Offshore platform emergency control method and related equipment based on Beidou satellite system

Abstract

The present application discloses an offshore platform emergency control method and related equipment based on the Beidou satellite system, which relates to the field of Beidou satellite technology. The offshore platform emergency control method based on the Beidou satellite system includes: obtaining Beidou satellite timing signals and real-time meteorological data, synchronously collecting structural deformation parameters of the offshore platform, dynamic parameters of the marine environment, and personnel positioning information, and constructing multi-dimensional data of the offshore platform; fusing and analyzing the multi-dimensional data of the offshore platform, extracting spatiotemporal correlation features and constructing a multi-factor causal chain through a pre-trained dynamic risk prediction model, and determining the platform risk level and accident type prediction results; triggering a graded emergency response based on the accident type prediction results, encrypting and transmitting the corresponding early warning instructions to a preset terminal through a Beidou short message, and executing the corresponding emergency control method. The present application constructs multi-dimensional data synchronized in time and space to perform risk prediction and emergency response, so that the offshore platform can perform timely emergency control.

Description

Technical Field

[0001] The present application relates to the field of Beidou satellite technology, and in particular to an emergency control method and related equipment for an offshore platform based on the Beidou satellite system. Background Art

[0002] With the continuous development of marine resources, offshore platforms are playing an increasingly important role in marine engineering. However, offshore platforms face complex marine environments and changeable meteorological conditions, such as strong winds, waves, and currents. These factors can cause structural deformation, equipment failure, and even accidents, seriously threatening the safe operation of the platform and the lives of personnel.

[0003] Existing emergency control methods for offshore platforms often fail to fully consider the spatiotemporal correlation and dynamic changes of multiple factors, and are unable to effectively integrate and analyze multi-source heterogeneous data from offshore platforms. In related technologies, emergency control can usually only be carried out after the problem occurs in an emergency, which is subject to serious lag.

[0004] Therefore, how to carry out timely and effective emergency control of offshore platforms in emergency situations has become an urgent problem to be solved. Summary of the Invention

[0005] The main purpose of this application is to provide an offshore platform emergency control method and related equipment based on the BeiDou satellite system, aiming to solve the technical problem of lag in emergency control of offshore platforms in emergency situations.

[0006] To achieve the above objectives, this application proposes a method for emergency control of an offshore platform based on the BeiDou satellite system, the method comprising:

[0007] Obtain Beidou satellite timing signals and real-time meteorological data, and simultaneously collect structural deformation parameters of offshore platforms, dynamic parameters of the marine environment, and personnel positioning information to construct multi-dimensional data of offshore platforms;

[0008] By integrating and analyzing the multi-dimensional data of the offshore platform, the pre-trained dynamic risk prediction model is used to extract spatiotemporal correlation features and construct a multi-factor causal chain to determine the platform risk level and accident type prediction results;

[0009] A graded emergency response is triggered based on the accident type prediction results, and the corresponding early warning instructions are transmitted to the preset terminal through Beidou short message encryption to execute the corresponding emergency control method.

[0010] In one embodiment, the step of extracting spatiotemporal correlation features and constructing a multi-factor causal chain using a pre-trained dynamic risk prediction model includes:

[0011] Obtain a preset historical accident database, platform finite element simulation data, and Beidou meteorological data. Use a transfer learning framework to spatially map the platform finite element simulation data with historical accident scenarios to construct a training set for offshore platform sudden event events.

[0012] Extracting the temporal features of the offshore platform sudden event training set through a neural network model, and establishing a corresponding causal chain model through a dynamic Bayesian network to perform risk prediction on the temporal features, thereby obtaining a risk prediction result;

[0013] If the risk prediction result does not reach the preset confidence level, the process returns to the step of extracting the temporal characteristics of the offshore platform mutation event training set through the neural network model until the risk prediction result reaches the confidence level, and a dynamic risk prediction model that meets the confidence level requirements is determined.

[0014] In one embodiment, the steps of acquiring Beidou satellite timing signals and real-time meteorological data, synchronously collecting structural deformation parameters of the offshore platform, dynamic parameters of the marine environment, and personnel positioning information, and constructing multi-dimensional data of the offshore platform include:

[0015] Based on the BeiDou satellite timing signal, a cross-modal data synchronization channel is established to perform spatiotemporal alignment on the structural deformation data, the marine environment data, and the personnel positioning data, thereby eliminating the spatiotemporal misalignment of the multi-source data and obtaining real-time synchronized data;

[0016] A unified spatiotemporal data coding structure is constructed at the edge computing node, and the real-time synchronous data is dynamically labeled according to the spatiotemporal dimensions, physical quantity types, and data credibility, and combined into the multi-dimensional data of the offshore platform.

[0017] In one embodiment, the steps of extracting the time series features of the offshore platform sudden event training set through a neural network model, and performing risk prediction on the time series features by establishing a corresponding causal chain model through a dynamic Bayesian network to obtain a risk prediction result include:

[0018] Extracting spatial correlation features between the structural deformation data of the offshore platform mutation event training set and the corresponding marine environment parameters through a preset spatiotemporal convolutional network;

[0019] Through long-short-term memory networks, the temporal evolution patterns in historical accident data are mined to generate dynamic risk prior knowledge;

[0020] The spatial correlation features and the dynamic risk prior knowledge are input into a pre-trained causal reasoning model to establish a multi-factor coupled Bayesian causal chain, and output a risk prediction result with confidence assessment.

[0021] In one embodiment, the step of triggering a graded emergency response based on the accident type prediction result includes:

[0022] When public network communication is detected to be interrupted, a hybrid transmission link of Beidou short messages and ad hoc network communication is activated. A multi-objective optimization function is constructed based on real-time channel quality to dynamically allocate the short message content compression rate and the number of network hops.

[0023] The encryption strategy is dynamically matched according to the risk level. Low-level risk instructions are transmitted through encrypted channels, while high-level risk instructions are transmitted through a self-organizing network dynamic key distribution mechanism.

[0024] In one embodiment, the step of executing the corresponding emergency control method includes:

[0025] When the risk of oil film spreading is identified, the preset Beidou positioning terminal and the preset marine environment sensor are activated to generate a rescue coordinate set containing the oil film spreading vector prediction;

[0026] Through the preset multi-agent path search algorithm, the optimal evacuation path that avoids the dynamic risk area is constructed, and the rescue coordinate set and the optimal evacuation path are sent to the preset safety management device via Beidou short message;

[0027] Based on the offshore platform's attitude adjustment requirements, the pressure compensation amount of the offshore platform's hydraulic legs is calculated in real time, and the platform's structural stability threshold is maintained through a closed-loop control algorithm.

[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes an emergency control device for an offshore platform of a BeiDou satellite system, the emergency control device for an offshore platform of a BeiDou satellite system comprising:

[0029] The acquisition module is used to obtain Beidou satellite timing signals and real-time meteorological data, and simultaneously collect the structural deformation parameters of the offshore platform, the dynamic parameters of the marine environment, and the personnel positioning information to construct multi-dimensional data of the offshore platform;

[0030] A prediction module is used to integrate and analyze the multi-dimensional data of the offshore platform, extract spatiotemporal correlation features and construct a multi-factor causal chain through a pre-trained dynamic risk prediction model, and determine the platform risk level and accident type prediction results;

[0031] The response module is used to trigger a graded emergency response based on the accident type prediction result, transmit the corresponding early warning instruction to the preset terminal through Beidou short message encryption, and execute the corresponding emergency control method.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes an emergency control device for an offshore platform of a Beidou satellite system, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the emergency control method for an offshore platform based on the Beidou satellite system as described above.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the offshore platform emergency control method based on the Beidou satellite system as described above are implemented.

[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the offshore platform emergency control method based on the Beidou satellite system as described above.

[0035] One or more technical solutions proposed in this application have at least the following technical effects:

[0036] Compared with the related art, which usually can only carry out emergency control after the problem occurs in an emergency, and has serious lag, the present application obtains Beidou satellite timing signals and real-time meteorological data, and synchronously collects the structural deformation parameters, marine environment dynamic parameters and personnel positioning information of the offshore platform to construct multi-dimensional data of the offshore platform; integrates and analyzes the multi-dimensional data of the offshore platform, extracts spatiotemporal correlation features through a pre-trained dynamic risk prediction model and constructs a multi-factor causal chain to determine the platform risk level and accident type prediction results; triggers a graded emergency response based on the accident type prediction results, transmits the corresponding early warning instructions to the preset terminal through Beidou short message encryption, and executes the corresponding emergency control method. It can be understood that the present application constructs multi-dimensional data synchronized in time and space through the Beidou satellite system, integrates and analyzes the multi-dimensional data for dynamic risk prediction and realizes a timely emergency response mechanism in the early stage of the accident development, which can respond to offshore platform emergencies quickly and accurately, ensure the safety of the offshore platform and personnel, and thus enable the offshore platform to carry out timely and effective emergency control in an emergency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0039] Figure 1 A flowchart of the first embodiment of the method for emergency control of an offshore platform based on the BeiDou satellite system is provided in this application;

[0040] Figure 2 A flowchart illustrating a second embodiment of the method for emergency control of an offshore platform based on the BeiDou satellite system is provided in this application;

[0041] Figure 3 A schematic diagram of a simplified flow chart of an emergency control method for an offshore platform based on the BeiDou satellite system provided in Example 2 of the present application;

[0042] Figure 4 This is a schematic diagram of the module structure of the offshore platform emergency control device of the Beidou satellite system according to an embodiment of the present application;

[0043] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the emergency control method of the offshore platform based on the Beidou satellite system in the embodiment of the present application.

