps 101 to 104 shown, or Figure 2 Alternatively, when the processor 40 executes the computer program 42, the functions of the modules / units in the above-mentioned device embodiments are realized, for example Figure 3 The functions of each module are shown.

[0132] Exemplarily, the computer program 42 may be divided into one or more modules / units, one or more modules / units being stored in the memory 41 and executed by the processor 40 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4. For example, the computer program 42 may be divided into Figure 3 The modules shown.

[0133] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0134] The processor 40 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), 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.

[0135] Memory 41 can be an internal storage unit of terminal 4, such as a hard drive or memory in terminal 4. Memory 41 can also be an external storage device in terminal 4, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, memory 41 can include both internal storage units and external storage devices in terminal 4. Memory 41 is used to store computer programs and other programs and data required by the terminal. Memory 41 can also be used to temporarily store data that has been output or is about to be output.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0137] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0138] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0139] In the embodiments provided herein, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of modules or units is merely a logical functional division. In actual implementation, other division methods may be used, such as multiple units or components being combined or integrated into another system, or some features being ignored or not implemented. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interface, or the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0140] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0141] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0142] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the process steps in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned ship mooring drift state prediction method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media.

[0143] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for predicting the mooring drift state of a ship, characterized in that: include: Obtaining ship size data and historical mooring data of each ship moored at the pier, and obtaining historical environmental data affecting ship mooring safety during the same period; wherein the historical mooring data includes historical data on the movement distance and movement angle of the ship; Using the ship size data and the historical environmental data as input and the historical mooring data as output, a ship mooring drift prediction model is trained; Inputting target ship size data of a target ship moored at a pier and predicted environmental data of a prediction period into the ship mooring drift prediction model to obtain movement distance prediction data and movement angle prediction data of the target ship during the prediction period; determining whether the mooring drift state of the target ship is safe according to the movement distance prediction data and the movement angle prediction data; The process of obtaining the predicted environmental data for the predicted period includes: Build a numerical model of the dynamic environment at the dock location; Simulating environmental data of the terminal during the forecast period according to the numerical model to obtain initial environmental data; Simulating environmental data of the dock during a historical period according to the numerical model to obtain historical simulated environmental data; Perform fitting based on the historical simulation environment data and the historical environment data corresponding to the historical period to obtain a correction function; Correcting the initial environmental data according to the correction function to obtain predicted environmental data for the prediction period; After obtaining the ship size data and historical mooring data of each ship moored at the terminal, and obtaining historical environmental data affecting ship mooring safety during the same period, it also includes: Calculate the correlation between each historical environmental data and each historical mooring data, and determine the strongly correlated historical environmental data corresponding to each historical mooring data; The ship mooring drift prediction optimization model is obtained by training the historical environmental data and the ship size data corresponding to each type of historical mooring data as input and the historical mooring data corresponding to the historical environmental data as output; Inputting target ship size data of a target ship moored at a pier and predicted environmental data of a predicted period into the ship mooring drift prediction optimization model to obtain optimized movement distance data and optimized movement angle data of the target ship during the predicted period; Determining whether the mooring drift state of the target ship is safe according to the movement distance prediction data and the movement angle prediction data includes: determining whether the mooring drift state of the target ship is safe based on the movement distance prediction data, the movement distance optimization data, the movement angle prediction data, and the movement angle optimization data; The calculating of the correlation between each type of historical environmental data and each type of historical mooring data includes: Calculate the derivative of each historical environmental data, record it as the first derivative sequence, calculate the derivative of each historical mooring data, record it as the second derivative sequence; Calculating a distance matrix between each type of historical environmental data and each type of historical mooring data according to the first derivative sequence and the second derivative sequence; Based on the distance matrix, a dynamic time warping algorithm is used to obtain the minimum cumulative distance between each historical environmental data and each historical mooring data as the correlation between each historical environmental data and each historical mooring data.

2. The method for predicting the ship mooring drift state according to claim 1, characterized in that: The movement distance prediction data includes the relative distance prediction data between the target ship and the dock, and the movement angle prediction data includes the turning angle prediction data of the target ship; Determining whether the mooring drift state of the target ship is safe according to the movement distance prediction data and the movement angle prediction data includes: Correcting the relative distance prediction data according to the rotation angle prediction data and the target ship size data to obtain actual relative distance prediction data of the mooring position of the target ship; The actual relative distance prediction data is compared with a preset drift distance warning value, and whether the mooring drift state of the target ship is safe is determined based on the comparison result.

3. The method for predicting the ship mooring drift state according to claim 1, characterized in that: Determining whether the mooring drift state of the target ship is safe according to the movement distance prediction data, the movement distance optimization data, the movement angle prediction data, and the movement angle optimization data includes: Acquire the actual movement distance data and the actual movement angle data of the target ship in the period before the prediction period; Calculating a difference between the movement distance prediction data and the movement distance actual measurement data, which is recorded as a first distance difference, and calculating a difference between the movement distance optimization data and the movement distance actual measurement data, which is recorded as a second distance difference; Calculating a difference between the motion angle prediction data and the motion angle measured data, which is recorded as a first angle difference, and calculating a difference between the motion angle optimization data and the motion angle measured data, which is recorded as a second angle difference; Correcting the movement distance prediction data and the movement distance optimization data according to the first distance difference and the second distance difference to obtain movement distance correction data; Correcting the motion angle prediction data and the motion angle optimization data according to the first angle difference and the second angle difference to obtain motion angle correction data; Whether the mooring drift state of the target ship is safe is determined according to the movement distance correction data and the movement angle correction data.

4. The method for predicting the ship mooring drift state according to claim 3, characterized in that: Correcting the movement distance prediction data and the movement distance optimization data according to the first distance difference and the second distance difference to obtain movement distance correction data includes: determining a first distance correction coefficient for the movement distance prediction data and a second distance correction coefficient for the movement distance optimization data according to the first distance difference and the second distance difference; Performing a weighted summation on the movement distance prediction data and the movement distance optimization data according to the first distance correction coefficient and the second distance correction coefficient to obtain movement distance correction data; Correcting the motion angle prediction data and the motion angle optimization data according to the first angle difference and the second angle difference to obtain motion angle correction data includes: Determining a first angle correction coefficient of the motion angle prediction data and a second angle correction coefficient of the motion angle optimization data according to the first angle difference and the second angle difference; A weighted sum is performed on the motion angle prediction data and the motion angle optimization data according to the first angle correction coefficient and the second angle correction coefficient to obtain motion angle correction data.

5. A device for predicting the mooring drift state of a ship, characterized in that: It is used to perform the method according to any one of claims 1 to 4, comprising: An acquisition module is used to acquire ship size data and historical mooring data of each ship moored at the pier, and to acquire historical environmental data affecting the safety of ship mooring during the same period; wherein the historical mooring data includes historical data of movement distance and movement angle of the ship; a training module, configured to use the ship size data and the historical environmental data as input and the historical mooring data as output to train a ship mooring drift prediction model; A prediction module, configured to input target ship size data of a target ship moored at a pier and predicted environmental data of a prediction period into the ship mooring drift prediction model, and obtain predicted movement distance data and predicted movement angle data of the target ship during the prediction period; An evaluation module is used to determine whether the mooring drift state of the target ship is safe based on the movement distance prediction data and the movement angle prediction data.

6. A terminal, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images