Wellhead skid-mounted equipment control optimization method and system for offshore platform

Abstract

The invention relates to the technical field of equipment control, in particular to a wellhead skid-mounted equipment control optimization method and system for an offshore platform. The method comprises the following steps: acquiring sea area environment monitoring data and wellhead skid-mounted equipment state data; establishing a dynamic model based on sea conditions based on the sea area environment monitoring data, and importing the state data of the wellhead skid-mounted equipment into the dynamic model based on the sea conditions to carry out control linkage modeling so as to generate a self-adaptive control model; and confirming the equipment-sea wave jitter influence of the sea area environment monitoring data on the wellhead skid-mounted equipment state data, and designing an equipment control optimization algorithm based on the equipment-sea wave jitter influence. By introducing the adaptive control model, sea wave prediction, advanced response compensation and other technologies, the problems of neglect of sea wave jitter, response lag, insufficient data storage and visualization and the like in the control of the existing wellhead skid-mounted equipment are effectively solved, and the stability, real-time performance and intelligent level of the equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and particularly to a control optimization method and system for wellhead skid-mounted equipment used in an offshore platform. Background Art

[0002] Initially, the wellhead skid-mounted equipment on offshore platforms relied on traditional manual operations. Operators controlled and adjusted the wellhead through manual valves, hydraulic devices, and mechanical devices. However, with the increasingly complex operating environment of offshore platforms and the increasing requirements for safety, the traditional manual operation mode faces problems such as high work intensity, low efficiency, and high safety risks. After entering the 21st century, automated control technologies have gradually been applied to wellhead skid-mounted equipment, especially automated control systems based on PLC (Programmable Logic Controller) and DCS (Distributed Control System), which have significantly improved the response speed and operation accuracy of the equipment. In the environment of a Floating Production Storage and Offloading unit (FPSO), the control of wellhead skid-mounted equipment faces greater challenges. Due to its dynamic characteristics, the FPSO has continuous movements such as pitching, rolling, and heaving under the action of waves, wind loads, and ocean currents. This complex movement mode makes it difficult for the traditional control system of wellhead skid-mounted equipment to operate stably. Especially in severe sea conditions, the response lag of the equipment will lead to a reduction in production efficiency and even cause safety accidents. In addition, since the FPSO is usually deployed in deep or ultra-deep water areas, the wellhead skid-mounted equipment needs to highly cooperate with the subsea production tree and riser system to ensure the stable production and transportation of oil and gas. Therefore, how to optimize the control strategy of wellhead skid-mounted equipment on the FPSO platform and improve the adaptability of the system to wave disturbances has become an important direction for the current upgrade of automated control technologies. Summary of the Invention

[0003] Based on this, it is necessary to provide a control optimization method and system for wellhead skid-mounted equipment used in an offshore platform to solve at least one of the above technical problems.

[0004] To achieve the above object, a control optimization method for wellhead skid-mounted equipment used in an offshore platform, the method includes the following steps:

[0005] Step S1: Obtain sea area environment monitoring data and wellhead skid-mounted equipment status data; establish a sea condition-based dynamic model based on the sea area environment monitoring data, and import the wellhead skid-mounted equipment status data into the sea condition-based dynamic model for control linkage modeling to generate an adaptive control model;

[0006] Step S2: Confirm the equipment-wave jitter impact of the sea area environment monitoring data on the wellhead skid-mounted equipment status data, and design an equipment control optimization algorithm based on the equipment-wave jitter impact; import the equipment control optimization algorithm into the adaptive control model to perform equipment jitter compensation on the wellhead skid-mounted equipment to generate equipment jitter compensation data;

[0007] Step S3: Perform wave prediction on the sea area environmental monitoring data to generate wave prediction data; perform early response compensation on the equipment jitter compensation data according to the wave prediction data to generate equipment jitter compensation response data; import the equipment jitter compensation response data into the adaptive control model for equipment jitter control to generate equipment adaptive control data and equipment standby control data;

[0008] Step S4: Store the equipment adaptive control data and the equipment standby control data in the cloud and visualize them, so as to generate an equipment control storage report to perform the optimization operation of the wellhead skid-mounted equipment control.

[0009] By combining the sea area environmental data and the equipment status data, the present invention constructs a sea condition dynamic model and generates an adaptive control model, enabling the wellhead skid-mounted equipment to dynamically adjust the control strategy according to the real-time sea condition changes, improving the adaptability and stability of the equipment under different sea conditions, thereby optimizing the control effect and the equipment operation efficiency. Identify and compensate for the impact of wave jitter on the equipment, control the movement of the equipment through an optimized algorithm, reduce the instability of the equipment caused by waves, thereby reducing the equipment failure risk and improving the safety and reliability of the operation. Through wave prediction and early response compensation, the system can make adaptive adjustments before the wave changes, reduce the lag of the equipment control response, and improve the timeliness and accuracy of the operation, thereby ensuring that the equipment is always in the best operating state under changing sea conditions and improving the operation efficiency. Through cloud storage and real-time visualization technology, the operator can monitor the equipment status and control effect at any time, ensure data security and facilitate later analysis. In addition, the generated control storage report helps to improve the transparency and management efficiency of the operation, and is convenient for continuously optimizing the equipment control strategy and the operation process. Therefore, the present invention effectively solves the problems of ignoring wave jitter, response lag, insufficient data storage and visualization in the existing wellhead skid-mounted equipment control by introducing technologies such as an adaptive control model, wave prediction and early response compensation, and improves the stability, real-time performance and intelligent level of the equipment.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Use sensors to obtain sea area environmental monitoring data and wellhead skid-mounted equipment status data;

[0012] Step S12: Perform data preprocessing on the sea area environmental monitoring data to generate standard sea area environmental monitoring data, where the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization;

[0013] Step S13: Perform environmental change analysis on the standard sea area environmental monitoring data through an edge computing device to generate sea area environmental change data;

[0014] Step S14: Extract the wave height, period, direction, and frequency from the sea area environmental change data to establish a dynamic model based on sea conditions, and import the wellhead skid-mounted equipment status data into the dynamic model based on sea conditions for control linkage modeling to generate an adaptive control model.

[0015] Through data preprocessing (such as denoising, filling missing values, etc.), the present invention can effectively improve the data quality, reduce the deviation caused by environmental interference or sensor errors, and ensure that the monitoring data is more reliable. By using edge computing devices for real-time environmental change analysis, the response speed can be effectively improved, the timeliness of data processing and analysis can be ensured, and the impact caused by data delay can be reduced. Extracting key sea condition parameters such as wave height, period, direction, and frequency, and establishing a dynamic model, helps to accurately reflect the law of sea condition changes. Combining with the wellhead skid-mounted equipment status data, the equipment can be controlled more precisely, adapt to sea condition changes, and improve the safety and efficiency of equipment operation. Combining the sea area environmental changes and the wellhead skid-mounted equipment status data, the formed adaptive control model can dynamically adjust the control strategy, optimize the operation status of the wellhead equipment, improve the intelligence and automation level of the system, thereby reducing human intervention and improving the overall operation efficiency.

