Method, device and equipment for predicting mooring force under time-varying marine environment and medium

Abstract

The application discloses a kind of time-varying marine environment under mooring force prediction method, device, equipment and medium, wherein method includes: obtaining long-term historical data of offshore platform working sea area;According to long-term historical data, the training is carried out to the foundation mooring force prediction model pre-constructed, and the mooring force prediction model is obtained;Obtain short-term historical data of offshore platform working sea area;Calculate the time difference between short-term marine monitoring data and short-term mooring force data, adjust the time stamp of short-term marine monitoring data according to time difference, to obtain short-term training set;According to short-term training set, the migration training is carried out to the mooring force prediction model, and the real-time mooring force prediction model is obtained;In actual prediction process, real-time monitoring data is input into real-time mooring force prediction model and is predicted, to obtain the mooring force of offshore platform in future time period.The method provided by the application realizes the real-time prediction of accurate mooring force.

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 offshore drilling, oil production, and shipping operations. During normal operations, it is common for offshore platforms to be moored to ships or other offshore platforms. During close-range mooring operations on offshore platforms, two floating bodies are physically connected in parallel via 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 is affected by the real-time, randomly changing marine environment. Excessive movement of the floating bodies may occur at any time, causing the force response of certain connecting structures (such as mooring cables or fenders) to be excessive and exceed the threshold, thereby causing catastrophic accidents and resulting in substantial property losses.

[0003] Existing technologies typically use sensor networks to monitor key parameters such as mooring tension and buoy position in real time. However, the measurement of ocean environmental parameters (such as wind speed, wave height, and current velocity) is affected by a variety of factors, including the accuracy and location of the measurement equipment, as well as the complexity of the ocean environment. These factors can lead to inaccurate measurement data, which in turn affects the accuracy of mooring tension predictions. 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] To solve the above technical problems, an embodiment of the present invention provides a method for predicting mooring tension in a time-varying ocean environment. The method is applied to an offshore platform connected by mooring tension, wherein a plurality of monitoring points are provided in the operating sea area of ​​the offshore platform for interacting with the platform's ocean data. The method comprises:

[0006] Acquiring 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] The time difference between the short-term ocean monitoring data and the short-term mooring line tension data is calculated based on the hysteresis effect of the position distribution of the monitoring points on the tension prediction, the time stamp of the short-term ocean monitoring data is adjusted according to the time difference, the adjusted short-term ocean monitoring data is aligned with the short-term mooring line tension data, and a short-term training set is obtained;

[0010] The mooring line tension prediction model is trained according to the short-term training set, and a real-time mooring line tension prediction model is obtained.

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

[0012] As one of the preferred solutions, the pre-constructed basic mooring line tension prediction model is trained according to the long-term historical data to obtain a mooring line tension prediction model, which comprises:

[0013] A basic mooring line tension prediction model based on a double-layer neural network is constructed.

[0014] The long-term historical data is divided according to a preset proportion to obtain a training data set and a verification data set.

[0015] The basic mooring line 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 line tension prediction model meeting the preset accuracy is obtained.

[0016] As one of the preferred solutions, the time difference between the short-term ocean monitoring data and the short-term mooring line tension data is calculated based on the hysteresis effect of the position distribution of the monitoring points on the tension prediction, which comprises:

[0017] The horizontal distance of each monitoring point from the offshore platform and the wave propagation speed along the monitoring point to the offshore platform are obtained.

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

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

[0020] n≥L,

[0021] t=s / v,

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

[0023] As one of the preferred solutions, before the migration training of the mooring tension prediction model according to the short-term training set, it further includes:

[0024] The long-term historical data is preprocessed, and the preprocessing includes data cleaning and data transformation;

[0025] The preprocessed short-term historical data is smoothed using the moving average method;

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

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

[0028] Based on the structure of the mooring tension prediction model, the frozen layer of the mooring tension prediction model is selected;

[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 blank fully connected layer and blank output layer;

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

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

[0032] According to the physical characteristics and environmental conditions of the offshore platform, the tension thresholds of the bow cable, the stern cable, the bow-stern reverse cable and the bow-stern transverse cable are set, the tension thresholds include low, medium and high three levels, which correspond to different risk levels and response measures;

[0033] The mooring tension is compared, and if the mooring tension exceeds the tension threshold, a corresponding early warning signal is sent to remind the risk of cable rupture.

