Method, device and equipment for predicting mooring line tension in time-varying marine environment and medium

Abstract

The invention discloses a method, a device, equipment and a medium for predicting mooring line tension in a time-varying marine environment. The method comprises the following steps: acquiring long-term historical data of a working sea area of an ocean platform; training a pre-constructed basic mooring line tension prediction model according to the long-term historical data to obtain a mooring line tension prediction model; acquiring short-term historical data of the working sea area of the ocean platform; calculating the time difference between the short-term marine monitoring data and the short-term mooring line tension data, and adjusting the timestamp of the short-term marine monitoring data according to the time difference to obtain a short-term training set; carrying out migration training on the mooring line tension prediction model according to the short-term training set to obtain a real-time mooring line tension prediction model; in the actual prediction process, real-time monitoring data are input into the real-time mooring line tension prediction model for prediction, and the mooring line tension of the ocean platform in the future time period is obtained. According to the method provided by the invention, accurate real-time prediction of the tension of the mooring line is realized.

Description

Technical Field

[0001] The present invention relates to the field of marine engineering technology, and in particular to a method, device, equipment and medium for predicting mooring tension in a time-varying marine environment. Background Art

[0002] Offshore platforms are structures that provide production and living facilities for drilling, oil production, and shipping operations at sea. It is common for offshore platforms to be moored with ships or other offshore platforms during normal operations. During close-range mooring operations of offshore platforms, the two floating bodies are physically connected in parallel by mooring cables, and fenders are used to avoid collisions. However, due to the harsh and unstable marine environment, the movement of the two floating bodies will be affected by the real-time randomly changing marine environment. Excessive movement of the floating body may occur at any time, causing excessive force response at certain connection structures (such as mooring cables or fenders) that exceeds the threshold, thereby causing catastrophic accidents and resulting in a large amount of property losses.

[0003] In the existing technology, sensor networks are usually used to monitor key parameters such as mooring tension and floating body position in real time. However, the measurement of marine environmental parameters (such as wind speed, wave height, current velocity, etc.) is affected by many factors, including the accuracy of the measuring equipment, the layout location and the complexity of the marine environment, which may lead to inaccurate measurement data and thus affect the accuracy of mooring tension prediction. Summary of the invention

[0004] The present invention aims to provide a method, device, equipment and medium for predicting mooring cable tension in a time-varying marine environment, so as to solve the technical problem of insufficient accuracy in predicting mooring cable tension.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for predicting mooring tension in a time-varying marine environment, which is applied to an offshore platform connected by mooring tension, and a plurality of monitoring points for interacting with marine data are provided in the working sea area of ​​the offshore platform. The method comprises:

[0006] Acquire long-term historical data of a first time interval in the working sea area of ​​the offshore platform;

[0007] Training a pre-built basic mooring cable tension prediction model according to the long-term historical data to obtain a mooring cable tension prediction model;

[0008] Acquire short-term historical data of a second time interval in the working sea area of ​​the offshore platform, wherein the short-term historical data includes short-term ocean monitoring data and short-term mooring cable tension data, and the first time interval is greater than the second time interval;

[0009] Calculating the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point location distribution on the tension prediction, adjusting the timestamp of the short-term ocean monitoring data according to the time difference, and aligning the adjusted short-term ocean monitoring data with the short-term mooring tension data to obtain a short-term training set;

[0010] Performing migration training on the mooring cable tension prediction model according to the short-term training set to obtain a real-time mooring cable tension prediction model;

[0011] In the actual prediction process, the real-time monitoring data is input into the real-time mooring tension prediction model for prediction to obtain the mooring tension of the offshore platform in the future time period.

[0012] As one preferred solution, the pre-built basic mooring cable tension prediction model is trained according to the long-term historical data to obtain the mooring cable tension prediction model, including:

[0013] Construct a basic mooring cable tension prediction model based on a double-layer neural network;

[0014] Dividing the long-term historical data according to a preset ratio to obtain a training data set and a verification data set;

[0015] The basic mooring cable tension prediction model is trained according to the training data set, and the performance of the model is evaluated in real time through the verification data set until a mooring cable tension prediction model that meets a preset accuracy is obtained.