[0016] Preferably, importing the wellhead skid-mounted equipment status data into the dynamic model based on sea conditions for control linkage modeling includes:

[0017] Import the wellhead skid-mounted equipment status data into the dynamic model based on sea conditions to screen the status of affected equipment and obtain the status data of key components of the equipment;

[0018] Analyze the dynamic response characteristics of the equipment for the status data of key components of the equipment and the dynamic model based on sea conditions to generate the equipment sea condition response characteristic data;

[0019] Adjust the mobility of the model equipment for the dynamic model based on sea conditions according to the equipment sea condition response characteristic data to generate an adaptive control model.

[0020] By importing the status data of the wellhead skid-mounted equipment into the dynamic model based on sea conditions, the present invention can screen the status of each key component of the equipment. This process helps to clarify which equipment components are affected by sea condition changes, provides accurate data support for subsequent control optimization, avoids unnecessary operation adjustments, and improves operation efficiency. By analyzing the response characteristics of the status data of the key components of the equipment and the dynamic model, the dynamic performance of the equipment under different sea conditions can be deeply understood. This analysis can help identify the performance fluctuations, risk points, and potential failure modes of the equipment under specific sea conditions, and thus provide a decision-making basis for equipment maintenance and operation adjustment. Based on the sea condition response characteristic data of the equipment, the mobility of the dynamic model is adjusted to achieve the adaptive control of the model. This adjustment enables the system to dynamically optimize the operation status of the equipment according to the real-time sea conditions, so that the wellhead skid-mounted equipment can maintain the best working state and efficiency under changing sea conditions, thereby reducing the risk of equipment failure or improper operation.

[0021] Preferably, step S2 includes the following steps:

[0022] Step S21: Perform time series analysis of the equipment jitter of the wellhead skid-mounted equipment status data to generate equipment jitter time series data; extract the wave change trend from the standard sea area environmental monitoring data according to the equipment jitter time series data to obtain wave change trend data;

[0023] Step S22: Fit the directions of the equipment jitter time series data and the wave change trend data to generate equipment influence azimuth data; extract the maximum influence azimuth in the equipment influence azimuth data and label it as strong wave azimuth data, and label the remaining influence azimuths as weak wave azimuth data;

[0024] Step S23: Calculate the associated wave fluctuation amplitude of the strong wave azimuth data and the weak wave azimuth data to obtain the comprehensive wave fluctuation amplitude of the associated azimuth;

[0025] Step S24: Design an equipment control optimization algorithm based on the comprehensive wave fluctuation amplitude of the associated azimuth, and import it into the adaptive control model to perform equipment jitter compensation on the wellhead skid-mounted equipment to generate equipment jitter compensation data.

[0026] Through the timing analysis of the jitter of the wellhead skid-mounted equipment, the present invention can clarify the jitter characteristics of the equipment at different time periods, identify the critical moments and periodic fluctuations affected by the sea waves. According to these jitter timing data, the sea wave change trend data can be extracted to help the system capture the impact of the sea conditions on the equipment operation more accurately, especially the dynamic response under severe sea conditions. By fitting the direction of the equipment jitter timing data and the sea wave change trend data, the impact direction of the sea waves on the equipment can be clarified. By identifying the maximum sea wave direction (strong sea wave direction) affecting the equipment and other weaker impact directions (weak sea wave directions), it is possible to accurately judge which directions have the greatest impact on the equipment during the sea condition change, providing more accurate direction data for subsequent control optimization and improving the accuracy of equipment control. By calculating the sea wave fluctuation amplitude of the data in the strong sea wave direction and the weak sea wave direction, the comprehensive sea wave fluctuation data in different directions can be obtained to help further evaluate the impact degree of the sea conditions on different directions of the equipment. This process can not only provide quantitative data for the analysis of the equipment operation state, but also provide an important basis for optimizing the control strategy. The equipment control optimization algorithm designed based on the comprehensive sea wave fluctuation amplitude data can intelligently adjust the working state of the wellhead skid-mounted equipment to cope with the impact of the sea waves in different driving directions. In this case, the equipment can automatically adjust its working mode according to the intensity and direction of the sea waves to avoid excessive jitter and reduce the damage caused to the equipment by unstable fluctuations. At the same time, the jitter compensation can effectively improve the stability of the equipment and ensure the continuity and safety of the operation.

[0027] Preferably, step S23 includes the following steps:

[0028] Step S231: Evaluate the mutual information of the strong sea wave direction data and the weak sea wave direction data to generate a sea wave direction similarity measurement result;

[0029] Step S232: Calculate the fluctuation amplitudes of the strong sea wave direction data and the weak sea wave direction data respectively to obtain the strong sea wave fluctuation amplitude and the weak sea wave fluctuation amplitude;

[0030] Step S233: Use the sea wave direction similarity measurement result to perform amplitude fluctuation superposition calculation on the strong sea wave fluctuation amplitude and the weak sea wave fluctuation amplitude to obtain the comprehensive sea wave fluctuation amplitude of the associated direction, where the formula for the amplitude fluctuation superposition calculation is as follows:

[0031] A total =W strong ·(ρ strong,weak ·A strong )+W weak ·((1-ρ strong,weak )·A weak );

[0032] Where, A totalFor the comprehensive wave fluctuation amplitude of the associated azimuth, A strong For the wave fluctuation amplitude of strong waves, A weak For the wave fluctuation amplitude of weak waves, ρ strong,weak For the azimuth similarity measure between strong waves and weak waves, W strong For the wave fluctuation weight of strong waves, W weak For the wave fluctuation weight of weak waves.

