Intelligent prediction system and method for towed body motion by fusing multi-scale test regression data

Abstract

The application provides a system and method for intelligently predicting the movement of a drag anchor based on regression data of multi-scale tests, comprising: an environment simulation module for generating a ship anchor model; a drag anchor test module for designing a drag anchor test water tank and a track traction device; a data analysis module for establishing an exponential relationship between the drag anchor tension and the geometric scale based on different drag anchor speeds of the multi-scale test data; and a prediction module for converting environmental parameters into the drag anchor tension, and regressing to the prototype scale ship anchor through a mapping relationship to obtain the prototype drag anchor tension under different drag anchor speeds. The system effectively reduces the influence of scale effects on test results, greatly improves the accuracy of drag anchor movement prediction, and greatly improves the prediction accuracy by fusing multi-scale test data.

Description

Technical Field

[0001] This invention relates to the field of marine engineering prediction technology, and in particular to an intelligent prediction system and method for towed anchor motion that integrates multi-scale experimental regression data. Background Technology

[0002] Dragging anchors is a common problem in anchorages. Under the combined forces of tides, waves, and wind, a ship exerts a pulling force on the anchor on the seabed. When this pulling force exceeds the maximum resistance provided by the seabed, the anchor is dragged. The hazards of dragging anchors mainly include: damaging seabed facilities such as pipelines and cables; threatening navigational safety, such as loss of control and collisions, broken anchor chains, and blockage of waterways.

[0003] There are three main methods for predicting the force and motion response of anchor dragging in the past: (1) Empirical formula method (such as API, PIANC specifications), which is mainly based on static equilibrium and predicts the critical tension required when the anchor drags. It cannot predict the motion response process of the anchor dragging. (2) Single scale physical model test method, which mainly uses a model anchor dragging test with a geometric scale (such as model / prototype = 1:50) and directly converts the experimental results to the prototype according to the scale. This method cannot solve the influence of scale effect on the test results. Therefore, the prediction effect may have a large error with the actual situation. Moreover, the error caused by scale effect often works together with measurement error, making it difficult to distinguish its specific influence law. To this day, we still lack a true understanding of scale effect. (3) Numerical simulation method, which requires calibration of a large number of soil physical parameters through physical tests or field measurements. It is a numerical generalization simulation method for the dragging process. Generally, it needs to be combined with physical tests or field observations to carry out research work. Numerical simulation of dragging alone will generally bring a large error. Therefore, this method still has a large limitation.

[0004] It is evident that both empirical formulas and numerical simulations are generalizations of the anchor dragging process. Physical model testing remains the method that most closely approximates the on-site physical process, but it faces the problem of scale effect.

[0005] Therefore, it is necessary to provide a new intelligent prediction system and method for anchor movement that integrates multi-scale experimental regression data to solve the above-mentioned technical problems. Summary of the Invention

[0006] To solve the above-mentioned technical problems, this invention provides an intelligent prediction system and method for anchor motion that integrates multi-scale test regression data. It develops a series of model test methods that can predict anchor pull and motion response. The core advantages are twofold: (1) effectively reducing the impact of scale effect on test results; (2) predicting the motion response of anchors under different anchor pulls. This method provides technical support for anchorage management and refined assessment and safety assurance of anchor risks of ships.

[0007] The intelligent prediction system for anchor motion that integrates multi-scale test regression data provided by the present invention includes: an environmental simulation module, used to generate an anchor model and simulate environmental parameters under normal and extreme weather conditions through wind field model, tidal field model and wave field model, and use the simulated environmental parameters as input data for the ship mooring model to calculate the range of the ship's drag force on the anchor; The towing anchor test module is used to design the towing anchor test water tank and the rail traction device. Water is arranged in the towing anchor test water tank according to the scale, and natural bed sand from the evaluation sea area is selected as silt. Anchor models with different geometric scales are made. The speed of the anchor movement is controlled by the rail traction device. The silt is stirred before the test to make the soil density consistent with the site. The towing anchor tension data at different scales and speeds are collected in real time. The data analysis module is used to establish an exponential relationship between anchor tension and geometric scale based on different anchor speeds from multi-scale test data. The prediction module is used to convert environmental parameters into anchor pulling force, and then regress to the prototype scale anchor through mapping relationship to obtain the prototype anchor pulling force at different anchor speeds.

