Marine three-dimensional layered right setting project monitoring and early warning method and system

Abstract

The invention discloses a marine three-dimensional layered right setting project monitoring and early warning method and system, and relates to the technical field of marine monitoring and early warning. According to the marine three-dimensional layered right setting project monitoring and early warning method, a marine monitoring time sequence data set in a set marine oil exploitation area is continuously obtained, and feature analysis is carried out respectively, so that a monitoring and early warning index set of each time point in the set marine oil exploitation area is obtained; comprising a sea surface mining stress index, an ocean middle-layer operation disturbance index and a seabed mining comprehensive risk index; and performing comprehensive analysis on the monitoring early warning index set of each time point in the set offshore oil exploitation area to obtain an oil exploitation early warning index of each time point. Intelligent oil exploitation early warning is performed based on the oil exploitation early warning index of each time point in the set offshore oil exploitation area; therefore, the accuracy of early warning is improved, potential risks are recognized in time, and a powerful guarantee is provided for the safety of ocean exploitation activities.

Description

Technical Field

[0001] The present invention relates to the technical field of marine monitoring and early warning, and specifically to a monitoring and early warning method and system for a marine three-dimensional layered rights project. Background Art

[0002] With the development of the global economy and technology, the exploitation and utilization of marine resources have become increasingly important. Especially in the fields of energy, mineral resource extraction, and marine ecological protection, activities such as the exploitation of deep-sea oil and gas and the extraction of seabed minerals bring huge economic benefits, but also pose potential threats to the marine environment. In order to ensure the efficient development of marine resources and at the same time guarantee the sustainable development of the marine ecosystem, marine environmental monitoring and early warning systems have become crucial technical means. The proposed marine three-dimensional layered monitoring technology aims to comprehensively monitor each layer of the ocean, timely detect potential risks in the marine environment, be able to obtain multi-dimensional marine environmental data comprehensively and in real time, provide a scientific basis for decision-makers, and ensure the safety of marine resource development and the effectiveness of environmental protection.

[0003] The prior art, such as a patent application with the publication number: CN119479211A, discloses a method and system for marine environmental monitoring and early warning based on big data. The steps are as follows: It relates to the technical field of marine environmental monitoring. This method includes: collecting environmental data in real time through sensors in monitoring stations and transmitting it to a database; using positioning technology to obtain the location information of each monitoring station, and calculating the distance between a randomly selected reference monitoring station and the corresponding comparison monitoring station; analyzing the change trend of environmental data, and determining the propagation speed of abnormal environmental data based on the analysis results; combining the distance and the propagation speed, and using a linear propagation algorithm to calculate the arrival time of abnormal environmental data from the reference monitoring station to the comparison monitoring station; setting an alarm activation time according to the arrival time and issuing an alarm message. The present invention realizes the real-time monitoring and data collection of the marine environment through the deployment of monitoring stations and the integration of sensor technology, providing a comprehensive and accurate information basis for subsequent data analysis and early warning.

[0004] Based on the above scheme, it is found that the limitations of the prior art at least include the following problems. The prior art lacks a comprehensive analysis of different layers of the ocean, resulting in difficulties in comprehensively and accurately evaluating the mutual influence of environmental data at each layer in the face of complex marine environmental changes. For example, climate changes on the ocean surface are likely to affect the middle-layer water flow, and changes in the middle-layer water flow are likely to indirectly affect the bottom topography and microbial activity, resulting in a lag in the response of the early warning system to marine environmental changes, failing to timely capture the dynamic changes on the ocean surface, in the middle layer, and at the bottom, thus affecting the accuracy and timeliness of early warning information, and further reducing the safety of marine oil exploitation. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a method and system for monitoring and early warning of ocean three-dimensional stratified rights projects, which solves the problems that the prior art is difficult to comprehensively reflect the complex changes of the ocean environment, affects the accuracy and timeliness of early warning information, and reduces the safety of ocean oil exploitation.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for monitoring and early warning of ocean three-dimensional stratified rights projects, including the following steps: Continuously obtain the ocean monitoring time series data set within the set ocean oil exploitation area, including ocean surface layer monitoring time series data, ocean middle layer monitoring time series data, and ocean bottom layer monitoring time series data; perform feature analysis on the ocean monitoring time series data set within the set ocean oil exploitation area respectively to obtain the monitoring and early warning index set at each time point within the set ocean oil exploitation area, including sea surface exploitation stress index, ocean middle layer operation disturbance index, and seabed exploitation comprehensive risk index; perform comprehensive analysis on the monitoring and early warning index set at each time point within the set ocean oil exploitation area to obtain the oil exploitation early warning index at each time point within the set ocean oil exploitation area; perform intelligent oil exploitation early warning based on the oil exploitation early warning index at each time point within the set ocean oil exploitation area.

[0007] Furthermore, the specific formula for calculating the oil exploitation early warning index at each time point within the set ocean oil exploitation area is as follows: ; where is the oil exploitation early warning index at the th time point within the set ocean oil exploitation area, is the sea surface exploitation stress index at the th time point within the set ocean oil exploitation area, is the sea surface stress coefficient stored in the database, is the sea surface stress adjustment coefficient stored in the database, is the smoothing coefficient stored in the database, is the ocean middle layer operation disturbance index at the th time point within the set ocean oil exploitation area, is the middle layer disturbance coefficient stored in the database, is the middle layer disturbance adjustment coefficient stored in the database, is the seabed exploitation comprehensive risk index at the th time point within the set ocean oil exploitation area, is the seabed risk coefficient stored in the database, is the seabed risk adjustment coefficient stored in the database, is the interaction coefficient stored in the database, , 1, 2, 3, …, , is the number of time points.

[0008] Further, the surface ocean monitoring time-series data includes the sea surface climate stability index, sea surface evaporation rate value, wave height value, and sea surface biological photosynthetic intensity value at each time. The specific steps to obtain the sea surface mining stress index at each time point in the set ocean oil mining area are as follows: Standardize the sea surface climate stability index, sea surface evaporation rate value, wave height value, and sea surface biological photosynthetic intensity value at each time point in the set ocean oil mining area; and comprehensively analyze the sea surface climate stability index, sea surface evaporation rate value, wave height value, and sea surface biological photosynthetic intensity value at each time point in the set ocean oil mining area after the standardization process to obtain the sea surface mining stress index at each time point in the set ocean oil mining area.

[0009] Further, the middle ocean monitoring time-series data includes the middle pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, and water body shear stress value. The specific steps to obtain the middle ocean operation disturbance index at each time point in the set ocean oil mining area are as follows: Normalize the middle pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, and water body shear stress value at each time point in the set ocean oil mining area; and comprehensively analyze the middle pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, and water body shear stress value at each time point in the set ocean oil mining area after the normalization process to obtain the middle ocean operation disturbance index at each time point in the set ocean oil mining area.