[0016] As one preferred solution, the method of calculating the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point location distribution on the tension prediction includes:

[0017] Obtaining the horizontal distance between each of the monitoring points and the offshore platform and the wave propagation speed from the monitoring point to the offshore platform;

[0018] The time difference between the short-term ocean monitoring data and the short-term mooring cable tension data is calculated according to the horizontal distance and the partial propagation speed.

[0019] As one of the preferred solutions, the time difference between the short-term ocean monitoring data and the short-term mooring tension data is calculated according to the horizontal distance and the partial propagation speed, which is expressed by the formula:

[0020] n ≥ L,

[0021] t=s / v,

[0022] Where n is the time difference between the short-term ocean monitoring data and the mooring cable tension to be predicted, L is the time period length of the short-term mooring cable tension data, t is the time difference between the short-term ocean monitoring data and the short-term mooring cable tension data, s is the horizontal distance between the monitoring point and the offshore platform, and v is the wave propagation velocity along the monitoring point-offshore platform direction.

[0023] As one preferred solution, before performing migration training on the mooring cable tension prediction model according to the short-term training set, the method further includes:

[0024] Preprocessing the long-term historical data, wherein the preprocessing includes data cleaning and data transformation;

[0025] Use the moving average method to smooth the preprocessed short-term historical data;

[0026] According to the characteristics of ocean monitoring and mooring tension, feature extraction is performed on the smoothed data to construct a short-term training set.

[0027] As one of the preferred solutions, the transfer training of the mooring cable tension prediction model according to the short-term training set to obtain the real-time mooring cable tension prediction model includes:

[0028] Based on the structure of the mooring cable tension prediction model, selecting a frozen layer of the mooring cable tension prediction model;

[0029] According to the frozen layer and the feature-based transfer learning method, the fully connected layer and the output layer of the mooring tension prediction model are adjusted to a blank fully connected layer and a blank output layer;

[0030] The adjusted mooring cable tension prediction model is trained based on the short-term training set, and the mooring cable tension prediction model is adjusted according to the parameters obtained during the training process to obtain a real-time mooring cable tension prediction model.

[0031] As one preferred solution, after obtaining the mooring tension of the offshore platform in the future time period, the method further includes:

[0032] According to the physical characteristics and environmental conditions of the offshore platform, the tension thresholds of the bow cable, stern cable, bow and stern return cable and bow and stern transverse cable are set. The tension thresholds include three levels: low, medium and high, corresponding to different risk levels and response measures;

[0033] The mooring cable tension is compared with , and if the mooring cable tension exceeds the tension threshold, a corresponding warning signal is issued to warn of the risk of cable breakage.

[0034] Another embodiment of the present invention provides a device for predicting mooring tension in a time-varying marine environment, which is applied to a marine platform connected by mooring tension, and a plurality of monitoring points for interacting with marine data are provided in the working sea area of ​​the marine platform, and the device comprises:

[0035] A first acquisition module is used to acquire long-term historical data of a first time interval in the working sea area of ​​the offshore platform;

[0036] A first training module is used to train a pre-built basic mooring cable tension prediction model according to the long-term historical data to obtain a mooring cable tension prediction model;

[0037] A second acquisition module is used to acquire short-term historical data of a second time interval in the working sea area of ​​the offshore platform, wherein the short-term historical data includes short-term ocean monitoring data and short-term mooring cable tension data, and the first time interval is greater than the second time interval;

[0038] An alignment module, configured to calculate the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point location distribution on the tension prediction, adjust the timestamp of the short-term ocean monitoring data according to the time difference, and align the adjusted short-term ocean monitoring data with the short-term mooring tension data to obtain a short-term training set;

[0039] A second training module is used to perform migration training on the mooring cable tension prediction model according to the short-term training set to obtain a real-time mooring cable tension prediction model;

[0040] The prediction module is used to input the real-time monitoring data into the real-time mooring tension prediction model to make predictions during the actual prediction process, so as to obtain the mooring tension of the offshore platform in the future time period.

