Offshore platform early warning method and device based on ocean numerical model parameter adjustment

Abstract

The invention discloses an offshore platform early warning method and device based on ocean numerical model parameter adjustment, and the method comprises the steps: simulating ocean parameters which may affect the safety of an offshore platform in a period of time in the future through a large-region ocean numerical model; extracting parameter information near an offshore platform in the large-area ocean numerical model, and processing a model forecasting result; whether the offshore platform has potential safety hazards or not is automatically judged according to a model forecasting result, and early warning information is sent to workers; and monitoring ocean data in real time to continuously verify the simulation accuracy of the numerical model, and automatically adjusting parameter values of the model based on AI big data. The invention provides an efficient and accurate offshore platform safety early warning method, which is helpful for finding the potential safety hazard of the offshore platform in advance, reducing the working risk of offshore platform workers and achieving the effect of disaster prevention and reduction, and is particularly suitable for being applied to sea areas with changeable sea conditions.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of offshore platform early warning, and particularly relates to an offshore platform early warning method and device based on marine numerical model parameter adjustment. BACKGROUND

[0002] With the development of science and technology and the progress of society, offshore operation platforms have been widely applied, such as in marine surveying, resource collection, environmental nursing, scientific research and the like. In the face of various complex marine operation environments such as wind, wave and current and the requirements of offshore safety and technical specification clauses, the offshore operation platforms have positive significance for various types of offshore operations and are indispensable equipment for people's marine work, providing stable working places for offshore operations, and their importance is self-evident. However, due to the frequent occurrence of extreme weather at sea, strong wind and large wave weather can easily threaten the safety of offshore platforms, and once a safety accident occurs, the survival probability of platform workers is extremely small, and the economic loss and social influence caused are huge.

[0003] In view of the importance of offshore platforms and the problems faced by their safety, it is particularly important to develop a timely and accurate offshore platform safety risk early warning method. The method helps workers to receive accurate offshore platform risk early warning messages in advance and to take timely measures according to the early warning messages. This method not only helps to reduce the probability of accidents on offshore platforms, but also collects marine data when offshore platforms are threatened, which has important significance for scientific research on the stability and safety of offshore platforms. Therefore, developing a timely and accurate offshore platform safety early warning method has immeasurable value for offshore platform operations. SUMMARY

[0004] The present application aims at the deficiencies of the prior art, and provides an offshore platform early warning method and device based on marine numerical model parameter adjustment, which combines large-area marine numerical models with marine observation data, analyzes and processes simulated data based on AI big data, has a prediction cycle, and has the characteristics of automatic optimization and upgrading of numerical models and full-process automation, aiming to provide a timely and accurate offshore platform safety early warning method to reduce the risk of offshore platforms.

[0005] The purpose of the present application is achieved by the following technical solution: an offshore platform early warning method based on marine numerical model parameter adjustment, comprising the following steps:

[0006] S1. Using a large-area marine numerical model, simulate the marine parameters that may affect the safety of the offshore platform in the region in the future period of time;

[0007] S2. Extracting the marine parameter information near the offshore platform in the large-area marine numerical model, processing the model prediction results;

[0008] S3, judging whether the offshore platform has a safety hazard according to the model prediction result and sending a warning information to the staff;

[0009] S4, monitoring the marine data in real time to continuously verify the simulation accuracy of the large-area marine numerical model;

[0010] S5, returning to step S1 to perform the next round of prediction and warning if the verification is good, and entering the next step if the verification is not good;

[0011] S6, based on the AI big database information, automatically adjusting the parameter setting value of the large-area marine numerical model, and verifying the marine parameters in the period of poor verification again until the next round of prediction and warning is performed.

[0012] Further, the large-area marine numerical model in step S1 is implemented as follows:

[0013] S11, a coupling model is established based on the FVCOM hydrodynamic model, the wave module and the sediment module to analyze the three-dimensional hydrodynamic and sediment dynamic characteristics of the sea;

[0014] S12, the model draws a grid according to the imported coastline data and water depth data;

[0015] S13, the model is driven including open boundary driving and surface forced driving;

[0016] S14, a dry-wet processing module is started during the simulation process of the model.

