Seabed foundation stability prediction method, system and equipment

Abstract

The invention discloses a seabed foundation stability prediction method, system and device, and relates to the field of foundation stability prediction, and the method comprises the steps: dividing a target monitoring region into a plurality of monitoring sub-regions; collecting seabed data of each monitoring sub-area, wherein the seabed data comprises seabed slope stability data, seabed foundation safety data and seabed liquefaction data; according to the seabed data of each monitoring sub-region and a pre-trained seabed foundation stability evaluation model, obtaining a seabed foundation stability evaluation index of each monitoring sub-region; and according to the size relationship between the seabed foundation stability evaluation index of each monitoring sub-region and a preset seabed foundation stability threshold value, obtaining an evaluation result of the seabed foundation stability of each monitoring sub-region, thereby improving the accuracy of seabed foundation stability prediction.

Description

Technical Field

[0001] The present application relates to the field of foundation stability prediction, in particular to a method, system and device for predicting the stability of seabed foundations. Background Art

[0002] Under the background of the rapid development of the global marine economy, as an important cornerstone to support marine resource development and marine economic development, the safety and stability of marine infrastructure have become hot and difficult issues in the industry. With the rapid development of industries such as marine oil and gas resource development, offshore wind power, marine fishery and marine tourism, the demand for marine engineering infrastructure is increasing day by day. Therefore, the stability of the seabed foundation is directly related to the safe and effective operation of the entire marine project.

[0003] When traditional methods for predicting the stability of seabed foundations process and analyze seabed data, they often apply the evaluation models of land foundations. However, in fact, there are significant differences between the seabed and land in terms of geological characteristics, stress environments, etc. Land sites are relatively stable and less affected by hydrodynamic forces, while the seabed is in a long-term seawater immersion environment, and the physical and mechanical properties of its soil are very different from those of land soils. Applying the evaluation models of land foundations to analyze seabed foundations will ignore the special properties of the seabed and reduce the accuracy of prediction. Summary of the Invention

[0004] The purpose of the present application is to provide a method, system and device for predicting the stability of seabed foundations, which can improve the accuracy of predicting the stability of seabed foundations.

[0005] To achieve the above object, the present application provides the following solutions:

[0006] In a first aspect, the present application provides a method for predicting the stability of seabed foundations, characterized in that the method for predicting the stability of seabed foundations includes:

[0007] Dividing a target monitoring area into a plurality of monitoring sub-areas; the target monitoring area is the seabed foundation for which stability prediction is required;

[0008] Collecting seabed data of each of the monitoring sub-areas, the seabed data including: seabed slope stability data, seabed foundation safety data, and seabed liquefaction data, the seabed slope stability data including: slope surface displacement value, slope depth displacement value, soil bearing capacity, and marine soil foundation bearing capacity, the seabed foundation safety data including: seabed ground stress, seabed pore water pressure, and structural additional stress; the seabed liquefaction data including: wave height, wave period, and wave length;

[0009] Obtain the seabed foundation stability evaluation index for each of the monitoring sub - regions according to the seabed data of each of the monitoring sub - regions and a pre - trained seabed foundation stability evaluation model;

[0010] Obtain the evaluation result of the seabed foundation stability for each of the monitoring sub - regions according to the magnitude relationship between the seabed foundation stability evaluation index of each of the monitoring sub - regions and a preset seabed foundation stability threshold.

[0011] In a second aspect, the present application provides a seabed foundation stability prediction system, characterized in that the seabed foundation stability prediction system includes:

[0012] A seabed foundation prediction area division module for dividing a target monitoring area into multiple monitoring sub - regions; the target monitoring area is the seabed foundation for which stability prediction is required;

[0013] A seabed data collection module for collecting seabed data for each of the monitoring sub - regions, where the seabed data includes: seabed slope stability data, seabed foundation safety data, and seabed liquefaction data. The seabed slope stability data includes: slope surface displacement value, slope depth displacement value, soil bearing capacity, and marine soil foundation bearing capacity. The seabed foundation safety data includes: seabed ground stress, seabed pore water pressure, and additional stress of the structure. The seabed liquefaction data includes: wave height, wave period, and wave length;

[0014] A seabed data analysis module for obtaining the seabed foundation stability evaluation index for each of the monitoring sub - regions according to the seabed data of each of the monitoring sub - regions and a pre - trained seabed foundation stability evaluation model;

[0015] A seabed foundation stability evaluation module for obtaining the evaluation result of the seabed foundation stability for each of the monitoring sub - regions according to the magnitude relationship between the seabed foundation stability evaluation index of each of the monitoring sub - regions and a preset seabed foundation stability threshold.

[0016] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the seabed foundation stability prediction method described in any one of the above.

[0017] According to the specific embodiments provided by the present application, the following technical effects are disclosed by the present application:

[0018] By dividing the monitoring sub - regions of the seabed foundation, the present disclosure can achieve refined monitoring of the seabed foundation at different locations. Each monitoring sub - region is carried out independently, more precisely capturing the subtle changes of the seabed foundation, providing more accurate data support for subsequent data analysis and prediction. Moreover, the present disclosure will collect the seabed slope stability data, seabed foundation safety data, and seabed liquefaction data of each said monitoring sub - region, and will also input the seabed slope stability, seabed foundation safety, and seabed liquefaction characteristics into the pre - trained seabed foundation stability evaluation model dedicated to evaluating the seabed to evaluate the seabed foundation stability. Since the seabed slope stability data can reflect the seabed slope stability, the seabed foundation safety data can reflect the seabed foundation safety, and the seabed liquefaction data can reflect the seabed liquefaction characteristics, by combining these three dimensions and the dedicated seabed foundation stability evaluation model to analyze the seabed foundation stability, the accuracy of the seabed foundation stability evaluation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 is a flowchart of a method for predicting the stability of a seabed foundation shown according to an exemplary embodiment;

[0021] Figure 2 is Figure 1 a detailed flowchart diagram of step S103 of the method for predicting the stability of a seabed foundation in;

[0022] Figure 3 is a schematic diagram of the functional modules of a system for predicting the stability of a seabed foundation provided in an embodiment of the present application;

[0023] Figure 4 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0025] To make the above objects, features, and advantages of the present application more apparent and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] In the context of the rapid development of the global marine economy, as an important cornerstone supporting marine resource development and marine economic development, the safety and stability of marine infrastructure construction have become hot and difficult issues of concern in the industry. With the rapid development of industries such as marine oil and gas resource development, offshore wind power, marine fisheries, and marine tourism, the demand for marine engineering infrastructure is increasing day by day. Therefore, the stability of the seabed foundation is directly related to the safe and effective operation of the entire marine project.

[0027] Traditional methods for predicting the stability of seabed foundations are mainly based on physical models and limited measured data, combined with empirical judgments and simplified models for prediction, including seabed data collection steps, seabed data processing and analysis steps, and seabed foundation stability prediction steps. Among them, the seabed data collection steps are responsible for collecting on-site data such as the geology, hydrology, and meteorology of the seabed foundation; the seabed data processing and analysis steps perform operations such as cleaning, sorting, and converting the collected data, and simulate the relationship between the seabed and its foundation through the relationship between land sites and foundations to meet the needs of stability assessment; the seabed foundation stability prediction steps are used to construct a mathematical model or simplified model of the seabed foundation stability and predict the stability of the seabed foundation.