[0010] Further, the specific steps to obtain the middle pycnocline index at each time point in the set ocean oil mining area are as follows: Obtain the temperature values and salinity values at several depths at each time point in the set ocean oil mining area, and comprehensively analyze them respectively to obtain the temperature gradient value and salinity gradient value at each time point in the set ocean oil mining area; and comprehensively analyze the temperature gradient value and salinity gradient value at each time point in the set ocean oil mining area to obtain the middle pycnocline index at each time point in the set ocean oil mining area.

[0011] Further, the marine bottom monitoring time-series data includes seabed topographic image data, seabed pulsation risk index, and seabed microbial activity index at each time point. The seabed topographic image data specifically includes the pixel values and two-dimensional coordinates of each pixel point in the seabed topographic map. The specific steps to obtain the seabed mining comprehensive risk index at each time point within the set marine oil exploitation area are as follows: Input the seabed topographic image data at each time point within the set marine oil exploitation area into a pre-trained terrain recognition model for predictive analysis to obtain the seabed topographic mining risk index at each time point within the set marine oil exploitation area; comprehensively analyze the seabed topographic mining risk index, seabed disaster index, and seabed microbial activity index at each time point within the set marine oil exploitation area to obtain the seabed mining comprehensive risk index at each time point within the set marine oil exploitation area.

[0012] Further, the specific steps to calculate the seabed mining comprehensive risk index at each time point within the set marine oil exploitation area are as follows: ; where is the seabed mining comprehensive risk index at the th time point within the set marine oil exploitation area, is the seabed topographic mining risk index at the th time point within the set marine oil exploitation area, is the seabed topographic adjustment coefficient stored in the database, is the seabed pulsation risk index at the th time point within the set marine oil exploitation area, is the pulsation risk adjustment coefficient stored in the database, is the seabed microbial activity index at the th time point within the set marine oil exploitation area, is the microbial activity adjustment coefficient stored in the database, is the collaborative adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of time points.

[0013] Further, the terrain recognition model is specifically a convolutional neural network, which includes an input layer, several convolutional layers, an activation layer, a pooling and flattening layer, and a risk output layer. The specific steps to obtain the seabed terrain mining risk index at each time point within the set marine oil mining area are as follows: In the input layer of the convolutional neural network, receive the seabed terrain image data at each time point within the set marine oil mining area and perform preprocessing; in the convolutional layer of the convolutional neural network, perform feature extraction processing on the preprocessed seabed terrain image data at each time point within the set marine oil mining area to obtain the seabed terrain feature map at each time point within the set marine oil mining area; in the activation layer of the convolutional neural network, perform non-linear transformation processing on the seabed terrain feature map at each time point within the set marine oil mining area; in the pooling and flattening layer of the convolutional neural network, perform pooling and flattening processing on the seabed terrain feature map at each time point within the set marine oil mining area after activation processing to obtain the seabed terrain feature vector at each time point within the set marine oil mining area; in the risk output layer of the convolutional neural network, perform fusion processing on the seabed terrain feature vector at each time point within the set marine oil mining area to obtain the seabed terrain mining risk index at each time point within the set marine oil mining area.

[0014] Further, the specific steps for intelligent oil mining warning based on the oil mining warning index at each time point within the set marine oil mining area are as follows: Conduct trend analysis on the oil mining warning index at each time point within the set marine oil mining area to obtain several groups of oil mining warning index change rates within the set marine oil mining area; and conduct comprehensive analysis on each group of oil mining warning index change rates and the oil mining warning index at each time point within the set marine oil mining area to obtain the predicted oil mining warning index within the set marine oil mining area, and regard it as the oil mining warning index for the next time within the set marine oil mining area; take corresponding preset warning measures based on the oil mining warning index at the next time point within the set marine oil mining area.

[0015] The monitoring and early warning system for the marine three-dimensional layered rights project includes: a marine monitoring time series acquisition module for continuously acquiring a marine monitoring time series dataset within a set marine oil exploitation area, including marine surface layer monitoring time series data, marine middle layer monitoring time series data, and marine bottom layer monitoring time series data; a marine layered feature analysis module for performing feature analysis on the marine monitoring time series dataset within the set marine oil exploitation area respectively to obtain a monitoring and early warning index set for each time point within the set marine oil exploitation area, including a sea surface exploitation stress index, a marine middle layer operation disturbance index, and a seabed exploitation comprehensive risk index; a comprehensive early warning assessment module for comprehensively analyzing the monitoring and early warning index set for each time point within the set marine oil exploitation area to obtain an oil exploitation early warning index for each time point within the set marine oil exploitation area; and an intelligent early warning module for performing intelligent oil exploitation early warning based on the oil exploitation early warning index for each time point within the set marine oil exploitation area.

[0016] The present invention has the following beneficial effects: (1) The monitoring and early warning method for the marine three-dimensional layered rights project can comprehensively understand the dynamic changes of the marine environment by performing three-dimensional and hierarchical analysis on the real-time monitoring data of the marine surface layer, middle layer, and bottom layer, and can provide a more accurate oil exploitation early warning by comprehensively analyzing the influencing factors at different layers. For example, the impact of climate change on the middle layer water flow and the impact of the middle layer water flow on the seabed topography and microbial activity are effectively evaluated, thereby improving the accuracy of the early warning, being able to identify potential risks more timely, and providing a strong guarantee for the safety of marine exploitation activities.

[0017] (2) The monitoring and early warning method for the marine three-dimensional layered rights project can accurately evaluate the impact of the seabed environment on the exploitation operation by performing in-depth analysis on the seabed topography image data through a convolutional neural network and combining data such as the seabed pulsation risk index and the microbial activity index. For example, the seabed topography image can reveal potential deep sea cracks, unstable sediment areas or karst caves, which are likely to pose a serious threat to equipment such as seabed oil and gas pipelines and drilling platforms. By combining the pulsation risk index, the impact of seabed vibration on seabed facilities can be evaluated. Pulsation changes are likely to trigger equipment failures or leakage incidents, and thus potential threats in the seabed environment can be identified in advance, providing a more reliable risk early warning for seabed exploitation and ensuring the safety of marine oil exploitation and environmental protection.

[0018] (3) The monitoring and early warning method for the marine three-dimensional stratified rights project can accurately evaluate and predict the potential impact of the middle-layer environment on oil extraction operations by combining data at all levels of the marine environment, especially by analyzing factors such as the water flow intensity and oxygen-sulfur corrosion index in the middle layer of the ocean. The disturbance of the middle-layer water body has an important impact on marine oil extraction. For example, strong ocean currents can easily cause wear or even breakage of oil and gas pipelines, while the oxygen-sulfur corrosion index can reflect the concentration of corrosive substances in the water body and affect the durability of subsea facilities. By real-time monitoring the data of the middle-layer environment, potential environmental risks during the operation can be identified and early warnings can be issued, so as to take effective countermeasures in advance, thereby improving the efficiency and sustainability of the operation.