[0044] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0046] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0047] The main solutions of the embodiments of this application are:

[0048] Obtain Beidou satellite timing signals and real-time meteorological data, and simultaneously collect structural deformation parameters of offshore platforms, dynamic parameters of the marine environment, and personnel positioning information to construct multi-dimensional data of offshore platforms;

[0049] By integrating and analyzing the multi-dimensional data of the offshore platform, the pre-trained dynamic risk prediction model is used to extract spatiotemporal correlation features and construct a multi-factor causal chain to determine the platform risk level and accident type prediction results;

[0050] A graded emergency response is triggered based on the accident type prediction results, and the corresponding early warning instructions are transmitted to the preset terminal through Beidou short message encryption to execute the corresponding emergency control method.

[0051] In this embodiment, the present application takes the BeiDou satellite system's offshore platform emergency control device as the execution subject. For ease of description, it is specifically described below as "device".

[0052] Because existing technologies often fail to fully consider the spatiotemporal correlation and dynamic changes of multiple factors, they are unable to perform effective fusion analysis of multi-source heterogeneous data from offshore platforms. In related technologies, in emergency situations, emergency control can usually only be carried out after the problem occurs, which is subject to serious lags.

[0053] This application provides a solution that constructs multi-dimensional data synchronized in time and space through the Beidou satellite system, integrates and analyzes the multi-dimensional data to perform dynamic risk prediction and implement a timely emergency response mechanism in the early stages of accident development. It can respond to emergencies on offshore platforms quickly and accurately, ensure the safety of offshore platforms and personnel, and enable offshore platforms to carry out timely and effective emergency control in emergency situations.

[0054] Based on this, the embodiment of the present application provides an emergency control method for an offshore platform based on the BeiDou satellite system. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the emergency control method for an offshore platform based on the BeiDou satellite system of this application.

[0055] In this embodiment, the offshore platform emergency control method based on the BeiDou satellite system includes steps S10 to S30:

[0056] Step S10: Acquire Beidou satellite timing signals and real-time meteorological data, synchronously collect structural deformation parameters of the offshore platform, dynamic parameters of the marine environment, and personnel positioning information, and construct multi-dimensional data of the offshore platform;

[0057] It should be noted that Beidou satellite timing signals refer to the high-precision time synchronization signals provided by the Beidou Navigation Satellite System (BDS). The Beidou satellite system transmits time signals via satellites, providing a precise time reference for ground-based receiving equipment, typically with nanosecond accuracy. In this application, Beidou satellite timing signals are used to provide a unified time reference for multi-source data collection and processing on offshore platforms, ensuring the time synchronization and accuracy of the data, thereby supporting real-time monitoring and emergency control.

[0058] Real-time meteorological data refers to current meteorological information obtained through meteorological sensors or satellite meteorological services, including but not limited to wind speed, wind direction, air pressure, temperature, humidity, etc. In the offshore platform environment, real-time meteorological data is crucial for assessing environmental risks and formulating emergency response strategies. For example, when the wind speed exceeds a certain threshold, the level switching or autonomous shutdown logic of the emergency communication protocol is triggered to ensure the safety of the platform. Structural deformation parameters refer to physical quantities that reflect the shape changes of offshore platform structures under the influence of external environments (such as wind and waves, ocean currents, earthquakes, etc.). These parameters are usually collected through strain sensors, displacement sensors and other equipment installed on the platform, including but not limited to the platform's inclination angle, displacement, stress distribution, etc. In this application, structural deformation parameters are used to evaluate the structural safety and stability of the platform. They are an important part of multi-dimensional data and are used for risk prediction and emergency control.

[0059] Dynamic ocean environment parameters refer to physical quantities that describe real-time changes in the ocean environment, including wave height, current velocity, seawater temperature, and salinity. These parameters are collected by ocean environment sensors and can reflect the dynamic changes in the ocean environment surrounding the platform. In this application, dynamic ocean environment parameters are combined with platform structural deformation parameters to comprehensively assess the risk level of the platform's environment and provide data support for emergency response.

[0060] Personnel location information refers to the real-time location of personnel on offshore platforms, obtained through positioning technologies (such as Beidou positioning, GPS positioning, or indoor positioning systems). In emergency situations, personnel location information can be used to quickly determine personnel locations, guide evacuation or rescue operations, and ensure personnel safety. In this application, personnel location information is integrated and analyzed as part of multi-dimensional data to enable a comprehensive emergency response.

[0061] Multidimensional offshore platform data is a collection of data generated by integrating and synchronizing multiple data sources, including Beidou satellite timing signals, real-time meteorological data, structural deformation parameters, dynamic marine environmental parameters, and personnel location information. This data reflects the operating status and environmental information of offshore platforms from different perspectives. Through fusion analysis, dynamic prediction and assessment of platform risks can be achieved, providing comprehensive data support for emergency response.

[0062] For example, referring to Figure 2 Assume that an offshore oil platform is equipped with BeiDou satellite timing receivers, meteorological sensors, structural deformation sensors, marine environment sensors, and personnel positioning terminals during its daily operations. During a sudden severe typhoon, the platform's monitoring system operates according to the following steps:

[0063] Beidou satellite timing signals provide a precise time reference, ensuring the synchronization of all sensor data. Meteorological sensors detect in real time that wind speeds exceed a preset danger level, triggering the system to enter emergency mode. Structural deformation sensors detect that the platform's tilt angle has reached a preset warning threshold and is approaching a preset danger threshold. Marine environmental sensors detect that wave heights have exceeded a preset warning value and that currents are accelerating. Personnel positioning terminals track the location of all personnel on the platform in real time.

[0064] The above multi-dimensional data are synchronously combined and processed, and the spatiotemporal correlation characteristics of the data are analyzed through a pre-trained dynamic risk prediction model.

[0065] The model predicts that the platform has a high risk of structural damage, with a risk level of "high".

[0066] Based on the risk assessment results, a hierarchical emergency response mechanism is triggered. The Beidou short message communication link is activated, encrypting and transmitting warning information to the land-based control center. Simultaneously, the pre-set emergency control strategy is automatically executed, shutting down critical equipment, activating emergency power supplies, and directing personnel to evacuate to a safe area.

[0067] It's understandable that through the real-time collection and integrated analysis of multi-dimensional data, the system can quickly identify risks and trigger emergency responses in extreme environments like severe typhoons, significantly shortening the time from risk discovery to emergency response execution and improving platform safety. Leveraging spatiotemporal correlation features and causal chain models, the system accurately assesses the platform's risk level, avoiding misjudgments caused by a single data source and improving the scientific nature and reliability of emergency decision-making. Using real-time personnel location information, the system can quickly determine personnel locations and guide evacuation, reducing the risk of casualties. Based on dynamic analysis of multi-dimensional data, the system can predict risks in advance and rationally dispatch emergency resources, such as rescue vessels and backup power supplies, improving resource utilization efficiency and reducing emergency response costs.

[0068] Step S20: fusion analysis of the multi-dimensional data of the offshore platform, extraction of spatiotemporal correlation features and construction of a multi-factor causal chain using a pre-trained dynamic risk prediction model, and determination of the platform risk level and accident type prediction results;

[0069] It should be noted that a dynamic risk prediction model is a model built based on machine learning or artificial intelligence algorithms, used to predict the risk level and accident type of offshore platforms in complex environments in real time. By learning the spatiotemporal correlation characteristics and causal relationships in historical data (such as historical accident records, meteorological data, and platform operation data), this model can dynamically assess the risk of the current platform status. Its core lies in its ability to adjust prediction results in real time based on changes in real-time data, thereby providing timely and accurate evidence for emergency response. In this application, the dynamic risk prediction model is one of the key technologies for achieving intelligent emergency control.

[0070] Spatiotemporal correlation features refer to the correlation of data across time and space. In the multidimensional data of offshore platforms, spatiotemporal correlation features may include the synchronized changes in platform structural deformation and meteorological conditions, as well as the spatial correlation between sensor data at different locations. Extracting these features can better understand the changing patterns of platform status, providing more accurate input for risk prediction. For example, an increase in wind speed may cause a change in the platform's tilt angle. This temporal and spatial correlation is crucial for accurately predicting platform risks.