[0028] However, in actual use, there are still some disadvantages. For example, due to the continuous changes in the marine environment and the continuous progress of engineering activities, the stability of the seabed foundation will also change accordingly. Therefore, the lack of real-time and dynamic prediction methods in traditional seabed data collection steps may not meet the needs of actual projects; in the seabed data processing and analysis steps, applying the relationship between land sites and foundations does not fully consider the characteristics of marine soil itself, nor does it reasonably account for the actual state of the seabed under wave action and its deformation and failure mechanism. Therefore, the accuracy of predicting the stability of seabed foundations in the prior art is relatively low.

[0029] To solve the above technical problems, the present disclosure proposes a method, system, and device for predicting the stability of seabed foundations.

[0030] Figure 1 is a flowchart of a method for predicting the stability of seabed foundations shown according to an exemplary embodiment. As Figure 1 shown, the method includes the following steps S101 - S104:

[0031] In step S101, the target monitoring area is divided into multiple monitoring sub-areas.

[0032] The target monitoring area is the seabed foundation for which stability prediction is required.

[0033] The complex seabed foundation that needs stability prediction is set as the target monitoring area, and the target monitoring area is divided into multiple monitoring sub-areas, which are marked as 1, 2, ..., k respectively.

[0034] In this embodiment, it should be specifically explained that the target monitoring area is composed of monitoring equipment, a system operation database, a system central processing module and a user information terminal. The monitoring equipment includes a real-time dynamic differential global positioning system and various sensors. The system operation database includes all data texts for seabed foundation stability monitoring, and collects information texts output from each step in real time. The system central processing module is used to centrally control the information text instructions output from each step. The user information terminal is an information output device for receiving seabed foundation stability predictions, and is bound to a mobile phone or any output-capable electronic device based on the administrator's work information. The division of each monitoring sub-area selects appropriate division accuracy based on the actual seabed foundation position, and this disclosure does not limit the division method.

[0035] In step S102, seabed data of each monitoring sub-area is collected.

[0036] Among them, seabed data includes: seabed slope stability data, seabed foundation safety data and seabed liquefaction data.

[0037] Seabed slope stability data include: slope surface displacement value, slope depth displacement value, soil bearing capacity and marine soil foundation bearing capacity.

[0038] Seabed foundation safety data include: seabed ground stress, seabed pore water pressure and additional stress of structures.

[0039] Seabed liquefaction data include: wave height, wave period and wave length.

[0040] In this embodiment, it is necessary to collect seabed data for each monitoring sub-area, specifically including:

[0041] The seabed slope stability data of the monitoring sub-area are collected, including slope surface displacement value, slope depth displacement value, soil bearing capacity and marine soil foundation bearing capacity, which are respectively denoted as So j 、Si j 、F j and f j ; Among them, So j represents the slope surface displacement value of the jth monitoring sub-area, Si j represents the slope depth displacement value of the jth monitoring sub-area, F j represents the soil bearing capacity of the jth monitoring sub-area, f j represents the marine soil foundation bearing capacity of the jth monitoring sub-area. In actual scenarios, the soil bearing capacity of all monitoring sub-areas can be the same and is represented by F.

[0042] Collect the seabed foundation safety data of the monitoring sub-region, including seabed ground stress, seabed pore water pressure, and additional stress of the structure, denoted as Fs j , Fp j and Fc j ; Fs j represents the seabed ground stress of the j-th monitoring sub-region, Fp j represents the seabed pore water pressure of the j-th monitoring sub-region, Fc j represents the additional stress of the structure in the j-th monitoring sub-region.

[0043] Collect the seabed liquefaction data of the target monitoring area, including wave height, wave period, and wave length, denoted as Wh j , Wc j and Wb j , Wh j represents the wave height of the j-th monitoring sub-region, Wc j represents the wave period of the j-th monitoring sub-region, Wb j represents the wave length of the j-th monitoring sub-region.

[0044] Furthermore, the surface displacement value and depth displacement value of the slope are continuously measured for the slope monitoring points by installing laser rangefinders on the slope through the reflection of infrared rays; the geological characteristics and soil characteristics of the target monitoring area are obtained by multi-wave velocity sounding, and they are compared and matched with various soil types to obtain the corresponding soil types of each monitoring sub-region of the seabed slope, and then the corresponding soil bearing capacity and marine soil foundation bearing capacity are obtained by querying the preset soil bearing capacity table; the seabed ground stress is the natural stress existing in the earth's crust that has not been disturbed by engineering. By drilling holes in rocks or soils, taking out rock cores or soil samples, and then measuring the strain difference of the rocks or soils before and after taking them out, the magnitude of the ground stress can be calculated; the seabed pore water pressure is the positive stress generated by water on the solid skeleton when the rock and soil are saturated with water, and it is measured by installing vibrating wire sensors in the monitoring area; the additional stress of the structure is the stress increase caused by the load in the foundation, the wave height is the vertical distance between the wave crest and the wave trough, the wave period is the time required for the wave to pass through a certain point, and the wave length is the spatial length of one wave period, and the waves are accurately measured by wave sensors.

[0045] In the present disclosure, the seabed data of each monitoring sub-region collected in step S102 can be stored in the system operation database, and then when performing steps S103 - S104, the corresponding data can be retrieved from the system operation data.

[0046] In step S103, according to the seabed data of each monitoring sub-region and the pre-trained seabed foundation stability evaluation model, obtain the seabed foundation stability evaluation index for each monitoring sub-region.

[0047] In one embodiment, as Figure 2 shown, obtaining the seabed foundation stability evaluation index for each monitoring sub-region according to the seabed data of each monitoring sub-region and the pre-trained seabed foundation stability evaluation model includes the following sub-steps S1031 - S1033:

[0048] S1031. Preprocess the seabed data of each monitoring sub-region.

[0049] In one embodiment, preprocessing the seabed data of each monitoring sub-region includes the following sub-steps A1 - A2:

[0050] A1. Clean the seabed data of each monitoring sub-region.

[0051] A2. Normalize the cleaned seabed data of each monitoring sub-region to obtain the preprocessed seabed data of each monitoring sub-region.

[0052] In the process of seabed data processing, data cleaning and normalization are important links to improve data quality and ensure the accuracy of subsequent analysis. The specific steps of data cleaning are as follows: First, deal with missing values. For a small number of missing values in the seabed data, if the data has time series characteristics, linear interpolation method can be used to reasonably estimate and supplement according to the data of adjacent time points; if there are many missing values and they are concentrated in a certain feature dimension, it may be necessary to consider re-collecting this part of the data. Then is the detection and processing of outliers. Find the data points that deviate from the normal range through methods such as box plot analysis. For the outliers obviously caused by measurement errors, they can be corrected according to the data distribution, for example, replaced by the mean or median of the same type of data; for the outliers caused by special geological phenomena, it is necessary to carefully evaluate their rationality, and when necessary, retain and mark them in combination with professional knowledge.

[0053] In terms of data normalization, since the seabed data involves various different types of physical quantities, such as soil density, porosity, water pressure, etc., the dimensions and value ranges of each data vary greatly, and normalization processing is required. The commonly used method is min-max normalization, and its steps are: for the data of each feature dimension, find its minimum value and maximum value, and then convert the original data x to the interval [0, 1] through the following formula, which can eliminate the influence of dimensions, enable different feature data to be compared and analyzed on the same scale, and provide a better data basis for subsequent model training and analysis.