[0019] (4) The monitoring and early warning system for the marine three-dimensional stratified rights project realizes the efficient acquisition, analysis, and early warning of real-time environmental data in the marine oil extraction area by integrating multiple functional modules. The marine monitoring time series acquisition module can continuously monitor the environmental data of the ocean surface, middle layer, and bottom layer to ensure the integrity and timeliness of the data. The marine stratified feature analysis module conducts in-depth analysis on the data of different layers to accurately evaluate the potential impact of each layer on oil extraction activities. The intelligent early warning module adjusts the operation strategy in real time according to the oil extraction early warning index generated by the comprehensive early warning evaluation module to effectively avoid potential risks brought by environmental changes and improve the safety of marine oil extraction activities, thereby ensuring the smooth progress of the extraction operation in a complex marine environment and reducing equipment damage and environmental accidents at the same time.

[0020] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flowchart of the monitoring and early warning method for the marine three-dimensional stratified rights project of the present invention.

[0022] Figure 2 It is a time series diagram of the middle-layer pycnocline index set in the marine oil extraction area in the monitoring and early warning method for the marine three-dimensional stratified rights project of the present invention.

[0023] Figure 3 It is a time series diagram of the ocean current intensity set in the marine oil extraction area in the monitoring and early warning method for the marine three-dimensional stratified rights project of the present invention.

[0024] Figure 4 It is a time series diagram of the oxygen-sulfur corrosion index set in the marine oil extraction area in the monitoring and early warning method for the marine three-dimensional stratified rights project of the present invention.

[0025] Figure 5It is the time series diagram of the water body shear stress in the set marine oil exploitation area in the monitoring and early warning method for the marine three-dimensional hierarchical rights setting project of the present invention.

[0026] Figure 6 It is the specific step flowchart for obtaining the comprehensive risk index of seabed exploitation at each time point in the set marine oil exploitation area in the monitoring and early warning method for the marine three-dimensional hierarchical rights setting project of the present invention.

[0027] Figure 7 It is the block diagram of the monitoring and early warning system for the marine three-dimensional hierarchical rights setting project of the present invention. Specific implementation mode

[0028] Please refer to Figure 1 , an embodiment of the present invention provides a technical solution: a monitoring and early warning method for a marine three-dimensional hierarchical rights setting project, including the following steps: continuously obtaining a marine monitoring time series data set in a set marine oil exploitation area, including marine surface layer monitoring time series data, marine middle layer monitoring time series data, and marine bottom layer monitoring time series data; respectively performing feature analysis on the marine monitoring time series data set in the set marine oil exploitation area to obtain a monitoring and early warning index set at each time point in the set marine oil exploitation area, including a sea surface exploitation stress index (i.e., the impact of the environment of the marine surface layer on oil exploitation), a marine middle layer operation disturbance index, and a seabed exploitation comprehensive risk index; comprehensively analyzing the monitoring and early warning index set at each time point in the set marine oil exploitation area to obtain an oil exploitation early warning index at each time point in the set marine oil exploitation area; performing intelligent oil exploitation early warning based on the oil exploitation early warning index at each time point in the set marine oil exploitation area.

[0029] The specific formula for calculating the oil exploitation early warning index at each time point in the set marine oil exploitation area is as follows: ; where is the oil exploitation early warning index at the th time point in the set marine oil exploitation area, is the sea surface exploitation stress index at the th time point in the set marine oil exploitation area, is the sea surface stress coefficient stored in the database, is the sea surface stress adjustment coefficient stored in the database, is the smoothing coefficient stored in the database, and its value is 0.001 in this implementation example, is the marine middle layer operation disturbance index at the th time point in the set marine oil exploitation area, is the middle layer disturbance coefficient stored in the database, is the middle layer disturbance adjustment coefficient stored in the database, To set the comprehensive seabed mining risk index at the th time point within the offshore oil mining area, is the seabed risk coefficient stored in the database, is the seabed risk adjustment coefficient stored in the database, is the interaction coefficient stored in the database, , 1, 2, 3, …, , is the number of time points.

[0030] It should be noted that in the formula, this term is used to adjust the superposition effect among the sea surface mining stress index, the mid - ocean operation disturbance index, and the comprehensive seabed mining risk index, to avoid the oil mining warning index being too high or too low.

[0031] 、 、 can be obtained through the following steps: Read the sea surface mining stress index, the mid - ocean operation disturbance index, and the comprehensive seabed mining risk index at each time point within the set offshore oil mining area, and conduct a summation analysis to obtain the warning sum value. Then, conduct a ratio analysis of the sea surface mining stress index, the mid - ocean operation disturbance index, and the comprehensive seabed mining risk index at each time point within the set offshore oil mining area with the warning sum value respectively, and use the ratio analysis results as the corresponding coefficients.

[0032] 、 、 、 can be obtained through the following steps: Use historical data, combine the sea surface mining stress index, the mid - ocean operation disturbance index, and the comprehensive seabed mining risk index, conduct a statistical regression analysis to quantify the specific impact of each factor on the oil mining warning index, so as to fit the initial weight values. Secondly, adopt the sensitivity analysis method to adjust the value range of each coefficient, observe its impact on the oil mining warning result, ensure the stability and rationality of the model, and based on the characteristics and actual situation of the oil mining area, correct and optimize the initially fitted coefficients, and finally determine the coefficient values applicable to a specific oil mining area.

[0033] Specifically, the time - series data of ocean surface monitoring includes the sea - surface climate stability index, sea - surface evaporation rate value, sea - wave height value, and sea - surface biological photosynthetic intensity value at each time. The specific steps to obtain the sea - surface exploitation stress index at each time point in the set ocean oil exploitation area are as follows: Standardize the sea - surface climate stability index, sea - surface evaporation rate value, sea - wave height value, and sea - surface biological photosynthetic intensity value at each time point in the set ocean oil exploitation area; and comprehensively analyze (i.e., perform weighted processing) the standardized sea - surface climate stability index, sea - surface evaporation rate value, sea - wave height value, and sea - surface biological photosynthetic intensity value at each time point in the set ocean oil exploitation area to obtain the sea - surface exploitation stress index at each time point in the set ocean oil exploitation area.

[0034] Among them, the sea - surface climate stability index is used to measure the stability of the ocean surface environment. It can be obtained by acquiring the sea - surface temperature value (obtained through a temperature sensor), sea - surface air pressure value (obtained through a barometric sensor), sea - surface wind speed value (obtained through an anemometer), sea - surface temperature reference value, sea - surface air pressure reference value, and sea - surface wind speed reference value, and respectively performing difference analysis (such as the absolute value of the difference between the sea - surface temperature value and the sea - surface temperature reference value), and then performing standardization processing. Based on the standardized processing results, weighted processing is performed, and the reciprocal is taken. The resulting value is the sea - surface climate stability index, and the sea - surface temperature reference value, sea - surface air pressure reference value, and sea - surface wind speed reference value can all be obtained from the ocean meteorological database.

[0035] The sea - surface evaporation rate value is the amount of water vapor evaporated from seawater to the atmosphere per unit time on the surface of the ocean oil exploitation area. A high evaporation rate means drastic weather changes, which can easily affect the stability of oil platforms and the operating conditions of equipment.

[0036] The sea - wave height value is the average of multiple sea - wave heights (the vertical distance between the wave crest and wave trough) in the ocean oil exploitation area, and each sea - wave height can be obtained through an altimeter in a wave buoy. High sea - waves can affect the stability of oil platforms, increase the swaying or tilting of the platforms, and thus affect operation safety.