[0033] The present invention can quantify the similarity between different wave azimuths by evaluating the mutual information of strong wave azimuth data and weak wave azimuth data. This evaluation can help judge the laws and connections of wave changes in different azimuths, providing scientific support for subsequent wave amplitude calculations. Through this evaluation, the system can identify the commonalities and differences of waves in different azimuths, providing a strong basis for optimizing control strategies. By calculating the wave fluctuation amplitudes of strong waves and weak waves respectively, the wave fluctuation intensity under different wave conditions can be accurately evaluated. The wave amplitude is a key factor affecting the equipment under sea condition changes. Through the calculation of the wave amplitude, quantitative reference data can be provided for the control optimization of the equipment, helping the equipment to intelligently respond to different sea conditions. Using the result of the wave azimuth similarity measure to superimpose and calculate the wave fluctuation amplitudes of strong waves and weak waves can comprehensively consider the influences of both in different directions, generating the comprehensive wave fluctuation amplitude of the associated azimuth. This calculation not only accurately reflects the comprehensive influence of wave amplitudes in each direction, but also can adjust the superimposition weight according to the similarity of wave azimuths, making the final wave amplitude calculation more scientific and accurate. Through this method, the equipment can adapt to wave fluctuations of different intensities and azimuths, ensuring stable operation under unstable sea conditions. The generated comprehensive wave fluctuation amplitude data provides reliable data support for the equipment control optimization algorithm, enabling the control strategy to be flexibly adjusted under real-time sea condition changes. By adjusting the weight of wave amplitude superimposition, the control model can intelligently optimize the equipment jitter compensation strategy according to the actual wave conditions, improving the adaptability and stability of the equipment under harsh sea conditions.

[0034] Preferably, the equipment control optimization algorithm designed based on the comprehensive wave fluctuation amplitude of the associated azimuth includes:

[0035] Defining equipment control parameters based on the comprehensive wave fluctuation amplitude of the associated azimuth, where the equipment control parameters include the hydraulic pressure and movement speed of the wellhead skid-mounted equipment;

[0036] Constructing an adjustment formula according to the hydraulic pressure and movement speed of the wellhead skid-mounted equipment, where the hydraulic pressure adjustment formula is as follows:

[0037] P new = P base ×(1 + k pressure ·A total ;

[0038] Among them, P new is the adjusted hydraulic pressure, P base is the basic hydraulic pressure, k pressure A is the adjustment coefficient of hydraulic pressure. total is the comprehensive wave amplitude;

[0039] The motion speed adjustment formula is as follows:

[0040] V new =V base ×(1+V speed ·A total );

[0041] Among them, V new is the adjusted hydraulic pressure, V base is the basic hydraulic pressure, k speed is the adjustment coefficient of the movement speed, A total is the comprehensive wave amplitude;

[0042] PID control is used to adaptively adjust the hydraulic pressure regulation formula and the motion speed regulation formula to generate an equipment control optimization algorithm.

[0043] The present invention ensures that the wellhead skid-mounted equipment can maintain sufficient power output under different sea conditions by adjusting the hydraulic pressure according to the wave fluctuation amplitude, while avoiding equipment damage caused by excessive pressure under strong wave conditions. The movement speed of the equipment is dynamically adjusted so that the equipment can flexibly adapt according to the wave intensity and direction, avoiding unnecessary jitter or accidents caused by too fast movement speed, and accelerating the operation under appropriate circumstances to improve efficiency. By introducing PID control (proportional-integral-differential control), the adjustment of hydraulic pressure and movement speed can be made smoother and more accurate. PID control can monitor the operating status of the equipment in real time, and dynamically adjust the control parameters according to the error, thereby reducing the problem of over-adjustment or lag, and ensuring that the equipment runs smoothly under fluctuating sea conditions. The adjustment algorithm based on the wave fluctuation amplitude can perceive and adapt to changes in sea conditions in real time, avoiding excessive fluctuations or response lags in the equipment under complex wave conditions. Adaptive adjustment of hydraulic pressure and movement speed helps to improve the operating stability of the equipment, enabling the equipment to maintain the best operating state in strongly fluctuating waves, and reducing the risk of equipment failure and damage. The adaptive characteristics of PID control ensure that the equipment can adjust quickly when the sea conditions change dramatically, avoid performance fluctuations caused by wave changes, and improve the equipment's adaptability in dynamic environments. By accurately adjusting the hydraulic pressure and movement speed, the equipment can increase the operating speed under suitable wave conditions and slow down the operation process under adverse conditions to ensure safe and efficient operation. For example, in strong waves, the equipment movement speed is reduced to reduce the equipment's workload; while in stable sea conditions, the operating speed is increased to improve operating efficiency.

[0044] Preferably, step S3 includes the following steps:

[0045] Step S31: Extract historical data from the standard sea area environmental monitoring data to obtain historical sea condition data; construct a wave prediction model based on the historical sea condition data, and use the wave prediction model to predict the waves of the standard sea area environmental monitoring data to generate wave prediction data;

[0046] Step S32: Perform equipment impact early warning on the equipment jitter compensation data according to the wave prediction data to generate equipment impact early warning data; adjust the compensation response of the equipment jitter compensation data through the equipment impact early warning data to generate equipment jitter compensation response data, where the compensation response adjustment includes compensation time adjustment and compensation coefficient adjustment;

[0047] Step S33: Import the equipment jitter compensation response data into the adaptive control model for equipment adaptive jitter control to generate equipment adaptive control data;

[0048] Step S34: Design redundant nodes for the wellhead skid-mounted equipment status data to obtain equipment redundant control nodes; perform equipment exception fault tolerance control on the wellhead skid-mounted equipment status data based on the equipment redundant control nodes to generate equipment standby control data.

[0049] The present invention provides the jitter compensation system of the equipment with the trend of future wave fluctuations through wave prediction data, helps the equipment to respond in advance, reduces the impact of sudden waves, and enhances the predictability of the equipment. Using the prediction data to accurately compensate the equipment for jitter, it can reduce the damage of the equipment caused by unstable sea conditions and improve the adaptability of the equipment in complex sea conditions. The equipment impact warning data can identify the wave conditions that will affect the equipment in advance, issue an alarm in advance, and remind the operator to be prepared, which can not only reduce equipment failures, but also reduce the operation stagnation time caused by sudden changes in sea conditions. By adjusting the compensation time and compensation coefficient, the compensation strength and timing can be accurately controlled, so that the equipment jitter control system can be adaptively adjusted under different sea conditions. The optimization of the compensation response improves the stability of the equipment and avoids unnecessary over-compensation or under-compensation. The equipment can intelligently adjust the working state according to different wave conditions to enhance the operational stability of the equipment under severe sea conditions. The adaptive adjustment of real-time feedback greatly improves the control accuracy. Adaptive jitter control not only reduces the risk of equipment damage, but also reduces the situation where the equipment is overloaded due to not adapting to wave changes, thereby extending the service life of the equipment. By introducing redundant control nodes, the equipment can continue to operate even if some systems fail, and the operation will not be interrupted due to single point failure. The redundant design improves the robustness and fault tolerance of the system, ensuring that the operation tasks can be completed under extreme conditions. The equipment abnormal fault-tolerant control can automatically identify the faulty node and switch to the backup control system in time to ensure the stable operation of the equipment and avoid the operation safety risks caused by equipment failure. The introduction of the fault-tolerant mechanism enhances the reliability of the operation process.