[0071] A multi-factor causal chain refers to the construction of a causal network that reflects the operating laws of a complex system by analyzing the causal relationship between multiple factors. In this application, a multi-factor causal chain is used to describe the causal relationship between multiple source data such as the structural deformation of an offshore platform, changes in the marine environment, and personnel activities. By establishing a causal chain, we can more clearly understand the impact of different factors on platform risks, thereby providing a scientific basis for emergency decision-making. For example, when the wind speed increases and the platform's tilt angle increases, it may further cause equipment failure or personnel safety risks. This causal relationship can be modeled and analyzed through a multi-factor causal chain.

[0072] The platform risk level refers to the classification of the degree of danger currently faced by the offshore platform based on the output of the risk prediction model. The risk level is generally divided into three levels: low, medium, and high, and can be further subdivided according to specific needs. In this application, the determination of the risk level is based on the output of the dynamic risk prediction model, combined with preset thresholds or rules for classification. The classification of risk levels is crucial for triggering appropriate emergency response measures. For example, a high risk level may trigger measures such as emergency shutdown or personnel evacuation.

[0073] Accident type prediction results refer to the output of a dynamic risk prediction model that predicts the types of accidents that may occur on an offshore platform. Accident types may include structural damage, equipment failure, casualties, and environmental pollution. In this application, accident type prediction results are used to guide the selection of emergency response strategies. For example, if a high risk of structural damage is predicted, platform reinforcement or personnel evacuation measures may be initiated. If a high risk of equipment failure is predicted, equipment maintenance or the activation of backup equipment may be initiated in advance.

[0074] For example, suppose an offshore oil platform is caught in a sudden severe typhoon. The platform's monitoring system operates according to the following steps: It collects real-time data on wind speed, wave height, platform inclination angle, and oil pressure fluctuation rate. Simultaneously, the personnel positioning system indicates that some personnel on the platform are concentrated in the living area, while others are in the work area. This multi-dimensional data (including wind speed, wave height, platform inclination angle, and oil pressure fluctuation rate) is fed into a pre-trained dynamic risk prediction model.

[0075] By extracting spatiotemporal correlation features, the model discovered a clear, synchronized relationship between wind speed and platform tilt angle. Combined with the causal chain model derived from historical data, the model predicted a high risk of structural damage and personnel safety for the platform. The model assigned a "high" risk rating and predicted the following types of accidents: "structural damage risk" and "personnel evacuation risk." Based on the predicted risk level and accident type, a high-level emergency response mechanism was triggered. Key equipment on the platform, such as the oil pipeline solenoid valve, was automatically shut down, and the emergency power supply was activated to maintain power to critical sensors.

[0076] Warning information (such as "high-risk warning: structural damage risk, personnel evacuation risk") is sent to the land control center and the personnel positioning terminal on the platform through Beidou short messages to guide personnel to evacuate to a safe area.

[0077] It's understandable that by integrating and analyzing multi-dimensional data and extracting spatiotemporal correlation features, we can accurately assess the platform's risk level and accident type, avoiding misjudgments caused by a single data source and improving the scientific nature and reliability of emergency decision-making. Real-time output from a dynamic risk prediction model can quickly trigger appropriate emergency response measures at the earliest stages of a risk, significantly shortening response time and reducing the likelihood of accidents. Predicting evacuation risks and promptly guiding evacuation effectively safeguards the safety of platform personnel and reduces casualties from unexpected accidents. Preemptively shutting down critical equipment and activating emergency power effectively protects platform equipment and structures, minimizing equipment and structural damage caused by extreme conditions like strong typhoons and reducing economic losses. The BeiDou short message system provides timely and effective feedback of early warning information.

[0078] Step S30: triggering a graded emergency response based on the accident type prediction result, transmitting the corresponding early warning instruction to the preset terminal via Beidou short message encryption, and executing the corresponding emergency control method.

[0079] It should be noted that graded emergency response refers to the classification of emergency response measures into different levels based on the severity of the predicted results of the accident type, and the adoption of corresponding emergency strategies for different levels. This graded mechanism can reasonably allocate resources according to the severity of risks, ensuring a quick and effective response in emergency situations. In this application, the graded emergency response mechanism can dynamically adjust the intensity and scope of emergency measures based on the platform's risk level and accident type, thereby improving the flexibility and effectiveness of the emergency response. Beidou short message encrypted transmission refers to the use of the short message communication function of the Beidou satellite system, combined with encryption technology, to securely transmit early warning instructions to the preset terminal. Beidou short message communication is a two-way data transmission function based on the Beidou satellite system, which can realize information transmission in areas without public network coverage. Encrypted transmission ensures the security of information during transmission and prevents information from being tampered with or leaked. In this application, Beidou short message encrypted transmission is a key technology for achieving reliable communication between offshore platforms and land control centers or other terminals, and is particularly suitable for emergency communications in extreme environments. A preset terminal refers to a pre-set device or system for receiving early warning instructions. These terminals can be monitoring equipment in a land control center, emergency command terminals on offshore platforms, mobile terminals of rescue teams, etc. In this application, the preset terminal is used to receive early warning instructions transmitted by Beidou short messages, and execute corresponding emergency control methods according to the content of the instructions. The setting of the preset terminal ensures that emergency instructions can be conveyed to the relevant responsible parties quickly and accurately, thereby improving the efficiency of emergency response. Emergency control methods refer to specific measures taken according to the type of accident and risk level after the emergency response is triggered. These measures may include shutting down key equipment, starting backup systems, evacuating personnel, scheduling resources, etc. In this application, the emergency control method is a specific implementation step of hierarchical emergency response. Through preset logic and algorithms, the system can automatically execute corresponding control strategies according to the prediction results of different accident types, thereby realizing intelligent emergency management of offshore platforms.

[0080] For example, suppose an offshore oil platform is hit by a sudden severe typhoon. The platform's monitoring system operates according to the following steps:

[0081] A dynamic risk prediction model analyzes multi-dimensional data and predicts the platform faces "structural damage risk" and "personnel evacuation risk," assigning a high risk level. Based on these predictions, a high-level emergency response mechanism is triggered. Based on pre-set rules, the necessary emergency control measures are determined, including shutting down critical equipment, activating emergency power supplies, and evacuating personnel.

[0082] The warning instructions (such as "high-risk warning: structural damage risk, personnel evacuation risk, immediate implementation of shutdown and evacuation procedures") are transmitted via Beidou short message encryption to the land control center and preset terminals on the platform (such as emergency command terminals, personnel positioning terminals, etc.).

[0083] Upon receiving the warning, the emergency command terminal on the platform automatically closed the oil pipeline solenoid valve and activated the emergency power supply to maintain power to key sensors. Upon receiving the evacuation command, the personnel positioning terminal guided the platform's personnel to a safe area through voice prompts and navigation. Upon receiving the warning, the land-based control center immediately initiated emergency resource dispatch, dispatched a rescue vessel to the platform, and monitored the platform's emergency response process in real time.

[0084] It's understandable that the hierarchical emergency response mechanism enables rapid triggering of appropriate emergency measures based on the type of incident and risk level, significantly improving the speed and efficiency of emergency response. Beidou short message encryption technology ensures the reliable transmission of warning instructions in extreme environments, avoiding information transmission failures caused by public network outages or interference. Promptly guiding personnel evacuation effectively safeguards the lives of those on the platform and reduces casualties from sudden incidents. Preemptively shutting down critical equipment and activating emergency power effectively protects platform equipment and structures, minimizing equipment and structural damage caused by extreme conditions like strong typhoons and reducing economic losses. Transmitting warning instructions to a land-based control center enables remote monitoring and rapid dispatch of emergency resources, improving the overall coordination and scientific nature of the emergency response.

[0085] This embodiment provides an offshore platform emergency control method based on the Beidou satellite system. By constructing multi-dimensional data synchronized in time and space through the Beidou satellite system, dynamic risk prediction is performed by integrating and analyzing the multi-dimensional data, and a timely emergency response mechanism is implemented in the early stages of accident development. This method can respond quickly and accurately to emergencies on the offshore platform, ensuring the safety of the offshore platform and personnel, thereby enabling the offshore platform to perform timely and effective emergency control in emergency situations.

[0086] In a feasible embodiment, the step of extracting spatiotemporal correlation features and constructing a multi-factor causal chain through a pre-trained dynamic risk prediction model includes:

[0087] Obtain a preset historical accident database, platform finite element simulation data, and Beidou meteorological data. Use a transfer learning framework to spatially map the platform finite element simulation data with historical accident scenarios to construct a training set for offshore platform sudden event events.