[0037] The sea - surface biological photosynthetic intensity value is the intensity of photosynthesis carried out by phytoplankton (mainly phytoplankton algae) in the seawater in the ocean oil exploitation area, expressed by photosynthetically active radiation (PAR). It can be obtained through a photosynthesis radiation sensor. Oil and its derivatives (such as toxic chemicals like benzene and toluene) are likely to have a toxic effect on the photosynthesis of phytoplankton, that is, affect the efficiency of phytoplankton in obtaining light energy and reduce the photosynthetic intensity.

[0038] In this implementation plan, through standardization processing, different environmental data are converted into a unified measurement standard and weighted analysis is carried out, which can reasonably quantify the impact of each indicator on marine exploitation operations. For example, the impacts of wave height and sea surface evaporation rate on platform stability and operating conditions are effectively integrated, and the change in the photosynthetic intensity of marine organisms can indicate potential environmental pollution risks, so as to accurately predict the impact of environmental changes on exploitation safety. Secondly, comprehensive analysis of multiple environmental parameters helps to provide a comprehensive emergency response framework for oil exploitation under different environmental changes, thereby providing a more flexible and adaptable early warning mechanism and timely identifying potential operating risks. Finally, monitoring the photosynthetic intensity of marine organisms can effectively evaluate the impact of environmental pollution (such as oil spills) on the photosynthesis of phytoplankton, thereby predicting the potential threats of exploitation activities to the marine ecosystem. By monitoring these key environmental factors, events that may harm the environment can be discovered and warned in advance, providing guarantees for the safety of oil exploitation activities and environmental protection.

[0039] Specifically, the marine middle layer monitoring time series data include the middle layer pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, and water body shear stress value. The specific steps to obtain the marine middle layer operation disturbance index at each time point in the set marine oil exploitation area are as follows: Normalize the middle layer pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, and water body shear stress value at each time point in the set marine oil exploitation area (i.e., remove the unit); and comprehensively analyze the middle layer pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, and water body shear stress value at each time point in the set marine oil exploitation area after normalization to obtain the marine middle layer operation disturbance index at each time point in the set marine oil exploitation area.

[0040] The specific formula for calculating the marine middle layer operation disturbance index at each time point in the set marine oil exploitation area is as follows: ; where is the marine middle layer operation disturbance index at the th time point in the set marine oil exploitation area, is the middle layer pycnocline index at the th time point in the set marine oil exploitation area after normalization, is the pycnocline adjustment coefficient stored in the database, is the ocean current intensity value at the th time point in the set marine oil exploitation area after normalization, is the ocean current intensity adjustment coefficient stored in the database, is the oxygen-sulfur corrosion index at the th time point in the set marine oil exploitation area after normalization, is the oxygen-sulfur corrosion adjustment coefficient stored in the database, is the water body shear stress value at the th time point in the set offshore oil exploitation area after normalization, is the water body shear adjustment coefficient (not zero) stored in the database, 1, 2, 3, …, , is the number of time points.

[0041] It should be noted that , , , can be obtained through the following steps: Based on historical data, determine the initial influence weights of each variable (mid-layer pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, water body shear stress value) on the mid-ocean layer operation disturbance index through statistical regression analysis. Then, use the sensitivity analysis method to adjust the value range of the coefficients to evaluate the stability and applicability of these parameters to the formula output. Next, further fit the weights through model optimization (such as machine learning algorithms) to ensure that the formula can accurately reflect the actual state of mid-ocean layer operation disturbances. Fine-tune the coefficients based on different regional characteristics to ensure its applicability to specific mid-ocean layer operation disturbance assessment requirements.

[0042] Among them, the ocean current intensity value is the flow intensity of seawater in the mid-layer of the seawater in the set offshore oil exploitation area. Strong ocean currents are likely to affect the stability of pipelines, and it can be obtained through an acoustic Doppler current profiler, that is, the device continuously emits sound waves and measures the water flow rate at different depths, and performs mean processing to obtain the ocean current intensity.

[0043] The oxygen-sulfur corrosion index is used to evaluate the corrosion effect of dissolved oxygen concentration and sulfide concentration in the ocean environment on equipment such as pipelines in the mid-layer of seawater. It can be obtained by acquiring the dissolved oxygen concentration value (which can be obtained through a dissolved oxygen sensor) and hydrogen sulfide concentration value (which can be obtained through a chemical sensor) in the mid-layer of seawater in the set offshore oil exploitation area, and performing standardization processing. Based on the standardization processing results, weighted processing is performed, but the reciprocal of the standardized dissolved oxygen concentration value is taken during the weighting process, that is, 1 / (1 + standardized dissolved oxygen concentration value), and the resulting value is the oxygen-sulfur corrosion index.

[0044] The water body shear stress value is the shear force caused by the velocity difference between water layers during the flow of seawater in the middle layer of seawater in the set offshore oil exploitation area. In the case of high-speed water flow, it may lead to an increase in the friction force of the pipeline, vibration or movement, and even cause the pipeline to lose stability. It can be obtained by acquiring the dynamic viscosity of the middle layer of seawater (i.e., the viscosity of the middle layer of seawater, which can be based on the temperature value and salinity value at the middle position of the middle layer of seawater obtained by a CTD sensor, weighted through standardized processing, and multiplied by the initial viscosity value of seawater stored in the data, such as 1.002 mPa·s at 20°C) and the water flow velocities at different depths (obtained by an acoustic Doppler current profiler), and performing a difference analysis on the water flow velocities at different depths, dividing by the corresponding depth difference, and multiplying by the dynamic viscosity. The resulting value is the water body shear stress value.

[0045] The specific implementation example of calculating the ocean middle layer operation disturbance index at each time point in the set offshore oil exploitation area is as follows. The following data is available: including the middle layer pycnocline index, ocean current intensity value, oxygen-sulfur corrosion index, and water body shear stress value at 5 time points in the set offshore oil exploitation area, as shown in Table 1 and Figures 2 - 5 shown below: Table 1 Example of ocean middle layer monitoring time series data at 5 time points in the set offshore oil exploitation area

[0046] Perform normalization processing on the data examples in Table 1 to obtain Table 2: Table 2 Example of ocean middle layer monitoring time series data at 5 time points in the set offshore oil exploitation area after normalization processing

[0047] The pycnocline adjustment coefficient stored in the database is approximately: 0.193; The ocean current intensity adjustment coefficient stored in the database is approximately: 0.267; The oxygen-sulfur corrosion adjustment coefficient stored in the database is approximately: 0.351; The water body shear adjustment coefficient stored in the database is approximately: 0.684; Substitute the data in Table 2 and the above adjustment coefficients into the specific formula for calculating the ocean middle layer operation disturbance index at each time point in the set offshore oil exploitation area to obtain: The ocean middle layer operation disturbance index at time point 1 in the set offshore oil exploitation area ≈ 0.256; The ocean middle layer operation disturbance index at time point 2 in the set offshore oil exploitation area ≈ 0.237; Set the mid - ocean operation disturbance index at time point 3 in the offshore oil exploitation area ≈ 0.198; Set the mid - ocean operation disturbance index at time point 4 in the offshore oil exploitation area ≈ 0.214; Set the mid - ocean operation disturbance index at time point 5 in the offshore oil exploitation area ≈ 0.249.