[0041] Another embodiment of the present invention provides a device for predicting mooring tension in a time-varying marine environment, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the method for predicting mooring tension in a time-varying marine environment as described above.

[0042] Yet another embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the method for predicting mooring tension in a time-varying marine environment as described above is implemented.

[0043] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0044] (1) The present application obtains a real-time mooring tension prediction model by migrating and adjusting the long-term prediction model and using short-term training samples for training; the model can combine long-term and short-term monitoring data to make more accurate real-time predictions of mooring tension.

[0045] (2) The real-time mooring tension prediction model of the present application can predict the changing trend of the mooring tension in advance, thereby issuing an early warning when the mooring tension approaches or exceeds the safety threshold; this provides operators with sufficient time to take emergency measures, such as adjusting the position of the buoy, increasing the number or strength of moorings, etc., to reduce the risk of accidents.

[0046] (3) This application collects short-term historical monitoring data during the prediction work of the marine platform and performs time difference processing to eliminate the impact of the inconsistent distances between each monitoring point and the marine platform on the prediction results. This processing method makes the short-term training samples closer to the monitoring conditions during the actual prediction, thereby improving the adaptability of the model and the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a schematic flow chart of a method for predicting mooring tension in a time-varying marine environment in one embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of the relative time difference between the input part and the output part when the fast migration training is performed using short-term historical monitoring data as training samples in one embodiment of the present invention;

[0049] Figure 3 is a schematic diagram of the structure of a device for predicting mooring tension in a time-varying marine environment in one embodiment of the present invention;

[0050] Figure 4 It is a schematic diagram of a device for predicting mooring tension in a time-varying marine environment in one embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0053] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0054] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0055] An embodiment of the present invention provides a method for predicting mooring tension in a time-varying marine environment. For details, see Figure 1 , Figure 1 The flowchart of the method for predicting the mooring tension in a time-varying marine environment provided in one embodiment of the present invention is shown. The method comprises steps S1 to S6:

[0056] S1. Acquire long-term historical data of a first time interval in the working sea area of ​​the offshore platform;

[0057] S2. Training a pre-constructed basic mooring cable tension prediction model according to the long-term historical data to obtain a mooring cable tension prediction model;

[0058] S3, acquiring short-term historical data of a second time interval in the working sea area of ​​the offshore platform, wherein the short-term historical data includes short-term ocean monitoring data and short-term mooring cable tension data, and the first time interval is greater than the second time interval;

[0059] S4, calculating the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point location distribution on the tension prediction, adjusting the timestamp of the short-term ocean monitoring data according to the time difference, and aligning the adjusted short-term ocean monitoring data with the short-term mooring tension data to obtain a short-term training set;

[0060] S5, performing migration training on the mooring cable tension prediction model according to the short-term training set to obtain a real-time mooring cable tension prediction model;

[0061] S6. In the actual prediction process, the real-time monitoring data is input into the real-time mooring tension prediction model for prediction to obtain the mooring tension of the offshore platform in the future time period.

[0062] It should be noted that the purpose of the present invention is to provide a method for predicting mooring tension in a time-varying marine environment, so as to make real-time predictions on the mooring state, timely discover abnormal extreme values ​​of tension, and predict the risk of cable breakage in a short period of time. The time-varying marine environment refers to the marine environment in which the wind, waves, currents, directions, and characteristic parameters of the marine platform change in real time during actual operation. The mooring tension includes the cable tension in the mooring system composed of multiple cables such as the bow cable and the stern cable connecting the two buoys, the bow and stern reverse cables, and the bow and stern transverse cables. The elements required for the prediction method include:

[0063] There are multiple distant wave height monitoring points, which are embedded on the distant sea surface of two connected marine platforms and are centrally symmetrically distributed with the sea area where the two platforms are located as the center, so as to collect information such as the direction and characteristic parameters of wind, wave and current that will act on the marine platforms;

[0064] A mooring cable tension sensor, one for each mooring cable, which is arranged at the connection between the mooring cable and the offshore floating platform to collect short-term historical tension information of the mooring cable, including tension information at the connection and tension information in the middle of the mooring cable. Generally speaking, there is a correlation between the mooring cables, so all the historical data of the mooring cables can be used as analytical data for predicting a specific mooring cable;

[0065] A data processing unit connected to the remote wave height monitoring point unit and the mooring cable tension sensor to integrate and pre-process the collected data;

[0066] A data analysis platform is connected to the data processing unit, analyzes the data transmitted by the data processing unit and the long-term historical monitoring data of the sea area, conducts deep learning modeling based on the influence of the above data, and quickly predicts the changes in the future mooring tension;

[0067] The tension warning terminal is connected to the data analysis platform unit to determine whether the predicted future mooring cable tension extreme value exceeds the tension alarm threshold and issue a warning.

[0068] Firstly, the long-term historical monitoring data of the working area of ​​the offshore platform are normalized to improve the convergence speed and accuracy of the model.

[0069] Preferably, in one embodiment of the present invention, the pre-constructed basic mooring cable tension prediction model is trained according to the long-term historical data to obtain the mooring cable tension prediction model, including:

[0070] Construct a basic mooring cable tension prediction model based on a double-layer neural network;

[0071] Dividing the long-term historical data according to a preset ratio to obtain a training data set and a verification data set;

[0072] The basic mooring cable tension prediction model is trained according to the training data set, and the performance of the model is evaluated in real time through the verification data set until a mooring cable tension prediction model that meets a preset accuracy is obtained.

[0073] Specifically, the preliminary long-term and short-term neural network training model constructed adopts a two-layer long-term and short-term neural network structure consisting of an input layer, two hidden layers, a fully connected layer and an output layer. Both hidden layers are LSTM layers, and a dropout layer is added after them to improve the generalization ability of the model, with a dropout rate of 0.2. The activation function of the second LSTM layer is set to the ReLU function, which can handle nonlinear problems and prevent gradient disappearance; the training process uses the Adam optimization algorithm and adaptive learning rate to improve the convergence efficiency of the model and accelerate the training process of the neural network.

[0074] Divide the input preprocessed long-term historical monitoring data into a training set and a validation set, select an appropriate batch size and number of training rounds (usually need to be adjusted according to the size of the dataset), use the training dataset for training, and monitor the performance on the validation set.

[0075] Evaluate the performance of the model on the validation set, monitor the loss and other indicators (such as accuracy, precision, recall, etc.), and calculate the accuracy of the model. Based on the fit of the validation set, determine whether the model can be used as a pre-trained model for transfer training in a time-varying environment.

[0076] Preferably, in one embodiment of the present invention, the calculating the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point position distribution on the tension prediction comprises:

[0077] Obtaining the horizontal distance between each of the monitoring points and the offshore platform and the wave propagation speed from the monitoring point to the offshore platform;

[0078] The time difference between the short-term ocean monitoring data and the short-term mooring cable tension data is calculated according to the horizontal distance and the partial propagation speed.

[0079] For details, see Figure 2 , Figure 2 The figure shows a schematic diagram of the relative time difference between the input part and the output part when the rapid migration training is performed using short-term historical monitoring data as training samples provided in one embodiment of the present invention. The horizontal distance of each monitoring point relative to the marine platform is obtained, which can usually be obtained through a geographic information system (GIS) or on-site measurement; the sub-propagation speed of the wave from the monitoring point to the marine platform can be measured by the monitoring point, because the horizontal distance of different monitoring points from the marine platform and the sub-propagation speed of the wave along the monitoring point-marine platform direction are not consistent, so the time difference of the short-term historical marine environment (wind wave current direction and characteristic parameters) monitoring data input by each monitoring point relative to the output of the predicted mooring tension is not exactly the same.