[0008] Furthermore, the wind field model is a WRF model, the tidal current field model is an FVCOM model, and the wave field model is an SWAN model. The environmental simulation module simulates the wind field, tidal current field, and wave field using the WRF, FVCOM, and SWAN models respectively, and inputs the simulation results into the ship mooring model for towing force calculation.

[0009] Furthermore, the dragging anchor test module includes: The towed anchor test tank uses natural seabed sand from the evaluation area as seabed sediment. The track traction device is set above the water tank and is used to move the anchor model. The mud and sand mixer is located below the traction device and is used to mix mud and sand before the test to ensure that the soil density is consistent with that of the site. A tension sensor, connecting the anchor model to the traction device, is used to measure the tension of the towing anchor; The data acquisition unit is used to control the traction speed and record the anchor pulling force data.

[0010] Furthermore, the data analysis module establishes an exponential relationship between the anchor pulling force and the geometric scale as follows:

[0011] in The drag force of the prototype ship's anchor is the dragging speed. Geometric scale The drag force of the model below, For undetermined coefficients, and These are the velocity correction coefficients for the prototype and the model, respectively.

[0012] Furthermore, the relationship between the speed correction coefficient and the anchor speed is as follows: ,

[0013] in , , The coefficients are determined by regression using a multiscale experimental dataset. , where V is the scale index correction term, V is the anchoring speed, and C is the speed correction coefficient.

[0014] Furthermore, the prediction module converts environmental parameters into anchor pulling force by: inputting wind field parameters output by the WRF model, tidal current field parameters output by the FVCOM model, and wave field parameters output by the SWAN model into the ship mooring model; calculating the range of the ship's pulling force on the anchor through the ship mooring model; and using the range of pulling force as the model's pulling force. The model is regressed to its prototype through mapping relationships.

[0015] Another aspect of the present invention provides a method for intelligent prediction of anchor movement by fusing multi-scale experimental regression data, the method comprising the following steps: Step 1: Simulate environmental parameters: Simulate wind field, tidal field, and wave field using WRF, FVCOM, and SWAN models; Step 2: Calculate the towing force of the ship: Calculate the range of the ship's towing force on the anchor using the ship mooring model; Step 3: Collect anchoring test data: Conduct a series of multi-scale anchoring tests in the anchoring test tank and collect anchoring force data at different scales and speeds; Step 4: Establish mapping relationship: Establish an exponential relationship between anchor pulling force and geometric scale based on multi-scale test data; Step 5: Predict the prototype anchor pull force: Convert the environmental parameters into anchor pull force, and regress them to the prototype through the mapping relationship to obtain the prototype anchor pull force at different anchor speeds. This is then continuously applied to the prediction of prototype anchor motion.

[0016] Furthermore, in step five, the range of the ship's drag force on the anchor under the action of wind, waves, and current, obtained from the simulated environmental parameters, is used to establish an exponential relationship between the drag force and the geometric scale based on different dragging speeds. If the dragging speed is the same as the drag force of the prototype anchor... If the anchor's bearing capacity is exceeded, it is determined that anchoring has occurred, and the critical speed is output to obtain whether the ship has anchored and the anchor's speed under the current wind, wave, and current environmental dynamic conditions.

[0017] Compared with related technologies, the intelligent prediction system and method for anchor movement that integrates multi-scale experimental regression data provided by this invention has the following beneficial effects: 1. This system effectively reduces the long-standing "scale effect" problem in the field of ship anchor dragging prediction, that is, the impact of the scale effect on the test results, and greatly improves the accuracy of anchor dragging motion prediction. Traditional single-scale physical model tests have large deviations between the prediction results and the actual situation due to the scaling effect, while this system greatly improves the prediction accuracy by integrating multi-scale test data.

[0018] 2. Traditional standards only provide formulas for calculating static anchor holding force, which cannot predict the anchor movement response process. This system establishes a mapping relationship between anchor pulling force and anchor speed to achieve refined prediction of anchor movement, solving the problem that standard formulas underestimate anchor risks. It can predict the anchor movement response under different anchor pulling forces. This method provides technical support for anchorage management and refined assessment and safety assurance of anchor risks for ships.