[0034] Another embodiment of the present application provides a device for predicting mooring line tension in a time-varying marine environment, applied to a marine platform connected by a mooring line, a plurality of monitoring points for marine data interaction being arranged in a working sea area of the marine platform, the device comprising:

[0035] a first obtaining module configured to obtain long-term historical data of the marine platform working sea area in a first time interval;

[0036] a first training module configured to train a pre-constructed basic mooring line tension prediction model according to the long-term historical data to obtain a mooring line tension prediction model;

[0037] a second obtaining module configured to obtain short-term historical data of the marine platform working sea area in a second time interval, wherein the short-term historical data comprises short-term marine monitoring data and short-term mooring line tension data, and the first time interval is greater than the second time interval;

[0038] an alignment module configured to calculate a time difference between the short-term marine monitoring data and the short-term mooring line tension data based on the lagging influence of the mooring line tension prediction on the position distribution of the monitoring points, adjust the time stamp of the short-term marine monitoring data according to the time difference, and align the adjusted short-term marine monitoring data with the short-term mooring line tension data to obtain a short-term training set;

[0039] a second training module configured to perform transfer 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;

[0040] a prediction module configured to input real-time monitoring data into the real-time mooring line tension prediction model for prediction to obtain the mooring line tension of the marine platform in a future time period.

[0041] Still another embodiment of the present application provides a device for predicting mooring line 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, the processor implementing the method for predicting mooring line tension in a time-varying marine environment as described above when executing the computer program.

[0042] Still another embodiment of the present application provides a computer readable storage medium storing a computer program, wherein a device in which the computer readable storage medium is located implements the method for predicting mooring line tension in a time-varying marine environment as described above when executing the computer program.

[0043] Compared with the prior art, the embodiment of the present application has at least one of the following advantages:

[0044] (1) The application can obtain a real-time mooring line tension prediction model by migrating and adjusting the long-term prediction model and training using short-term training samples. The model can combine long-term and short-term monitoring data to more accurately predict the real-time mooring line tension.

[0045] (2) The real-time mooring line tension prediction model of the application can predict the change trend of the mooring line tension in advance, thereby issuing a warning when the mooring line tension approaches or exceeds the safety threshold. This provides sufficient time for the operator to take emergency measures, such as adjusting the position of the floating body, increasing the number or strength of the mooring lines, etc., to reduce the risk of accidents.

[0046] (3) The application collects short-term historical monitoring data when the offshore platform is predicted to work, and performs time difference processing to eliminate the influence of the inconsistent distance of each monitoring point from the offshore platform on the prediction results. This processing method makes the short-term training samples more close to the actual monitoring situation during prediction, improving the adaptability and prediction accuracy of the model. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 is a flowchart of the mooring line tension prediction method in a time-varying marine environment in one embodiment of the application;

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

[0049] Figure 3 is a structural schematic diagram of the mooring line tension prediction device in a time-varying marine environment in one embodiment of the application;

[0050] Figure 4 is a schematic diagram of the mooring line tension prediction device in a time-varying marine environment in one embodiment of the application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the application will be described in detail below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, not all embodiments. The purpose of providing these embodiments is to make the disclosure of the application more thorough and comprehensive. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the application.

[0052] In the description of the present application, the terms "first", "second", "third", etc. are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", "third", etc. can be explicitly or implicitly included one or more of the features. In the description of the present application, unless otherwise stated, the meaning of "a plurality of" is two or more.

[0053] In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium, or it can be connected inside two elements. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are for the purpose of description only, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those skilled in the art, the specific meaning of the above terms in the present application can be understood in specific cases.