[0088] Extracting the temporal features of the offshore platform sudden event training set through a neural network model, and establishing a corresponding causal chain model through a dynamic Bayesian network to perform risk prediction on the temporal features, thereby obtaining a risk prediction result;

[0089] If the risk prediction result does not reach the preset confidence level, the process returns to the step of extracting the temporal characteristics of the offshore platform mutation event training set through the neural network model until the risk prediction result reaches the confidence level, and a dynamic risk prediction model that meets the confidence level requirements is determined.

[0090] It should be noted that the pre-set historical accident database refers to a collection of collected and organized data on past accidents related to offshore platforms. This data typically includes information such as the type of accident, time of occurrence, location, environmental conditions, platform status, cause, and consequences. In this application, the historical accident database provides a real-world data foundation for the risk prediction model, used to train the model to identify accident characteristics and patterns, thereby improving the model's ability to identify potential risks. Its scope of protection includes all types of accident data related to offshore platforms, including but not limited to structural damage, equipment failure, casualties, and environmental disasters. Platform finite element simulation data refers to data obtained by simulating offshore platform structures using finite element analysis methods. This data reflects the platform's physical characteristics, such as stress distribution, deformation, and structural response, under different operating conditions (such as wind and waves, earthquakes, and extreme weather). In this application, finite element simulation data is used to supplement the data in the historical accident database. By simulating platform behavior under different scenarios, it provides more comprehensive characteristic information for the risk prediction model. Its scope of protection includes simulation results of the platform under various design and extreme operating conditions. The transfer learning framework is a machine learning technique used to transfer knowledge learned from one task (the source task) to another related task (the target task). In this application, the transfer learning framework is used to spatially map platform finite element simulation data with historical accident scenarios. This involves associating and matching features in the simulation data with features in historical accident scenarios, thereby constructing a training set of offshore platform sudden events that more closely resembles real-world scenarios. Its scope of protection encompasses various transfer learning algorithms and frameworks used to achieve feature mapping and fusion between different data sources. The offshore platform sudden event training set refers to a dataset constructed by integrating a historical accident database, finite element simulation data, and Beidou meteorological data for training risk prediction models. This dataset contains characteristics of sudden events on the platform under different environmental conditions, such as structural deformation, equipment failure, and changing meteorological conditions. Its scope of protection encompasses training sets constructed using various data fusion methods, as well as various feature data used to describe sudden events on the offshore platform. Time series features refer to the patterns and characteristics of data changes over time. In this application, time series features reflect the state changes of the offshore platform at different time points, such as the change in platform tilt angle, wind speed, and equipment parameters over time. By extracting time series features, the dynamic changes in platform status can be captured, providing an important basis for risk prediction. Its scope of protection can cover time series features extracted through various algorithms related to changes in offshore platform status. A dynamic Bayesian network is a graphical model used to model and infer causal relationships in time series data. In this application, a dynamic Bayesian network is used to establish a causal chain model in a training set of offshore platform mutation events. By analyzing time series features, the causal relationships between different factors are inferred and potential risks are predicted.The scope of protection may include various dynamic Bayesian network construction methods and inference algorithms for achieving dynamic prediction of offshore platform risks. Confidence refers to the degree of reliability of risk prediction results. In this application, confidence is used to measure the credibility of the output results of the risk prediction model. If the confidence of the prediction result does not reach the preset threshold, the model's prediction result is considered unreliable and requires retraining or optimization. The scope of protection may include various methods and indicators for evaluating the credibility of risk prediction results, as well as model optimization strategies based on confidence.

[0091] For example, suppose an offshore oil platform is hit by a sudden severe typhoon. The platform's monitoring system operates according to the following steps:

[0092] Accident data of offshore platforms in the past 10 years are obtained from the preset historical accident database, including structural damage and equipment failure during typhoons.

[0093] The simulation data of the platform under different wind speed and wave height conditions are obtained from the finite element simulation software, including the platform stress distribution, tilt angle change, etc.

[0094] Obtain real-time meteorological data during typhoons from Beidou meteorological data, including wind speed, wind direction, air pressure, etc.

[0095] A transfer learning framework is used to spatially map finite element simulation data with historical accident scenarios, match features in the simulation data with features in historical accident scenarios, and construct a training set of offshore platform mutation events.

[0096] The training set contains characteristic data such as the platform's structural deformation and equipment status changes under different wind speeds and wave heights.

[0097] A neural network model is used to extract time series features from the training set, such as the change of platform tilt angle over time, the dynamic relationship between wind speed and platform stress, etc.

[0098] A causal chain model is established through a dynamic Bayesian network to analyze the causal relationship between different features and predict the risk level of the platform under current typhoon conditions.

[0099] The initial risk prediction results showed a confidence level of 75%, which did not reach the preset confidence threshold (85%).

[0100] The system returns the neural network model, re-extracts the time series features, and optimizes the model parameters.

[0101] After multiple iterations of optimization, the confidence level of the final risk prediction results reached 88%, meeting the preset requirements, and determining a dynamic risk prediction model that met the confidence requirements.

[0102] The model predicts that the platform has "structural damage risk" and "personnel evacuation risk", and the risk level is "high".

[0103] Based on the prediction results, a high-level emergency response mechanism is triggered, and early warning instructions are transmitted to the land control center and the preset terminals on the platform through Beidou short message encryption, and corresponding emergency control methods are executed, such as shutting down key equipment, starting emergency power supply, and guiding personnel evacuation.

[0104] It is understandable that by integrating historical accident data, finite element simulation data, and real-time meteorological data, a comprehensive training set was constructed, and risk prediction was performed using neural networks and dynamic Bayesian networks, significantly improving the accuracy and reliability of risk prediction. Through confidence assessment and model iterative optimization mechanisms, model parameters can be automatically adjusted to ensure that the confidence level of risk prediction results meets preset requirements, thereby improving the adaptability and robustness of the model. Based on high-confidence risk prediction results, emergency responses can be triggered in the early stages of an accident, and measures can be taken in advance to reduce the possibility of accidents and losses. The causal chain model established through the dynamic Bayesian network can clearly demonstrate the causal relationship between different factors, provide a scientific basis for emergency decision-making, and improve the scientific nature and effectiveness of emergency response.

[0105] In a feasible embodiment, the steps of obtaining Beidou satellite timing signals and real-time meteorological data, synchronously collecting structural deformation parameters of the offshore platform, marine environment dynamic parameters, and personnel positioning information, and constructing multi-dimensional data of the offshore platform include:

[0106] Based on the BeiDou satellite timing signal, a cross-modal data synchronization channel is established to perform spatiotemporal alignment on the structural deformation data, the marine environment data, and the personnel positioning data, thereby eliminating the spatiotemporal misalignment of the multi-source data and obtaining real-time synchronized data;

[0107] A unified spatiotemporal data coding structure is constructed at the edge computing node, and the real-time synchronous data is dynamically labeled according to the spatiotemporal dimensions, physical quantity types, and data credibility, and combined into the multi-dimensional data of the offshore platform.

[0108] It should be noted that a cross-modal data synchronization channel refers to a communication and processing mechanism used to integrate data from different types of sensors or data sources (such as structural deformation sensors, marine environment sensors, and personnel positioning equipment) and ensure that this data is aligned on a time basis. In this application, the cross-modal data synchronization channel is based on Beidou satellite timing signals and uses precise time synchronization technology to eliminate time differences between different data sources, thereby achieving real-time synchronization of multi-source data. Its scope of protection can cover various data synchronization methods and systems based on Beidou timing, as well as technical solutions for achieving spatiotemporal alignment of data.

[0109] Spatiotemporal alignment refers to the unified processing of data from different sensors or data sources in both time and space, ensuring that the data has the same reference datum in both time and space. In this application, spatiotemporal alignment achieves temporal alignment through Beidou satellite timing signals, and spatial alignment through the use of geographic information systems (GIS) or other spatial positioning technologies. The scope of protection includes Beidou timing-based time alignment methods, spatial positioning technologies, and related data processing algorithms.

[0110] An edge computing node is a computing device or system deployed at the edge of a network, used to process and analyze locally generated data in real time, thereby reducing data transmission latency and improving system response speed. In this application, edge computing nodes are used to process multi-source data from offshore platforms, including structural deformation data, marine environmental data, and personnel location data. The scope of protection encompasses various edge computing devices deployed on offshore platforms, data processing algorithms, and network architecture related to edge computing.

[0111] A unified spatiotemporal data encoding structure is a data organization method used to uniformly encode and store multi-source data according to temporal and spatial dimensions. In this application, this encoding structure enables dynamic data classification and management by assigning temporal and spatial labels to each data point. Its scope of protection includes data encoding methods, data storage structures, and related data management technologies.

[0112] Dynamic labeling refers to the process of classifying and labeling data in real time based on attributes such as its spatiotemporal characteristics, physical quantity type, and data credibility. In this application, dynamic labeling is used to add descriptive tags to multi-dimensional data from offshore platforms to facilitate subsequent data analysis and processing. The scope of protection encompasses data-feature-based labeling algorithms, data classification methods, and related data processing processes.