[0019] 3. Based on multi-scale test data, this invention establishes an accurate exponential relationship between anchor pulling force and geometric scale. The coefficients determined by regression of the multi-scale test dataset ensure the high accuracy of the mapping relationship. Attached Figure Description

[0020] Figure 1 A structural block diagram of the intelligent prediction system for anchor motion fusion based on multi-scale experimental regression data provided by the present invention; Figure 2 A schematic diagram illustrating the relationship between the experimental dragging anchor force and the dragging anchor speed provided by the present invention; Figure 3 This is a schematic diagram illustrating the mapping relationship between anchor tension and geometric scale at different anchoring speeds provided by the present invention. Figure 4 The flowchart of the intelligent prediction method for anchor motion that integrates multi-scale experimental regression data provided by the present invention is shown in the figure. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] Please refer to the following: Figure 1 , Figure 2 , Figure 3 as well as Figure 4 ,in, Figure 1 A structural block diagram of the intelligent prediction system for anchor motion fusion based on multi-scale experimental regression data provided by the present invention; Figure 2 A schematic diagram illustrating the relationship between the experimental dragging anchor force and the dragging anchor speed provided by the present invention; Figure 3 This is a schematic diagram illustrating the mapping relationship between anchor tension and geometric scale at different anchoring speeds provided by the present invention. Figure 4 The flowchart of the intelligent prediction method for anchor motion that integrates multi-scale experimental regression data provided by the present invention is shown in the figure. Example

[0023] In the specific implementation process, such as Figures 1-3 As shown, the intelligent prediction system for anchor movement that integrates multi-scale test regression data includes: an environmental simulation module, which generates an anchor model and simulates environmental parameters under normal and extreme weather conditions through wind field model, tidal field model and wave field model. The simulated environmental parameters are used as input data for the ship mooring model MoorDyn to calculate the range of the ship's drag force on the anchor. The anchor dragging test module is used to design the anchor dragging test tank and track traction device, make anchor models with different geometric scales, control the anchor movement speed through the track traction device, and collect anchor dragging force data at different scales and speeds in real time. The data analysis module is used to establish an exponential relationship between anchor tension and geometric scale based on different anchor speeds from multi-scale test data. The prediction module is used to convert environmental parameters into anchor pulling force, and then regress to the prototype scale anchor through mapping relationship to obtain the prototype anchor pulling force at different anchor speeds.

[0024] In some embodiments, the wind field model is the WRF model, the tidal current field model is the FVCOM model, and the wave field model is the SWAN model. The environmental simulation module simulates the wind field, tidal current field, and wave field using the WRF, FVCOM, and SWAN models respectively, and inputs the simulation results into the ship mooring model MoorDyn for towing force calculation.

[0025] In some embodiments, the dragging anchor test module includes: The towing test tank is 50m long and 0.7m wide, and uses natural seabed sand from the evaluation area as seabed sediment. The track traction device is set above the water tank and is used to move the anchor model. The mud and sand mixer is located below the traction device and is used to mix mud and sand before the test to ensure that the soil density is consistent with that of the site. A tension sensor, connecting the anchor model to the traction device, is used to measure the tension of the towing anchor; The data acquisition unit is used to control the traction speed and record the anchor pulling force data.

[0026] To further explain, before the test, mud and water were placed in the tank according to the ratio, and the mud and sand were thoroughly mixed by a mixer to ensure that the soil density was consistent with that of the site. The anchor model was connected to the traction device through a tension sensor. The tension sensor had a sampling frequency of up to 100Hz and a measurement accuracy of 0.1N. The sampling process was controlled by a computer. The calibration of the sensor was completed in advance before the test. In the series of model tests, the physical properties of the bottom sand should be consistent with the properties of the bottom sediment of the target anchorage. Therefore, on-site sampling was required. Under the premise that the particle size composition of the mud and sand was consistent and the degree of consolidation and density were the same, the dragging anchor test was carried out. The multi-scale series of dragging anchor tests conducted by the dragging anchor test data acquisition module include: Three geometric scales: 1:15, 1:20, and 1:30; Six anchor dragging speeds: 0.1m / s, 0.2m / s, 0.3m / s, 0.4m / s, 0.5m / s, and 0.6m / s; Each operating condition was repeated five times to ensure data reliability.

[0027] The specific working conditions for the dragging anchor test are shown in the table below:

[0028] The results of the dragging anchor test are shown in the table below:

[0029] In some embodiments, the data analysis module establishes an exponential relationship between the anchor pull force and the geometric scale as follows:

[0030] in The drag force of the prototype ship's anchor is the dragging speed. Geometric scale The drag force of the model below, For undetermined coefficients, and These are the velocity correction coefficients for the prototype and the model, respectively.