[0048] The specific steps to obtain the mid - ocean pycnocline index at each time point in the set offshore oil exploitation area are as follows: Obtain the temperature values (which can be obtained through a CTD sensor) and salinity values (which can be obtained through a CTD sensor) at several depths at each time point in the set offshore oil exploitation area, and conduct comprehensive analysis (i.e., standard deviation processing) respectively to obtain the temperature gradient value and salinity gradient value at each time point in the set offshore oil exploitation area; and conduct comprehensive analysis on the temperature gradient value and salinity gradient value at each time point in the set offshore oil exploitation area (i.e., first conduct standardization processing, and then conduct weighted processing based on the results of the standardization processing) to obtain the mid - ocean pycnocline index at each time point in the set offshore oil exploitation area.

[0049] In this implementation plan, by normalizing and comprehensively analyzing multiple key environmental parameters, the comprehensive impact of the mid - ocean environment on oil exploitation operations can be comprehensively reflected. The comprehensive analysis can provide a more accurate disturbance index, making the early warning system more effective. Secondly, through regression analysis, sensitivity analysis, and model optimization, the influence weights of each parameter can be dynamically adjusted to ensure that the mid - ocean operation disturbance index can accurately reflect real - time changes in the ocean environment, thereby improving the adaptability and accuracy of monitoring and early warning. And by adjusting the coefficients, its stability and applicability under different environmental conditions can be ensured. Through real - time monitoring and analysis, early warnings can be made for possible equipment problems during offshore oil exploitation, so as to take measures in advance to reduce operation risks. Finally, through comprehensive analysis and optimization calculations, potential risk factors can be accurately evaluated, providing a safer operating environment for oil exploitation, thereby reducing the likelihood of accidents and improving the safety and long - term sustainability of offshore oil exploitation operations.

[0050] Specifically, as Figure 6As shown, the ocean bottom monitoring time-series data includes the seabed topographic image data at each time point, the seabed pulsation risk index (used to measure the stability of the seabed formation and the risk of energy release during oil extraction), and the seabed microbial activity index. The seabed topographic image data specifically refers to the pixel values and two-dimensional coordinates of each pixel point in the seabed topographic map. The specific steps to obtain the comprehensive seabed mining risk index at each time point within the set ocean oil extraction area are as follows: Input the seabed topographic image data at each time point within the set ocean oil extraction area into a pre-trained topographic recognition model for predictive analysis to obtain the seabed topographic mining risk index at each time point within the set ocean oil extraction area; conduct a comprehensive analysis of the seabed topographic mining risk index, the seabed disaster index, and the seabed microbial activity index at each time point within the set ocean oil extraction area to obtain the comprehensive seabed mining risk index at each time point within the set ocean oil extraction area.

[0051] Among them, the specific steps to obtain the seabed pulsation risk index at each time point within the set ocean oil extraction area are as follows: Obtain the seabed pressure gradient value, the seabed vibration value, the sediment reverse intensity value, and the seabed vibration value at each time point within the set ocean oil extraction area, and perform standardization processing; conduct a comprehensive analysis (weighted processing) of the seabed pressure gradient value, the seabed vibration value, the sediment reverse intensity value, and the seabed vibration value at each time point within the set ocean oil extraction area after standardization processing to obtain the seabed pulsation risk index at each time point within the set ocean oil extraction area.

[0052] The seabed pressure gradient value is the standard deviation of the pressure values at different depths in the seabed layer within the set ocean oil extraction area. The pressure values at different depths can all be obtained through pressure sensors, and a high pressure gradient is likely to cause uneven pressure in the seawater or oil and gas layer, thereby affecting the fluidity of oil and gas during the drilling process.

[0053] The seabed microbial activity index is the activity level of the microbial community in the seabed environment within the set ocean oil extraction area, which is likely to cause seabed corrosion, especially corrosion of metal equipment, and thus affect the lifespan and stability of oil and gas collection equipment. It can be obtained by acquiring the methane concentration value, carbon dioxide concentration value, ammonia concentration value, and hydrogen chloride concentration value at multiple positions in the seabed layer within the set ocean oil extraction area, performing standardization processing, and based on the results of the standardization processing, performing weighted processing and mean processing. The obtained result is the seabed microbial activity index, and the methane concentration value, carbon dioxide concentration value, ammonia concentration value, and hydrogen chloride concentration value can all be obtained through underwater gas sensors.

[0054] The seabed vibration value is the intensity of the seabed vibration activity within the set ocean oil extraction area, which is likely to affect the stability of equipment and oil and gas reservoirs, and it can be obtained through vibration sensors.

[0055] The backscattering intensity value of the sediment can be obtained by a sonar detector. After the sound wave is emitted to the seabed, part of it will be reflected back to the detection device by the seabed sediment. The intensity of the reflected sound wave (i.e., the backscattering intensity) is used to reflect the density and fluidity of the sediment. A lower backscattering intensity value of the sediment indicates that the sediment is looser, posing a potential risk of landslide or collapse, thus threatening the safety of subsea oil and gas exploitation operations and the stability of equipment.

[0056] The specific steps for calculating the comprehensive subsea exploitation risk index at each time point within the set offshore oil exploitation area are as follows: ; where is the comprehensive subsea exploitation risk index at the -th time point within the set offshore oil exploitation area, is the subsea terrain exploitation risk index at the -th time point within the set offshore oil exploitation area, is the subsea terrain adjustment coefficient stored in the database, is the subsea pulsation risk index at the -th time point within the set offshore oil exploitation area, is the pulsation risk adjustment coefficient stored in the database, is the subsea microbial activity index at the -th time point within the set offshore oil exploitation area, is the microbial activity adjustment coefficient stored in the database, is the co - adjustment coefficient stored in the database (used to adjust the combined influence of the subsea terrain adjustment coefficient and the subsea pulsation risk index), 1, 2, 3, …, , is the number of time points.

[0057] It should be noted that in the formula, the term is used to adjust the interaction between the subsea terrain adjustment coefficient and the subsea pulsation risk index, to avoid the comprehensive subsea exploitation risk index being too high or too low.

[0058] The expression of the Tanh function is , where is the natural constant, and in this embodiment, its value is 2.71, with the domain being (-∞, +∞) and the range being (-1, 1).

[0059] , , , It can be obtained through the following steps: Based on historical data, determine the initial influence weights of each variable (submarine terrain mining risk index, submarine disaster index, submarine microbial activity index) on the comprehensive submarine mining risk index through statistical regression analysis. Then, use the sensitivity analysis method to adjust the value range of the coefficients to evaluate the stability and applicability of these parameters to the formula output. Next, further fit the weights through model optimization (such as machine learning algorithms or multi-objective optimization) to ensure that the formula can accurately reflect the state of the actual comprehensive submarine mining risk. Fine-tune the coefficients based on different regional characteristics to ensure its applicability to the specific comprehensive submarine mining risk assessment requirements.

