Anchor mooring force prediction method of immersed tube workboat based on prediction model

Abstract

The invention discloses a prediction model-based anchor mooring force prediction method for an immersed tube workboat. According to the method, water area environment characteristics, ship body posture characteristics, anchor mooring parameter characteristics and construction state characteristics are used as key data characteristics for predicting the anchor mooring force of the immersed tube construction ship; according to the method, an anchor cable tension prediction model is constructed, historical data, reduced scale physical model test data, numerical simulation data and short-term test data are subjected to data fusion to form a data set, and the model is trained and verified; and finally, predicting the tension value of each anchor mooring line on line by using the trained anchor mooring line tension prediction model. According to the method, the stress condition of each anchor mooring line can be predicted in real time under multiple working conditions (such as sinking, leveling, steering and self-storage states), and powerful support is provided for accurate positioning and safety control of installation and construction of the immersed tunnel.

Description

Technical Field

[0001] The invention belongs to the technical field of water transport engineering construction monitoring and control, and more specifically, relates to a method for predicting the anchor cable force of a submerged tube construction vessel based on a prediction model. Background Art

[0002] When constructing immersed tube tunnels in inland rivers or offshore environments, it is usually necessary to use immersed tube construction vessels (composed of square barges, connecting beams and related construction equipment) to carry out operations such as crushing and leveling, floating, sinking and positioning of immersed tubes. During these construction processes, the immersed tube construction vessels and immersed tubes are affected by complex environmental factors such as waves and currents. At the same time, due to the need for frequent steering, twisting, lowering and leveling, the tension of anchor cables and mooring cables changes significantly. These changes in mooring force directly affect construction accuracy and equipment safety.

[0003] Traditional mooring force analysis is often based on empirical formulas or numerical simulation models. When faced with dynamically changing working conditions and multi-source complex environmental data (including flow velocity, wave height, wave direction, ship attitude, initial tension of the cable, and anchor cable arrangement), numerical models are difficult to respond in a timely and accurate manner. Summary of the invention

[0004] The purpose of the present invention is to provide a method for predicting the anchor and mooring force of an immersed tube construction vessel based on a prediction model in view of the shortcomings of the prior art. The method can predict the force of each anchor and mooring cable (including anchor cables and mooring cables) in real time under multiple working conditions (such as sinking, leveling, turning, and self-storage), providing strong support for the precise positioning and safety control of the installation and construction of immersed tube tunnels.

[0005] The present invention is achieved through the following technical solutions: A method for predicting the anchor and mooring force of an immersed tube construction vessel based on a prediction model comprises the following steps: Step 1: Determine the key data characteristics for predicting anchor and mooring forces during immersed tube construction, including: Water environment parameter characteristics: flow velocity, wave height, water level and flow direction; Hull attitude characteristics: heel angle, trim angle and heading; Mooring cable parameter characteristics: initial tension of mooring cable, winch load, and material and elastic coefficient of mooring cable; Construction status characteristics: ship's turning angle, cable force, ship's ballast water distribution and ship's moving speed; Step 2, constructing a mooring cable tension prediction model; Step 3: Build the dataset, including the following steps: Step 3.1: Obtain historical data on water environment parameters, hull attitude, anchor and mooring cable parameters, construction status, and corresponding tension of each anchor and mooring cable of previous actual operation cases of immersed tube construction vessels; Step 3.2: Conduct physical model tests and CFD simulations to obtain test data and numerical simulation data of water environment parameters, hull attitude, anchor and mooring cable parameters, construction status, and corresponding tension of each anchor and mooring cable; Step 3.3: Conduct on-site short-term working tests on the immersed tube construction vessel to obtain on-site short-term test data on water environment parameters, hull attitude, anchor and mooring cable parameters, construction status, and corresponding tension of each anchor and mooring cable; Step 3.4: Fusing the historical data obtained in step 3.1, the test data and numerical simulation data obtained in step 3.2, and the on-site short-term test data obtained in step 3.3; Step 3.5: Divide the fused data into training set, validation set and test set; Step 4: Use the training set obtained in step 3 to train the anchor cable tension prediction model; The water environment parameters, ship attitude, mooring cable parameters, construction status and mooring cable tension data at the past moment are used as the input of the mooring cable tension prediction model; the output of the mooring cable tension prediction model is: the tension value of each mooring cable at the current or next moment; Step 5: Verify and evaluate the anchor cable tension prediction model; Step 6: Use the trained mooring cable tension prediction model to predict the tension value of each mooring cable online.