[0113] Data credibility refers to the reliability and accuracy of data. In this application, data credibility is used to assess data quality so that appropriate weights can be assigned during multi-source data fusion. Data credibility can be measured based on factors such as the reliability of the data source, data integrity, and consistency. The scope of protection includes data credibility assessment methods, data quality control technologies, and related data verification mechanisms.

[0114] For example, assuming that an offshore oil platform is operating in a complex marine environment, the platform's monitoring system operates according to the following steps:

[0115] The platform is equipped with a variety of sensors, including structural deformation sensors (monitoring platform tilt angle and displacement), marine environment sensors (monitoring wind speed, wave height, and current velocity), and personnel positioning equipment (based on Beidou positioning). All sensors are synchronized using Beidou satellite timing signals to ensure consistent data collection time.

[0116] Through the cross-modal data synchronization channel, the collected structural deformation data, marine environment data and personnel positioning data are aligned in time and space to eliminate the time and space dislocation of multi-source data and obtain real-time synchronized data.

[0117] At the edge computing node, the system processes real-time synchronized data and builds a unified spatiotemporal data coding structure.

[0118] Each data point is assigned a time and space tag. The system dynamically tags the data based on its temporal and spatial characteristics, physical quantity type, and data credibility, and combines this data into multi-dimensional offshore platform data. This multi-dimensional data is transmitted to the central control system for real-time monitoring of platform status and environmental changes.

[0119] By integrating and analyzing these data, it was found that the tilt angle of the northeast corner of the platform gradually increased, and the wind speed and wave height also increased.

[0120] Combined with personnel positioning data, it is determined that there may be risks in the area, and an early warning signal is immediately issued to prompt personnel to evacuate the area and activate relevant equipment for reinforcement.

[0121] As can be understood, through cross-modal data synchronization channels and spatiotemporal benchmark alignment technology, the system can eliminate spatiotemporal misalignment of multi-source data, ensuring data integrity and consistency. This provides a reliable data foundation for subsequent data analysis and decision-making. By establishing a unified spatiotemporal data coding structure and dynamic tagging, the system can rapidly classify and manage massive amounts of multi-source data, improving data processing efficiency and response speed. Based on the fusion analysis of multi-dimensional data, the system can monitor platform status and environmental changes in real time, and promptly issue early warning signals, allowing preemptive measures to reduce the possibility of accidents. Through dynamic tagging and real-time data analysis, the system can quickly identify potential risk areas and promptly guide personnel evacuation to ensure their safety. Through data credibility assessment, the system can rationally allocate resources, prioritize high-credibility data, and improve the scientific nature and effectiveness of emergency response.

[0122] In a feasible embodiment, the steps of extracting the time series features of the offshore platform mutation event training set through a neural network model, and performing risk prediction on the time series features by establishing a corresponding causal chain model through a dynamic Bayesian network, and obtaining the risk prediction results include:

[0123] Extracting spatial correlation features between the structural deformation data of the offshore platform mutation event training set and the corresponding marine environment parameters through a preset spatiotemporal convolutional network;

[0124] Through long-short-term memory networks, the temporal evolution patterns in historical accident data are mined to generate dynamic risk prior knowledge;

[0125] The spatial correlation features and the dynamic risk prior knowledge are input into a pre-trained causal reasoning model to establish a multi-factor coupled Bayesian causal chain, and output a risk prediction result with confidence assessment.

[0126] It should be noted that a spatiotemporal convolutional network (STN) is a deep learning model that combines the spatial feature extraction capabilities of a convolutional neural network (CNN) with the processing capabilities of time series data. It can simultaneously process both the spatial and temporal dimensions of data, extracting spatiotemporal correlation features within the data. In this application, the STN is used to analyze the spatial correlation features between structural deformation data of offshore platforms and marine environmental parameters, such as the relationship between the platform's tilt angle and wind speed and wave height. The scope of protection encompasses STN-based feature extraction methods and their application in multi-source data fusion.

[0127] Long-Short-Term Memory (LSTM) networks are a special type of recurrent neural network (RNN) that effectively handles long-term dependencies in time series data. In this application, LSTM networks are used to mine temporal evolution patterns in historical accident data, such as how platform status changes over time and the dynamic process of accident occurrence. Using LSTM networks, the system can generate dynamic risk prior knowledge, providing a temporal dimension for risk prediction. The scope of protection encompasses methods for extracting temporal features based on LSTM networks and their application in risk prediction.

[0128] Dynamic risk prior knowledge refers to risk-related knowledge obtained through the analysis and mining of historical accident data. This knowledge reflects the evolution and characteristics of risk events over time. In this application, dynamic risk prior knowledge is generated by a long-short-term memory network and is used to describe the risk evolution patterns of offshore platforms under different historical scenarios. The scope of protection encompasses methods for generating dynamic risk prior knowledge based on historical data and its application in risk prediction.

[0129] A causal inference model is a model used to analyze and infer causal relationships in data. In this application, the causal inference model is used to establish a Bayesian causal chain involving multiple coupled factors. This model combines spatial correlation features with prior knowledge of dynamic risk, infers causal relationships between different factors, and outputs risk prediction results. The scope of protection encompasses model construction methods based on causal inference and their application in risk prediction.

[0130] A multi-factor coupled Bayesian causal chain refers to a chain of causal relationships between multiple factors established through a Bayesian network. In this application, the Bayesian causal chain is used to comprehensively consider the interactions between multiple factors, such as the structural deformation of an offshore platform, marine environmental parameters, and historical accident data, to more accurately predict the platform's risk level. The scope of protection encompasses methods for constructing multi-factor coupled causal chains based on Bayesian networks and their application in risk prediction.

[0131] Confidence assessment refers to the process of quantitatively evaluating the reliability of risk prediction results. In this application, confidence assessment is used to measure the credibility of risk prediction results and ensure their accuracy and reliability. The scope of protection may include confidence assessment techniques based on statistical analysis or machine learning methods and their application in risk prediction.

[0132] For example, suppose an offshore oil platform is in a severe typhoon event. The platform's monitoring system operates according to the following steps:

[0133] The platform's structural deformation data (such as tilt angle and displacement) and ocean environment parameters (such as wind speed and wave height) are extracted from the preset training set.

[0134] The data were analyzed using a spatiotemporal convolutional network to extract spatial correlation features between structural deformation and ocean environmental parameters. For example, a significant spatial correlation was found between the tilt angle of the northeast corner of the platform and wind speed.

[0135] Long-short-term memory networks are used to mine temporal evolution patterns in historical accident data. For example, an analysis of the changing patterns of platform tilt angles during typhoons over the past 10 years revealed that the tilt angle increases rapidly when wind speeds exceed 40 m / s.

[0136] Generate dynamic risk prior knowledge to describe the risk change pattern of the platform under different wind speed conditions.

[0137] The extracted spatial correlation features and dynamic risk prior knowledge are input into the pre-trained causal inference model.

[0138] The model uses a Bayesian causal chain coupled with multiple factors to comprehensively consider current structural deformation, marine environmental parameters, and historical accident patterns, output risk prediction results, and perform confidence assessments at the same time.

[0139] The risk prediction results show that there is a high risk of structural damage in the northeast corner of the platform, with a confidence level of 90%.

[0140] The emergency response mechanism is triggered based on high-confidence risk prediction results.

[0141] The early warning instructions were transmitted via encrypted Beidou short messages to the land control center and the preset terminals on the platform, prompting the shutdown of key equipment in the northeast corner, the initiation of emergency reinforcement measures, and the guidance of personnel to evacuate the area.

[0142] It is understandable that by extracting spatial correlation features through spatiotemporal convolutional networks and mining temporal patterns through long-short-term memory networks, the system can more comprehensively analyze the risk factors of offshore platforms and significantly improve the accuracy of risk prediction.

[0143] Based on a Bayesian causal chain coupled with multiple factors, the system clearly demonstrates the causal relationships between different factors, providing a scientific basis for emergency decision-making and avoiding misjudgments caused by single-factor analysis. Through confidence assessment, the system ensures the reliability of risk prediction results, avoids unnecessary emergency responses, and improves resource utilization efficiency. Based on high-confidence risk prediction results, the system can trigger emergency responses at an early stage of an accident, take preemptive measures, and reduce the likelihood of accidents and losses. By comprehensively analyzing multi-source data and historical patterns, the system can provide intelligent decision-making support for emergency response on offshore platforms, improving platform safety and operational efficiency.

[0144] In a feasible implementation, the step of triggering a graded emergency response according to the accident type prediction result includes:

[0145] When public network communication is detected to be interrupted, a hybrid transmission link of Beidou short messages and ad hoc network communication is activated. A multi-objective optimization function is constructed based on real-time channel quality to dynamically allocate the short message content compression rate and the number of network hops.