[0080] The formula "propagation time = horizontal distance / minute propagation speed" is used to calculate the time required for waves to propagate from the monitoring point to the offshore platform. This calculation is performed for each monitoring point to obtain a set of propagation times.

[0081] Analyze the time correspondence between ocean monitoring data and mooring cable tension data. Since it takes a certain amount of time for waves to propagate to the ocean platform and cause changes in mooring cable tension, the time difference can be determined by comparing the timestamps between the two; combined with the previously calculated propagation time, it can be determined which monitoring point's data can most accurately reflect the time lag of mooring cable tension changes.

[0082] According to the calculated time difference, the ocean monitoring data is corrected in time to ensure its temporal consistency with the mooring cable tension data. The corrected ocean monitoring data is compared with the mooring cable tension data for verification to check the accuracy of the time difference calculation. If a deviation is found in the time difference calculation, the propagation speed or other relevant parameters can be readjusted and the above calculation steps can be repeated. The correlation between the corrected ocean monitoring data and the mooring cable tension data is analyzed to evaluate the impact of the time difference calculation on the tension prediction, providing a reference for future monitoring point layout and data analysis.

[0083] Preferably, in one embodiment of the present invention, the time difference between the short-term ocean monitoring data and the short-term mooring tension data is calculated according to the horizontal distance and the partial propagation speed, and is expressed by the formula:

[0084] n ≥ L,

[0085] t=s / v,

[0086] Where n is the time difference between the short-term ocean monitoring data and the mooring cable tension to be predicted, L is the time period length of the short-term mooring cable tension data, t is the time difference between the short-term ocean monitoring data and the short-term mooring cable tension data, s is the horizontal distance between the monitoring point and the offshore platform, and v is the wave propagation velocity along the monitoring point-offshore platform direction.

[0087] Preferably, in one embodiment of the present invention, before performing migration training on the mooring cable tension prediction model according to the short-term training set, the method further includes:

[0088] Preprocessing the long-term historical data, wherein the preprocessing includes data cleaning and data transformation;

[0089] Use the moving average method to smooth the preprocessed short-term historical data;

[0090] According to the characteristics of ocean monitoring and mooring tension, feature extraction is performed on the smoothed data to construct a short-term training set.

[0091] Before performing migration training on the mooring tension prediction model based on the short-term training set, data preprocessing, smoothing, and feature extraction are key steps in building a high-quality training set. Specifically, missing value processing includes checking the missing values ​​in the data. For records with fewer missing values, interpolation methods (such as linear interpolation, Lagrange interpolation, etc.) can be used to fill them; for records with more missing values, they may need to be directly deleted or processed by other methods. Outlier processing includes identifying and processing outliers in the data. Outliers may be caused by measurement errors, equipment failures, or extreme weather conditions. Outliers can be processed by elimination, correction, or robust statistical methods. Data consistency checks include ensuring that the data is logically consistent, such as checking whether timestamps, data formats, etc. meet the requirements.

[0092] The moving average method is a commonly used time series smoothing method. It eliminates random fluctuations by weighted averaging data points, thereby revealing the trend and periodicity of the data. Specifically, it is necessary to select an appropriate moving average window size based on the fluctuation of the data and the forecasting requirements. The choice of window size will affect the effect of smoothing. If the window is too large, the data may be over-smoothed and lose detailed information. If the window is too small, random fluctuations may not be effectively eliminated. Apply the moving average method to the preprocessed short-term historical data to obtain a smoothed data series.

[0093] According to the characteristics of ocean monitoring and mooring tension, select features that have a significant impact on the prediction results. These features may include wave height, wave period, wind speed, wind direction, water flow speed, etc. Perform feature extraction on the smoothed data, including calculating statistics (such as mean, variance, maximum, minimum, etc.), performing Fourier transform to extract frequency domain features, etc. Combine the extracted features with the corresponding mooring tension data to construct a short-term training set. The training set should contain enough samples to cover various possible ocean environments and mooring tension conditions.