[0017] Further, the hydrodynamic model, the wave module and the sediment module in S11 are as follows:

[0018] The hydrodynamic model and the wave module are based on FVCOM and coupled with the wave-current interaction process, unstructured triangular grid coordinates are selected in the horizontal direction, and sigma coordinates are applied in the vertical direction. When calculating, the inner and outer modes are split, the two-dimensional outer mode control equation is integrated and solved by using the improved fourth-order Runge-Kutta time step method, which has a second-order time accuracy, and the three-dimensional inner mode momentum equation is solved by using the second-order upwind format difference method combined with the explicit and implicit methods; the sigma coordinate transformation formula in the vertical direction is as follows:

[0019]

[0020] In the formula: z is the Cartesian vertical coordinate, positive, η is the free surface change, D is the total water depth; when located at the seabed, -1 is taken; when located at the sea surface, 0 is taken;

[0021] The sediment module considers the coupling of water and sediment density, flocculation and sedimentation process and the characteristics of the floating mud bottom boundary layer, and uses the following suspended sediment concentration diffusion equation to calculate:

[0022]

[0023] In the formula, x, y, z are the components of the east, north and vertical coordinates, u, v, w are the velocities in the x, y, z directions, C is the suspended sediment concentration, w s is the settling velocity of suspended sediment, positive downward, K h is the vertical sediment diffusion coefficient, A H is the horizontal sediment diffusion coefficient.

[0024] Further, the shoreline data and water depth data in S12 are as follows:

[0025] The shoreline data is from the United States National Oceanic and Atmospheric Administration, and the shoreline data in the key area is corrected by satellite map;

[0026] The water depth data uses ETOP1 topographic data provided by the United States National Oceanic and Atmospheric Administration, with a resolution of 1'x1', and high-resolution measured data and chart data are supplemented in the key research area.

[0027] Further, the open boundary driving in S13 includes tidal level driving and temperature-salinity driving; the surface forcing driving includes wind driving and heat flux driving;

[0028] The tidal level driving uses the time series tidal level generated by the TPXO7.2 global tidal model, and the hourly tidal level is composed of four full-day partial tides K1, O1, P1, Q1, four semi-diurnal tides M2, S2, N2, K2, three shallow water tides M4, MS4, MN4 and two long-period tides M f , M m ;

[0029] The runoff driving is used for sea areas obviously affected by runoff, including flow and sediment discharge information;

[0030] The wind driving includes normal weather and storm surge processes; the wind field data under normal weather comes from the wind speed data at a distance of 10 m from sea level provided by the United States National Environmental Prediction Center NCEP, with a time resolution of 6 h and a spatial resolution of 0.2°, involving parameters such as wind speed u and v components; the field under the storm surge process is superimposed by the calculated rotational wind field, the moving wind field and the NCEP wind field, and the near typhoon area mainly depends on the model calculation value, and the typhoon periphery calculates the NCEP wind field, and the calculation formula is as follows:

[0031]

[0032]

[0033]

[0034] wherein: V mov_x , V mov_y are the x, y direction components of the translation wind field, respectively, V NCEP_x , V NCEP_y are the x, y direction components of the NCEP wind field, respectively; θ w represents the angle between the line connecting the calculation point and the typhoon center and the due east direction counterclockwise; β in is the inflow angle, which represents the deflection angle of the gradient wind vector through the isobaric line, and is approximately 20°; C1 is a correction coefficient, and is 0.71 according to the atmospheric boundary layer theory; and n is a constant, and is 9.

[0035] The heat flux driver uses the GFSv2 database of the National Environmental Prediction Center (NCEP) climate prediction system, the data horizontal resolution is 0.2°, and the data is initialized four times every day, that is, 0000, 0600, 1200 and 1800 UTC, and the parameters involved in the driving are: upward long-wave radiation flux, downward long-wave radiation flux, upward short-wave radiation flux, downward short-wave radiation flux, sensible heat flux and latent heat flux.

[0036] The temperature-salinity driver comes from the GOFS 3.1 database of the global ocean prediction system (GOFS) in the hybrid coordinate ocean model (HYCOM), the data horizontal resolution is 1 / 12°, and the vertical resolution is 41 layers.

[0037] Further, the step S2 comprises the following steps:

[0038] S21, based on the offshore platform position, grabbing the large-area ocean numerical model simulation data near the position;

[0039] S22, uploading the simulation data to a server;

[0040] S23, processing the data in the server, and displaying in the form of images and texts.

[0041] Further, the server in the step S22 comprises a data uploading module, a data processing module, a storage module, a security judgment module, a warning message pushing module and a monitoring board.

[0042] The data uploading module is used for automatically uploading the offshore platform position model simulation data and receiving real-time monitoring videos around the offshore platform.

[0043] The data processing module is used for checking the quality of the uploaded data, and drawing the data into a line graph, a two-dimensional plane graph and a three-dimensional solid graph.

[0044] The storage module is used for storing the screened data, the drawn image and the early warning message content;

[0045] The safety judgment module is used for judging whether the predicted sea state will pose a threat to the safety of the offshore platform based on various design values of the offshore platform;

[0046] The early warning message pushing module is used for sending early warning information to the receiving end electronic device based on the judgment result of the safety judgment module; the early warning information includes the predicted sea state, the judgment result of the safety judgment module and the recommended response measures; the response measures are intelligently selected according to the AI big database;

[0047] The monitoring board is used for monitoring the real-time monitoring video based on the data uploading module, the model simulation result based on the data processing module and the early warning information based on the early warning message pushing module.