[0054]

[0055] Among them, x is the original data, x norm is the normalized original data, x min is the minimum value under the characteristic dimension corresponding to the original data, x max is the maximum value under the characteristic dimension corresponding to the original data.

[0056] S1032. Obtain the average seabed slope stability data according to the preprocessed seabed data of each monitoring sub-region.

[0057] The average seabed slope stability data includes: seabed geotechnical data, seabed dynamic data, and ocean wave data.

[0058] The seabed geotechnical data includes: the average surface displacement value of the seabed slope, the average depth displacement value of the seabed slope, and the average ocean soil foundation bearing capacity.

[0059] The seabed dynamic data includes: the seabed ground stress fluctuation value, the seabed pore water pressure fluctuation value, and the additional stress fluctuation value of the structure.

[0060] The ocean wave data includes: the average wave height, the average wave period, and the average wave length.

[0061] Obtain the average seabed slope stability data according to the preprocessed seabed data of each monitoring sub-region, including:

[0062] Obtain the seabed geotechnical data in the average seabed slope stability data according to the following formula:

[0063]

[0064] Among them, So represents the average surface displacement value of the seabed slope, So j represents the surface displacement value of the slope of the j-th monitoring sub-region, Si represents the average depth displacement value of the seabed slope, Si j represents the depth displacement value of the slope of the j-th monitoring sub-region, f represents the average ocean soil foundation bearing capacity, f j represents the ocean soil foundation bearing capacity of the j-th monitoring sub-region, and k represents the number of monitoring sub-regions.

[0065] Obtain the seabed dynamic data in the average seabed slope stability data according to the following formula:

[0066]

[0067] Among them, Fs represents the seabed ground stress fluctuation value, Fs j represents the seabed ground stress fluctuation value of the j-th monitoring sub-region, Fp represents the seabed pore water pressure fluctuation value, Fp jdenotes the seabed pore water pressure fluctuation value of the j-th monitoring sub-region, Fc denotes the additional stress fluctuation value of the structure, and Fc j denotes the additional stress fluctuation value of the structure in the j-th monitoring sub-region.

[0068] Obtain the ocean wave data in the average seabed slope stability data according to the following formula:

[0069]

[0070] where, Wh denotes the average wave height, and Wh j denotes the wave height of the j-th monitoring sub-region; Wc denotes the average wave period, and Wc j denotes the wave period of the j-th monitoring sub-region; Wb denotes the average wave length, and Wb j denotes the wave length of the j-th monitoring sub-region.

[0071] In the present disclosure, data can be cleaned and normalized through big data and machine learning to ensure data consistency and integrity, and statistical methods and machine learning algorithms are used to extract key features in the seabed data, and then the average seabed slope stability data is obtained based on the extracted key features.

[0072] S1033. Obtain the seabed slope stability coefficient, seabed foundation safety coefficient, and seabed liquefaction coefficient of each monitoring sub-region according to the preprocessed seabed data and the average seabed slope stability data of each monitoring sub-region.

[0073] A seabed slope stability analysis model can be established through machine learning algorithms, and the average seabed slope surface displacement value, average seabed slope depth displacement value, average ocean soil foundation bearing capacity, and soil bearing capacity are imported to obtain the seabed slope stability coefficient.

[0074] Specifically, the seabed slope stability coefficient of each monitoring sub-region is obtained according to the following formula:

[0075]

[0076] where, Υ j denotes the seabed slope stability coefficient of the j-th monitoring sub-region, F j denotes the soil bearing capacity of the j-th monitoring sub-region, f denotes the average ocean soil foundation bearing capacity, So denotes the average seabed slope surface displacement value, Si denotes the average seabed slope depth displacement value, and So j denotes the slope surface displacement value of the j-th monitoring sub-region, and Si j denotes the slope depth displacement value of the j-th monitoring sub-region.

[0077] Establish a seabed foundation safety analysis model, import the seabed ground stress fluctuation value, the seabed pore water pressure fluctuation value, and the additional stress fluctuation value of the structure, and obtain the seabed foundation safety coefficient. Specifically, obtain the seabed foundation safety coefficient of each monitoring sub-region according to the following formula:

[0078]

[0079] Among them, Z j represents the seabed foundation safety coefficient of the j-th monitoring sub-region, Fs represents the seabed ground stress fluctuation value, Fp represents the seabed pore water pressure fluctuation value, Fc represents the additional stress fluctuation value of the structure, and Fs j represents the seabed ground stress of the j-th monitoring sub-region, and Fp j represents the seabed pore water pressure of the j-th monitoring sub-region, and Fc j represents the additional stress of the structure in the j-th monitoring sub-region.

[0080] Establish a seabed liquefaction analysis model, import the average wave height, the average wave period, and the average wave length, and obtain the seabed liquefaction coefficient. Specifically, obtain the seabed liquefaction coefficient of each monitoring sub-region according to the following formula:

[0081]

[0082] Among them, T j represents the seabed liquefaction coefficient of the j-th monitoring sub-region, Wh represents the average wave height, Wb represents the average wave length, Wc represents the average wave period, and Wc j represents the average wave period of the j-th monitoring sub-region, and kr represents the wave reflection coefficient.

[0083] S104. Obtain the evaluation result of the seabed foundation stability of each monitoring sub-region according to the magnitude relationship between the seabed foundation stability evaluation index and the preset seabed foundation stability threshold of each monitoring sub-region.

[0084] Before performing step S104, it is also necessary to obtain a pre-trained seabed foundation stability evaluation model through training. Specifically, the above method further includes the following steps B1 - B7:

[0085] B1. Obtain the original seabed foundation stability evaluation model.

[0086] B2. Obtain the training data.

[0087] The training data includes: the historical seabed slope stability coefficient, the historical seabed foundation safety coefficient, the historical seabed liquefaction coefficient, and the labeled seabed foundation stability evaluation index.

[0088] B3. Divide the training data into a training set, a validation set, and a test set.

[0089] B4. Input the training set into the original seabed foundation stability evaluation model for training to obtain the trained seabed foundation stability evaluation model.

[0090] Specifically, these data need to be divided into different subsets first, namely: the training set, the test set, and the validation set. The training set is used for model learning and training, accounting for approximately 60%-80%, ensuring that the model has enough data for learning while avoiding overfitting. The test set is used to preliminarily evaluate the model performance after the model training is completed, accounting for approximately 10%-20%. The validation set is used to evaluate the final performance of the model to monitor the model's performance on unknown data, accounting for approximately 10%-20%, ensuring that there is enough data for validation during the model training process. To simplify the data division process, the train_test_split function in the model_selection module provided by the sklearn library in the Python programming language can be used to quickly and randomly divide the dataset into the training set and the test set.

[0091] It can be understood that the training set is used to train the model. During the training process, the model will continuously learn these sample data, identify and extract the features and patterns therein. Through repeated iteration and optimization on the training set, the model can gradually master the regularity in the data and establish a preliminary prediction ability. The test set is used to evaluate the generalization ability of the model, that is, the model's prediction ability for new data. After the model is trained, by testing the model on the test set, the generalization ability of the model on unseen data can be tested. A relatively objective evaluation criterion can be provided to measure the model's performance in actual applications. The role of the validation set is to adjust the parameters during the model training process. The data in the validation set also comes from the original data, but they neither participate in the model training nor are used for the final performance test, but are used as a reference standard for model tuning. Through the evaluation of the validation set, the true performance of the model can be objectively reflected.