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

[0055] An embodiment of the present application provides a method for predicting mooring line tension in a time-varying marine environment, specifically, please refer to Figure 1 , Figure 1 A flowchart of the method for predicting mooring line tension in a time-varying marine environment is shown in one embodiment of the present application. It includes steps S1-S6:

[0056] S1, obtaining long-term historical data of the first time interval of the working sea area of the offshore platform;

[0057] S2, training the pre-constructed basic mooring line tension prediction model according to the long-term historical data to obtain a mooring line tension prediction model;

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

[0059] S4, calculate a time difference between the short-term ocean monitoring data and the short-term mooring tension data based on the hysteresis effect of the position distribution of the monitoring points on the tension prediction, adjust the time stamp 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;

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

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

[0062] It should be noted that the purpose of the present application is to provide a mooring tension prediction method in a time-varying ocean environment, so as to instantly predict the mooring state and timely discover abnormal extreme values of the tension to predict the risk of cable rupture in a short time. The time-varying ocean environment refers to the ocean environment in which the wind, wave and current directions and characteristic parameters of the offshore 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 and stern cables, the bow and stern back cables, and the bow and stern transverse cables connecting two floating bodies. The elements required by the prediction method include:

[0063] A plurality of remote wave height monitoring points are embedded on the sea surface far away from the two connected offshore platforms to centrally and symmetrically distribute around the sea area where the two platforms are located, so as to collect information such as the wind, wave and current directions and characteristic parameters acting on the offshore platform;

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

[0065] A data processing unit is connected with the remote wave height monitoring point unit and the mooring tension sensor to integrate and preprocess the collected data;

[0066] a data analysis platform connected with the data processing unit, analyzing the data transmitted by the data processing unit and long-term historical monitoring data of the sea area, comprehensively learning the influence of the above data, and rapidly predicting the change of the future mooring line tension;

[0067] a tension warning terminal connected with the data analysis platform unit, judging whether the predicted extreme value of the future mooring line tension exceeds the tension warning threshold and issuing a warning.

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

[0069] Preferably, in an embodiment of the present application, the pre-constructed basic mooring line tension prediction model is trained according to the long-term historical data to obtain a mooring line tension prediction model, comprising:

[0070] a basic mooring line tension prediction model based on a double-layer neural network is constructed;

[0071] The long-term historical data is divided according to a preset proportion to obtain a training data set and a verification data set;

[0072] The basic mooring line 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 line tension prediction model meeting the preset accuracy is obtained.

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

[0074] The input preprocessed long-term historical monitoring data is divided into a training set and a verification set, and appropriate batch size and training rounds are selected (usually need to be adjusted according to the size of the data set). The training data set is used for training, and the performance on the verification set is monitored.

[0075] The performance of the model is evaluated on the verification set, the loss and other indicators (such as accuracy, precision, recall rate, etc.) are monitored, and the accuracy of the model is calculated. Based on the fitting condition of the verification set, it is judged whether the model can be used as a pre-training model for migration training in time-varying environment.

[0076] Preferably, in one embodiment of the present application, the time difference between the short-term ocean monitoring data and the short-term mooring line tension data is calculated by the hysteresis effect prediction based on the distribution of monitoring point positions, including:

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

[0078] Calculating the time difference between the short-term ocean monitoring data and the short-term mooring line tension data according to the horizontal distance and the propagation speed.

[0079] Specifically, please refer to Figure 2 , Figure 2 The relative time difference between the input part and the output part when using short-term historical monitoring data as training samples for fast transfer training is shown in the schematic diagram of one embodiment of the present application. The horizontal distance of each monitoring point from the offshore platform can be obtained through geographic information system (GIS) or field measurement; the wave propagation speed along the monitoring point to the offshore platform can be measured by the monitoring point. Because the horizontal distance of different monitoring points from the offshore platform and the wave propagation speed along the monitoring point-offshore platform direction at that point are not consistent, the time difference between the input part of the short-term historical ocean environment (wind wave flow direction and characteristic parameter) monitoring data and the output part of the predicted mooring line tension for each monitoring point is not the same.

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

[0081] The time corresponding relationship between the ocean monitoring data and the mooring line tension data is analyzed. Because it takes a certain time for wave propagation to the offshore platform and cause the mooring line tension to change, the time difference can be determined by comparing the time stamps 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 the mooring line tension change.