[0006] In the above technical solution, hydrological observation points are set up in the target water area to collect water area environmental parameter data.

[0007] In the above technical scheme, anchor cable tension sensors, mooring cable tension sensors, suspension cable tension sensors, inclinometers, ballast water meters and displacement meters are deployed on the submerged tube construction vessel to collect hull attitude data, anchor and mooring cable tension data and construction status data.

[0008] In the above technical solution, the anchor cable tension prediction model adopts a long short-term memory network model or a time convolution network model.

[0009] In the above technical solution, in step 4, the loss function of the anchor cable tension prediction model uses mean square error or mean absolute error to quantify the deviation between the predicted value and the measured value.

[0010] In the above technical solution, in step 5, the loss value of the model is monitored in real time in the validation set; when the validation effect is stable, a final evaluation is performed on the test set, and the model is quantitatively scored to ensure that it has high generalization ability in various operating conditions.

[0011] In the above technical solution, step 6 includes the following process: Rolling sampling: During the construction phase, the latest water environment parameters, ship attitude, anchor cable parameters, construction status and anchor cable tension data are collected at the set sampling frequency; the input data at the current moment is formed, and together with the input at the previous moment, a time series window is formed; Model reasoning: Call the trained mooring cable tension prediction model, input the current time and historical window data, and the mooring cable tension prediction model can quickly predict and output the predicted tension value of each mooring cable at the next moment.

[0012] In the above technical solution, the predicted tension value of each anchor cable is compared with the set safety threshold value, and if the tension of any anchor cable exceeds the set safety threshold value, an early warning is issued.

[0013] The advantages and beneficial effects of the present invention are as follows: The present invention uses water environment characteristics, hull attitude characteristics, anchor cable parameter characteristics and construction status characteristics as key data characteristics for predicting anchor and mooring force of immersed tube construction ships; constructs an anchor and mooring force prediction model, and fuses historical data, scaled physical model test data, numerical simulation data and short-term test data to form a data set, and trains and verifies the model; finally, the trained anchor and mooring force prediction model is used to predict the tension value of each anchor and mooring cable online. The present invention can predict the stress conditions of each anchor and mooring cable (including anchor cable and mooring cable) in real time under multiple working conditions (such as sinking, leveling, steering, and self-storage state), providing strong support for the precise positioning and safety control of immersed tube tunnel installation and construction. By predicting the mooring force in real time before or during the operation, abnormal load conditions can be discovered in time, and adjustment measures can be taken in advance to reduce engineering risks. The prediction results provide a reliable reference for on-site decision-making (such as cable adjustment, ballast adjustment, and construction step arrangement), shorten the decision-making cycle, and improve construction safety and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flow chart of the method for predicting the anchor cable force of a submerged tube construction vessel based on a prediction model of the present invention.

[0015] Figure 2 is a schematic diagram of the sinking condition of the immersed tube construction vessel.

[0016] Figure 3 is a comparison chart of the predicted cable force and the actual cable force of the immersed tube construction vessel during the sinking condition.

[0017] For ordinary technicians in this field, other relevant drawings can be obtained based on the above drawings without any creative work. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is further described below in conjunction with specific embodiments. Embodiment 1

[0019] The present invention designs a method for predicting the anchor cable force of a submerged tube construction vessel based on a prediction model. Figure 1 , including the following steps.

[0020] Step 1: Determine the key data characteristics for predicting anchor and mooring forces during immersed tube construction.

[0021] According to the actual operation of the immersed tube construction ship, the present invention selects the following features as key data features that affect the prediction of the anchor and mooring force of the immersed tube construction ship: (1) Characteristics of water environment parameters: flow velocity v , wave height H , water level W and flow direction θ; (2) Hull attitude characteristics: heel angle , pitch angle and heading β ； (3) Anchor cable parameter characteristics: initial tension of the anchor cable, winch load, and material and elastic coefficient of the anchor cable. Anchor cable refers to the cable anchored to the seabed or riverbed by an anchor, and the mooring cable refers to the cable tied to the fixed pier. Both the anchor cable and the mooring cable are used to fix and adjust the position and attitude of the ship. ； (4) Construction status characteristics: ship's turning angle, cable force, ship's ballast water distribution and ship's moving speed. The cable refers to the cable used to connect the submerged tube.