[0092] B5. Adjust the trained seabed foundation stability evaluation model based on the test set to obtain the adjusted seabed foundation stability evaluation model.

[0093] Specifically, after obtaining the seabed foundation stability evaluation model through training, in order to make the model output more accurate, the model needs to be further adjusted and optimized. By fine-tuning the model parameters, it is ensured that the model can more accurately obtain the seabed foundation stability evaluation index based on the seabed slope stability coefficient, the seabed foundation safety coefficient, and the seabed liquefaction coefficient.

[0094] B6. Evaluate the adjusted seabed foundation stability evaluation model based on the validation set.

[0095] B7. When it is determined that the evaluation result meets the preset requirements, the corresponding adjusted seabed foundation stability evaluation model is the pre-trained seabed foundation stability evaluation model. When the evaluation result does not meet the preset requirements, the corresponding adjusted seabed foundation stability evaluation model is corrected, and the corrected seabed foundation stability evaluation model is used as the original seabed foundation stability evaluation model. The training, adjustment, and evaluation processes are re-executed for the corrected seabed foundation stability evaluation model until the evaluation result meets the preset requirements.

[0096] Specifically, for the deficiencies of the model identified during the evaluation process, the training dataset is adjusted. In addition, to ensure that the performance of the model can be continuously improved in actual applications, the validation set needs to be updated regularly to capture the latest data trends and changes. By continuously repeating the above evaluation process, it can be ensured that the model is in the best working state.

[0097] Exemplarily, the constructed original seabed foundation stability evaluation model can be shown as follows:

[0098]

[0099] Where, φ represents the seabed foundation stability evaluation index, λ1 represents the factor affecting the seabed slope stability coefficient, λ2 represents the factor affecting the seabed foundation safety coefficient, λ3 represents the factor affecting the seabed liquefaction coefficient (the factor ranges from 0 to 0.1), Y represents the seabed slope stability coefficient, Z represents the seabed foundation safety coefficient, T represents the seabed liquefaction coefficient. Through training, λ1, λ2, and λ3 can be obtained. Then, when calculating the seabed foundation stability evaluation index of the jth monitoring sub-region, Y in the formula represents Υ in the above embodiments j , Z in the formula represents Zj in the above embodiments, and T in the formula represents Tj in the above embodiments j , and at this time, φ represents the seabed foundation stability evaluation index of the jth monitoring sub-region.

[0100] After obtaining the seabed foundation stability evaluation index φ of each monitoring sub-region, the preset seabed foundation stability threshold φ is obtained through the system operation database D , if φ < φ D , it indicates that the seabed foundation stability evaluation index is less than the preset seabed foundation stability threshold, which means that the seabed foundation stability of the monitoring sub-region is poor; if φ ≥ φ D , it indicates that the seabed foundation stability evaluation index is greater than or equal to the preset seabed foundation stability threshold, which means that the seabed foundation stability of the monitoring sub-region is good.

[0101] Through the division of the monitoring sub - regions of the seabed foundation, the present disclosure can achieve refined monitoring of the seabed foundation at different locations. Each monitoring sub - region is carried out independently, more precisely capturing the subtle changes of the seabed foundation, providing more accurate data support for subsequent data analysis and prediction; collecting multi - dimensional data related to the seabed foundation, and then cleaning and normalizing the data to ensure data consistency and integrity, providing an important basis for data analysis; analyzing the pre - processed data to obtain the seabed slope stability coefficient, the seabed foundation safety coefficient, and the seabed liquefaction coefficient, and through the construction of a machine learning model, selecting appropriate machine learning algorithms (such as SVM, RF, GBDT, etc.) to establish a seabed foundation stability evaluation model, improving the accuracy and efficiency of the seabed foundation stability evaluation.

[0102] In one embodiment, after obtaining the evaluation results of the seabed foundation stability of each monitoring sub - region according to the size relationship between the seabed foundation stability evaluation index of each monitoring sub - region and the preset seabed foundation stability threshold, the method further includes the following sub - steps C1 - C10:

[0103] C1. Obtain the specified monitoring sub - regions in the monitoring sub - regions according to the seabed foundation stability evaluation index of each monitoring sub - region.

[0104] Among them, the seabed foundation stability evaluation index of the specified monitoring sub - region is greater than the preset threshold.

[0105] Screen the monitoring sub - regions with poor seabed foundation stability and the monitoring sub - regions with good seabed foundation stability, set the monitoring sub - regions with good seabed foundation stability as the specified monitoring sub - regions, and transmit the evaluation results of all monitoring sub - regions and the specified monitoring sub - regions to the system operation database.

[0106] Based on the evaluation results of S104, the present disclosure performs secondary analysis on the seabed data to obtain the seabed foundation stability prediction value and the seabed foundation stability prediction difference value.

[0107] C2. Collect the formation structure data and historical seabed foundation monitoring data of each specified monitoring sub - region.

[0108] The formation structure includes: the sediment characteristics and seabed topography of different ages in the specified monitoring sub - region.

[0109] The historical seabed foundation monitoring data includes: the long - term observation records and submarine geological disaster records of the specified monitoring sub - region, where the long - term observation records include the seabed elevation change, the seabed water depth change, and the long - term crustal activity of the seabed.

[0110] Specifically, the seabed elevation change can be characterized by the following multiple types of data:

[0111] Levelling data: By using instruments such as level gauges, elevation measurements at specific points on the seabed are obtained through the establishment of bench marks at different times, so as to analyze the changes in the seabed elevation over a long period.

[0112] Satellite altimetry data: Equipment such as radar altimeters carried by satellites can measure the distance from the satellite to the sea surface. Combining precise satellite orbit data and the Earth's gravity field model, etc., through a series of data processing and corrections, large-area seabed elevation information can be obtained.

[0113] Multi-beam bathymetry data: The multi-beam bathymetry system is installed on a ship. By emitting and receiving acoustic waves of multiple beams, the depths of multiple points on the seabed can be measured simultaneously, and then three-dimensional topographic data of the seabed can be obtained. Through multiple measurements and comparisons, the changes in the seabed elevation can be obtained.

[0114] The changes in the seabed water depth can be characterized by the following various types of data:

[0115] Tide gauge data: Tide gauges record the changes in the sea level height over a long period through equipment such as water level meters. Combining with the seabed topographic data, the changes in the seabed water depth can be indirectly reflected. Tide gauge data has the characteristics of a long time series and high precision, and can provide long-term change information of the seabed water depth at specific locations, which is very important for studying the changes in the seabed water depth caused by factors such as tides and storm surges.

[0116] Acoustic Doppler current profiler (ADCP) data: ADCP can measure the water flow velocities at different depth layers and can also obtain certain water depth information. By using ADCP for measurements at different times and locations and analyzing the changes in the water flow and water depth data, it helps to understand the dynamic changes in the seabed water depth, especially in studying the changes in the water depth caused by processes such as water flow scouring and sedimentation on the seabed.

[0117] Synthetic aperture radar (SAR) data: SAR satellites can measure information such as the roughness of the sea surface, invert the sea surface height and water flow conditions, and then infer the changes in the seabed water depth.