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

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

[0084] n≥L,

[0085] t=s / v,

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

[0087] Preferably, in an embodiment of the present application, before the mooring line tension prediction model is trained according to the short-term training set, the method further comprises:

[0088] preprocessing the long-term historical data, the preprocessing comprising data cleaning and data transformation;

[0089] smoothing the preprocessed short-term historical data using a moving average method;

[0090] extracting features from the smoothed data according to the characteristics of ocean monitoring and mooring line tension to construct a short-term training set.

[0091] Before the mooring line tension prediction model is trained according to the short-term training set, data preprocessing, smoothing and feature extraction are key steps for constructing a high-quality training set. Specifically, missing value processing includes checking missing values in the data. For records with fewer missing values, interpolation methods such as linear interpolation, Lagrange interpolation, etc. can be used for filling. For records with more missing values, they may need to be deleted directly or processed using other methods. Abnormal value processing includes identifying and processing abnormal values in the data. Abnormal values may be caused by measurement errors, equipment failures or extreme weather conditions, etc. For abnormal values, they can be processed by rejection, correction or using robust statistical methods. Data consistency check includes ensuring that the data is logically consistent, such as checking whether the time stamp, data format, etc. meet the requirements.

[0092] The moving average method is a commonly used time series smoothing method that eliminates random fluctuations by taking a weighted average of data points, thereby revealing the trend and periodicity of the data. Specifically, the appropriate moving average window size needs to be selected according to the fluctuation of the data and the prediction requirements. The selection of the window size will affect the effect of smoothing, and a too large window size may cause the data to be over-smoothed and lose detailed information, and a too small window size may not effectively eliminate random fluctuations. The moving average method is applied to the pre-processed short-term historical data for smoothing to obtain a smoothed data sequence.

[0093] According to the characteristics of ocean monitoring and mooring tension, features that have a significant impact on the prediction results are selected. These features may include wave height, wave period, wind speed, wind direction, current speed, etc. Feature extraction is performed on the smoothed data, including calculating statistical quantities (such as mean, variance, maximum, minimum, etc.), performing Fourier transform to extract frequency domain features, etc. The extracted features are combined 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 situations.

[0094] Preferably, in an embodiment of the present application, the migration training of the mooring tension prediction model based on the short-term training set to obtain a real-time mooring tension prediction model comprises:

[0095] Based on the structure of the mooring tension prediction model, the frozen layer of the mooring tension prediction model is selected;

[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 blank fully connected layers and blank output layers;

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

[0098] Specifically, in the case of real-time changes in ocean environmental conditions, the original mapping relationship parameters in the mooring tension prediction model will be adjusted based on short-term historical monitoring data. For this purpose, based on the mooring tension prediction model, the data correlation learned by the model in the part of long-term historical mooring tension monitoring data and long-term historical ocean environment (wind wave flow direction and feature parameters) monitoring data and the part of outputting the predicted mooring tension is retained, and the last two layers of the model are adjusted to new blank fully connected layers and output layers.

[0099] Preferably, in an embodiment of the present application, after obtaining the mooring tension of the offshore platform in the future time period, it further comprises:

[0100] According to the physical characteristics and environmental conditions of the offshore platform, the tension thresholds of the head cable, the tail cable, the head-tail reverse cable and the head-tail cross cable are set, the tension thresholds include three levels of low, medium and high, and correspond to different risk levels and countermeasures respectively;

[0101] The mooring cable tension is compared, and if the mooring cable tension exceeds the tension threshold, a corresponding early warning signal is sent to remind the risk of cable rupture.

[0102] When a round of prediction is completed, S1-S6 are repeatedly executed to update the short-term historical data and the real-time mooring cable tension prediction model, so as to ensure the timeliness of the prediction.

[0103] Another embodiment of the present application provides a mooring cable tension prediction device in a time-varying marine environment, specifically, please refer to Figure 3 , Figure 3 The structure diagram of the mooring cable tension prediction device in a time-varying marine environment provided in one of the embodiments of the present application is shown, the mooring cable tension prediction device 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] The first acquisition module 11 is used for acquiring long-term historical data of a first time interval of a working sea area of the offshore platform;

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

[0106] The second acquisition module 13 is used for acquiring short-term historical data of a second time interval of the working sea area of the offshore platform, wherein the short-term historical data comprises short-term marine monitoring data and short-term mooring cable tension data, and the first time interval is greater than the second time interval;