[0022] For water environment parameter data, hydrological observation points can be set up in the target waters to collect real-time water environment parameter data such as water level, water flow velocity, flow direction, wave height, wave period, etc. in the waters around the immersed tube construction vessel.

[0023] By deploying monitoring devices such as anchor cable tension sensors, mooring cable tension sensors, suspension cable tension sensors, inclinometers, ballast water meters and displacement meters on the submerged tube construction vessel, it is possible to collect hull attitude data, anchor and mooring cable tension and construction status data.

[0024] Step 2: Construct an anchor cable tension prediction model.

[0025] The anchor cable tension prediction model of the present invention may adopt but is not limited to the following model.

[0026] (1) Long Short-Term Memory Network Model (LSTM) Applicable scenarios: Suitable for capturing long-term dependencies in time series data. In this project, the mooring cable tension is not only related to the current environmental parameters and ship status, but also affected by the cumulative effects of water flow and ship movement over the past few minutes or even hours.

[0027] Specific advantages: The gating mechanism of LSTM (forget gate, input gate, output gate) can effectively alleviate the gradient disappearance or explosion problem caused by "long-term dependence" and maintain a high memory capacity in long-term construction monitoring.

[0028] (2) Temporal Convolutional Network (TCN) Applicable scenarios: TCN uses a one-dimensional convolution kernel to slide on the time dimension, which can extract multi-scale time series features in parallel and cover a longer historical window through dilated convolution.

[0029] Specific advantages: For high-frequency data (such as sampling at intervals of 1 second or less) or scenarios that require parallel processing of long time series, TCN can obtain stable results in a shorter training time. At the same time, different convolutional layer depths can adapt to the multiple working conditions of immersed tube construction ships.

[0030] (3) Graph Neural Network (GNN) Applicable scenarios: If the mutual influence between the anchor cables is taken into account (such as adjacent anchor cables being impacted by the same sudden water flow, or the traction mechanism being linked, etc.), each anchor cable can be regarded as a node in the graph; the hull posture, surrounding environment data, etc. are used as node / edge features.

[0031] Specific advantages: Modeling the potential coupling relationship in the anchor cable network improves the overall prediction accuracy, especially better capturing the linkage effect when the tension of some anchor cables fluctuates abnormally.

[0032] Step 3: Build the dataset.

[0033] Step 3.1: Get historical data.

[0034] Content: Based on the actual operation cases of immersed tube construction vessels in the past, the actual historical data of water environment parameters, hull posture, anchor and mooring cable parameters, construction status and corresponding tension of each anchor and mooring cable (anchor cable and mooring cable) of the immersed tube construction vessel during the working process are obtained.

[0035] Significance: It allows the model to have richer scene cognition at the initial stage and has better prediction effects on common working conditions (such as normal flow speed or medium waves).

[0036] Step 3.2: Conduct physical model tests and CFD simulations to obtain test data and numerical simulation data.

[0037] Scaled physical model test: A scaled physical model of the immersed tube construction vessel and the construction water environment is established, and a scaled physical model test is carried out. Different water environment parameters, hull postures, anchor and mooring cable parameters and construction conditions are simulated in the test field, and the tension data of each anchor and mooring cable under each condition is measured.

[0038] CFD simulation: Establish a CFD simulation model of the immersed tube construction vessel and the construction water environment. Through numerical simulation, calculate the complex flow field and the hull motion of the immersed tube construction vessel, obtain the working conditions of different water environment parameters, hull posture, anchor and mooring cable parameters and construction status, and measure the tension data of each anchor and mooring cable under each working condition.

[0039] Significance: Greatly expand the sample data under extreme working conditions (such as high flow velocity and super-large waves during flood season) or scenarios that are difficult to reproduce on site, and enhance the model's ability to learn about unconventional conditions.