[0146] The encryption strategy is dynamically matched according to the risk level. Low-level risk instructions are transmitted through encrypted channels, while high-level risk instructions are transmitted through a self-organizing network dynamic key distribution mechanism.

[0147] It should be noted that a hybrid transmission link refers to a communication link built by combining multiple communication technologies or methods to achieve data transmission under different conditions. In this application, the hybrid transmission link consists of Beidou short message communication and ad hoc network communication, and is used to provide reliable emergency communication when public network communication is interrupted. Its scope of protection can cover the link design that combines Beidou short message communication and ad hoc network communication, as well as related communication protocols and switching mechanisms.

[0148] Real-time channel quality refers to the transmission performance indicators of a communication link at the current moment, including signal strength, bit error rate, bandwidth, and other indicators. In this application, real-time channel quality is used to assess the communication status of a hybrid transmission link to dynamically adjust communication parameters. Its scope of protection includes technologies and methods for measuring and assessing channel quality, as well as communication parameter adjustment strategies based on channel quality.

[0149] A multi-objective optimization function is a mathematical model used to simultaneously optimize multiple objectives. In this application, the multi-objective optimization function is used to dynamically allocate the compression ratio of short message content and the number of network hops in an ad hoc network to balance communication efficiency and reliability. The scope of protection may include methods for constructing the multi-objective optimization function and dynamic parameter allocation techniques based on the function.

[0150] The short message content compression ratio refers to the degree of data compression applied to Beidou short message content. In this application, by adjusting the compression ratio, more effective information can be transmitted within limited communication bandwidth while reducing transmission delay. The scope of protection may include data compression algorithms and their application in Beidou short message communications, as well as related dynamic compression ratio adjustment mechanisms.

[0151] Network hop count refers to the number of intermediate nodes required to transmit data from a source node to a destination node in an ad hoc network. In this application, dynamically adjusting network hop count can optimize communication paths, improving communication efficiency and reliability. This protection may include path planning methods in ad hoc network communications, as well as network hop count adjustment strategies based on real-time channel quality.

[0152] A dynamic key distribution mechanism refers to a technology that dynamically generates and distributes encryption keys during communications. In this application, this mechanism is used to encrypt the transmission of high-risk instructions, ensuring communication security. Its scope of protection may include methods for key generation, distribution, and management, as well as related cryptographic communication protocols.

[0153] For example, suppose an offshore oil platform experiences a severe typhoon and its public network communications are interrupted due to inclement weather. The platform's emergency communication system operates as follows:

[0154] Upon detecting a disruption in public network communications, the platform automatically activates a hybrid transmission link combining Beidou short message and ad hoc network communications. The platform's communication equipment switches to Beidou short message mode, while simultaneously activating ad hoc network communication nodes to establish an internal platform communication network.

[0155] The system monitors the channel quality of the hybrid transmission link in real time, including the Beidou short message bit error rate and the signal strength of the ad hoc network. Based on this real-time channel quality, the system constructs a multi-objective optimization function to dynamically adjust the compression ratio of the short message content and the number of network hops in the ad hoc network. For example, when the Beidou short message bit error rate is high, the system increases the short message compression ratio to reduce the amount of transmitted data. Simultaneously, it optimizes the path planning of the ad hoc network to reduce the number of network hops and improve communication efficiency.

[0156] The system dynamically adapts encryption strategies based on risk levels. Low-risk instructions (such as equipment status monitoring data) are transmitted over encrypted channels; high-risk instructions (such as emergency shutdown commands) are encrypted using a dynamic key distribution mechanism within an ad hoc network. For example, if the platform's tilt angle exceeds a safety threshold, the system generates a high-risk instruction and transmits it encrypted via the dynamic key distribution mechanism to the platform's emergency control terminal.

[0157] After decrypting and interpreting the command, the receiving terminal executes the corresponding emergency response measures, such as shutting down critical equipment, activating emergency power supplies, and directing personnel evacuation. Simultaneously, the system transmits emergency response status to the land-based control center via Beidou short messages, ensuring real-time remote monitoring.

[0158] As can be seen, by enabling a hybrid transmission link combining Beidou short messages and ad hoc network communications, the system maintains reliable communication capabilities even when the public network is interrupted, ensuring the timely transmission of emergency commands. A multi-objective optimization function based on real-time channel quality dynamically adjusts the compression ratio of short message content and the number of network hops in the ad hoc network, balancing communication efficiency and reliability and reducing transmission delays. Dynamically matching encryption strategies based on risk levels ensures efficient transmission of low-risk commands and secure transmission of high-risk commands, improving communication security and adaptability. By encrypting high-risk commands through a dynamic key distribution mechanism, the system can quickly and securely execute emergency response measures, reducing the likelihood of accidents and losses. Emergency response status is fed back to the land-based control center via Beidou short messages, enabling remote monitoring and coordinated command, improving the overall efficiency and scientific nature of the emergency response.

[0159] In a feasible implementation manner, the step of executing the corresponding emergency control method includes:

[0160] When the risk of oil film spreading is identified, the preset Beidou positioning terminal and the preset marine environment sensor are activated to generate a rescue coordinate set containing the oil film spreading vector prediction;

[0161] Through the preset multi-agent path search algorithm, the optimal evacuation path that avoids the dynamic risk area is constructed, and the rescue coordinate set and the optimal evacuation path are sent to the preset safety management device via Beidou short message;

[0162] Based on the offshore platform's attitude adjustment requirements, the pressure compensation amount of the offshore platform's hydraulic legs is calculated in real time, and the platform's structural stability threshold is maintained through a closed-loop control algorithm.

[0163] It should be noted that oil film spread vector prediction involves predicting the direction and speed of oil film spread in the marine environment through numerical simulation or data analysis. This technology combines marine environmental parameters (such as wind speed and current velocity) with the physical properties of the oil film to generate a dynamic model of oil film spread, which is used to determine the oil film's spread range and impact area in advance. Its scope of protection covers oil film spread prediction methods based on numerical simulation and their application in emergency response.

[0164] A rescue coordinate set is a data set containing the location information of rescue targets, typically generated by a Beidou positioning terminal. These coordinates are used to guide rescue teams to the accident site quickly, improving rescue efficiency. The scope of protection includes Beidou-based rescue coordinate generation methods and their application in emergency response.

[0165] A multi-agent path-finding algorithm is used to plan conflict-free paths for multiple agents (such as rescue robots or humans) in complex environments. By optimizing path planning, the algorithm ensures that the agents can reach their target locations efficiently and safely. The scope of protection encompasses machine learning-based multi-agent path-planning algorithms and their applications in dynamic and risky environments.

[0166] A closed-loop control algorithm is a feedback-based control method that monitors system status in real time and adjusts control parameters to maintain system stability and performance. In this application, the closed-loop control algorithm is used to calculate the pressure compensation for hydraulic outriggers in real time to maintain the stability of the platform structure. The scope of this application includes a PID-based pressure compensation method for hydraulic outriggers and its application in maintaining offshore platform stability.

[0167] Hydraulic outrigger pressure compensation refers to the pressure adjustment applied to the outriggers to maintain the stability of the offshore platform structure. Real-time calculation of this pressure compensation through a closed-loop control algorithm effectively addresses platform attitude changes and ensures platform stability in complex environments. This includes the calculation method for hydraulic outrigger pressure compensation and its application in offshore platform attitude adjustment.

[0168] Offshore platform attitude adjustment refers to the real-time adjustment of an offshore platform's tilt, roll, and pitch, using technical means (such as hydraulic outriggers and tank water injection) to maintain platform stability and safety. The scope of protection encompasses technical solutions for offshore platform attitude adjustment and their application in complex environments.

[0169] Pre-installed security management equipment refers to terminal equipment used to receive and process emergency information, typically deployed in land-based control centers or emergency command centers. The scope of protection may include the design of security management equipment and its application in emergency communications.

[0170] For example, suppose an offshore oil platform experiences a sudden oil spill. The platform's emergency response system operates according to the following steps:

[0171] After identifying the risk of oil film spread, the preset Beidou positioning terminal and marine environment sensor are immediately activated.

[0172] The Beidou positioning terminal monitors the location information of the oil film diffusion area in real time, and the marine environment sensor collects wind speed and wave height data.

[0173] Combined with the oil film diffusion vector prediction, a rescue coordinate set containing the rescue target location is generated.

[0174] Through preset multi-agent path search algorithms (such as machine learning-driven path planning algorithms), the system constructs the optimal evacuation path that avoids dynamic risk areas.

[0175] The rescue coordinate set and optimal evacuation path are sent to the preset security management device via Beidou short message.

[0176] After receiving the information, the safety management equipment directs the rescue team to the target location according to the planned route, while guiding the evacuation of platform personnel.