[0094] Preferably, in one embodiment of the present invention, the transfer training of the mooring cable tension prediction model according to the short-term training set to obtain the real-time mooring cable tension prediction model includes:

[0095] Based on the structure of the mooring cable tension prediction model, selecting a frozen layer of the mooring cable tension prediction model;

[0096] According to the frozen layer and the feature-based transfer learning method, the fully connected layer and the output layer of the mooring tension prediction model are adjusted to a blank fully connected layer and a blank output layer;

[0097] The adjusted mooring cable tension prediction model is trained based on the short-term training set, and the mooring cable tension prediction model is adjusted according to the parameters obtained during the training process to obtain a real-time mooring cable tension prediction model.

[0098] Specifically, when the marine environment conditions change in real time, the original mapping relationship parameters in the mooring tension prediction model will be adjusted based on the short-term historical monitoring data. To this end, on the basis of the mooring tension prediction model, the data correlation learned by the model in the long-term historical mooring tension monitoring data and the long-term historical marine environment (wind, wave, current direction and characteristic parameters) monitoring data part and the output of the predicted mooring tension part is retained, and the last two layers of the model are adjusted to new blank fully connected layers and output layers.

[0099] Preferably, in one embodiment of the present invention, after obtaining the mooring tension of the offshore platform in the future time period, the method further includes:

[0100] According to the physical characteristics and environmental conditions of the offshore platform, the tension thresholds of the bow cable, stern cable, bow and stern return cable and bow and stern transverse cable are set. The tension thresholds include three levels: low, medium and high, corresponding to different risk levels and response measures;

[0101] The mooring cable tension is compared with , and if the mooring cable tension exceeds the tension threshold, a corresponding warning signal is issued to warn of the risk of cable breakage.

[0102] When a round of forecasting is completed, S1-S6 are repeated to update the short-term historical data and the real-time mooring tension prediction model to ensure the timeliness of the forecast.

[0103] Another embodiment of the present invention provides a device for predicting mooring tension in a time-varying marine environment. For details, see Figure 3 , Figure 3 The figure shows a schematic diagram of the structure of a prediction device for mooring cable tension in a time-varying marine environment provided in one embodiment of the present invention. The prediction device for mooring cable tension in a time-varying marine environment comprises: a first acquisition module 11, a first training module 12, a second acquisition module 13, an alignment module 14, a second training module 15, and a prediction module 16, wherein:

[0104] A first acquisition module 11 is used to acquire long-term historical data of a first time interval in the working sea area of ​​the offshore platform;

[0105] A first training module 12 is used to train the pre-constructed basic mooring cable tension prediction model according to the long-term historical data to obtain a mooring cable tension prediction model;

[0106] A second acquisition module 13 is used to acquire short-term historical data of a second time interval in the working sea area of ​​the offshore platform, wherein the short-term historical data includes short-term ocean monitoring data and short-term mooring cable tension data, and the first time interval is greater than the second time interval;

[0107] An alignment module 14 is used to calculate the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point position distribution on the tension prediction, adjust the timestamp of the short-term ocean monitoring data according to the time difference, and align the adjusted short-term ocean monitoring data with the short-term mooring tension data to obtain a short-term training set;

[0108] A second training module 15 is used to perform migration training on the mooring cable tension prediction model according to the short-term training set to obtain a real-time mooring cable tension prediction model;

[0109] The prediction module 16 is used to input the real-time monitoring data into the real-time mooring tension prediction model to perform prediction in the actual prediction process, so as to obtain the mooring tension of the offshore platform in the future time period.