[0060] In this implementation plan, by combining multiple factors such as submarine terrain, submarine pulsation risk, and microbial activity, submarine risk analysis can be carried out from multiple perspectives, which helps to comprehensively understand the complexity of the submarine environment, and then ensures the accurate identification and prediction of potential risks. Secondly, by analyzing the submarine terrain mining risk index at each time point, the accuracy of risk assessment is improved. Real-time obtaining data such as submarine pressure gradient, vibration value, sediment backscattering intensity, etc., and performing standardization and weighted analysis can monitor the changes in the submarine environment in real time and quickly discover potential risks, thus avoiding the occurrence of accidents. Finally, by introducing adjustment coefficients and co-adjustment coefficients, the weights of each risk index can be flexibly adjusted according to different submarine environmental characteristics and actual situations to ensure the stability and adaptability of the calculation results, thereby enhancing the flexibility and reliability of monitoring and early warning, and providing data support for the maintenance and protection of equipment, thus extending the service life of the equipment and ensuring the stable progress of oil mining operations.

[0061] Specifically, the terrain recognition model is a specific convolutional neural network. The convolutional neural network includes an input layer, several convolutional layers, an activation layer, a pooling and flattening layer, and a risk output layer. The specific steps to obtain the seabed terrain mining risk index for each time point within the set offshore oil mining area are as follows: In the input layer of the convolutional neural network, receive the seabed terrain image data (i.e., the pixel values and two-dimensional coordinates of each pixel point in the seabed topographic map) for each time point within the set offshore oil mining area and perform preprocessing; in the convolutional layer of the convolutional neural network, perform feature extraction processing on the preprocessed seabed terrain image data for each time point within the set offshore oil mining area (i.e., perform a convolution operation between the convolution kernel and the input image to extract local features from the image, such as cracks, faults, gullies, seabed ridges, etc. on the seabed), to obtain the seabed terrain feature map for each time point within the set offshore oil mining area; in the activation layer of the convolutional neural network, perform a non-linear transformation on the seabed terrain feature map for each time point within the set offshore oil mining area (use the ReLU activation function to introduce non-linearity, enabling the network to learn complex terrain patterns and enhancing the network's sensitivity to important features such as mining risks); in the pooling and flattening layer of the convolutional neural network, perform pooling and flattening processing on the activated seabed terrain feature map for each time point within the set offshore oil mining area (use max pooling to reduce the spatial size of the feature map while retaining the most important feature information, that is, by sliding a fixed-size window over the feature map and combining the elements within the window into a single value, i.e., the maximum value within the pooling window is retained, thus obtaining a reduced-dimensional feature map and converting the reduced-dimensional feature map into a one-dimensional feature vector), to obtain the seabed terrain feature vector for each time point within the set offshore oil mining area (including but not limited to gully erosion degree, complexity of the seabed terrain, stability of faults, etc.); in the risk output layer of the convolutional neural network, perform fusion processing on the seabed terrain feature vector for each time point within the set offshore oil mining area (perform feature weighting on different terrain features in the seabed terrain feature vector, and apply a non-linear activation function to the weighted features so that the network can capture the complex non-linear relationships between terrain features, then enter a fully connected layer to map the input features to a high-dimensional space to further capture the relationships between features, and after the fully connected layer, enter a regression layer to map it to a continuous numerical output, i.e., the seabed terrain mining risk index, and the numerical range is between 0 and 1), to obtain the seabed terrain mining risk index for each time point within the set offshore oil mining area.

[0062] Among them, the input layer is used to receive the original seabed terrain image data as the input of the neural network.

[0063] The convolutional layer is used to extract features from the input image data. Through convolutional operations, local features in the image are found, and a seabed terrain feature map is generated.

[0064] The activation layer is used to perform a non - linear transformation on the features extracted by the convolutional layer (i.e., the seabed terrain feature map), enabling the model to learn more complex patterns.

[0065] The pooling and flattening layer is used to perform pooling operations (such as max - pooling or average - pooling), reducing the spatial size of the seabed terrain feature map (downsampling), and then flattening the pooled feature map into a one - dimensional seabed terrain feature vector.

[0066] The risk output layer is used to generate the final seabed terrain mining risk index based on the one - dimensional seabed terrain feature vector.

[0067] And the pre - training process of the convolutional neural network is as follows: Obtain a seabed terrain image dataset, including several seabed terrain images (e.g., seabed cracks, faults, gullies, etc.), and containing corresponding annotation information (e.g., danger level, risk index, etc.). Then divide the seabed terrain image dataset into a training set and a validation set, usually in a ratio of 80%:20%.

[0068] Initialize the convolutional neural network, initializing the weights and biases in the network to ensure that the network can effectively learn features. Initialization methods include Xavier initialization and He initialization. For example, initialize the weights of the convolutional layer (using He initialization), and initialize the bias term to zero. Then use the ReLU activation function to increase the non - linearity of the network.

[0069] Train based on the training set, setting the number of training loops (e.g., train 50 times or 100 times). In each training loop, perform forward propagation (the network obtains a batch of data from the training set, e.g., inputs a seabed terrain image data at a time, and passes through the convolutional layer, activation layer, pooling layer, etc. to generate the seabed terrain mining risk index), calculate the loss (compare the predicted value of the network, i.e., the predicted seabed terrain mining risk index and the true label value, and calculate the loss of the model. Commonly used loss functions include mean squared error, cross - entropy loss, etc.), and backpropagation (calculate the gradients in the network according to the loss function and update the model parameters through the optimizer).

[0070] And after each training loop ends, perform evaluation and analysis based on the validation set. Use the images in the validation set for forward propagation, calculate the loss value between the predicted seabed terrain mining risk index and the true seabed terrain mining risk index, and calculate the loss function value and accuracy of the model on the validation set to evaluate the performance of the model.

[0071] Adjust the model parameters based on the evaluation results. If the loss on the validation set does not decrease or the accuracy does not improve, it may be necessary to adjust the hyperparameters of the network (such as the learning rate, network structure, etc.). If the performance on the validation set is poor, hyperparameters such as the learning rate, batch size, and number of convolutional layers can be adjusted to improve the training effect. If the loss on the validation set does not show significant improvement over several training epochs, stop the training to prevent overfitting. Based on the training and validation results, the structure of the model, such as the number of layers and the size of the convolutional kernels, can be adjusted.

[0072] When the training is completed and the loss and accuracy on the validation set reach the expected standards, the training process ends, and a trained network model is obtained.