[0177] Based on the offshore platform's posture adjustment requirements, the hydraulic leg pressure compensation is calculated in real time. Through a closed-loop control algorithm, the hydraulic leg pressure is dynamically adjusted to maintain the stability of the platform structure.

[0178] It is understandable that through the Beidou positioning terminal and multi-agent path search algorithm, the system can quickly generate a rescue coordinate set and an optimal evacuation path, significantly improving rescue efficiency and the safety of personnel evacuation. The optimal evacuation path can avoid dynamic risk areas in real time, ensuring the safety of personnel and equipment in complex environments. By adjusting the pressure compensation amount of the hydraulic legs in real time through a closed-loop control algorithm, the system can effectively maintain the structural stability of the platform and reduce platform attitude imbalance caused by environmental changes. Utilizing Beidou short message communication, the system can achieve reliable information transmission in areas without public network coverage, ensuring the timeliness of emergency response. By combining rescue paths with platform stability maintenance, the system achieves efficient coordination of emergency response and improves the emergency handling capabilities of offshore platforms in sudden accidents.

[0179] For example, in order to help understand the implementation process of the Beidou satellite system-based offshore platform emergency control method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flowchart of an emergency control method for an offshore platform based on the BeiDou satellite system is provided. Specifically:

[0180] The sensor network on the platform collects structural deformation parameters (such as tilt angle and displacement), marine environment dynamic parameters (such as wind speed, wave height, and current speed), and personnel positioning information in real time.

[0181] Based on the Beidou satellite timing signal, the system aligns the time and space benchmarks of these data through a cross-modal data synchronization channel to eliminate the time and space misalignment of multi-source data.

[0182] At the edge computing node, the system builds a unified spatiotemporal data coding structure, dynamically labels the real-time synchronized data according to the spatiotemporal dimensions, physical quantity types, and data credibility, and combines them into multi-dimensional data of the offshore platform.

[0183] The system obtains a preset historical accident database, platform finite element simulation data and Beidou meteorological data, and spatially maps the finite element simulation data with historical accident scenarios through a transfer learning framework to construct a training set of offshore platform mutation events.

[0184] The spatial correlation characteristics between structural deformation data and marine environmental parameters are extracted using a spatiotemporal convolutional network, and the temporal evolution laws in historical accident data are mined through a long-short-term memory network to generate dynamic risk prior knowledge.

[0185] Spatial correlation features and dynamic risk prior knowledge are input into the pre-trained causal inference model to establish a multi-factor coupled Bayesian causal chain and output risk prediction results with confidence assessment.

[0186] If the risk prediction result does not meet the preset confidence level, the optimization model will be returned until the requirements are met.

[0187] When the risk of oil film spread is identified, the system activates the preset Beidou positioning terminal and marine environment sensor to generate a rescue coordinate set containing the oil film spread vector prediction.

[0188] Through the preset multi-agent path search algorithm, the system constructs the optimal evacuation path that avoids dynamic risk areas, and transmits the rescue coordinate set and the optimal evacuation path to the preset security management device through Beidou short message encryption.

[0189] When public network communication is interrupted, a hybrid transmission link of Beidou short messages and ad hoc network communication is enabled, and the short message content compression rate and networking network hop count are dynamically allocated based on real-time channel quality.

[0190] The encryption strategy is dynamically matched according to the risk level. Low-level risk instructions are transmitted using encrypted channels, and high-level risk instructions are transmitted using the self-organizing network dynamic key distribution mechanism.

[0191] Based on the offshore platform's attitude adjustment requirements, the system calculates the pressure compensation of the hydraulic legs in real time and maintains the platform's structural stability threshold through a closed-loop control algorithm.

[0192] The closed-loop control algorithm dynamically adjusts the pressure of the hydraulic legs based on real-time monitoring data to ensure the stability of the platform in complex environments.

[0193] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the offshore platform emergency control method based on the Beidou satellite system of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0194] This application also provides an emergency control device for an offshore platform of the Beidou satellite system. Please refer to Figure 4 The BeiDou satellite system's offshore platform emergency control device includes:

[0195] The acquisition module 10 is used to obtain Beidou satellite timing signals and real-time meteorological data, and simultaneously collect structural deformation parameters of the offshore platform, dynamic parameters of the marine environment, and personnel positioning information to construct multi-dimensional data of the offshore platform;

[0196] The prediction module 20 is used to integrate and analyze the multi-dimensional data of the offshore platform, extract spatiotemporal correlation features and construct a multi-factor causal chain through a pre-trained dynamic risk prediction model, and determine the platform risk level and accident type prediction results;

[0197] The response module 30 is used to trigger a graded emergency response according to the accident type prediction result, transmit the corresponding early warning instruction to the preset terminal through Beidou short message encryption, and execute the corresponding emergency control method.

[0198] And / or, the offshore platform emergency control device based on the BeiDou satellite system includes:

[0199] The first acquisition module is used to obtain a preset historical accident database, platform finite element simulation data, and Beidou meteorological data. Through the transfer learning framework, the platform finite element simulation data is spatially mapped with historical accident scenarios to construct a training set of offshore platform sudden event events.

[0200] The first prediction module is used to extract the time series features of the offshore platform mutation event training set through a neural network model, and to establish a corresponding causal chain model through a dynamic Bayesian network to perform risk prediction on the time series features to obtain a risk prediction result;

[0201] The first loop module is used to return to the step of extracting the time series characteristics of the offshore platform mutation event training set through the neural network model if the risk prediction result does not reach the preset confidence level, until the risk prediction result reaches the confidence level, and determine a dynamic risk prediction model that meets the confidence level requirements.

[0202] And / or, the acquisition module 10 includes:

[0203] A first establishing module is used to establish a cross-modal data synchronization channel based on the Beidou satellite timing signal, perform spatiotemporal benchmark alignment on the structural deformation data, the marine environment data, and the personnel positioning data, and obtain real-time synchronized data after eliminating spatiotemporal misalignment of multi-source data;

[0204] The first label module is used to construct a unified spatiotemporal data coding structure at the edge computing node, dynamically label the real-time synchronous data according to the spatiotemporal dimension, physical quantity type and data credibility, and combine them into the multi-dimensional data of the offshore platform.

[0205] And / or, the first prediction module includes:

[0206] A first extraction module is used to extract spatial correlation features between the structural deformation data of the offshore platform mutation event training set and the corresponding marine environment parameters through a preset spatiotemporal convolutional network;

[0207] The first generation module is used to mine the temporal evolution patterns in historical accident data through long-short-term memory networks to generate dynamic risk prior knowledge;

[0208] The first output module is used to input the spatial correlation features and the dynamic risk prior knowledge into a pre-trained causal reasoning model, establish a Bayesian causal chain with multi-factor coupling, and output risk prediction results with confidence assessment.

[0209] And / or, the response module 30 includes:

[0210] The first activation module is used to activate the hybrid transmission link of Beidou short message and ad hoc network communication when public network communication interruption is detected. It builds a multi-objective optimization function based on real-time channel quality and dynamically allocates the short message content compression rate and the number of network hops;

[0211] The first matching module is used to dynamically match encryption strategies according to risk levels, using encrypted channels to transmit low-level risk instructions and using a self-organizing network dynamic key distribution mechanism to transmit high-level risk instructions.

[0212] And / or, the response module 30 includes:

[0213] The first identification module is used to activate a preset Beidou positioning terminal and a preset marine environment sensor when an oil film spreading risk is identified, and generate a rescue coordinate set containing an oil film spreading vector prediction;

[0214] The first construction module is used to construct an optimal evacuation path that avoids the dynamic risk area through a preset multi-agent path search algorithm, and send the rescue coordinate set and the optimal evacuation path to a preset safety management device through a Beidou short message;

[0215] The first calculation module is used to calculate the pressure compensation amount of the hydraulic legs of the offshore platform in real time based on the offshore platform posture adjustment requirements, and maintain the platform structure stability threshold through a closed-loop control algorithm.

[0216] The BeiDou satellite system's offshore platform emergency control device provided in this application adopts the BeiDou satellite system-based offshore platform emergency control method in the above-mentioned embodiment, which can solve the technical problem of lag in emergency control of offshore platforms in emergency situations. Compared with the prior art, the beneficial effects of the BeiDou satellite system's offshore platform emergency control device provided in this application are the same as the beneficial effects of the BeiDou satellite system-based offshore platform emergency control method provided in the above-mentioned embodiment, and the other technical features of the BeiDou satellite system's offshore platform emergency control device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0217] The present application provides an emergency control device for an offshore platform of a Beidou satellite system. The emergency control device for an offshore platform of a Beidou satellite system includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the emergency control method for an offshore platform based on the Beidou satellite system in the first embodiment above.