[0048] Further, in step S4, the marine data is monitored in real time by arranging sensors near the offshore platform, the carrier of the sensor is a floating buoy, and the buoy body includes a sensor, a solar panel, a storage battery, a solar integrated navigation light, a radar reflector, a safety alarm device, a Beidou communication positioning device, a data acquisition and transmission device and a data storage device;

[0049] The buoy body is fixed near the offshore platform by an anchor chain; the specification and material of the anchor chain are determined according to the specific sea area;

[0050] The marine parameters monitored by the sensor include wave height, wave direction, wave period, flow velocity, flow direction, tidal level and suspended sediment concentration; the measurement range and accuracy of each marine parameter are determined according to the specific sea area;

[0051] The solar panel is used for powering the entire buoy and powering the internal storage battery;

[0052] The storage battery ensures that the buoy equipment can work normally under continuous 15-day rainy conditions;

[0053] The solar integrated navigation light, the radar reflector and the safety alarm device are used for warning ships to keep away from the buoy when the visibility is lower than a threshold value, so as to ensure the safety of the buoy;

[0054] The Beidou communication positioning device is used for feeding back whether the position of the buoy changes to avoid the buoy from falling off and being lost;

[0055] The data acquisition and transmission device is used for online monitoring of communication between the buoy system and the shore station, and selects 4G / 5G or a combination of Beidou satellite communication modes according to the actual communication condition of the station.

[0056] The data storage device is used for storing the collected data.

[0057] Further, in step S6, the AI automatically adjusts the model parameters that may cause the deviation according to the marine parameters that appear the simulation deviation based on the learning and analysis of the existing marine large-area numerical model in the AI large database, and modifies the parameters, thereby realizing real-time updating of the numerical model.

[0058] In another aspect, the present application also provides a marine platform early warning device based on marine numerical model parameter adjustment, comprising a memory and one or more processors, the memory stores executable code, and the processor executes the executable code to realize the marine platform early warning method based on marine numerical model parameter adjustment.

[0059] In summary, the present application has the following beneficial effects:

[0060] 1. The present application provides a marine platform early warning method and device based on marine numerical model parameter adjustment, which uses a large-area marine numerical model to simulate and predict the marine environment of the sea area where the marine platform is located, realizes timely, accurate and automatic risk warning of the marine platform, and ensures the safety of the marine platform.

[0061] 2. The present application collects measured data near the marine platform by a numerical buoy, automatically processes model simulation data based on AI big data, and continuously verifies and optimizes the numerical model combined with the collected measured data, thereby ensuring the accuracy of the numerical model prediction. BRIEF DESCRIPTION OF DRAWINGS

[0062] Figure 1 It is a flowchart of a marine platform early warning method based on marine numerical model parameter adjustment.

[0063] Figure 2 It is a triangular mesh calculation schematic diagram.

[0064] Figure 3 It is a model mesh schematic diagram of a certain marine area.

[0065] Figure 4 It is a vertical sigma coordinate schematic diagram.

[0066] Figure 5 It is a server composition conceptual diagram.

[0067] Figure 6 It is a server monitoring board schematic diagram.

[0068] Figure 7 is a schematic diagram of a buoy structure.

[0069] Figure 8 is a schematic diagram of a buoy position.

[0070] Figure 9 is a structural diagram of a marine platform early warning device based on ocean numerical model parameter adjustment.

[0071] In the figure: 51. data upload module, 52. data analysis module, 53. data storage module, 54. security judgment module, 55. early warning message pushing module, 56. monitoring board, 61. marine platform real-time monitoring video, 62. safety early warning information, 63. prediction data visualization image, 71. sensor, 72. solar panel, 73. storage battery, 74. solar integrated navigation light, 75. radar reflector, 76. safety alarm device, 77. Beidou communication positioning device, 78. data acquisition and transmission device, 79. data storage device. DETAILED DESCRIPTION

[0072] The specific embodiments of the present application will be described below with reference to the accompanying drawings, so that those skilled in the art can understand the present application, but it should be clear that the present application is not limited to the scope of the specific embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor, and all the inventions using the concept of the present application are within the scope of protection.

[0073] The embodiment of the present application provides a marine platform early warning method based on ocean numerical model parameter adjustment, which is executed by an electronic device, which can be a server or a terminal device. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication, and the present application is not limited thereto, such as shown in the figure, the method comprises steps S1-S6, wherein, Figure 1

[0074] Step S1, using a large-area ocean numerical model, simulating the wave height, flow rate and other ocean parameters that may affect the safety of the marine platform in the future 2-3 days.