[0031] In some embodiments, the relationship between the speed correction factor and the anchor dragging speed is as follows: ,

[0032] in , , The coefficients are determined by regression using a multiscale experimental dataset. , where V is the scale index correction term, V is the anchoring speed, and C is the speed correction coefficient.

[0033] In some embodiments, the prediction module converts environmental parameters into anchor pulling force by: inputting wind field parameters output by the WRF model, tidal current field parameters output by the FVCOM model, and wave field parameters output by the SWAN model into the ship mooring model MoorDyn; calculating the range of ship pulling force on the anchor using the ship mooring model MoorDyn; and using the range of pulling force as the model pulling force. The model is regressed to its prototype through mapping relationships.

[0034] It should be noted that, based on the multi-scale towed anchor dataset, different towed anchor speeds can be established. The prototype drag anchor pull force Scaling different sets The drag force of the model below The mapping relationship is used to revert to the prototype, i.e. =1, and the prototype anchor pull force at different anchor dragging speeds can be obtained; The following table shows the anchor pull force corresponding to different anchor dragging speeds:

[0035] Based on the range of ship-anchor drag force under the action of wind, waves and current obtained from the simulated environmental parameters, an exponential relationship between drag force and geometric scale is established according to different dragging speeds (i.e., the relationship in the table above). If the dragging speed is the same as the drag force of the prototype anchor... If the anchor's bearing capacity is exceeded, it is determined that anchoring has occurred, and the critical speed is output to obtain whether the ship has anchored and the anchor's speed under the current wind, wave, and current environmental dynamic conditions.

[0036] Currently, domestic and international standards regarding ship anchor dragging (such as API standards, PIANC standards, and the standards adopted in my country are relatively close to PIANC standards) generally agree that during the dragging process, the anchor tension should be considered as follows: It is a fixed value, mainly related to the weight and volume of the anchor and the seabed shear stress. An empirical formula table for anchor pulling force can be used. The anchor pulling speed can be determined through... Integral calculation, For ship quality, For the quality of sediment, This refers to the forces exerted on a ship by water currents, waves, and wind. However, during the movement of the anchor, the anchor pull force and the anchor speed are positively correlated; that is, under constant speed anchoring conditions, the anchor pull force... Under the influence of wind, waves, and currents, at the initial moment The anchor accelerates, and with The increase, It is also constantly increasing, when When the ship anchor moves at a constant speed, in practice, when the external load is fixed, the anchor pulling force and the anchor speed have a one-to-one mapping relationship in equilibrium. Since this mapping relationship has not yet been discovered, if the anchor holding force is calculated using the empirical formula provided by the standard, the anchor speed will often differ greatly from reality. It can be seen that there are two problems with the standard formula for calculating ship anchors: (1) the anchor holding force formula is too generalized and does not consider the influence of the ship anchor movement on the anchor holding force; (2) it is impossible to effectively predict the anchor movement speed. The empirical formula for anchor pulling force is as follows:

[0037] Numerical simulation of anchor dragging generally requires three steps: "soil parameter calibration", "model verification", and "anchor dragging process simulation". "Soil parameter calibration" is generally solved through physical tests or field measurements. "Model verification" generally requires the results of physical model tests to verify the calibration parameters of the mathematical model. Only a verified mathematical model can guarantee the accuracy of the third step, "anchor dragging process simulation". Therefore, the calculation results of the anchor dragging mathematical model often depend on the results of physical model tests.

[0038] However, anchoring physical model tests generally only select one geometric scale for model testing. The scale effect caused by model scaling will have a certain impact on the test results. The scale effect is inherent in the single-scale physical model test system and cannot be solved.

[0039] Taking a 15.4t ship anchor as an example, the prediction accuracy of the system is verified: 0.1 271.4 99.7 79.1 74.0 271.4 0.2 769.7 282.5 226.3 208.2 769.7 0.3 1416.2 519.6 419.2 383.5 1416.2 0.4 2149.3 792.6 637.8 588.3 2149.3 0.5 3027.8 1105.8 891.4 821.7 3027.8 0.6 4000.0 1458.2 1171.4 1079.3 4000.0 Based on the empirical formula for anchor holding force, on a soft clay seabed, for a bulk carrier with an anchor weight of 15.4t (approximately 150,000 tons), the anchor holding force is... =4 × 15.4 × 9.81 = 604.3 kN, approximately 604.3 kN. The drag force exerted by a ship on its anchor under the influence of wind, waves, and current. When the load reaches 271 kN, the environmental load exceeds the ship's anchor holding power, i.e. According to the standard, the anchor will not be dragged. However, according to the prediction method of dragging anchor motion response based on a series of model tests proposed in this patent, the anchor can be dragged at a speed of 0.1m / s. If the dragging risk is underestimated according to the standard, the anchor risk may be underestimated.