[0218] Reference below Figure 5 , which shows a schematic structural diagram of an offshore platform emergency control device for the BeiDou satellite system suitable for implementing an embodiment of the present application. The offshore platform emergency control device for the BeiDou satellite system in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, tablet computers, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The shown offshore platform emergency control device of the BeiDou satellite system is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

[0219] like Figure 5As shown, the BeiDou satellite system's offshore platform emergency control equipment may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the BeiDou satellite system's offshore platform emergency control equipment. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the Beidou satellite system's offshore platform emergency control equipment to communicate wirelessly or wired with other devices to exchange data. While the figure shows the Beidou satellite system's offshore platform emergency control equipment with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0220] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0221] The BeiDou satellite system's offshore platform emergency control device provided in this application adopts the BeiDou satellite system-based offshore platform emergency control method in the above-mentioned embodiment, which can solve the technical problem of lag in emergency control of offshore platforms in emergency situations. Compared with the prior art, the beneficial effects of the BeiDou satellite system's offshore platform emergency control device provided in this application are the same as the beneficial effects of the BeiDou satellite system-based offshore platform emergency control method provided in the above-mentioned embodiment, and the other technical features of the BeiDou satellite system's offshore platform emergency control device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0222] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0223] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0224] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the Beidou satellite system-based offshore platform emergency control method in the above-mentioned embodiment.

[0225] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0226] The above-mentioned computer-readable storage medium may be included in the Beidou satellite system's offshore platform emergency control device; or it may exist independently without being assembled into the Beidou satellite system's offshore platform emergency control device.

[0227] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the Beidou satellite system's offshore platform emergency control equipment, the Beidou satellite system's offshore platform emergency control equipment enables the following: to obtain Beidou satellite timing signals and real-time meteorological data, and simultaneously collect the offshore platform's structural deformation parameters, marine environment dynamic parameters and personnel positioning information to construct offshore platform multi-dimensional data; to integrate and analyze the offshore platform's multi-dimensional data, extract spatiotemporal correlation features through a pre-trained dynamic risk prediction model and construct a multi-factor causal chain to determine the platform risk level and accident type prediction results; to trigger a graded emergency response based on the accident type prediction results, and to encrypt and transmit the corresponding early warning instructions to the preset terminal through Beidou short messages to execute the corresponding emergency control method.

[0228] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0229] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0230] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0231] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the BeiDou satellite system-based offshore platform emergency control method. This computer-readable storage medium can address the technical issue of delayed emergency control of offshore platforms in emergency situations. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the BeiDou satellite system-based offshore platform emergency control method provided in the aforementioned embodiments, and are not further elaborated here.

[0232] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned Beidou satellite system-based offshore platform emergency control method.

[0233] The computer program product provided in this application can resolve the technical problem of delayed emergency control of offshore platforms in emergency situations. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the BeiDou satellite system-based offshore platform emergency control method provided in the above-mentioned embodiment, and are not further elaborated here.

[0234] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for emergency control of an offshore platform based on the BeiDou satellite system, characterized in that: The method comprises: Obtain Beidou satellite timing signals and real-time meteorological data, and simultaneously collect structural deformation parameters of offshore platforms, dynamic parameters of the marine environment, and personnel positioning information to construct multi-dimensional data of offshore platforms; Fusing and analyzing the multi-dimensional data of the offshore platform, and extracting spatial correlation features between the structural deformation data of the offshore platform mutation event training set and the corresponding marine environmental parameters through a preset spatiotemporal convolutional network; Through long-short-term memory networks, the temporal evolution patterns in historical accident data are mined to generate dynamic risk prior knowledge; Input the spatial correlation features and the dynamic risk prior knowledge into a pre-trained causal reasoning model, establish a multi-factor coupled Bayesian causal chain, and output a risk prediction result with confidence assessment; If the risk prediction result does not reach the preset confidence level, return to the step of extracting the temporal features of the offshore platform sudden change event training set through the neural network model until the risk prediction result reaches the confidence level, and determine a dynamic risk prediction model that meets the confidence level requirements; The pre-trained dynamic risk prediction model extracts spatiotemporal correlation features and constructs a multi-factor causal chain to determine the platform risk level and accident type prediction results. The multi-factor causal chain is the causal relationship between different influencing factors in the multi-dimensional data and the various expected platform accident types. A graded emergency response is triggered based on the accident type prediction results, and the corresponding early warning instructions are transmitted to the preset terminal through Beidou short message encryption to execute the corresponding emergency control method.

2. The method according to claim 1, wherein The step of extracting spatiotemporal correlation features and constructing a multi-factor causal chain through a pre-trained dynamic risk prediction model includes: Obtain a preset historical accident database, platform finite element simulation data, and Beidou meteorological data. Use a transfer learning framework to spatially map the platform finite element simulation data with historical accident scenarios to construct a training set for offshore platform sudden event events. The platform finite element simulation data is the simulation results of the offshore platform structure under various design and extreme working conditions. The time series features of the offshore platform mutation event training set are extracted through a neural network model, and a corresponding causal chain model is established through a dynamic Bayesian network to perform risk prediction on the time series features to obtain a risk prediction result.

3. The method according to claim 1, wherein The steps of obtaining Beidou satellite timing signals and real-time meteorological data, synchronously collecting structural deformation parameters of the offshore platform, dynamic parameters of the marine environment, and personnel positioning information, and constructing multi-dimensional data of the offshore platform include: Based on the BeiDou satellite timing signal, a cross-modal data synchronization channel is established to perform spatiotemporal alignment on the structural deformation parameters, the marine environment dynamic parameters, and the personnel positioning information, thereby eliminating the spatiotemporal misalignment of multi-source data and obtaining real-time synchronized data; A unified spatiotemporal data coding structure is constructed at the edge computing node, and the real-time synchronous data is dynamically labeled according to the spatiotemporal dimensions, physical quantity types, and data credibility, and combined into the multi-dimensional data of the offshore platform.

4. The method according to claim 1, wherein The step of triggering a graded emergency response according to the accident type prediction result includes: When public network communication is detected to be interrupted, a hybrid transmission link of Beidou short messages and ad hoc network communication is activated. A multi-objective optimization function is constructed based on real-time channel quality to dynamically allocate the short message content compression rate and the number of network hops. The encryption strategy is dynamically matched according to the risk level. Low-level risk instructions are transmitted through encrypted channels, while high-level risk instructions are transmitted through a self-organizing network dynamic key distribution mechanism.

5. The method according to claim 1, wherein The steps of executing the corresponding emergency control method include: When the risk of oil film spreading is identified, the preset Beidou positioning terminal and the preset marine environment sensor are activated to generate a rescue coordinate set containing the oil film spreading vector prediction; Through the preset multi-agent path search algorithm, the optimal evacuation path that avoids the dynamic risk area is constructed, and the rescue coordinate set and the optimal evacuation path are sent to the preset safety management device via Beidou short message; Based on the offshore platform's attitude adjustment requirements, the pressure compensation amount of the offshore platform's hydraulic legs is calculated in real time, and the platform's structural stability threshold is maintained through a closed-loop control algorithm.

6. An offshore platform emergency control device based on the BeiDou satellite system, characterized in that: The device comprises: The acquisition module is used to obtain Beidou satellite timing signals and real-time meteorological data, and simultaneously collect the structural deformation parameters of the offshore platform, the dynamic parameters of the marine environment, and the personnel positioning information to construct multi-dimensional data of the offshore platform; A prediction module is used to integrate and analyze the multi-dimensional data of the offshore platform and extract the spatial correlation characteristics between the structural deformation data of the offshore platform mutation event training set and the corresponding marine environmental parameters through a preset spatiotemporal convolutional network; Through long-short-term memory networks, the temporal evolution patterns in historical accident data are mined to generate dynamic risk prior knowledge; Input the spatial correlation features and the dynamic risk prior knowledge into a pre-trained causal reasoning model, establish a multi-factor coupled Bayesian causal chain, and output a risk prediction result with confidence assessment; If the risk prediction result does not reach the preset confidence level, return to the step of extracting the temporal features of the offshore platform sudden change event training set through the neural network model until the risk prediction result reaches the confidence level, and determine a dynamic risk prediction model that meets the confidence level requirements; The pre-trained dynamic risk prediction model extracts spatiotemporal correlation features and constructs a multi-factor causal chain to determine the platform risk level and accident type prediction results. The multi-factor causal chain is the causal relationship between different influencing factors in the multi-dimensional data and the various expected platform accident types. The response module is used to trigger a graded emergency response based on the accident type prediction result, transmit the corresponding early warning instruction to the preset terminal through Beidou short message encryption, and execute the corresponding emergency control method.

7. An offshore platform emergency control device based on the BeiDou satellite system, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the BeiDou satellite system-based offshore platform emergency control method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the Beidou satellite system-based offshore platform emergency control method according to any one of claims 1 to 5 are implemented.

9. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the Beidou satellite system-based offshore platform emergency control method according to any one of claims 1 to 5 are implemented.

Images