[0050] Preferably, performing equipment abnormality fault tolerance control on the wellhead skid-mounted equipment status data based on the equipment redundancy control node includes:

[0051] Extract the status data of the wellhead skid-mounted equipment to measure the equipment pressure, equipment flow and equipment temperature, and perform abnormal detection on the equipment pressure, equipment flow and equipment temperature based on the preset equipment status threshold. When no abnormality is detected, the equipment redundant control node is put into node hibernation;

[0052] When an abnormality is detected, the abnormal impact identification is performed on the wellhead skid-mounted equipment status data to generate equipment abnormal impact identification results, where the equipment abnormal impact identification results include core equipment abnormal impact identification results and edge equipment abnormal impact identification results, and the edge equipment abnormal impact identification results are excluded;

[0053] The device redundant control node is activated according to the abnormal impact identification result of the core device, and the abnormal impact identification result of the core device is controlled according to the activated device redundant control node to generate device backup control data, wherein the backup control formula is as follows:

[0054] C backup = (f redundant (D backup , C current ));

[0055] In the formula, C backup is spare control data, f redundant is a calculation function for generating control data of redundant nodes, D backup is the spare data of the redundant control node, and C current is the control data in the current device state.

[0056] Through real-time monitoring of key parameters such as device pressure, flow rate, and temperature, the present invention can promptly detect abnormal conditions of the device and dynamically monitor the device state. When no abnormality is detected, the system can reduce power consumption and resource consumption by putting the redundant control nodes into the sleep state, ensuring efficient operation of the system in the normal state. When the device is in the normal working state, the redundant control nodes are in the sleep state, effectively reducing energy consumption and the system burden. By real-time detecting various parameters of the device, it is ensured that the system can identify device abnormalities within the shortest time and respond quickly. Once an abnormal condition of the device is detected, the system conducts in-depth analysis of the device state data to identify the abnormal impacts, and identifies different abnormal impacts on the core device and the edge device. The abnormalities of the edge device are eliminated to ensure that only the key devices are processed. By hierarchically identifying the abnormalities of the core device and the edge device, it can be ensured that when a device fails, the problems of the key device are preferentially identified, avoiding unnecessary intervention. By eliminating the abnormal identification of the edge device, the system can avoid the ineffective activation of the redundant control nodes and save system resources. When an abnormality occurs in the core device, the redundant control nodes will be activated and provide spare control for the core device. Through the generation of control data of the redundant nodes and the application of the spare control strategy, it can be ensured that the device quickly switches to the spare control mode when a failure occurs, thereby avoiding downtime and device damage. Through the activation of the redundant control nodes, the system can quickly restore the normal operation of the device, reduce production interruptions caused by failures, and improve the reliability of the device. Through the implementation of the spare control, when a failure occurs in the core device, it can be ensured that the device continues to operate stably, reducing the impact of the failure on the overall production.

[0057] Preferably, step S4 includes the following steps:

[0058] Step S41: Package the device adaptive control data and the device spare control data to generate a device control log; upload the device control log to the cloud platform for data storage to generate a device control storage log;

[0059] Step S42: Visualize the data of the device control storage log to generate a device control storage report for performing the wellhead skid-mounted device control optimization operation.

[0060] In the present invention, the device adaptive control data and the standby control data are encapsulated to generate a device control log, ensuring a detailed record of each device adjustment, optimization, or fault handling process. This detailed recording method provides a comprehensive data tracking function. Each device control operation and event is recorded in the log, providing complete historical data for subsequent analysis, inspection, and auditing. The storage of the device control log provides data support for future faults or anomalies, facilitating tracing and finding the root cause of problems when they occur. The device control log is uploaded to the cloud platform for data storage to ensure that the data can be stored for a long time and accessed at any time. The storage capacity of the cloud platform can also efficiently manage a large amount of device control data and provide powerful data analysis and processing functions. Through cloud platform storage, the device control log can be stored for a long time, avoiding the space limitation and data loss risk of local storage. Through the cloud platform, relevant personnel can access and view the device control log at any time, facilitating remote monitoring, fault troubleshooting, and optimization adjustment. Visualizing the data of the device control storage log can present complex control data in the form of charts, dashboards, etc., greatly improving the readability and analysis efficiency of the data. Through the visual device control storage report, users can intuitively understand the operating status, historical adjustments, and optimization of the device, helping managers make decisions quickly.

[0061] In this specification, a wellhead skid-mounted device control optimization system for an offshore platform is provided for performing the wellhead skid-mounted device control optimization method for an offshore platform described above. The wellhead skid-mounted device control optimization system for an offshore platform includes:

[0062] A control model construction module, configured to obtain sea area environment monitoring data and wellhead skid-mounted device status data; establish a sea condition-based dynamic model based on the sea area environment monitoring data, and import the wellhead skid-mounted device status data into the sea condition-based dynamic model for control linkage modeling to generate an adaptive control model;

[0063] A jitter compensation module, configured to confirm the device-wave jitter influence of the sea area environment monitoring data on the wellhead skid-mounted device status data, and design a device control optimization algorithm based on the device-wave jitter influence; import the device control optimization algorithm into the adaptive control model to perform device jitter compensation on the wellhead skid-mounted device to generate device jitter compensation data;

[0064] A response compensation module is used to perform wave prediction on the sea area environmental monitoring data to generate wave prediction data; perform early response compensation on the equipment jitter compensation data according to the wave prediction data to generate equipment jitter compensation response data; import the equipment jitter compensation response data into an adaptive control model for equipment jitter control to generate equipment adaptive control data and equipment standby control data;

[0065] A control data storage module is used to store and visualize the equipment adaptive control data and equipment standby control data in the cloud, thereby generating an equipment control storage report to perform wellhead skid-mounted equipment control optimization operations.

[0066] The beneficial effects of the present invention are as follows: By obtaining the sea area environmental monitoring data and the wellhead skid-mounted equipment status data, establishing a dynamic model in combination with the sea conditions, and generating an adaptive control model, the equipment can dynamically adjust the control strategy according to the real-time sea condition changes, thereby optimizing the operation stability and adaptability of the equipment under different sea conditions, and improving the operation efficiency and long-term reliability of the equipment. By identifying the influence of the sea area environmental monitoring data on the wave jitter of the equipment state and designing an optimization algorithm for jitter compensation, this module can effectively reduce the negative impact of wave jitter on the equipment, improve the stability of the equipment during offshore operations, reduce the equipment failure rate, and ensure the operation safety. By performing early response compensation on the equipment jitter through wave prediction, optimizing the timeliness of the equipment control response, ensuring effective adjustment of the equipment before the sea condition changes, avoiding the risks brought by response lag, improving the real-time performance and accuracy of the operation, and at the same time ensuring that the equipment is always in the best control state. By storing and visualizing the equipment adaptive control data and standby control data in the cloud, this module realizes the centralized management and real-time monitoring of the equipment operation data, provides efficient data query and analysis functions, and helps decision-making support during the operation process. At the same time, the generated control storage report is convenient for later review, optimization, and continuous improvement of the equipment control strategy and operation process, increasing the transparency and optimization space of the operation. Therefore, the present invention effectively solves the problems of neglecting wave jitter, response lag, insufficient data storage and visualization in the existing wellhead skid-mounted equipment control by introducing technologies such as adaptive control models, wave prediction, and early response compensation, and improves the stability, real-time performance, and intelligent level of the equipment. Brief Description of the Drawings