[0040] Step 3.3: Conduct on-site short-term working tests on the immersed tube construction vessel and obtain on-site short-term test data.

[0041] Content: At the beginning of the project, an on-site short-term working test of the immersed tube construction vessel is carried out, and a relatively dense sampling frequency is set. During the short-term test, the actual water environment parameters, hull posture, anchor and mooring cable parameters, construction status and the corresponding tension data of each anchor and mooring cable (anchor cable and mooring cable) are recorded at a high frequency; further, the on-site short-term working test should cover key working conditions such as "immersed tube entering the water", "leveling construction", "turning operation" and "self-storage anchoring".

[0042] Significance: It is used to quickly correct the model to match the actual river environment characteristics of this project (such as local flow patterns, surges, bank reflections, etc.), and to make preliminary calibration and fine-tuning of the model to ensure that the prediction is targeted.

[0043] Step 3.4: Perform data fusion on the historical data obtained in step 3.1, the test data and numerical simulation data obtained in step 3.2, and the on-site short-term test data obtained in step 3.3.

[0044] The integration of the above three data sources can effectively cover multiple scenarios, including conventional and unconventional, historical and on-site, simulation and actual measurement. By labeling each sample with a working condition label (such as "leveling", "sinking", etc.), the prediction model can more specifically learn the changing laws of anchor cable tension under different operating modes.

[0045] Step 3.5: Divide the fused data into data sets.

[0046] The fused multi-dimensional data with timestamps (water environment parameters, hull posture, anchor cable parameters, construction status and anchor cable tension data) are divided into training set, validation set and test set according to chronological order or random sampling.

[0047] Step 4: Use the training set obtained in step 3 to train the anchor cable tension prediction model.

[0048] First, set the time window: for example, 10 minutes / 30 minutes / 1 hour as the single step duration.

[0049] The water environment parameters, hull attitude, anchor cable parameters, construction status and anchor cable tension data of several past moments (such as the previous 5 to 10 windows) are used as the input of the anchor cable tension prediction model; the output of the anchor cable tension prediction model is: the tension value of each anchor cable at the current or next moment.

[0050] The loss function of the anchor cable tension prediction model can be the mean square error (MSE) or the mean absolute error (MAE) to quantify the deviation between the predicted value and the measured value.

[0051] Optimization algorithm: Adam or SGD method is often used to iteratively update model parameters (such as neural network weights and biases).

[0052] Hyperparameter tuning: Observe the training curve and error indicators in the validation set, and adjust the number of network layers, number of neurons, learning rate, and regularization coefficient (such as L2 or Dropout) according to actual conditions.

[0053] Step 5: Verify and evaluate the anchor cable tension prediction model.

[0054] Monitor the loss value of the model in real time in the validation set. If the prediction accuracy requirement is not met (such as MAE is too large or the correlation coefficient R is too low), you need to: Increase or decrease the network depth to observe the underfitting or overfitting phenomenon of the model; Changing activation functions (ReLU, LeakyReLU, Tanh, etc.); Supplement training data, especially under conditions with large errors, and increase corresponding test and monitoring samples.

[0055] When the verification effect is stable, a final evaluation is performed on the test set, and the model is "quantitatively" scored, including MSE, MAE, correlation coefficient R, etc., to ensure that it has high generalization ability in various operating conditions.

[0056] Step 6: Use the trained mooring cable tension prediction model to predict the tension value of each mooring cable online.

[0057] Rolling sampling: During the construction phase, the latest water environment parameters, ship attitude, anchor cable parameters, construction status and anchor cable tension data are collected at a set sampling frequency (such as every 1 minute or 5 minutes); the input data at the current moment is formed, and together with the input at the previous moment, it forms a time series window.

[0058] Model reasoning: Call the trained mooring cable tension prediction model (deployed in the shipboard computer or shore-based control center), input the current time and historical window data, and the mooring cable tension prediction model can quickly predict and output the predicted tension value of each mooring cable at the next moment or in the short term (such as the next sampling window).

[0059] Furthermore, the predicted tension values ​​of each anchor cable are compared with the set safety threshold. If the tension of any anchor cable exceeds the set safety threshold, the system will immediately issue an early warning. In addition, the auxiliary operator can also make adjustments by combining the control means such as ballast adjustment, steering or winch power adjustment of the submerged tube construction vessel, such as: (1) Changing the anchor point or adjusting the tightness of the anchor cable ； (2) Adding or discharging ballast water to reduce heel or trim ； (3) Reasonably select the construction window (avoid periods with excessively high flow velocity or high waves).