[0040] Meanwhile, based on the 1:30 single-scale dragging anchor test, there is a relationship between the dragging force and the dragging speed V. When the anchor speed When the speed is 0.1 m / s, its drag anchor pull force Only 74kN; according to a 1:20 scale test, its drag force is related to the dragging speed V. When the anchor speed When the speed is 0.1 m / s, its drag anchor pull force Only 79.1 kN; according to a 1:15 scale test, its drag force is related to the dragging speed V. When the anchor speed When the speed is 0.1 m / s, its drag anchor pull force The value was 99.7 kN, indicating that the difference in test results between different scales was over 40%, demonstrating the significant impact of the scale effect on the experimental results. This invention proposes a prediction method for the motion response of dragged anchors based on a series of model tests. Compared with single-scale tests, the prediction accuracy is improved by over 40%. The difference between the 1:30 single-scale test and the predicted value of this method is 3.67 times, and the difference between the 1:15 single-scale test and the predicted value of this method is 2.72 times. The difference between the test results and the single-scale test results is between 200% and 400%. This invention systematically corrects the influence of the scale effect on the dragged anchor tension and dragged anchor speed, significantly improving the refinement and accuracy of dragged anchor prediction. Example

[0041] In the specific implementation process, refer to Figure 4 As shown, the intelligent prediction method for anchor movement by integrating multi-scale experimental regression data includes the following steps: Step 1: Simulate environmental parameters: Simulate wind field, tidal field, and wave field using WRF, FVCOM, and SWAN models; Step 2: Calculate the ship's towing force: Calculate the range of the ship's towing force on the anchor using the ship mooring model MoorDyn; Step 3: Collect anchoring test data: Conduct a series of multi-scale anchoring tests in the anchoring test tank and collect anchoring force data at different scales and speeds; Step 4: Establish mapping relationship: Establish an exponential relationship between anchor pulling force and geometric scale based on multi-scale test data; Step 5: Predict the prototype anchor pull force: Convert the environmental parameters into anchor pull force, and regress them to the prototype through the mapping relationship to obtain the prototype anchor pull force at different anchor speeds. This is then continuously applied to the prediction of prototype anchor motion.

[0042] According to embodiments of the present invention, a computing device that can be used to implement the above method includes a processor and a memory; The processor can be a multi-core processor or include multiple processors. In some embodiments, the processor may include a general-purpose main processor and one or more special coprocessors, such as a graphics processing unit (GPU), a digital signal processor (DSP), etc. In some embodiments, the processor may be implemented using custom circuitry, such as an application-specific integrated circuit (ASIC) or a field-programmable gate array (FPGA).

[0043] Memory can include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM can store static data or instructions required by the processor or other modules of the computer. Permanent storage devices can be read-write storage devices. Permanent storage devices can be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices can be removable storage devices (e.g., floppy disks, optical drives). System memory can be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory can store some or all of the instructions and data required by the processor during operation. Furthermore, memory can include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks can also be used. In some implementations, the memory may include removable storage devices that are readable and / or writable, such as laser discs (CDs), read-only digital versatile optical discs (e.g., DVD-ROMs, dual-layer DVD-ROMs), read-only Blu-ray discs, ultra-high density optical discs, flash memory cards (e.g., SD cards, mini SD cards, Micro-SD cards, etc.), magnetic floppy disks, etc. Computer-readable storage media do not include carrier waves and transient electronic signals transmitted wirelessly or via wired connections.

[0044] It should be understood that, unless otherwise expressly stated herein, there is no strict order restriction on the execution of the above steps, and these steps may be executed in other orders. Moreover, at least some steps in the processes involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0045] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or basic characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects. The scope of the invention is defined by the appended claims rather than the foregoing description. Therefore, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention, and no reference numerals in the claims should be construed as limiting the scope of the claims.