[0073] In this implementation, the convolutional neural network can automatically extract important features from the seabed terrain images, such as cracks, faults, and gullies, so as to obtain detailed terrain features, thereby improving the accuracy of risk assessment. Moreover, through the nonlinear transformation in the activation layer, the convolutional neural network can capture the complex nonlinear relationships in the seabed terrain data. Using a nonlinear activation function can enhance the sensitivity of the model to complex mining risks. The pooling and flattening layer reduces the spatial dimension of the seabed terrain image features through dimensionality reduction operations while retaining important information to avoid overfitting. Secondly, through the risk output layer of the convolutional neural network, the model can comprehensively process the extracted features and output the seabed terrain mining risk index, which helps to evaluate the mining risk at each time point and provides a scientific basis for decision-makers. Finally, the training process of the convolutional neural network can be optimized according to the actual data, and the model parameters for optimizing the mining risk assessment can be learned through a large amount of data, so as to dynamically adjust the risk prediction and then adapt to the complex and changing seabed environment, and ultimately enable the model to provide more accurate seabed mining risk predictions.

[0074] Specifically, the specific steps for intelligent oil production warning based on the oil production warning index at each time point within the set offshore oil production area are as follows: Conduct trend analysis on the oil production warning index at each time point within the set offshore oil production area to obtain several groups of oil production warning index change rates within the set offshore oil production area; and conduct comprehensive analysis on each group of oil production warning index change rates and the oil production warning index at each time point within the set offshore oil production area (that is, perform mean processing on the oil production warning index at each time point to obtain the mean value of the oil production warning index, and perform weighted processing on each group of oil production warning index change rates, and perform summation processing based on the weighted result and the mean value of the oil production warning index) to obtain the predicted oil production warning index within the set offshore oil production area, and regard it as the oil production warning index for the next time within the set offshore oil production area; Based on the oil production warning index at the next time point within the set offshore oil production area, take the preset warning measures, and the specific steps are as follows: Judge and analyze the oil production warning index at the next time point within the set offshore oil production area respectively with the preset set of oil production warning index thresholds, and the set of oil production warning index thresholds includes the first oil production warning index threshold (used to measure whether a production risk occurs), the second oil production warning index threshold (used to measure whether the production risk is at a low or medium risk), and the third oil production warning index threshold (used to measure whether a high risk occurs); If the oil production warning index at the next time point within the set offshore oil production area is lower than the first oil production warning index threshold, it is marked as safe and monitoring continues; If the oil production warning index at the next time point within the set offshore oil production area is higher than or equal to the first oil production warning index threshold and lower than the second oil production warning index threshold, it is marked as a low risk, a low risk warning notice is sent to relevant personnel, and the preset first warning measure is taken (that is, increasing the data monitoring frequency and performing preventive maintenance on key equipment to avoid higher risks caused by equipment aging or problems); If the oil production warning index at the next time point within the set offshore oil production area is higher than or equal to the second oil production warning index threshold and lower than the third oil production warning index threshold, it is marked as a medium risk, a medium risk warning notice is sent to relevant personnel, and the preset second warning measure is taken (that is, reducing the production speed and starting an underwater robot to conduct a more comprehensive inspection of key equipment to eliminate possible faults);If the oil extraction warning index at the next time point within the set offshore oil extraction area is higher than the third oil extraction warning index threshold, it is marked as high risk, a high-risk warning notice is sent to relevant personnel, and the preset third warning measures are taken (that is, immediately stop production or suspend operations to ensure the safety of personnel and equipment, and initiate a comprehensive emergency plan, including a series of emergency response measures such as evacuation, environmental protection, and accident handling, then report the situation to the superior management department and the offshore oil safety supervision agency, and conduct subsequent disposal as required).;

[0075] In this implementation plan, through the trend analysis of the oil extraction warning index, potential risks can be identified in advance, and preventive measures can be taken before dangerous situations occur, thereby reducing the probability of accidents, protecting the safety of extraction equipment, staff, and the environment. By setting different risk levels and warning thresholds (such as low, medium, and high risks), different levels of response measures can be taken according to the severity of the risk, avoiding over-reaction or insufficient reaction. Secondly, by predicting the oil extraction warning index at the next time point, the production strategy can be adjusted in real time. For example, when the warning index enters the low-risk area, data monitoring and equipment maintenance can be strengthened; when it is in the high-risk area, production can be immediately stopped and emergency response measures can be initiated. Finally, by setting an emergency response mechanism such as evacuation, environmental protection, and accident handling, a rapid response can be made when an emergency occurs, reducing the damage to the ecological environment and reducing the need for manual intervention, improving management efficiency and accuracy.

[0076] Please refer to Figure 7 , the embodiment of the present invention provides a technical solution: an offshore three-dimensional layered rights setting project monitoring and warning system, including: an offshore monitoring time series acquisition module for continuously acquiring an offshore monitoring time series data set within the set offshore oil extraction area, including offshore surface monitoring time series data, offshore middle layer monitoring time series data, and offshore bottom layer monitoring time series data; an offshore layered feature analysis module for respectively performing feature analysis on the offshore monitoring time series data set within the set offshore oil extraction area to obtain a monitoring and warning index set for each time point within the set offshore oil extraction area, including a sea surface extraction stress index, an offshore middle layer operation disturbance index, and an offshore bottom layer extraction comprehensive risk index; a comprehensive warning evaluation module for comprehensively analyzing the monitoring and warning index set for each time point within the set offshore oil extraction area to obtain an oil extraction warning index for each time point within the set offshore oil extraction area; an intelligent warning module for performing intelligent oil extraction warning based on the oil extraction warning index for each time point within the set offshore oil extraction area.

[0077] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0078] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. Monitoring and early warning method for marine three-dimensional layered rights project, characterized in that, It includes the following steps: Continuously obtain the marine monitoring time-series dataset within the set offshore oil exploitation area, including the sea surface monitoring time-series data, the mid-sea monitoring time-series data, and the sea bottom monitoring time-series data; Conduct feature analysis on the marine monitoring time-series dataset within the set offshore oil exploitation area respectively to obtain the monitoring warning index set at each time point within the set offshore oil exploitation area, including the sea surface exploitation stress index, the mid-sea operation disturbance index, and the sea bottom exploitation comprehensive risk index; Conduct comprehensive analysis on the monitoring warning index set at each time point within the set offshore oil exploitation area to obtain the oil exploitation warning index at each time point within the set offshore oil exploitation area; Carry out intelligent oil exploitation warning based on the oil exploitation warning index at each time point within the set offshore oil exploitation area; The specific formula for calculating the oil exploitation warning index at each time point within the set offshore oil exploitation area is as follows: ； Among them, , , , are, in sequence, the oil exploitation early warning index, sea surface exploitation stress index, mid - ocean operation disturbance index, and seabed exploitation comprehensive risk index at the -th time point within the set offshore oil exploitation area, is the sea surface exploitation stress index at the -th time point within the set offshore oil exploitation area, , , , , , , are, in sequence, the sea surface stress coefficient, sea surface stress adjustment coefficient, mid - layer disturbance coefficient, mid - layer disturbance adjustment coefficient, seabed risk coefficient, seabed risk adjustment coefficient, and interaction coefficient stored in the database, is the smoothing coefficient stored in the database, , 1, 2, 3, …, , is the number of time points.