[0060] This enables active control and risk management of the tension of each anchor cable, ensuring construction safety and efficiency while reducing unnecessary repeated movements or cable adjustments. Embodiment 2

[0061] Based on the solution of Example 1, this example performs the following verification.

[0062] Taking the immersed tube construction ship composed of two square barges and a connecting beam as an example, the hull is about 60 m long, about 25 m wide, and has a displacement of 4,000 tons. This embodiment constructs the following data set and uses the Transformer modeling model for verification.

[0063] Water environment parameter characteristics: flow rate v : 0.5~1.2 m / s, the flow velocity is about 0.8 m / s under common working conditions, and can reach 1.2 m / s in extreme cases; wave height H : 0.3~0.8 m. During the normal construction period, the wave height is mostly between 0.3~0.5 m. In some periods, the wind and waves are strong and can reach 0.8 m. Water level W : ±1.5 m tidal range, local daily tides cause the water level to vary by 1.5 m above or below the base elevation; flow direction θ : The angle relative to the bow of the construction ship is 0~30°, the river channel is generally straight, but there may be a deflection angle of up to ±30°.

[0064] Hull attitude characteristics: heel angle φ : -2°~+2°, generally maintained within ±1°, can reach ±2° when encountering eccentric load or tilt; Pitch angle α: -3°~+3°, affected by the difference in bow and stern loads, usually within ±2°; heading β : 0~360°, when turning β It varies depending on construction requirements, and usually the turning range does not exceed 30° each time.

[0065] Parameter characteristics of anchor cable: initial tension of anchor cable: 50-200 kN. The initial tension is about 50 kN when it is just laid. It can be pre-tensioned to 150-200 kN according to the stress conditions during construction; winch load: 0-300 kN. The winch can be adjusted according to construction requirements, and the maximum tension can reach about 300 kN; material and elastic coefficient of anchor cable: in this embodiment, steel wire cable is mainly used, and the elastic modulus is 10 ^8 ~10 ^9 N / m ^2 .

[0066] Construction status characteristics: ship's turning angle: 0~30°, the maximum one-time deflection is 30° in the turning condition, and about 10° in most cases; cable force: 0~800 kN, when the cable is used for lifting or assisting the positioning of the immersed tube, the force can reach 800 kN, and it is close to 0 when there is no lifting; ship's ballast water distribution: balanced ballast or local increase or decrease of ±20%. In order to control the longitudinal / transverse inclination of the hull, differential ballast will be performed on the left and right or bow and stern compartments, which may differ from the reference amount by up to 20%; ship's moving speed: 0~0.3 m / s, the moving speed is lower when leveling or sinking, usually not exceeding 0.2 m / s, and can reach 0.3 m / s occasionally when turning or shifting.

[0067] Under the above working conditions, about 2000 sets of anchor cable tension data were obtained, the above data were aligned in a unified time series, and missing values ​​were filled and outliers were removed.

[0068] In this embodiment, the mooring cable tension prediction model adopts the Transformer model, the learning rate is set to 0.0001, the number of training cycles can be set to 10 epochs, the number of decoder layers and the number of encoder layers are 24 and 12 respectively, and the Adam optimizer is used, and the initial momentum is set to 0.9.

[0069] See Figure 2, which is a schematic diagram of the sinking working condition of the immersed tube construction vessel. Figure 3The comparison between the predicted results of the anchor cable tension in the next three hours by the Transformer model trained based on the test data and the actual measured data under the sinking condition is shown. The horizontal axis is time (which can be expressed as hours or minutes), and the vertical axis is the cable force (unit kN). There are two curves in the figure: the solid line segment is the predicted tension under the sinking condition, and the dotted line is the measured tension under the sinking condition. Taking one hour as an example, the predicted tension under the sinking condition is 50.0kN, and the measured tension under the sinking condition is 48.2kN. The error between the predicted tension and the actual tension is 3.73%. The error does not exceed 5 kN in most periods, and the average deviation is small (maintained within the range of 2 to 5 kN). The predicted curve and the measured curve basically coincide, and the model has a good understanding and grasp of the evolution law of the cable force under the sinking condition; although there is a small error, it can be restored in a short time, and the average prediction error is within an acceptable range.