[0046] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment includes only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A smart prediction system for anchor motion that integrates multi-scale test regression data, characterized in that, include: The environmental simulation module is used to generate anchor models and simulate environmental parameters under normal and extreme weather conditions using wind field models, tidal field models, and wave field models. The simulated environmental parameters are used as input data for the ship mooring model to calculate the range of the ship's drag force on the anchor. The towing anchor test module is used to design the towing anchor test water tank and the rail traction device. Water is arranged in the towing anchor test water tank according to the scale, and natural bed sand from the evaluation sea area is selected as silt. Anchor models with different geometric scales are made. The speed of the anchor movement is controlled by the rail traction device. The silt is stirred before the test to make the soil density consistent with the site. The towing anchor tension data at different scales and speeds are collected in real time. The data analysis module is used to establish an exponential relationship between anchor tension and geometric scale based on different anchor speeds from multi-scale test data. The prediction module is used to convert environmental parameters into anchor pulling force, and then regress to the prototype scale anchor through mapping relationship to obtain the prototype anchor pulling force at different anchor speeds. The drag anchor test module includes: The towed anchor test tank uses natural seabed sand from the evaluation area as seabed sediment. The track traction device is set above the water tank and is used to move the anchor model. The mud and sand mixer is located below the traction device and is used to mix mud and sand before the test to ensure that the soil density is consistent with that of the site. A tension sensor, connecting the anchor model to the traction device, is used to measure the tension of the towing anchor; The data acquisition unit is used to control the traction speed and record the anchor pull data; The data analysis module establishes an exponential relationship between anchor pull force and geometric scale as follows: ； in The drag force of the prototype ship's anchor is the dragging speed. Geometric scale The drag force of the model below, For undetermined coefficients, and These are the velocity correction coefficients for the prototype and the model, respectively.

2. The intelligent prediction system for anchor motion fusion based on multi-scale test regression data according to claim 1, characterized in that, The wind field model is the WRF model, the tidal current field model is the FVCOM model, and the wave field model is the SWAN model. The environmental simulation module simulates the wind field, tidal current field, and wave field using the WRF, FVCOM, and SWAN models respectively, and inputs the simulation results into the ship mooring model for towing force calculation.

3. The intelligent prediction system for anchor motion fusion based on multi-scale test regression data according to claim 2, characterized in that, The relationship between the speed correction factor and the anchor speed is as follows: , ;in , , The coefficients are determined by regression using a multiscale experimental dataset. , where V is the scale index correction term, V is the anchoring speed, and C is the speed correction coefficient.

4. The intelligent prediction system for anchor motion fusion based on multi-scale test regression data according to claim 3, characterized in that, The prediction module converts environmental parameters into anchor pulling force by: inputting wind field parameters output from the WRF model, tidal current field parameters output from the FVCOM model, and wave field parameters output from the SWAN model into the ship mooring model; calculating the range of the ship's pulling force on the anchor using the ship mooring model; and using the range of pulling force as the model's pulling force. The model is regressed to its prototype through mapping relationships.

5. A method for intelligent prediction of anchor motion by integrating multi-scale test regression data, applicable to the intelligent prediction system for anchor motion by integrating multi-scale test regression data as described in any one of claims 1-4, characterized in that, The method includes the following steps: Step 1: Simulate environmental parameters: Simulate wind field, tidal field, and wave field using WRF, FVCOM, and SWAN models; Step 2: Calculate the towing force of the ship: Calculate the range of the ship's towing force on the anchor using the ship mooring model; Step 3: Collect anchoring test data: Conduct a series of multi-scale anchoring tests in the anchoring test tank and collect anchoring force data at different scales and speeds; Step 4: Establish mapping relationship: Establish an exponential relationship between anchor pulling force and geometric scale based on multi-scale test data; Step 5: Predict the prototype anchor pull force: Convert the environmental parameters into anchor pull force, and regress them to the prototype through the mapping relationship to obtain the prototype anchor pull force at different anchor speeds. This is then continuously applied to the prediction of prototype anchor motion.

6. The intelligent prediction method for anchor motion fusion based on multi-scale experimental regression data according to claim 5, characterized in that, Step five establishes an exponential relationship between the anchor pulling force and the geometric scale based on the range of the ship's dragging force under the action of wind, waves and current obtained from the simulated environmental parameters, according to different anchoring speeds. If the anchoring speed is the same as the prototype anchor's dragging force... If the anchor's bearing capacity is exceeded, it is determined that anchoring has occurred, and the critical speed is output to obtain whether the ship has anchored and the anchor's speed under the current wind, wave, and current environmental dynamic conditions.

Images