[0107] The alignment module 14 is used for calculating a time difference between the short-term marine monitoring data and the short-term mooring cable tension data based on the lagging influence of the monitoring point position distribution on the tension prediction, adjusting the time stamp of the short-term marine monitoring data according to the time difference, aligning the adjusted short-term marine monitoring data with the short-term mooring cable tension data, so as to obtain a short-term training set;

[0108] The second training module 15 is used for performing transfer training on the mooring cable tension prediction model according to the short-term training set, so as to obtain a real-time mooring cable tension prediction model;

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

[0110] Another embodiment of the present application provides a device for predicting mooring line tension in time-varying marine environment, specifically, please refer to Figure 3 , Figure 3 Fig. 1 shows a schematic diagram of a device for predicting mooring line tension in time-varying marine environment according to an embodiment of the present application, which 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, wherein the processor 21 implements the steps in the method for predicting mooring line tension in time-varying marine environment as described above, such as steps S1-S6 described in the embodiment of the method for predicting mooring line tension in time-varying marine environment; or the processor 21 implements the functions of the modules in the device as described above, such as the first obtaining module 11. Figure 1

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

[0112] The processor 21 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like, and the processor 21 is the control center of the device for predicting mooring line tension in time-varying marine environment, which connects all parts of the device for predicting mooring line tension in time-varying marine environment through various interfaces and lines.

[0113] ​The memory 22 can be used to store the computer programs and / or modules, and the processor 21 realizes various functions of the mooring line tension prediction device in the time-varying marine environment by running or executing the computer programs and / or modules 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, at least one application program required for a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), and the like. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0114] The modules integrated in the mooring line tension prediction device in the time-varying marine environment can be stored in a computer readable storage medium if they are realized in the form of software function units and sold or used as independent products. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of the above-mentioned various method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0115] It can be understood by those of ordinary skill in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium and can include the processes of the above-mentioned various method embodiments when executed. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0116] Compared with the prior art, the beneficial effects of the embodiments of the present application are at least one of the following:

[0117] (1) The present application can obtain a real-time mooring line tension prediction model by migrating and adjusting the long-term prediction model and training it using short-term training samples. This model can combine long-term and short-term monitoring data to more accurately predict the mooring line tension in real time.

[0118] (2) The real-time mooring line tension prediction model of the present application can predict the trend of the mooring line tension in advance, thereby issuing a warning when the mooring line tension approaches or exceeds the safety threshold. This provides sufficient time for the operator to take emergency measures, such as adjusting the position of the floating body, increasing the number or strength of the mooring lines, etc., to reduce the risk of accidents.

[0119] (3) The present application collects short-term historical monitoring data when the offshore platform is in the prediction working state, and performs time difference processing to eliminate the influence of the inconsistent distances of various monitoring points from the offshore platform on the prediction results. This processing method makes the short-term training samples more close to the actual monitoring situation during prediction, thereby improving the adaptability and prediction accuracy of the model.

[0120] The above-described embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as limiting the scope of the present patent. It should be noted that for ordinary skilled persons in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the scope of protection of the present patent should be subject to the appended claims.

Claims

1. A method of predicting mooring line tension in a time-varying marine environment, characterized by, The method is applied to a marine platform connected by a mooring line tension, and a plurality of monitoring points for marine data interaction are arranged in the working sea area of the marine platform, and the method comprises the following steps: obtaining long-term historical data of a first time interval of the working sea area of the marine 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; obtaining short-term historical data of a second time interval of the working sea area of the marine platform, wherein the short-term historical data comprises short-term marine monitoring data and short-term mooring line tension data, and the first time interval is greater than the second time interval; calculating the time difference between the short-term marine monitoring data and the short-term mooring line tension data based on the lagging influence of the mooring line tension prediction on the position distribution of the monitoring points, adjusting the time stamp of the short-term marine monitoring data according to the time difference, aligning the adjusted short-term marine monitoring data with the short-term mooring line tension data to obtain a short-term training set; migrating training 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, inputting real-time monitoring data into the real-time mooring line tension prediction model for prediction to obtain the mooring line tension of the marine platform in a future time period.