[0118] The long-term crustal activities of the seabed can be characterized by the following various types of data:

[0119] Seismic data: The seismic wave data recorded by the seismic monitoring network can be used to study the crustal structure and activities under the seabed. By analyzing the characteristics such as the propagation speed and amplitude of seismic waves, information such as the rock type and density distribution of the crust can be inferred, and then the structure of the seabed crust and potential active fault zones can be understood. Long-term seismic data monitoring can also track the spatio-temporal distribution law of seismic activities and evaluate the intensity and frequency of seabed crustal activities.

[0120] Global Positioning System (GPS) data: GPS observation stations are set up near the seabed or the coast. By receiving satellite signals, the three-dimensional coordinate changes of the observation points are accurately measured. Due to crustal movement, the positions of these observation points change over time. GPS data can directly reflect the displacement of the seabed crust in the horizontal and vertical directions, providing important quantitative data for studying the long-term crustal activities of the seabed.

[0121] Gravity data: A gravimeter is used to measure the changes in the gravity field of the seabed and its surrounding areas. The density change of crustal materials will cause anomalies in the gravity field. By analyzing the spatio-temporal changes of gravity data, the migration of crustal materials and tectonic activities below the seabed can be inferred. For example, the changes in gravity anomalies may be related to the uplift or subsidence of the seabed crust, magmatic activities, etc., providing important geophysical evidence for studying the long-term crustal activities of the seabed.

[0122] Collect the stratigraphic structure data and historical seabed foundation monitoring data of the specified monitoring sub-region. The stratigraphic structure includes the sediment characteristics and seabed topography of different ages. The historical seabed foundation monitoring data includes the long-term observation records and submarine geological disaster records of the specified monitoring sub-region. The long-term observation records include the changes in seabed elevation, seabed water depth, and the long-term crustal activities of the seabed.

[0123] C3. Construct a seabed foundation stability prediction model based on the stratigraphic structure data and historical seabed foundation monitoring data of the specified monitoring sub-region.

[0124] In an implementable manner, the stratigraphic structure data and historical seabed foundation monitoring data in seabed-related texts, articles, and web page information can be identified through feature word screening technology, and combined with the stratigraphic structure data and historical seabed foundation monitoring data collected in C2, and they are integrated to obtain a stratigraphic structure analysis data set and a historical seabed foundation monitoring analysis data set.

[0125] When integrating, the correlation degree between the stratigraphic structure data and historical seabed foundation monitoring data in seabed-related texts, articles, and web page information and the stratigraphic structure data and historical seabed foundation monitoring data collected in C2 can be determined, and then the data texts with a high correlation degree are integrated into a stratigraphic structure analysis data set and a historical seabed foundation monitoring analysis data set. Then, in step C3, a seabed foundation stability prediction model can be constructed based on the stratigraphic structure analysis data set and historical seabed foundation monitoring analysis data set of the specified monitoring sub-region.

[0126] Based on the stratigraphic structure analysis data set and historical seabed foundation monitoring analysis data set, construct a seabed foundation stability prediction model, specifically expressed as:

[0127]

[0128] Among them, W represents the predicted value of seabed foundation stability. α1 and α2 respectively represent the weight coefficients of the formation structure analysis dataset and the historical seabed foundation monitoring analysis dataset. The weight coefficients are obtained by the entropy method. φ represents the seabed foundation stability evaluation index of the specified monitoring sub-region.

[0129] When constructing a seabed foundation stability prediction model using the formation structure data and historical seabed foundation monitoring data of the specified monitoring sub-region, α1 and α2 respectively represent the weight coefficients of the formation structure data and the historical seabed foundation monitoring data.

[0130] C4. Obtain the predicted value W of the seabed foundation stability for each specified monitoring sub-region through the seabed foundation stability prediction model.

[0131] C5. Calculate the predicted difference value of the seabed foundation stability based on the predicted values of the seabed foundation stability for each specified monitoring sub-region.

[0132] The predicted difference value of the seabed foundation stability can be obtained through the following formula:

[0133] γ = (W max - W min ) / W min ;

[0134] Among them, γ represents the predicted difference value of the seabed foundation stability. W max represents the maximum value of the predicted values of the seabed foundation stability in all specified monitoring sub-regions. W min represents the minimum value of the predicted values of the seabed foundation stability in all specified monitoring sub-regions.

[0135] C6. Obtain the foundation stability level of each specified monitoring sub-region based on the predicted difference value of the seabed foundation stability and the predicted values of the seabed foundation stability of each specified monitoring sub-region.

[0136] In this step, the level determination of the seabed foundation is based on the predicted value of the seabed foundation stability and the predicted difference value of the seabed foundation stability.

[0137] Specifically, step C6 includes the following sub-steps C61 - C62:

[0138] C61. Obtain the threshold value of the seabed foundation stability level based on the predicted difference value of the seabed foundation stability and the predicted values of the seabed foundation stability of each specified monitoring sub-region.

[0139] C62. Obtain the foundation stability level of each specified monitoring sub-region based on the threshold value of the seabed foundation stability level and the seabed foundation stability evaluation index of each specified monitoring sub-region.

[0140] In this embodiment, it should be specifically noted that the seabed foundation stability levels include Seabed Foundation Stability Level 1, Seabed Foundation Stability Level 2, and Seabed Foundation Stability Level 3. Based on the seabed foundation stability prediction value and the seabed foundation stability prediction difference value, W min is set as the lower limit value of Seabed Foundation Stability Level 3, and W min ×(1 + γ / 2) is set as the lower limit value of Seabed Foundation Stability Level 2, and W min ×(1 + γ) is set as the lower limit value of Seabed Foundation Stability Level 1. If the grade determination of the specified monitoring sub-region is Seabed Foundation Stability Level 1, it indicates that the seabed foundation of the specified monitoring sub-region is stable and ocean engineering can be carried out; if the grade determination of the specified monitoring sub-region is Seabed Foundation Stability Level 2, it indicates that the seabed foundation of the specified monitoring sub-region is relatively stable, and reinforcement measures need to be taken to resist external forces or environmental changes during ocean engineering, such as grouting reinforcement and pile foundation reinforcement; if the grade determination of the specified monitoring sub-region is Seabed Foundation Stability Level 3, it indicates that the seabed foundation of the specified monitoring sub-region is unstable.

[0141] The present disclosure also proposes a human-computer interaction method, which can output the seabed slope stability coefficient, seabed foundation safety coefficient, seabed liquefaction coefficient of each monitoring sub-region, the evaluation results of the seabed foundation stability of other monitoring sub-regions except the specified monitoring sub-region in the monitoring sub-region, as well as the specified monitoring sub-region and the foundation stability levels of each specified monitoring sub-region according to the preset output method.

[0142] In this embodiment, it should be specifically noted that by building an intelligent decision-making platform, automatic early warning and intelligent decision-making are carried out for the seabed foundation stability prediction. When the prediction result is Seabed Foundation Stability Level 1, the platform will make an intelligent decision for the monitoring area. When the prediction result is Seabed Foundation Stability Level 2 or Seabed Foundation Stability Level 3, the platform will automatically issue an early warning and notify the management personnel. The management personnel will optimize or abandon the monitoring area according to the needs of ocean engineering; the preset summary methods include report summary, picture summary, and chart summary. The summary content is visually displayed through the preset summary methods. The summary content includes the seabed slope stability coefficient, seabed foundation safety coefficient, seabed liquefaction coefficient, seabed foundation stability evaluation index, specified monitoring sub-region, seabed foundation stability prediction value, and seabed foundation stability level.