[0075] ​For the examples of the present application, a large-area ocean numerical model is established based on a coupling model of an FVCOM hydrodynamic model, a wave module and a sediment module; a model grid is drawn according to imported coastline data and water depth data; model driving mainly includes open boundary driving and surface forcing driving; a dry-wet processing module is opened during simulation, the minimum water depth is set to 0.05 m, the simulation result output frequency is once per hour, and the entire simulation process is performed in the above-mentioned server.

[0076] An unstructured triangular grid coordinate is selected in the horizontal direction of the model, and each triangular grid is composed of 1 center, 3 nodes and 3 edges. Figure 2 As shown in FIG. 1, the FVCOM model calculates the velocity variables u and v at the center of the triangle, and calculates the scalar at the node of the triangle, and the grid of the entire model is composed of a plurality of triangular grids as shown in FIG. 2. Figure 3 As shown in FIG. 2, a model grid diagram of a certain marine area is shown. According to the water depth change of different sea areas, the grid resolution should be adjusted accordingly. It is suggested that the grid order can be 10 km-100 km at the open boundary of the model and where the water depth changes gently; the grid order can be 1 m-100 m at the place where the coastline is complex and the water depth changes greatly, or the place which needs to be focused on. The vertical direction applies the coordinate as shown in FIG. 3, and the inner and outer modes are split during calculation. The two-dimensional outer mode control equation is integrated and solved by using the improved fourth-order Runge-Kutta time step method, which has a second-order time accuracy. The three-dimensional inner mode momentum equation is solved by using the second-order upwind format difference method combined with the explicit and implicit methods; the coordinate transformation formula used in the vertical direction is as follows: Figure 4

[0077]

[0078] In the formula, z is the Cartesian vertical coordinate (positive upward), η is the free surface change, and D is the total water depth. When located at the seabed, -1 is taken; when located at the sea surface, 0 is taken.

[0079] The sediment module considers the water-sediment density coupling, flocculation settling process and floating mud bottom boundary layer characteristics, and calculates the suspended sediment concentration diffusion equation as follows:

[0080]

[0081] In the formula, x, y and z are the east, north and vertical components of the coordinate axes, u, v and w are the velocities in the x, y and z directions, C is the suspended sediment concentration, w s is the settling velocity of suspended sediment, positive downward; A H and K h are the horizontal and vertical sediment diffusion coefficients, respectively. ​

[0082] When the model is started, the wave module is calculated first, based on the instantaneous water level and flow rate provided by the tidal current model, to obtain wave height, wave direction, wave length, spectral peak period, and other wave elements. The relevant wave physical parameters are used to calculate Stokes drift velocity, wave dissipation, form drag, radiation stress, and other feedback to the tidal current model. Then the tidal current model is calculated to obtain water level, flow rate, vertical eddy viscosity coefficient, and other parameters, which are transmitted to the sediment module and the next time wave module. The bottom boundary layer model calculates the wave-current coupled bottom stress based on the received flow rate, wave elements, and bottom bed information, and feeds back to the tidal current model and sediment module. The sediment module calculates the suspended sediment transport, and updates the water density and bottom thickness to the tidal current model and wave module for the next time water dynamic element and wave element calculation.

[0083] The shoreline data is derived from high-precision data provided by the United States National Oceanic and Atmospheric Administration (NOAA), and the shoreline data in the key area is corrected using Landsat satellite images in 2019.

[0084] The water depth data uses ETOP1 topographic data provided by NOAA, with a resolution of 1'x1', and high-resolution measured data and chart data are supplemented in the key research area.

[0085] The open boundary driving of the model includes tidal level driving and temperature-salinity driving; the surface forcing driving includes wind driving and heat flux driving.

[0086] The tidal level driving uses the time series tidal level generated by the TPXO7.2 global tidal model, and the hourly tidal level is composed of four full-day tides (K1, O1, P1, Q1), four half-day tides (M2, S2, N2, K2), three shallow water tides (M4, MS4, MN4), and two long-period tides (Mf, Mm).

[0087] The runoff driving is used for sea areas that are obviously affected by runoff, including flow and sediment discharge information.

[0088] The wind driving includes normal weather and storm surge processes; the wind field data under normal weather comes from the wind speed data at a distance of 10 m from sea level provided by the United States National Environmental Prediction Center (NCEP), with a time resolution of 6 h and a spatial resolution of about 0.2°, involving parameters such as wind speed u and v components; the field under the storm surge process is superimposed by the calculated rotational wind field, the moving wind field, and the NCEP wind field, and the near typhoon area mainly depends on the model calculation value, and the typhoon periphery mainly uses the NCEP wind field, and the calculation formula is as follows:

[0089]

[0090]

[0091]

[0092] Vx, Vy are the x, y direction components of the translation wind field, respectively mov_x Vx, Vy are the x, y direction components of the translation wind field, respectively mov_y Vx, Vy are the x, y direction components of the translation wind field, respectively NCEP_x Vx, Vy are the x, y direction components of the translation wind field, respectively NCEP_y Vx, Vy are the x, y direction components of the translation wind field, respectively w θ represents the angle between the line connecting the calculation point and the typhoon center and the due east direction counterclockwise; β in β is the inflow angle, which represents the deflection angle of the gradient wind vector through the isobaric line, and is approximately 20°; C1 is a correction coefficient, and is 0.71 according to the atmospheric boundary layer theory; and n is a constant, and is 9.