2. The method for predicting mooring tension in a time-varying ocean environment according to claim 1, characterized in that: The training of the pre-constructed basic mooring line tension prediction model according to the long-term historical data to obtain a mooring line tension prediction model comprises: constructing a basic mooring line tension prediction model based on a double-layer neural network; dividing the long-term historical data according to a preset proportion to obtain a training data set and a verification data set; training the basic mooring line tension prediction model according to the training data set, and real-time evaluating the performance of the model through the verification data set until a mooring line tension prediction model meeting the preset accuracy is obtained.

3. The method of claim 1, wherein, The calculation of the time difference between the short-term marine monitoring data and the short-term mooring line tension data based on the lagging influence of the mooring line tension prediction on the position distribution of the monitoring points comprises: obtaining the horizontal distance of each monitoring point from the marine platform and the wave propagation speed along the monitoring point to the marine platform; calculating the time difference between the short-term marine monitoring data and the short-term mooring line tension data according to the horizontal distance and the propagation speed.

4. The method for predicting time varying mooring line tension in a marine environment according to claim 3, wherein, The calculation of the time difference between the short-term marine monitoring data and the short-term mooring line tension data according to the horizontal distance and the propagation speed is expressed by a formula as follows: n≥L, t=s / v, wherein n is the time difference between the short-term marine monitoring data and the mooring line tension to be predicted, L is the time period length of the short-term mooring line tension data, t is the time difference of the short-term marine monitoring data relative to the short-term mooring line tension data, s is the horizontal distance of the monitoring point from the marine platform, and v is the wave propagation speed along the monitoring point-marine platform direction.

5. The method of claim 1, wherein, Before the migrating training of the mooring line tension prediction model according to the short-term training set, the method further comprises: preprocessing the long-term historical data, wherein the preprocessing comprises data cleaning and data transformation; using a moving average method to smooth the preprocessed short-term historical data; According to the characteristics of marine monitoring and mooring tension, the data after smoothing processing is extracted to construct a short-term training set.

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

7. The method for predicting time varying mooring line tension in a marine environment according to claim 1, wherein, After obtaining the mooring tension of the offshore platform in the future time period, it further comprises: According to the physical characteristics and environmental conditions of the offshore platform, the tension threshold of the bowline, the sternline, the bow and stern reverse line and the bow and stern transverse line is set, the tension threshold comprises low, medium and high three levels, which correspond to different risk levels and countermeasures respectively; The mooring tension is compared, and if the mooring tension exceeds the tension threshold, a corresponding early warning signal is sent out to remind the risk of rope breakage.

8. A device for predicting mooring line tension in a time-varying marine environment, characterized by Applied to the offshore platform connected by mooring tension, a plurality of monitoring points for marine data interaction are arranged in the working sea area of the offshore platform, and the device comprises the following modules: The first acquisition module is used to acquire long-term historical data of the first time interval of the working sea area of the offshore platform; The first training module is used to train the pre-constructed basic mooring tension prediction model according to the long-term historical data, to obtain a mooring tension prediction model; The second acquisition module is used to acquire short-term historical data of the second time interval of the working sea area of the offshore platform, wherein the short-term historical data comprises short-term marine monitoring data and short-term mooring tension data, and the first time interval is greater than the second time interval; The alignment module is used to calculate the time difference between the short-term marine monitoring data and the short-term mooring tension data based on the lagging influence of the monitoring point position distribution on the tension prediction, to adjust the time stamp of the short-term marine monitoring data according to the time difference, and to align the adjusted short-term marine monitoring data with the short-term mooring tension data, to obtain a short-term training set; The second training module is used to migrate train the mooring tension prediction model according to the short-term training set, to obtain a real-time mooring tension prediction model; The prediction module is used to input real-time monitoring data into the real-time mooring tension prediction model for prediction in the actual prediction process, to obtain the mooring tension of the offshore platform in the future time period.

9. A device for predicting mooring line tension in a time-varying marine environment, characterized by The computer program is executed by the processor to realize the prediction method of the mooring tension in the time-varying marine environment as claimed in any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the prediction method of the mooring tension in the time-varying marine environment as claimed in any one of claims 1-7.

Images