[0143] By performing secondary analysis on seabed data to predict the stability of seabed foundations, the prediction efficiency of seabed foundation stability is further improved; by determining the level of seabed foundation stability, the stability of the seabed foundation can be intuitively reflected, ensuring that different stability adjustment methods and ocean engineering methods are adopted for seabed foundations with different stabilities, thereby improving the stability and economy of ocean engineering; combined with the seabed foundation stability prediction model, an intelligent decision-making platform is built to realize automatic early warning and intelligent decision-making for seabed foundation stability. Through the construction of human-computer interaction and the intelligent decision-making platform, digital management of the entire process of seabed foundation stability prediction is ultimately achieved.

[0144] In one realizable manner, the target monitoring area in the present disclosure consists of a monitoring device, a system operation database, a system central processing module, and a user information terminal. The monitoring device includes a real-time kinematic global positioning system and various sensors. The system operation database includes all data texts for seabed foundation stability monitoring and collects information texts output at each step in real time. The system central processing module is used to centrally control the information text instructions output at each step. The user information terminal is an information output device for receiving seabed foundation stability predictions and is bound to a mobile phone or any other outputtable electronic device based on the administrator's work information; the division of each monitoring sub-area selects an appropriate division accuracy according to the actual seabed foundation position.

[0145] From the above analysis, it can be seen that the present disclosure mainly solves the problems in the traditional technology of lacking real-time and dynamic prediction methods and being unable to meet the actual engineering requirements in the following aspects:

[0146] Collect multi-dimensional seabed data: Collect seabed data for each monitoring sub-area, covering seabed slope stability data, seabed foundation safety data, and seabed liquefaction data. These multi-dimensional data can more comprehensively reflect the actual situation of the seabed, providing a rich and accurate information basis for subsequent evaluation and prediction. Compared with traditional methods that only collect single or a small amount of data, it can better capture the dynamic changes of the seabed and provide data support for real-time and dynamic analysis.

[0147] Apply a pre-trained model: According to the seabed data of each monitoring sub-area and the pre-trained seabed foundation stability evaluation model, obtain the seabed foundation stability evaluation index for each monitoring sub-area. The pre-trained model is trained based on a large amount of historical data and experience and can quickly and accurately calculate the evaluation index according to the input seabed data, making the evaluation of the seabed foundation stability more scientific and accurate. Through the rapid calculation and analysis of the model, new collected data can be processed in a timely manner, achieving a certain degree of real-time evaluation, rather than lacking effective analysis means and model support like traditional methods, making it difficult to process and analyze data in a timely manner.

[0148] Judging stability based on evaluation index: According to the magnitude relationship between the seabed foundation stability evaluation index of each monitoring sub-region and the preset seabed foundation stability threshold, the evaluation result of the seabed foundation stability of each monitoring sub-region is obtained. By setting a reasonable threshold, the evaluation index can be converted into a clear stability evaluation result, quickly judging the stable state of the seabed foundation in each monitoring sub-region. This evaluation method based on data and model can update the evaluation result in real time according to new seabed data, reflecting the dynamic changes of the seabed foundation stability, meeting the requirements of real-time and dynamic nature of actual projects. However, due to the lack of such a scientific evaluation system and dynamic update mechanism, traditional methods cannot provide the evaluation result of the seabed foundation stability in a timely and accurate manner.

[0149] In summary, through a series of steps including collecting multi-dimensional data, applying a pre-trained model, and judging stability based on the evaluation index, the present disclosure realizes the real-time and dynamic evaluation of the seabed foundation stability, and solves the problems existing in the traditional technology.

[0150] Based on the same inventive concept, the embodiment of the present application also provides a seabed foundation stability prediction system for implementing the above-mentioned seabed foundation stability prediction method. The implementation solution provided by this system to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the seabed foundation stability prediction system provided below can refer to the limitations on the seabed foundation stability prediction method in the above text, and will not be elaborated here.

[0151] In an exemplary embodiment, as Figure 3 shown, a seabed foundation stability prediction system is provided. The seabed foundation stability prediction system includes:

[0152] A seabed foundation prediction area division module 11, configured to divide a target monitoring area into multiple monitoring sub-areas; the target monitoring area is the seabed foundation that needs to be predicted for stability;

[0153] A seabed data collection module 12, configured to collect seabed data of each of the monitoring sub-areas. The seabed data includes: seabed slope stability data, seabed foundation safety data, and seabed liquefaction data. The seabed slope stability data includes: slope surface displacement value, slope depth displacement value, soil bearing capacity, and marine soil foundation bearing capacity. The seabed foundation safety data includes: seabed ground stress, seabed pore water pressure, and additional stress of the structure. The seabed liquefaction data includes: wave height, wave period, and wave length;

[0154] A seabed data analysis module 13, configured to obtain the seabed foundation stability evaluation index of each of the monitoring sub-areas according to the seabed data of each of the monitoring sub-areas and the pre-trained seabed foundation stability evaluation model;

[0155] The seabed foundation stability evaluation module 14 is used to obtain the evaluation result of the seabed foundation stability of each monitoring sub-region according to the size relationship between the seabed foundation stability evaluation index and the preset seabed foundation stability threshold of each monitoring sub-region.

[0156] As an optional implementation manner, the seabed data analysis module 13 is specifically used for:

[0157] Preprocess the seabed data of each monitoring sub-region;

[0158] Obtain the average seabed slope stability data according to the preprocessed seabed data of each monitoring sub-region. The average seabed slope stability data includes: seabed geotechnical data, seabed dynamic data, and ocean wave data. The seabed geotechnical data includes: the average surface displacement value of the seabed slope, the average depth displacement value of the seabed slope, and the average ocean soil foundation bearing capacity. The seabed dynamic data includes: the seabed ground stress fluctuation value, the seabed pore water pressure fluctuation value, and the additional stress fluctuation value of the structure; the ocean wave data includes: the average wave height, the average wave period, and the average wave length;

[0159] Obtain the seabed slope stability coefficient, the seabed foundation safety coefficient, and the seabed liquefaction coefficient of each monitoring sub-region according to the preprocessed seabed data of each monitoring sub-region and the average seabed slope stability data;

[0160] Obtain the seabed foundation stability evaluation index of each monitoring sub-region according to the seabed slope stability coefficient, the seabed foundation safety coefficient, the seabed liquefaction coefficient of each monitoring sub-region, and the pre-trained seabed foundation stability evaluation model.

[0161] As an optional implementation manner, in terms of preprocessing the seabed data of each monitoring sub-region, the seabed data analysis module 13 is specifically used for:

[0162] Perform data cleaning on the seabed data of each monitoring sub-region;

[0163] Perform normalization processing on the cleaned seabed data of each monitoring sub-region to obtain the preprocessed seabed data of each monitoring sub-region.

[0164] As an optional implementation manner,

[0165] Obtain the seabed geotechnical data according to the following formula:

[0166]

[0167] wherein, So represents the average seabed slope surface displacement value, and So j represents the slope surface displacement value of the j-th monitoring sub-region, Si represents the average seabed slope depth displacement value, and Si j represents the slope depth displacement value of the j-th monitoring sub-region, f represents the average marine soil foundation bearing capacity, and f j represents the marine soil foundation bearing capacity of the j-th monitoring sub-region, and k represents the number of monitoring sub-regions;

[0168] The seabed dynamic data is obtained according to the following formula:

[0169]

[0170] wherein, Fs represents the seabed ground stress fluctuation value, and Fs j represents the seabed ground stress of the j-th monitoring sub-region, Fp represents the seabed pore water pressure fluctuation value, and Fp j represents the seabed pore water pressure of the j-th monitoring sub-region, Fc represents the structural additional stress fluctuation value, and Fc j represents the structural additional stress of the j-th monitoring sub-region.