[0110] Another embodiment of the present invention provides a prediction device for mooring tension in a time-varying marine environment. For details, see Figure 3 , Figure 3 The diagram shows a schematic diagram of a prediction device for mooring tension in a time-varying marine environment provided in one embodiment of the present invention. The prediction device for mooring tension in a time-varying marine environment comprises a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned method for predicting mooring tension in a time-varying marine environment are implemented, for example: Figure 1 or, when the processor 21 executes the computer program, the functions of the modules in the above-mentioned device embodiments are implemented, such as the first acquisition module 11.

[0111] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the prediction device for mooring tension in the time-varying marine environment. For example, the computer program may be divided into a first acquisition module 11, a first training module 12, a second acquisition module 13, an alignment module 14, a second training module 15, and a prediction module 16.

[0112] The processor 21 may be a central processing unit (CPU), or other general 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 processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the prediction device for mooring tension in a time-varying marine environment, and uses various interfaces and lines to connect various parts of the prediction device for mooring tension in a time-varying marine environment.

[0113] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the prediction device for mooring tension in the time-varying marine environment by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0114] Wherein, if the module integrated in the prediction device for mooring tension in a time-varying marine environment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0115] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0116] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0117] (1) The present application obtains a real-time mooring tension prediction model by migrating and adjusting the long-term prediction model and using short-term training samples for training; the model can combine long-term and short-term monitoring data to make more accurate real-time predictions of mooring tension.

[0118] (2) The real-time mooring tension prediction model of the present application can predict the changing trend of the mooring tension in advance, thereby issuing an early warning when the mooring tension approaches or exceeds the safety threshold; this provides operators with sufficient time to take emergency measures, such as adjusting the position of the buoy, increasing the number or strength of moorings, etc., to reduce the risk of accidents.

[0119] (3) This application collects short-term historical monitoring data during the prediction work of the marine platform and performs time difference processing to eliminate the impact of the inconsistent distances between each monitoring point and the marine platform on the prediction results. This processing method makes the short-term training samples closer to the monitoring conditions during the actual prediction, thereby improving the adaptability of the model and the prediction accuracy.

[0120] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for predicting mooring tension in a time-varying marine environment, characterized in that: Applied to an offshore platform connected by mooring cable tension, a plurality of monitoring points for interacting with the offshore platform's marine data are provided in the offshore platform's working sea area, and the method comprises the following steps: Acquire long-term historical data of a first time interval in the working sea area of ​​the offshore platform; Training a pre-built basic mooring cable tension prediction model according to the long-term historical data to obtain a mooring cable tension prediction model; Acquire short-term historical data of a second time interval in the working sea area of ​​the offshore platform, wherein the short-term historical data includes short-term ocean monitoring data and short-term mooring cable tension data, and the first time interval is greater than the second time interval; Calculating the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point location distribution on the tension prediction, adjusting the timestamp of the short-term ocean monitoring data according to the time difference, and aligning the adjusted short-term ocean monitoring data with the short-term mooring tension data to obtain a short-term training set; Performing migration training on the mooring cable tension prediction model according to the short-term training set to obtain a real-time mooring cable tension prediction model; In the actual prediction process, the real-time monitoring data is input into the real-time mooring tension prediction model for prediction to obtain the mooring tension of the offshore platform in the future time period.

2. The method for predicting mooring tension in a time-varying marine environment according to claim 1, characterized in that: The pre-built basic mooring cable tension prediction model is trained according to the long-term historical data to obtain the mooring cable tension prediction model, including: Construct a basic mooring cable tension prediction model based on a double-layer neural network; Dividing the long-term historical data according to a preset ratio to obtain a training data set and a verification data set; The basic mooring cable tension prediction model is trained according to the training data set, and the performance of the model is evaluated in real time through the verification data set until a mooring cable tension prediction model that meets a preset accuracy is obtained.

3. The method for predicting mooring tension in a time-varying marine environment according to claim 1, characterized in that: The calculating the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point position distribution on the tension prediction comprises: Obtaining the horizontal distance between each of the monitoring points and the offshore platform and the wave propagation speed from the monitoring point to the offshore platform; The time difference between the short-term ocean monitoring data and the short-term mooring cable tension data is calculated according to the horizontal distance and the partial propagation speed.