[0093] The heat flux driver uses the National Centers for Environmental Prediction (NCEP) Global Forecast System (GFSv2) database, the horizontal resolution of the data is 0.2°, and the data is initialized four times (0000, 0600, 1200 and 1800 UTC) every day, and the parameters involved in the driving are: upward longwave radiation flux, downward longwave radiation flux, upward shortwave radiation flux, downward shortwave radiation flux, sensible heat flux and latent heat flux.

[0094] The temperature-salinity driver comes from the Global Ocean Forecasting System (GOFS 3.1) database in the HYbrid Coordinate Ocean Model (HYCOM), the horizontal resolution of the data is 1 / 12°, and the vertical resolution is 41 layers.

[0095] Step S2, extracting each marine parameter information near the offshore platform in the large-area marine numerical model, processing the model prediction result, and specifically can be divided into the following steps:

[0096] Step S21, based on the offshore platform position, the model simulation data near the position is grabbed;

[0097] For the example of the present application, according to the coordinate position (latitude and longitude information) of the offshore platform concerned, the operator needs to input the range of the data to be grabbed in advance in the server, for example, a certain offshore platform is located at (30.044°N, 123.093°E), and the model data within a range of 1 km around the offshore platform needs to be extracted, so the range can be set as: 30.034°N-30.054°N, 123.083°E-123.103°E (latitude and longitude change 0.01°, distance change about 1000 m). The server can automatically extract the model simulation data of the corresponding area according to the setting.

[0098] Step S22, uploading the simulation data to the server;

[0099] For the examples of the present application, the model uploads the simulated data obtained to a server as shown in Figure 5 The server includes a data uploading module 51, a data analysis module 52, a data storage module 53, a security judgment module 54, an early warning message pushing module 55, and a monitoring board 56.

[0100] Step S23, the data is processed in the server and displayed in the form of images, texts, etc.

[0101] For the examples of the present application, the data uploading module 51 is used to automatically upload the model simulated data obtained, and receives real-time monitoring videos around the offshore platform; the data analysis module 52 is used to check the quality of the uploaded data and eliminate some obviously incorrect data. Meanwhile, according to the pre-set points of interest and the range of interest, the data of the points of interest is drawn into a one-dimensional line graph of time series, the data of the range of interest is drawn into a two-dimensional plane graph, and a three-dimensional solid graph with water depth is added. If necessary, the two-dimensional graph and the three-dimensional graph can also be drawn into dynamic pictures changing with time series; the data storage module 53 is used to store the screened data, the drawn images, and the early warning messages, etc. The storage space of the server should be able to guarantee at least half a year of data, and if necessary, the server storage space can be upgraded to retain data of a longer time series; the security judgment module 54 is used to judge whether the predicted sea conditions will pose a threat to the safety of the offshore platform; the early warning message pushing module 55 is used to send early warning information to the monitoring board 56 of the receiving end electronic device based on the judgment result of the security judgment module, and the content distribution of the monitoring board is as shown in Figure 6 The monitoring board includes real-time monitoring videos 61 of the offshore platform, safety early warning information 62, and visualized images 63 of the predicted data. The real-time monitoring videos 61 of the offshore platform can switch the pictures of different monitoring probes as needed and zoom the size of the monitoring pictures. The visualized images 63 of the predicted data are not limited to a single point or a single area. The server can simultaneously perform the above-mentioned processing on multiple points and areas and display them on the monitoring board, so that the operating personnel can switch and view the model prediction of different points or areas by themselves.

[0102] Step S3, automatically judging whether the offshore platform has safety hazards according to the model prediction result and sending early warning information to the staff;

[0103] For the example of the present application, the automatic determination of whether the offshore platform has safety hazards depends on the safety determination module 54 in the server. Based on the design values of the offshore platform, the module limits the values of the model simulation data to determine whether the offshore platform has safety hazards. For example, if the maximum wave height that a certain offshore platform can withstand is 5 m, the upper limit value of the wave height data can be set to 5 m. When the model simulation of the wave height data exceeds the upper limit, the server determines that the sea state at that time will pose a threat to the safety of the offshore platform. The other marine environmental parameter determination methods are consistent with the above method. The warning information is sent to the electronic device terminal based on the warning message pushing module 55. The receiving end electronic device includes but is not limited to: mobile phone, notebook computer, digital broadcast receiver, tablet computer, vehicle terminal, PMP (portable multimedia player), PAD (tablet computer); In addition, the format of the warning information can be set according to the operator, and different formats can be adopted, which are recommended to include the following: predicted sea state, safety determination module judgment result and recommended response measures; The recommended response measures can be intelligently selected and recommended by the AI big database.