[0171] The ocean wave data is obtained according to the following formula:

[0172]

[0173] wherein, Wh represents the average wave height, and Wh j represents the wave height of the j-th monitoring sub-region; Wc represents the average wave period, and Wc j represents the wave period of the j-th monitoring sub-region; Wb represents the average wave length, and Wb j represents the wave length of the j-th monitoring sub-region.

[0174] As an alternative implementation:

[0175] The seabed slope stability coefficient of each monitoring sub-region is obtained according to the following formula:

[0176]

[0177] wherein, Υj represents the seabed slope stability coefficient of the j-th monitoring sub-region, and F jDenote the soil bearing capacity of the j-th monitoring sub-region, where f represents the average marine soil foundation bearing capacity, So represents the average seabed slope surface displacement value, Si represents the average seabed slope depth displacement value, and So j Denote the slope surface displacement value of the j-th monitoring sub-region, and Si j Denote the slope depth displacement value of the j-th monitoring sub-region;

[0178] Obtain the seabed foundation safety factor of each monitoring sub-region according to the following formula:

[0179]

[0180] where Z j Denote the seabed foundation safety factor of the j-th monitoring sub-region, where Fs represents the seabed ground stress fluctuation value, Fp represents the seabed pore water pressure fluctuation value, Fc represents the additional stress fluctuation value of the structure, and Fs j Denote the seabed ground stress of the j-th monitoring sub-region, and Fp j Denote the seabed pore water pressure of the j-th monitoring sub-region, and Fc j Denote the additional stress of the structure in the j-th monitoring sub-region;

[0181] Obtain the seabed liquefaction coefficient of each monitoring sub-region according to the following formula:

[0182]

[0183] where T j Denote the seabed liquefaction coefficient of the j-th monitoring sub-region, where Wh represents the average wave height, Wb represents the average wave length, Wc represents the average wave period, and Wc j Denote the wave period of the j-th monitoring sub-region, and kr represents the wave reflection coefficient.

[0184] As an alternative implementation, it further includes a seabed data secondary analysis module, which is used for:

[0185] Obtain the specified monitoring sub-region in the monitoring sub-regions according to the seabed foundation stability evaluation index of each monitoring sub-region, where the seabed foundation stability evaluation index of the specified monitoring sub-region is greater than a preset threshold;

[0186] Collect the formation structure data and historical seabed foundation monitoring data of each of the specified monitoring sub-regions. The formation structure includes: the sediment characteristics and seabed topography of different ages in the specified monitoring sub-regions. The historical seabed foundation monitoring data includes: the long-term observation records and submarine geological hazard records in the specified monitoring sub-regions. The long-term observation records include seabed elevation changes, seabed water depth changes, and long-term seabed crustal activities;

[0187] Construct a seabed foundation stability prediction model based on the formation structure data and historical seabed foundation monitoring data of the specified monitoring sub-regions;

[0188] Obtain the seabed foundation stability prediction values of each of the specified monitoring sub-regions through the seabed foundation stability prediction model;

[0189] Calculate the seabed foundation stability prediction difference values based on the seabed foundation stability prediction values of each of the specified monitoring sub-regions;

[0190] Obtain the foundation stability grades of each of the specified monitoring sub-regions based on the seabed foundation stability prediction difference values and the seabed foundation stability prediction values of each of the specified monitoring sub-regions.

[0191] As an optional implementation manner, the system further includes a seabed foundation stability grade determination module, and this seabed foundation stability grade determination module is used for:

[0192] Obtain the seabed foundation stability grade thresholds based on the seabed foundation stability prediction difference values and the seabed foundation stability prediction values of each of the specified monitoring sub-regions;

[0193] Obtain the foundation stability grades of each of the specified monitoring sub-regions based on the seabed foundation stability grade thresholds and the seabed foundation stability evaluation indexes of each of the specified monitoring sub-regions.

[0194] As an optional implementation manner, the system further includes a human-computer interaction module.

[0195] The human-computer interaction module is used to output, in accordance with a preset output manner, the seabed slope stability coefficients, seabed foundation safety coefficients, and seabed liquefaction coefficients of each of the monitoring sub-regions, the evaluation results of the seabed foundation stability of other monitoring sub-regions except the specified monitoring sub-regions in the monitoring sub-regions, as well as the specified monitoring sub-regions and the foundation stability grades of each of the specified monitoring sub-regions.

[0196] In an exemplary embodiment, a computer device is provided. This computer device can be a server or a terminal, and its internal structure diagram can be as Figure 4As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for predicting the stability of seabed foundations.

[0197] Those skilled in the art can understand that Figure 4 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0198] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0199] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0200] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0201] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0202] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0203] The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0204] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0205] Specific examples are used in this article to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for predicting the stability of seabed foundation, characterized in that, The seabed foundation stability prediction method includes: Dividing the target monitoring area into multiple monitoring sub-areas; the target monitoring area is the seabed foundation for which stability prediction is required; Collecting seabed data for each of the monitoring sub-areas, where the seabed data includes: seabed slope stability data, seabed foundation safety data, and seabed liquefaction data. The seabed slope stability data includes: slope surface displacement value, slope depth displacement value, soil bearing capacity, and marine soil foundation bearing capacity. The seabed foundation safety data includes: seabed ground stress, seabed pore water pressure, and additional stress of the structure; the seabed liquefaction data includes: wave height, wave period, and wave length; Obtaining the seabed foundation stability evaluation index for each of the monitoring sub-areas according to the seabed data of each of the monitoring sub-areas and a pre-trained seabed foundation stability evaluation model; Obtaining the evaluation result of the seabed foundation stability for each of the monitoring sub-areas according to the size relationship between the seabed foundation stability evaluation index of each of the monitoring sub-areas and a preset seabed foundation stability threshold.

2. The seabed foundation stability prediction method according to claim 1, characterized in that, The step of obtaining the seabed foundation stability evaluation index for each of the monitoring sub-areas according to the seabed data of each of the monitoring sub-areas and a pre-trained seabed foundation stability evaluation model includes: Preprocessing the seabed data of each of the monitoring sub-areas; Obtaining the average seabed slope stability data according to the preprocessed seabed data of each of the monitoring sub-areas. The average seabed slope stability data includes: seabed geotechnical data, seabed dynamic data, and ocean wave data. The seabed geotechnical data includes: average seabed slope surface displacement value, average seabed slope depth displacement value, and average marine soil foundation bearing capacity. The seabed dynamic data includes: seabed ground stress fluctuation value, seabed pore water pressure fluctuation value, and additional stress fluctuation value of the structure; the ocean wave data includes: average wave height, average wave period, and average wave length; Obtaining the seabed slope stability coefficient, seabed foundation safety coefficient, and seabed liquefaction coefficient for each of the monitoring sub-areas according to the preprocessed seabed data of each of the monitoring sub-areas and the average seabed slope stability data; Obtaining the seabed foundation stability evaluation index for each of the monitoring sub-areas according to the seabed slope stability coefficient, seabed foundation safety coefficient, seabed liquefaction coefficient of each of the monitoring sub-areas and the pre-trained seabed foundation stability evaluation model.