[0067] Figure 1 It is a schematic diagram of the step flow of a control optimization method for wellhead skid-mounted equipment used on an offshore platform;

[0068] Figure 2 is Figure 1 a detailed implementation step flow diagram of step S2 in

[0069] Figure 3 is Figure 1Schematic diagram of the detailed implementation steps of step S3 in

[0070] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0071] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0072] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0073] It should be understood that although terms such as "first", "second", etc. may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0074] To achieve the above object, please refer to Figures 1 to 3 , a method for optimizing the control of a wellhead skid-mounted device for an offshore platform, the method comprising the following steps:

[0075] Step S1: Obtain sea area environment monitoring data and wellhead skid-mounted device status data; establish a sea condition-based dynamic model based on the sea area environment monitoring data, and import the wellhead skid-mounted device status data into the sea condition-based dynamic model for control linkage modeling to generate an adaptive control model;

[0076] Step S2: Confirm the equipment-wave jitter impact of the sea area environment monitoring data on the wellhead skid-mounted device status data, and design an equipment control optimization algorithm based on the equipment-wave jitter impact; import the equipment control optimization algorithm into the adaptive control model to perform equipment jitter compensation on the wellhead skid-mounted device to generate equipment jitter compensation data;

[0077] Step S3: Conduct wave prediction on the sea area environmental monitoring data to generate wave prediction data; perform early response compensation on the equipment jitter compensation data according to the wave prediction data to generate equipment jitter compensation response data; import the equipment jitter compensation response data into the adaptive control model for equipment jitter control to generate equipment adaptive control data and equipment standby control data;

[0078] Step S4: Store the equipment adaptive control data and the equipment standby control data in the cloud and visualize them, so as to generate an equipment control storage report to perform the optimization operation of the wellhead skid-mounted equipment control.

[0079] By combining the sea area environmental data with the equipment status data, the present invention constructs a sea condition dynamic model and generates an adaptive control model, enabling the wellhead skid-mounted equipment to dynamically adjust the control strategy according to the real-time sea condition changes, improving the adaptability and stability of the equipment under different sea conditions, thereby optimizing the control effect and the equipment operation efficiency. Identify and compensate for the impact of wave jitter on the equipment, control the movement of the equipment through an optimized algorithm, reduce the instability of the equipment caused by waves, thereby reducing the equipment failure risk and improving the safety and reliability of the operation. Through wave prediction and early response compensation, the system can make adaptive adjustments before the wave changes, reduce the lag of the equipment control response, and enhance the timeliness and accuracy of the operation, thereby ensuring that the equipment is always in the best operating state under changing sea conditions and improving the operation efficiency. Through cloud storage and real-time visualization technology, operators can monitor the equipment status and control effect at any time, ensure data security and facilitate later analysis. In addition, the generated control storage report helps to improve the transparency and management efficiency of the operation, facilitating the continuous optimization of the equipment control strategy and the operation process. Therefore, the present invention effectively solves the problems of neglecting wave jitter, response lag, insufficient data storage and visualization in the existing wellhead skid-mounted equipment control by introducing technologies such as adaptive control models, wave prediction and early response compensation, and improves the stability, real-time performance and intelligent level of the equipment.

[0080] In the embodiment of the present invention, refer to Figure 1 As shown, it is a schematic diagram of the step flow of a method for optimizing the control of a wellhead skid-mounted equipment for an offshore platform according to the present invention. In this example, the method for optimizing the control of a wellhead skid-mounted equipment for an offshore platform includes the following steps:

[0081] Step S1: Obtain the sea area environmental monitoring data and the wellhead skid-mounted equipment status data; establish a sea condition-based dynamic model based on the sea area environmental monitoring data, and import the wellhead skid-mounted equipment status data into the sea condition-based dynamic model for control linkage modeling to generate an adaptive control model;

[0082] In the embodiments of the present invention, environmental monitoring data is collected in the sea area by deploying marine environment sensors (such as wave sensors, wind speed sensors, temperature sensors, etc.). The sensors can transmit the data to the processing system in real time through wireless communication technologies (such as LoRa, 5G). According to the dynamic changes of the sea area environment, an appropriate data collection frequency (such as every minute, every hour, etc.) is selected to ensure that real-time data with sufficient accuracy is captured. The wellhead skid-mounted equipment is equipped with multiple sensors (such as pressure sensors, flow sensors, temperature sensors, vibration sensors, etc.) to collect the working state data of the equipment in real time. To ensure the synchronization of the sea area environmental monitoring data and the equipment state data, the data can be matched through timestamps, and a time synchronization protocol (such as NTP or IEEE 1588) is used to ensure that data from different sources is processed within the same time scale. Common wave dynamics models (such as linear wave theory or non-linear wave models) are used to describe the interaction between the sea conditions and the wellhead equipment. The core of the wave model is to establish an associated model between the wave characteristics (wave height, period, wave direction, etc.) of the sea area and the equipment control (hydraulic pressure, movement speed, etc.). For example, based on the linear theory model of waves, the propagation and influence of waves can be described by the following formula: A(t) = A0·cos(kx - ωt + φ); where A(t) is the wave height, A0 is the crest height, k is the wave number, ω is the angular frequency of the wave, φ is the initial phase, and x and t are the spatial position and time respectively. The sea area environmental data (such as wave height, wave period, etc.) is input into the wave model, and a mathematical model describing the dynamic changes of the sea conditions is established through numerical solution methods (such as the finite element method, the finite difference method, etc.). This model needs to be able to calculate and update the interaction response between the wave characteristics of the sea area and the wellhead equipment in real time. According to the historical sea condition data and the equipment operation conditions, the model parameters are optimized through machine learning algorithms (such as regression analysis, neural networks, etc.) to ensure the high accuracy and self-adaptability of the model in actual sea condition changes. Based on the sea condition model, the key state data of the wellhead skid-mounted equipment (such as hydraulic pressure, equipment movement speed, etc.) is mapped into the sea condition model. The purpose of this step is to establish an associated relationship between the influence of wave changes and the equipment state, so that the model can automatically adjust the control parameters of the equipment according to the sea condition changes. For example, when the wave height changes, the hydraulic pressure needs to be adjusted to keep the equipment working stably. At this time, based on the dynamic calculation results of the wave model, the equipment parameters can be adjusted through the following control formula: Padjusted = Pbase·(1 + kpressure·Awave); where Padjusted is the adjusted equipment hydraulic pressure, Pbase is the basic hydraulic pressure, kpressure is the adjustment coefficient, and Awave is the wave influence coefficient (calculated according to the wave height, period, etc. of the sea wave). Based on the dynamic model, control linkage rules are designed according to the changes in the equipment state data.For example, when the wave height exceeds the set threshold, increase the hydraulic pressure of the equipment, or slow down the movement speed of the equipment when the wave period increases. The control rules are implemented through algorithms such as fuzzy control systems, PID control, or adaptive control. An adaptive control strategy (such as model predictive control MPC or reinforcement learning, etc.) is adopted to dynamically adjust the control parameters of the wellhead skid-mounted equipment to cope with the changes in different sea conditions. In model predictive control, the sea condition model adjusts the equipment control strategy according to the predicted results of future sea waves. For example, at each time step, based on the current sea condition data, the system predicts the future sea conditions and optimizes the equipment control strategy. The adjustment of the control strategy takes into account the response time of the equipment and the predicted changes in sea waves. By combining the dynamic sea condition model with the wellhead equipment status data, an adaptive control algorithm is designed. Specific methods can use fuzzy control, PID control, or reinforcement learning, and these algorithms can dynamically adjust the control parameters according to the changes in the equipment status. According to the real-time sea condition data and equipment status feedback, the control model can adjust the control parameters in real time, such as hydraulic pressure, movement speed, etc., to ensure the stability and efficiency of the equipment under complex sea conditions. The output control model will include the adjustment parameters of the equipment (such as hydraulic pressure, speed, etc.), and these parameters will directly affect the working state of the wellhead skid-mounted equipment. Under complex sea condition changes, this model will dynamically adjust the operation strategy of the equipment according to the predetermined control rules to achieve optimal control.