4. The method for predicting mooring tension in a time-varying marine environment according to claim 3, characterized in that: The time difference between the short-term ocean monitoring data and the short-term mooring tension data is calculated according to the horizontal distance and the partial propagation speed, and is expressed by the formula: n ≥ L, t=s / v, Where n is the time difference between the short-term ocean monitoring data and the mooring cable tension to be predicted, L is the time period length of the short-term mooring cable tension data, t is the time difference between the short-term ocean monitoring data and the short-term mooring cable tension data, s is the horizontal distance between the monitoring point and the offshore platform, and v is the wave propagation velocity along the monitoring point-offshore platform direction.

5. The method for predicting mooring tension in a time-varying marine environment according to claim 1, characterized in that: Before performing migration training on the mooring cable tension prediction model according to the short-term training set, the method further includes: Preprocessing the long-term historical data, wherein the preprocessing includes data cleaning and data transformation; Use the moving average method to smooth the preprocessed short-term historical data; According to the characteristics of ocean monitoring and mooring tension, feature extraction is performed on the smoothed data to construct a short-term training set.

6. The method for predicting mooring tension in a time-varying marine environment according to claim 1, characterized in that: The step of performing migration training on the mooring cable tension prediction model according to the short-term training set to obtain a real-time mooring cable tension prediction model comprises: Based on the structure of the mooring cable tension prediction model, selecting a frozen layer of the mooring cable tension prediction model; According to the frozen layer and the feature-based transfer learning method, the fully connected layer and the output layer of the mooring tension prediction model are adjusted to a blank fully connected layer and a blank output layer; The adjusted mooring cable tension prediction model is trained based on the short-term training set, and the mooring cable tension prediction model is adjusted according to the parameters obtained during the training process to obtain a real-time mooring cable tension prediction model.

7. The method for predicting mooring tension in a time-varying marine environment according to claim 1, characterized in that: After obtaining the mooring tension of the offshore platform in the future time period, the method further includes: According to the physical characteristics and environmental conditions of the offshore platform, the tension thresholds of the bow cable, stern cable, bow and stern return cable and bow and stern transverse cable are set. The tension thresholds include three levels: low, medium and high, corresponding to different risk levels and response measures; The mooring cable tension is compared with , and if the mooring cable tension exceeds the tension threshold, a corresponding warning signal is issued to warn of the risk of cable breakage.

8. A device for predicting mooring tension in a time-varying marine environment, characterized in that: Applied to an offshore platform connected by mooring cable tension, a number of monitoring points for interacting with the offshore platform's marine data are provided in the offshore platform's working area, and the device includes the following modules: A first acquisition module is used to acquire long-term historical data of a first time interval in the working sea area of ​​the offshore platform; A first training module is used to train a pre-built basic mooring cable tension prediction model according to the long-term historical data to obtain a mooring cable tension prediction model; A second acquisition module is used to acquire short-term historical data of a second time interval in the working sea area of ​​the offshore platform, wherein the short-term historical data includes short-term ocean monitoring data and short-term mooring cable tension data, and the first time interval is greater than the second time interval; An alignment module, configured to calculate the time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the lag effect of the monitoring point location distribution on the tension prediction, adjust the timestamp of the short-term ocean monitoring data according to the time difference, and align the adjusted short-term ocean monitoring data with the short-term mooring tension data to obtain a short-term training set; A second training module is used to perform migration training on the mooring cable tension prediction model according to the short-term training set to obtain a real-time mooring cable tension prediction model; The prediction module is used to input the real-time monitoring data into the real-time mooring tension prediction model to make predictions during the actual prediction process, so as to obtain the mooring tension of the offshore platform in the future time period.

9. A device for predicting mooring tension in a time-varying marine environment, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for predicting mooring tension in a time-varying marine environment as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting mooring tension in a time-varying marine environment as described in any one of claims 1 to 7 is implemented.

Images