3. The seabed foundation stability prediction method according to claim 2, characterized in that The step of preprocessing the seabed data of each of the monitoring sub-areas includes: Performing data cleaning on the seabed data of each of the monitoring sub-areas; Performing normalization processing on the cleaned seabed data of each of the monitoring sub-areas to obtain the preprocessed seabed data of each of the monitoring sub-areas.

4. The seabed foundation stability prediction method according to claim 3, wherein The seabed geotechnical data is obtained according to the following formula: Wherein, the So represents the average slope surface displacement value of the seabed, and the So j represents the slope surface displacement value of the j-th monitoring sub-region, the Si represents the average slope depth displacement value of the seabed, and the Si j represents the slope depth displacement value of the j-th monitoring sub-region, the f represents the average marine soil foundation bearing capacity, and the f j represents the marine soil foundation bearing capacity of the j-th monitoring sub-region, and the k represents the number of the monitoring sub-regions; The seabed dynamic data is obtained according to the following formula: Among them, the Fs represents the seabed ground stress fluctuation value, and the Fs j represents the seabed ground stress of the j-th monitoring sub-region, the Fp represents the seabed pore water pressure fluctuation value, and the Fp j represents the seabed pore water pressure of the j-th monitoring sub-region, the Fc represents the additional stress fluctuation value of the structure, and the Fc j represents the additional stress of the structure in the j-th monitoring sub-region; the k is the total number of monitoring sub-regions; the k is a positive integer greater than 0; The ocean wave data is obtained according to the following formula: wherein, Wh represents the average wave height, and Wh j represents the wave height of the j-th monitoring sub-region; Wc represents the average wave period, and Wc j represents the wave period of the j-th monitoring sub-region; Wb represents the average wave length, and Wb j represents the wave length of the j-th monitoring sub-region.

5. The seabed foundation stability prediction method according to claim 4, wherein Obtain the seabed slope stability coefficient of each of the monitoring sub - regions according to the following formula: Among them, the Υ j represents the seabed slope stability coefficient of the j-th monitoring sub-region, the F j represents the soil bearing capacity of the j-th monitoring sub-region, the f represents the average marine soil foundation bearing capacity, the So represents the average seabed slope surface displacement value, the Si represents the average seabed slope depth displacement value, the So j represents the slope surface displacement value of the j-th monitoring sub-region, and the Si j represents the slope depth displacement value of the j-th monitoring sub-region; Obtain the seabed foundation safety coefficient of each of the monitoring sub - regions according to the following formula: Among them, Z j represents the seabed foundation safety factor of the j-th monitoring sub-region, where Fs represents the seabed ground stress fluctuation value, Fp represents the seabed pore water pressure fluctuation value, Fc represents the additional stress fluctuation value of the structure, and Fs j represents the seabed ground stress of the j-th monitoring sub-region, and Fp j represents the seabed pore water pressure of the j-th monitoring sub-region, and Fc j represents the additional stress of the structure in the j-th monitoring sub-region; Obtain the seabed liquefaction coefficient of each of the monitoring sub - regions according to the following formula: Among them, T j represents the seabed liquefaction coefficient of the j-th monitoring sub-region, where Wh represents the average wave height, Wb represents the average wave length, Wc represents the average wave period, and Wc j represents the wave period of the j-th monitoring sub-region, and kr represents the wave reflection coefficient.

6. The method for predicting the stability of seabed foundation according to claim 5, characterized in that, After obtaining the evaluation result of the seabed foundation stability of each of the monitoring sub - regions according to the magnitude relationship between the seabed foundation stability evaluation index of each of the monitoring sub - regions and the preset seabed foundation stability threshold, the method further includes: Obtain the specified monitoring sub - regions in the monitoring sub - regions according to the seabed foundation stability evaluation index of each of the monitoring sub - regions, where the seabed foundation stability evaluation index of the specified monitoring sub - regions is greater than the preset threshold; Collect the stratigraphic structure data and historical seabed foundation monitoring data of each of the specified monitoring sub - regions. The stratigraphic structure includes: sediment characteristics and seabed topography of different ages in the specified monitoring sub - regions. The historical seabed foundation monitoring data includes: long - term observation records and submarine geological disaster records in the specified monitoring sub - regions. The long - term observation records include seabed elevation changes, seabed water depth changes, and long - term crustal activities of the seabed; Construct a seabed foundation stability prediction model based on the stratigraphic structure data and historical seabed foundation monitoring data of the specified monitoring sub - regions; Obtain the seabed foundation stability prediction values of each of the specified monitoring sub - regions through the seabed foundation stability prediction model; Calculate the seabed foundation stability prediction difference value according to the seabed foundation stability prediction values of each of the specified monitoring sub - regions; Obtain the foundation stability grades of each of the specified monitoring sub - regions according to the seabed foundation stability prediction difference value and the seabed foundation stability prediction values of each of the specified monitoring sub - regions.

7. The seabed foundation stability prediction method according to claim 6, characterized in that The obtaining of the foundation stability grades of each of the specified monitoring sub - regions according to the seabed foundation stability prediction difference value and the seabed foundation stability prediction values of each of the specified monitoring sub - regions includes: Obtain the seabed foundation stability grade threshold according to the seabed foundation stability prediction difference value and the seabed foundation stability prediction values of each of the specified monitoring sub - regions; Obtain the foundation stability grades of each of the specified monitoring sub - regions according to the seabed foundation stability grade threshold and the seabed foundation stability evaluation index of each of the specified monitoring sub - regions.

8. The seabed foundation stability prediction method according to claim 7, characterized in that The seabed foundation stability prediction method further includes: Output the seabed slope stability coefficient, seabed foundation safety coefficient, and seabed liquefaction coefficient of each of the monitoring sub - regions, the evaluation results of the seabed foundation stability of other monitoring sub - regions except the specified monitoring sub - regions in the monitoring sub - regions, and the specified monitoring sub - regions and the foundation stability grades of each of the specified monitoring sub - regions in accordance with the preset output method.

9. A seabed foundation stability prediction system, characterized in that, The seabed foundation stability prediction system includes: A seabed foundation prediction area division module for dividing the target monitoring area into multiple monitoring sub - regions; the target monitoring area is the seabed foundation that needs to conduct stability prediction; A seabed data acquisition module for acquiring seabed data of each of the monitoring sub-regions, where the seabed data includes: seabed slope stability data, seabed foundation safety data, and seabed liquefaction data. The seabed slope stability data includes: slope surface displacement value, slope depth displacement value, soil bearing capacity, and marine soil foundation bearing capacity. The seabed foundation safety data includes: seabed ground stress, seabed pore water pressure, and additional stress of the structure. The seabed liquefaction data includes: wave height, wave period, and wave length. A seabed data analysis module for obtaining a seabed foundation stability evaluation index for each of the monitoring sub-regions according to the seabed data of each of the monitoring sub-regions and a pre-trained seabed foundation stability evaluation model. A seabed foundation stability evaluation module for obtaining an evaluation result of the seabed foundation stability of each of the monitoring sub-regions according to the magnitude relationship between the seabed foundation stability evaluation index of each of the monitoring sub-regions and a preset seabed foundation stability threshold.

10. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the seabed foundation stability prediction method according to any one of claims 1-8.

Images