[0104] Step S4, arranging sensors near the offshore platform to collect wave height, flow rate and other measured marine data to continuously verify the accuracy of the numerical model simulation;

[0105] For the example of the present application, it is recommended to select a floating buoy as the carrier of the sensor. The buoy body is as shown in Figure 7 The buoy body includes: a sensor 71, a solar cell panel 72, a storage battery 73, a solar integrated navigation light 74, a radar reflector 75, a safety alarm device 76, a Beidou communication positioning device 77, a data acquisition and transmission device 78, and a data storage device 79. The buoy is fixed near the offshore platform by anchor chain, as shown in Figure 8The anchor chain specification material is determined according to the specific sea area and the buoy condition; the ocean parameters that can be measured by the sensor 71 include wave height, wave direction, wave period, flow velocity, flow direction, tidal level, suspended sediment concentration, the measurement range and measurement accuracy of each ocean parameter are determined according to the specific sea area condition; the solar cell panel 72 is used for power supply of the whole buoy working, and can supply power for the internal storage battery; the storage battery 73 ensures that under the condition of continuous 15 days of rain, it can support the normal work of the buoy equipment; the solar integrated navigation beacon 74, the radar reflector 75 and the safety alarm device 76 are used for warning ships to keep away from the buoy under the condition of low visibility (lower than the set threshold), and ensuring the safety of the buoy; the Beidou communication positioning device supports multiple communication modes 77: USB, SDI12 and RS232, which are used for feeding back whether the position of the buoy changes, to avoid the buoy from falling off and being lost; the data acquisition and transmission device 78 supports online monitoring of the communication between the buoy system and the shore station, is compatible with multiple communication modes, and can select 4G / 5G or Beidou satellite combined communication mode according to the actual communication condition of the station site; the data storage device 79 has a storage capacity greater than or equal to 512MB, and should store not less than 1 million reading records, and does not lose data in power failure.

[0106] Step S5, if the verification is good, return to step S1 to perform the next round of prediction and early warning, if the verification is not good, enter the next step;

[0107] For the example of the application, the model verification method uses correlation coefficient (correlation coefficient, CC) and model evaluation coefficient (skill score, SS) to quantify the verification result, and the related formula is as follows:

[0108]

[0109]

[0110] In the formula: m i and o i are the model calculation value and the measured value respectively, and are the average values of the model calculation value and the measured value respectively, S m and S o are the standard deviations of the model calculation value and the measured value respectively.

[0111] The correlation coefficient is a parameter for studying the linear correlation degree between variables, and the closer to 1, the greater the correlation between the calculated value and the measured value, and the more accurate the model. When the model evaluation coefficient is greater than 0.65, the credibility of the model is very high; when it is between 0.50 and 0.65, the model has high credibility; and when it is less than 0.2, the credibility of the model is poor. The judgment basis for whether the model is verified well is that the correlation coefficient value calculated by the model is greater than or equal to 0.9, and the model evaluation coefficient is greater than or equal to 0.50; the correlation coefficient value calculated by the model is less than 0.9, or the model evaluation coefficient is less than 0.50.

[0112] Step S6, based on the AI big database information, automatically adjusting the parameter setting value of the model, and verifying the marine parameters in the poor verification period again to verify until the next round of forecasting and early warning is performed.

[0113] For the example of the present application, when the model appears to be poorly verified in step S5, the AI can automatically intercept the time range of poor verification, for example, the time period of the model simulation this time is from 00 on March 5 to 24 on March 7, but the model verification is poor from 19 on March 6 to 24 on March 7, at this time, the AI big data will only analyze the reasons for the deviation between the simulation data and the measured data in this time period, and adjust the model parameters according to the reasons. In addition, in the process of re-simulation, the AI will select the simulation result of the previous time (i.e. 18 on March 6) of the first time (i.e. 19 on March 6) of poor verification as the initial field of the model start, so as to save the time required for the second simulation, and achieve the purpose of quickly optimizing the model.

[0114] Corresponding to the foregoing embodiment of the offshore platform early warning method based on the adjustment of the marine numerical model parameters, the present application also provides an embodiment of an offshore platform early warning device based on the adjustment of the marine numerical model parameters.