[0070] The present invention is described above by way of example. It should be noted that, without departing from the core of the present invention, any simple deformation, modification or other equivalent replacement that can be made by those skilled in the art without inventive effort falls within the protection scope of the present invention.

Claims

1. A method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model, characterized in that: The following steps are involved: Step 1: Determine the key data characteristics for predicting anchor and mooring forces during immersed tube construction, including: Water environment parameter characteristics: flow velocity, wave height, water level and flow direction; Hull attitude characteristics: heel angle, trim angle and heading; Mooring cable parameter characteristics: initial tension of mooring cable, winch load, and material and elastic coefficient of mooring cable; Construction status characteristics: ship's turning angle, cable force, ship's ballast water distribution and ship's moving speed; Step 2, constructing a mooring cable tension prediction model; Step 3: Build the dataset, including the following steps: Step 3.1: Obtain historical data on water environment parameters, hull attitude, anchor and mooring cable parameters, construction status, and corresponding tension of each anchor and mooring cable of previous actual operation cases of immersed tube construction vessels; Step 3.2: Conduct physical model tests and CFD simulations to obtain test data and numerical simulation data of water environment parameters, hull attitude, anchor and mooring cable parameters, construction status, and corresponding tension of each anchor and mooring cable; Step 3.3: Conduct on-site short-term working tests on the immersed tube construction vessel to obtain on-site short-term test data on water environment parameters, hull attitude, anchor and mooring cable parameters, construction status, and corresponding tension of each anchor and mooring cable; Step 3.4: Fusing the historical data obtained in step 3.1, the test data and numerical simulation data obtained in step 3.2, and the on-site short-term test data obtained in step 3.3; Step 3.5: Divide the fused data into training set, validation set and test set; Step 4: Use the training set obtained in step 3 to train the anchor cable tension prediction model; The water environment parameters, ship attitude, mooring cable parameters, construction status and mooring cable tension data at the past moment are used as the input of the mooring cable tension prediction model; the output of the mooring cable tension prediction model is: the tension value of each mooring cable at the current or next moment; Step 5: Verify and evaluate the anchor cable tension prediction model; Step 6: Use the trained mooring cable tension prediction model to predict the tension value of each mooring cable online.

2. The method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model according to claim 1 is characterized in that: Hydrological observation points are set up in the target waters to collect water environment parameter data.

3. The method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model according to claim 1, characterized in that: Anchor cable tension sensors, mooring cable tension sensors, hoisting cable tension sensors, inclinometers, ballast water meters and displacement meters are deployed on the immersed tube construction vessel to collect hull attitude data, anchor and mooring cable tension data and construction status data.

4. The method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model according to claim 1, characterized in that: The anchor cable tension prediction model adopts a long short-term memory network model or a temporal convolutional network model.

5. The method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model according to claim 1, characterized in that: In step 4, the loss function of the anchor cable tension prediction model uses mean square error or mean absolute error to quantify the deviation between the predicted value and the measured value.

6. The method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model according to claim 1, characterized in that: In step 5, the loss value of the model is monitored in real time in the validation set; when the validation effect is stable, a final evaluation is performed on the test set to quantitatively score the model.

7. The method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model according to claim 1, characterized in that: Step 6 includes the following process: Rolling sampling: During the construction phase, the latest water environment parameters, ship attitude, anchor cable parameters, construction status and anchor cable tension data are collected at the set sampling frequency; the input data at the current moment is formed, and together with the input at the previous moment, a time series window is formed; Model reasoning: Call the trained mooring cable tension prediction model, input the current time and historical window data, and the mooring cable tension prediction model predicts and outputs the predicted tension value of each mooring cable at the next moment.

8. The method for predicting the anchor and mooring force of a submerged tube construction vessel based on a prediction model according to claim 1, characterized in that: The predicted tension value of each mooring cable is compared with the set safety threshold. If the tension of any mooring cable exceeds the set safety threshold, an early warning is issued.

Images