2. The monitoring and early warning method for the marine three-dimensional hierarchical rights setting project according to claim 1, characterized in that, The sea surface monitoring time-series data includes the sea surface climate stability index, the sea surface evaporation rate value, the wave height value, and the sea surface biological photosynthetic intensity value at each time. The specific steps for obtaining the sea surface exploitation stress index at each time point within the set offshore oil exploitation area are as follows: Conduct standardization processing on the sea surface climate stability index, the sea surface evaporation rate value, the wave height value, and the sea surface biological photosynthetic intensity value at each time point within the set offshore oil exploitation area; And conduct comprehensive analysis on the sea surface climate stability index, the sea surface evaporation rate value, the wave height value, and the sea surface biological photosynthetic intensity value at each time point within the set offshore oil exploitation area after the standardization processing to obtain the sea surface exploitation stress index at each time point within the set offshore oil exploitation area.

3. The monitoring and early warning method for the marine three-dimensional layered rights project according to claim 1, wherein, The mid-sea monitoring time-series data includes the mid-sea pycnocline index, the ocean current intensity value, the oxygen-sulfur corrosion index, and the water body shear stress value. The specific steps for obtaining the mid-sea operation disturbance index at each time point within the set offshore oil exploitation area are as follows: Conduct normalization processing on the mid-sea pycnocline index, the ocean current intensity value, the oxygen-sulfur corrosion index, and the water body shear stress value at each time point within the set offshore oil exploitation area; And conduct comprehensive analysis on the mid-sea pycnocline index, the ocean current intensity value, the oxygen-sulfur corrosion index, and the water body shear stress value at each time point within the set offshore oil exploitation area after the normalization processing to obtain the mid-sea operation disturbance index at each time point within the set offshore oil exploitation area.

4. The monitoring and early warning method for the marine three-dimensional layered rights setting project according to claim 3, characterized in that, The specific steps for obtaining the mid-sea pycnocline index at each time point within the set offshore oil exploitation area are as follows: Obtain the temperature values and salinity values at several depths at each time point within the set offshore oil exploitation area, and conduct comprehensive analysis respectively to obtain the temperature gradient value and the salinity gradient value at each time point within the set offshore oil exploitation area; And conduct comprehensive analysis on the temperature gradient value and the salinity gradient value at each time point within the set offshore oil exploitation area to obtain the mid-sea pycnocline index at each time point within the set offshore oil exploitation area.

5. The monitoring and early warning method for the marine three-dimensional hierarchical rights setting project according to claim 1, wherein The described marine bottom monitoring time-series data includes seabed topographic image data, seabed pulsation risk index, and seabed microbial activity index at each time point. And the specific steps to obtain the seabed mining comprehensive risk index at each time point within the set marine oil exploitation area for the seabed topographic image data, which is specifically the pixel value and two-dimensional coordinates of each pixel point in the seabed topographic map, are as follows: Input the seabed topographic image data at each time point within the set marine oil exploitation area into a pre-trained terrain recognition model for predictive analysis to obtain the seabed topographic mining risk index at each time point within the set marine oil exploitation area; Conduct a comprehensive analysis of the seabed topographic mining risk index, seabed disaster index, and seabed microbial activity index at each time point within the set marine oil exploitation area to obtain the seabed mining comprehensive risk index at each time point within the set marine oil exploitation area.

6. The monitoring and early warning method for the marine three-dimensional hierarchical rights setting project according to claim 5, characterized in that, The specific steps to calculate the seabed mining comprehensive risk index at each time point within the set marine oil exploitation area are as follows: ； Among them, , , , are, in sequence, the comprehensive risk index of subsea mining, the risk index of subsea terrain mining, the risk index of subsea pulsation, and the microbial activity index of the subsea at the -th time point within the set offshore oil mining area, is the risk index of subsea terrain mining at the -th time point within the set offshore oil mining area, , , , are, in sequence, the subsea terrain adjustment coefficient, the pulsation risk adjustment coefficient, the microbial activity adjustment coefficient, and the collaborative adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of time points.

7. The monitoring and early warning method for the marine three-dimensional hierarchical rights setting project according to claim 5, characterized in that, The terrain recognition model is specifically a convolutional neural network. The convolutional neural network includes an input layer, several convolutional layers, an activation layer, a pooling and flattening layer, and a risk output layer. And the specific steps to obtain the seabed topographic mining risk index at each time point within the set marine oil exploitation area are as follows: In the input layer of the convolutional neural network, receive the seabed topographic image data at each time point within the set marine oil exploitation area and perform preprocessing; In the convolutional layer of the convolutional neural network, perform feature extraction processing on the preprocessed seabed topographic image data at each time point within the set marine oil exploitation area to obtain the seabed topographic feature map at each time point within the set marine oil exploitation area; In the activation layer of the convolutional neural network, perform non-linear transformation processing on the seabed topographic feature map at each time point within the set marine oil exploitation area; In the pooling and flattening layer of the convolutional neural network, perform pooling and flattening processing on the activated seabed topographic feature map at each time point within the set marine oil exploitation area to obtain the seabed topographic feature vector at each time point within the set marine oil exploitation area; In the risk output layer of the convolutional neural network, perform fusion processing on the seabed topographic feature vector at each time point within the set marine oil exploitation area to obtain the seabed topographic mining risk index at each time point within the set marine oil exploitation area.

8. The monitoring and early warning method for the marine three-dimensional hierarchical rights setting project according to claim 1, characterized in that The specific steps for intelligent oil exploitation warning based on the oil exploitation warning index at each time point within the set marine oil exploitation area are as follows: Conduct a trend analysis on the oil exploitation warning index at each time point within the set marine oil exploitation area to obtain several groups of oil exploitation warning index change rates within the set marine oil exploitation area; And conduct a comprehensive analysis of each group of oil exploitation warning index change rates and the oil exploitation warning index at each time point within the set marine oil exploitation area to obtain the predicted oil exploitation warning index within the set marine oil exploitation area, and regard it as the oil exploitation warning index for the next time within the set marine oil exploitation area; Take corresponding preset warning measures based on the oil extraction warning index at the next time point within the set offshore oil extraction area.

9. The monitoring and early warning system for the marine three-dimensional layered rights project applies the monitoring and early warning method for the marine three-dimensional layered rights project according to any one of claims 1-8, and is characterized in that Including: An ocean monitoring time series acquisition module, which is used to continuously acquire the ocean monitoring time series data set within the set offshore oil extraction area, including ocean surface layer monitoring time series data, ocean middle layer monitoring time series data, and ocean bottom layer monitoring time series data; An ocean stratification feature analysis module, which is used to respectively analyze the features of the ocean monitoring time series data set within the set offshore oil extraction area to obtain the monitoring warning index set at each time point within the set offshore oil extraction area, including sea surface extraction stress index, ocean middle layer operation disturbance index, and seabed extraction comprehensive risk index; A comprehensive warning evaluation module, which is used to comprehensively analyze the monitoring warning index set at each time point within the set offshore oil extraction area to obtain the oil extraction warning index at each time point within the set offshore oil extraction area; An intelligent warning module, which is used to conduct intelligent oil extraction warning based on the oil extraction warning index at each time point within the set offshore oil extraction area.

Images