[0083] Step S2: Confirm the equipment-wave jitter impact of the sea area environment monitoring data on the wellhead skid-mounted equipment status data, and design an equipment control optimization algorithm based on the equipment-wave jitter impact; import the equipment control optimization algorithm into the adaptive control model to perform equipment jitter compensation on the wellhead skid-mounted equipment, and generate equipment jitter compensation data;

[0084] In the embodiments of the present invention, time series data related to equipment jitter (such as vibration frequency, acceleration, position change, etc.) of the wellhead skid-mounted equipment is extracted from the state data of the equipment. These data can reflect the response of the equipment to the changes in sea waves. Based on the wave parameters (such as wave height, period, direction, etc.) in the sea area environmental monitoring data, time series analysis techniques (such as Fourier transform, time-frequency analysis) are used to quantify the influence of waves on the equipment jitter. The purpose of this process is to establish the correlation between equipment jitter and sea wave fluctuations. A dynamic system modeling method (such as linear or nonlinear models, Kalman filters, etc.) is used to construct an influence model of equipment-sea wave jitter. This model describes the relationship between the wave characteristics of sea waves and the jitter response of the wellhead skid-mounted equipment as a mathematical model. The model can consider the following factors: the forces generated by the wave characteristics of sea waves (wave height, period, direction, etc.) on the equipment structure, the structural characteristics of the equipment (such as stiffness, mass distribution, etc.), and the time delay of sea wave influence: Since there will be a certain time delay in the propagation of sea wave fluctuations, a time delay parameter needs to be added to the model. The relationship between equipment jitter and sea wave fluctuations is verified by regression analysis of historical data or machine learning models (such as support vector machines, decision trees, etc.), and the degree of influence is determined. By comparing the simulation of the dynamic response of the equipment with the actual data, the accuracy of the model is verified, and an equipment-sea wave jitter influence factor is generated, which represents the intensity of equipment jitter under different sea wave conditions. For example, under a certain wave period and wave height, the change in the jitter amplitude or acceleration of the equipment. Based on the equipment-sea wave jitter influence model, a hydraulic pressure regulation strategy is designed. When the equipment jitter amplitude exceeds a predetermined threshold, the pressure of the hydraulic system is adjusted to stabilize the equipment. According to the dynamic response of the equipment, the movement speed of the equipment is optimized to reduce the influence of sea waves on the equipment. Using the PID control (Proportional-Integral-Derivative control) algorithm, the hydraulic pressure and movement speed are adjusted based on the real-time feedback in the equipment-sea wave jitter influence model. PID control can effectively regulate the hydraulic pressure and the movement speed of the equipment to suppress equipment jitter and improve the response speed. In order to cope with the dynamic characteristics of sea wave changes, an adaptive control strategy can be combined to adjust the PID control parameters (such as proportional, integral, and derivative coefficients) in real time, so that the equipment can flexibly respond to the changes in different sea conditions. The real-time sea area environmental monitoring data (such as sea wave height, period, direction, etc.) and the wellhead skid-mounted equipment state data (such as hydraulic pressure, flow rate, temperature, vibration, etc.) are input into the adaptive control model. The adaptive control model continuously calculates the jitter response of the equipment and adjusts the control parameters of the equipment (such as hydraulic pressure and movement speed) according to the real-time sea wave prediction data. According to the output of the adaptive control model, the control strategy of the equipment is adjusted in real time to compensate for the equipment jitter caused by sea waves. For example, when the sea wave fluctuations cause excessive vibration of the equipment, the hydraulic system can increase the pressure to improve the stability of the equipment.Through the real-time feedback data of the device (such as vibration sensors and accelerometers), the system can adjust the control parameters again according to the actual response of the device to achieve continuous optimization. The results after each adjustment of device control (such as the adjusted hydraulic pressure, movement speed, etc.) will be recorded as device jitter compensation data, which can be used for subsequent analysis and optimization and also provide a reference for device maintenance and servicing.