[0115] Referring to Figure 9 The offshore platform early warning device based on the adjustment of the marine numerical model parameters provided by the embodiment of the present application comprises a memory and one or more processors, the memory stores executable code, and the processor executes the executable code to implement the offshore platform early warning method based on the adjustment of the marine numerical model parameters in the foregoing embodiments.

[0116] The embodiment of the offshore platform early warning device based on marine numerical model parameter adjustment provided by the present application can be applied to any device with data processing capability, which can be a device or apparatus such as a computer. The device embodiment can be realized by software, or by hardware or a combination of software and hardware. Taking software realization as an example, as a logically meaningful device, it is formed by reading the corresponding computer program instructions in the non-volatile memory into the memory for running by the processor of the device with data processing capability. From the hardware level, as shown in Figure 9 The processor, the memory, the network interface, and the non-volatile memory are shown in the hardware structure diagram of the device with data processing capability of the offshore platform early warning device based on marine numerical model parameter adjustment provided by the present application, in addition to the processor, the memory, the network interface, and the non-volatile memory, the device with data processing capability in the embodiment can also include other hardware according to the actual functions of the device with data processing capability, and details are not described herein. Figure 9

[0117] The implementation process of the functions and roles of each unit in the above device is specifically described in the implementation process of the corresponding steps in the above method, and details are not described herein.

[0118] For the device embodiment, it basically corresponds to the method embodiment, so the related parts can refer to the part of the method embodiment. The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the present application scheme. Those skilled in the art can understand and implement without creative labor.

[0119] The embodiment of the present application also provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the offshore platform early warning method based on marine numerical model parameter adjustment in the above embodiment.

[0120] ​The computer readable storage medium can be an internal storage unit of any data processing capable device as described in any of the preceding embodiments, such as a hard disk or a memory. The computer readable storage medium can also be an external storage device of any data processing capable device, such as a plug-in hard disk, a Smart Media Card (SMC), an SD card, a Flash Card, etc. Further, the computer readable storage medium can include both an internal storage unit and an external storage device of any data processing capable device. The computer readable storage medium is used to store the computer program and other programs and data required by the data processing capable device, and can also be used to temporarily store data that has been output or will be output.

[0121] The application further provides a computer program product comprising a computer program, which, when executed by a processor, implements the offshore platform early warning method based on marine numerical model parameter adjustment.

[0122] The above description is only preferred embodiments of the present application and is not intended to limit the present application. It should be pointed out that, without departing from the principles of the present application, a number of improvements and supplements can be made, and these improvements and supplements should also be considered as the protection scope of the present application.

Claims

1. An offshore platform early warning method based on adjustment of ocean numerical model parameters, characterized in that: The method comprises the following steps: S1. Use a large-area ocean numerical model to simulate ocean parameters that may affect the safety of offshore platforms in the region over a period of time in the future; S2. Extract ocean parameter information near offshore platforms from large-area ocean numerical models and process model prediction results; S3. Determine whether the offshore platform has safety hazards based on the model prediction results and send early warning information to the staff; S4. Real-time monitoring of ocean data to continuously verify the accuracy of large-area ocean numerical model simulations; S5: If the verification is good, return to step S1 and proceed to the next round of forecast and warning; if the verification is not good, proceed to the next step; S6. Based on the information from the AI ​​big database, automatically adjust the parameter setting values ​​of the large-area ocean numerical model, and simulate and verify the ocean parameters in the poor verification period again until the verification is good and the next round of forecast and warning is carried out.

2. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 1 is characterized in that: The large-area ocean numerical model in step S1 is implemented as follows: S11. Establish a coupled model based on the FVCOM hydrodynamic model, wave module, and sediment module to analyze the three-dimensional hydrodynamic and sediment dynamic characteristics of the ocean; S12, the model draws a grid based on the imported shoreline data and water depth data; S13, Model driving includes open boundary driving and surface forced driving; S14. During the model simulation, the dry-wet processing module is turned on.

3. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 2 is characterized in that: The hydrodynamic model, wave module and sediment module in S11 are as follows: The hydrodynamic model and wave module are based on FVCOM and coupled with the wave-current interaction process. Unstructured triangular grid coordinates are used in the horizontal direction, and sigma coordinates are used in the vertical direction. The internal and external models are split during calculation. The two-dimensional external model governing equation is solved by integration using the fourth-order Runge-Kutta time-stepping method with second-order time accuracy. The three-dimensional internal model momentum equation is solved by a second-order upwind difference method combined with explicit and implicit methods. The sediment module considers the water-sediment density coupling, flocculation and sedimentation process, and the floating mud bottom boundary layer characteristics.

4. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 2 is characterized in that: The shoreline data and water depth data in S12 are as follows: The coastline data mentioned above is from the National Oceanic and Atmospheric Administration of the United States, and the coastline data of key areas are corrected using satellite images; The water depth data mentioned above adopts the ETOP1 topographic data provided by the National Oceanic and Atmospheric Administration of the United States, and the key research areas are supplemented by high-resolution measured data and nautical chart data.

5. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 2 is characterized in that: The open boundary driving in S13 includes: tide driving and temperature-haline driving; the surface forced driving includes: wind driving and heat flux driving; The tide level driver uses the time series tide level generated by the tide model. The hourly tide level consists of four full-day tides K1, O1, P1, Q1, four semi-day tides M2, S2, N2, K2, three shallow water tides M4, MS4, MN4 and two long period tides M f 、M m constitute; Runoff driven is used for sea areas significantly affected by runoff, including information on discharge and sediment transport; The wind drive includes two conditions: normal weather and storm surge process. The wind field data under normal weather is derived from the sea level wind speed data provided by the National Centers for Environmental Prediction (NCEP) of the United States. The field under the storm surge process adopts the calculated rotating wind field, the transitional wind field and the NCEP wind field superimposed. The area near the typhoon depends on the model calculation value, and the NCEP wind field is calculated in the periphery of the typhoon. The heat flux driver uses the U.S. National Centers for Environmental Prediction (NCEP) Climate Forecast System GFSv2 database. The parameters involved in the driver are: upward longwave radiation flux, downward longwave radiation flux, upward shortwave radiation flux, downward shortwave radiation flux, sensible heat flux, and latent heat flux. The thermohaline driving is derived from the Global Ocean Forecast System GOFS 3.1 database in the hybrid coordinate ocean model HYCOM.

6. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 1, characterized in that: The step S2 comprises the following steps: S21. Based on the location of the offshore platform, capture the ocean numerical model simulation data of a large area near the location; S22, uploading the simulation data to the server; S23. Process the data in the server and display it in the form of images and text.

7. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 6, characterized in that: The server described in step S22 includes: a data uploading module, a data processing module, a storage module, a security judgment module, an early warning message push module and a monitoring dashboard; The data uploading module is used to automatically upload the offshore platform position model simulation data and receive the real-time monitoring video around the offshore platform; The data processing module is used to check the quality of the uploaded data and draw the data into line graphs, two-dimensional plane graphs and three-dimensional stereograms; The storage module is used to store the filtered data, drawn images and warning message content; The safety judgment module is used to judge whether the predicted sea conditions will pose a threat to the safety of the offshore platform based on various design values ​​of the offshore platform; The warning message push module is used to send warning information to the receiving electronic device based on the judgment result of the safety judgment module; the warning information includes: predicted sea conditions, the judgment result of the safety judgment module, and recommended countermeasures; the countermeasures are intelligently selected based on the AI ​​big data database; The monitoring dashboard is used for real-time monitoring video based on the data uploading module, model simulation results based on the data processing module and warning information based on the warning message pushing module.

8. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 1 is characterized in that: In step S4, sensors are deployed near the offshore platform to monitor ocean data in real time. The sensor carrier is a floating buoy, which includes: sensors, solar panels, batteries, solar integrated navigation lights, radar reflectors, safety alarms, Beidou communication positioning devices, data acquisition and transmission devices, and data storage devices. The buoy body is fixed near the offshore platform by an anchor chain; the specifications and materials of the anchor chain are determined according to the specific conditions of the sea area; The ocean parameters monitored by the sensor include: wave height, wave direction, wave period, current velocity, current direction, tide level and suspended sediment concentration. The measurement range and measurement accuracy of each ocean parameter are determined according to the specific sea conditions. The solar panels are used to provide power for the entire buoy and for the internal batteries; The battery is guaranteed to support the normal operation of the buoy equipment under rainy conditions for 15 consecutive days; The solar integrated navigation light, radar reflector, and safety alarm device are used to warn ships to stay away from the buoy when visibility falls below a threshold, ensuring the safety of the buoy. The Beidou communication positioning device is used to feedback whether the buoy position has changed to prevent the buoy from falling off and being lost; The data acquisition and transmission device is used to monitor the communication between the buoy system and the shore station online, and selects 4G / 5G or Beidou satellite combined communication mode according to the actual communication conditions of the deployment station; The data storage device is used to store collected data.

9. The offshore platform early warning method based on ocean numerical model parameter adjustment according to claim 1, characterized in that: In step S6, AI automatically adjusts the learning and analysis of existing large-area ocean numerical models in the AI ​​big database, finds the model parameters that may cause such deviations based on the ocean parameters where simulation deviations occur, and modifies the parameters to achieve real-time updating of the numerical model.

10. An offshore platform early warning device based on adjustment of ocean numerical model parameters, comprising a memory and one or more processors, wherein the memory stores executable code, characterized in that: When the processor executes the executable code, an offshore platform early warning method based on ocean numerical model parameter adjustment according to any one of claims 1 to 9 is implemented.

Images