[0085] Step S3: Conduct a sea wave prediction on the sea area environmental monitoring data to generate sea wave prediction data; perform an advance response compensation on the device jitter compensation data according to the sea wave prediction data to generate device jitter compensation response data; import the device jitter compensation response data into the adaptive control model for device jitter control to generate device adaptive control data and device standby control data;

[0086] In the embodiments of the present invention, wave data, including wave height, period, direction, etc., is collected from a marine environment monitoring system (such as wave buoys, meteorological satellites, ocean sensors, etc.). These data should undergo preprocessing steps, including data denoising, missing value filling, and standardization, to ensure data quality and consistency. A time series prediction algorithm (such as ARIMA model, long short-term memory (LSTM) network, support vector machine regression (SVR), etc.) is used to model historical wave data to generate a prediction model. The prediction model is trained using historical wave data, and the accuracy and stability of the model are verified through techniques such as cross-validation. The wave prediction model should be able to predict wave height, period, direction, etc. within a future period of time. The trained wave prediction model is used to predict the changes in waves in real-time or in a future time period, generating wave prediction data, which includes information such as wave height, period, direction, etc. within a future period of time, and will be used as the basis for subsequent control adjustments. According to the wave prediction data, the impact of future wave fluctuations on equipment jitter is identified in advance. For example, when it is predicted that the wave height will increase, the system needs to adjust control parameters such as the hydraulic pressure and movement speed of the equipment in advance. According to the wave prediction data (such as wave height and period changes) and the dynamic response model of the equipment, the compensation measures that the equipment should take are calculated. For example, if it is predicted that the future waves will increase, the hydraulic pressure and movement speed can be adjusted through a formula. According to the pre-calculated compensation amount, jitter compensation response data for the equipment is generated, that is, the adjusted equipment control parameters (hydraulic pressure, movement speed, temperature, etc.), and these response data are fed back to the adaptive control model for further processing. The real-time state of the equipment (such as the acceleration, vibration, temperature, etc. of the equipment) and the predicted wave data are input into the adaptive control model. The adaptive control model makes dynamic adjustments based on the real-time wave data, equipment state, and equipment jitter compensation response data to minimize equipment jitter and maintain the stability of the equipment. Advanced control methods such as PID control and fuzzy control are used to adjust parameters such as the hydraulic system and movement speed of the equipment to ensure that the equipment can maintain the best working state under different sea conditions. Through the adaptive control model, parameters such as the hydraulic pressure, movement speed, and temperature of the equipment are adjusted in real-time to generate adaptive control data for the equipment, which contains the equipment control parameters automatically adjusted according to the current sea conditions and equipment responses. According to the design of equipment redundant nodes, when a fault or unforeseen abnormality in the equipment control system is detected, the redundancy control nodes are used to ensure the safety of the equipment. The generation of standby control data includes activating standby nodes, adjusting redundant control parameters, etc., to ensure that the equipment can still operate stably in case of a fault. The generation of standby control data involves combining the standby control data calculated by the redundant nodes with the current equipment control state to obtain the standby control data.

[0087] Step S4: Store the device adaptive control data and device standby control data in the cloud and visualize them to generate a device control storage report for performing the wellhead skid-mounted device control optimization operation.

[0088] In the embodiment of the present invention, through the device data acquisition system, the real-time adaptive control data of the device (such as hydraulic pressure, movement speed, temperature, etc.) and the standby control data (such as redundant control data, standby hydraulic parameters, etc.) are transmitted to the cloud for storage in real time. Select a suitable cloud service platform (such as AWS, Azure, Google Cloud, etc.) for storage to ensure high reliability, low latency, elastic scalability, and data security of the data. Store the adaptive control data and standby control data in a structured data format (such as JSON, CSV, etc.) to ensure the accessibility and compatibility of the data. Design a multi-level data storage structure, such as a data lake to store raw data, a real-time database to store processed data, a historical database to store long-term data, etc. Through IoT devices (such as sensors, actuators, etc.) and edge computing nodes, the device status is collected in real time and uploaded to the cloud platform after encryption and compression. The cloud ensures the timeliness of the device status and control data through a real-time data synchronization mechanism, avoiding the impact of data latency on the control optimization operation. For historical control data, device status and other information, cold storage (such as Amazon S3, Azure Blob Storage) is used for low-cost long-term storage. Regular data backups are performed to ensure the integrity of the data in the cloud and prevent data loss due to system failures. Use commercial data visualization tools (such as Tableau, Power BI, Grafana, etc.) or develop a customized Web visualization platform to display the real-time control data of the device, sea condition changes, and adaptive control adjustments. Design an interactive visualization interface that allows operators to view the device status, control data, and sea condition warnings in real time in the form of dashboards, charts, curves, etc. The real-time fluctuations of parameters such as hydraulic pressure, movement speed, and temperature are displayed through dynamic charts, and outliers are marked in real time. The relationship between the predicted wave height, period, direction of the sea wave and the adaptive control data of the device is displayed to help engineers more intuitively evaluate the control effect of the device under different sea conditions. The standby control data is visually displayed, and when the system fails, the activation status of the redundant nodes and the execution situation of the standby control strategy are clearly displayed. According to the real-time data, an alarm is triggered through a set threshold, and when the device is abnormal, an alarm message is automatically pushed to notify the staff to intervene in time.

[0089] Preferably, step S1 includes the following steps:

[0090] Step S11: Use sensors to obtain sea area environmental monitoring data and wellhead skid-mounted device status data;

[0091] Step S12: Perform data preprocessing on the sea area environmental monitoring data to generate standard sea area environmental monitoring data, where the data preprocessing includes data cleaning, data denoising, missing value filling, and data standardization;

[0092] Step S13: Analyze the environmental changes of the standard sea area environmental monitoring data through the edge computing device to generate sea area environmental change data;

[0093] Step S14: Extract the wave height, period, direction, and frequency in the sea area environmental change data to establish a dynamic model based on the sea conditions, and import the wellhead skid-mounted equipment status data into the dynamic model based on the sea conditions for control linkage modeling to generate an adaptive control model.

[0094] In the embodiments of the present invention, by selecting a marine multi-parameter buoy sensor (such as SeaBird SBE 39), this sensor can provide accurate environmental data such as wave data, temperature, salinity, pressure, etc. The specific data collected includes the wave height, period, direction, and frequency of ocean waves. The measurement accuracy of the ocean wave height is ±0.05m, the sampling frequency is 10Hz, and LoRaWAN or NB-IoT communication protocols are used for data transmission to ensure real-time data transmission and power consumption savings. A vibration sensor (such as PCB 356A01) is used to monitor the working state of the device, in combination with a temperature sensor (such as Omega RTD probe) and an accelerometer (such as STMicroelectronics LSM6DSO). The accuracy of the vibration sensor is ±0.1mm / s, the accuracy of the temperature sensor is ±1°C, and the accuracy of the accelerometer is ±0.01g. Data is transmitted in real time through LoRa or 5G communication technology. The IQR method is used for outlier detection, invalid data with a wave height lower than 0 is removed, the quartiles (Q1, Q3) of the wave height data are calculated, and the outlier threshold is set to 1.5 times the IQR, and all wave data outside this range is removed. The Kalman filter is used to remove the noise of time series data, especially to remove the sensor noise in the wave data. In the Kalman filter, the noise matrix Q = 0.1 and the observation noise matrix R = 0.5. This setting can effectively filter the noise in the wave data and ensure the smoothness of the data. The linear interpolation method is used to fill in the missing values in the sea area environmental data. For the missing data segment, linear interpolation is performed using its previous and next values to ensure the coherence of the data time series. The window size for each interpolation process is 5 minutes to ensure time accuracy. Z-score normalization is performed on data such as wave height, period, direction, and frequency. NVIDIA Jetson Xavier NX is selected as the edge computing device, which has high-performance computing capabilities and can support deep learning frameworks such as TensorFlowLite and PyTorch. The learning framework has a built-in 4-core ARM Cortex-A57, 8GB LPDDR4x, supports accelerated computing, and the processing frequency is 1.4GHz, which is suitable for large-scale data analysis. LSTM (Long Short-Term Memory Network) is used for time series analysis to identify the changing trends of the sea area environment. The LSTM model is built using Keras, a 2-layer LSTM network structure is selected, with 50 neurons in each layer, and the Adam optimizer is used with a learning rate of 0.001 and a batch size of 32 for training. The model inputs the wave height, period, and frequency data of the past 10 minutes, and the model outputs the wave change trend within the next 30 minutes. The Boussinesq equation is used to establish a wave dynamics model to simulate the propagation and changes of waves under different sea conditions. According to the parameters such as wave height, period, and direction monitored in the sea area, the Boussinesq equation is used to predict the propagation behavior of waves in the water area.The calculation of the wave propagation speed, wave form, and frequency is carried out using a grid subdivision with a spacing of 1 m, and the update is performed every 5 minutes. The wellhead equipment is adjusted in real time through the MPC controller, and the control objective is set to reduce the load fluctuation of the equipment under different sea conditions to ensure the stable operation of the equipment. The prediction time window is set to 10 minutes, and each optimization cycle is 1 minute. The vibration frequency and load of the wellhead equipment are controlled within a safe range to ensure that the equipment does not malfunction during wave fluctuations. An adaptive control model is generated through the MPC algorithm, and the sea condition change data is linked with the wellhead equipment status data to achieve the dynamic adjustment of the equipment.

[0095] Preferably, importing the wellhead skid-mounted equipment status data into the sea condition-based dynamic model for control linkage modeling includes:

[0096] Importing the wellhead skid-mounted equipment status data into the sea condition-based dynamic model to screen the status of affected equipment to obtain the status data of key components of the equipment;

[0097] Analyzing the dynamic response characteristics of the equipment for the status data of key components of the equipment and the sea condition-based dynamic model to generate the sea condition response characteristic data of the equipment;

[0098] Adjusting the mobility of the model equipment for the sea condition-based dynamic model according to the sea condition response characteristic data of the equipment to generate an adaptive control model.

[0099] In the embodiments of the present invention, the status data of the wellhead skid-mounted equipment is collected in real time by using an edge computing device (such as NVIDIA Jetson Xavier NX), and special attention is paid to key parameters such as the vibration, load, temperature, and rotational speed of the equipment. The sensors include a vibration sensor (such as PCB Piezotronics), a temperature sensor (such as Omega RTD), and a tachometer (such as Honeywell rotary sensor). Through data fusion and feature selection techniques, the equipment components affected by sea condition changes are screened out. A feature fusion algorithm based on Kalman filtering is adopted, combined with the historical status data, environmental data, and sea condition changes of the equipment, to identify the components in the equipment that are greatly affected by sea conditions. The Kalman filter is used to filter and estimate the vibration data of each component of the equipment, and the equipment components that are greatly affected by wave changes are screened out from them. Using the Kalman filter, the state transition matrix is set to the identity matrix, the observation noise R is set to 0.2, and the process noise Q is set to 0.1 to improve the smoothness and prediction accuracy of the signal. The status data of the key components of the equipment after screening (such as the vibration, temperature, and load of the key components) is imported into the sea condition dynamic model for subsequent analysis. The autocorrelation function and cross-correlation function are used to analyze the relationships among the vibration, load, and sea condition fluctuations of the key components of the equipment. Through time-domain analysis, the immediate impact of sea conditions on the equipment response can be evaluated. The fast Fourier transform (FFT) is used to transform the equipment status data from the time domain to the frequency domain, analyze the response characteristics of the key components of the equipment at different frequencies, and find out the main vibration frequencies and response modes. The maximum amplitude, fluctuation period, peak-to-peak value, etc. of the equipment are calculated to evaluate the dynamic response of the equipment under different sea conditions. The main frequency, frequency peak, and bandwidth are extracted from the spectrum, and these features help to understand the main frequency response of the equipment under sea condition changes. The frequency-domain analysis uses FFT, the sampling frequency is 1 kHz, the data window size for each analysis is 5 seconds, and the analysis frequency range is 0 - 500 Hz. The load, rotational speed, and other parameters of the equipment operation are adjusted by the MPC algorithm so that the equipment can adapt to different sea condition changes, thereby reducing vibration and load fluctuations. According to the response characteristic data of the equipment, the safe state range of the equipment (such as vibration frequency, temperature range, etc.) is set. Minimize the vibration and load fluctuations of the equipment under sea condition changes to ensure the stable operation of the equipment. The control strategy is optimized by adjusting parameters such as the influence coefficient of wave height change on the equipment load and the influence of wave period on the equipment vibration frequency in the model. The dynamic optimization algorithm (such as QP (Quadratic Programming) algorithm) in MPC is used for optimization to calculate the optimal control strategy. The optimization time window is set to 10 minutes, and the optimization step size is 1 minute each time. According to the optimized control strategy, a new adaptive control model is generated to control the key parameters such as the load and vibration of the wellhead skid-mounted equipment under different sea conditions. The working state of the equipment is adjusted in real time to ensure that the equipment can adapt to different sea condition environments and optimize the operation efficiency and safety of the equipment through automatic adjustment.

[0100] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0101] Step S21: Conduct a time series analysis of the equipment jitter status data of the wellhead skid-mounted equipment to generate equipment jitter time series data; extract the sea wave change trend from the standard sea area environmental monitoring data based on the equipment jitter time series data to obtain sea wave change trend data;

[0102] Step S22: Fit the directions of the equipment jitter time series data and the sea wave change trend data to generate equipment influence azimuth data; extract the maximum influence azimuth from the equipment influence azimuth data and label it as strong sea wave azimuth data, and label the remaining influence azimuths as weak sea wave azimuth data;

[0103] Step S23: Calculate the comprehensive sea wave fluctuation amplitude of the associated azimuths for the strong sea wave azimuth data and the weak sea wave azimuth data to obtain the comprehensive sea wave fluctuation amplitude of the associated azimuths;

[0104] Step S24: Design an equipment control optimization algorithm based on the comprehensive sea wave fluctuation amplitude of the associated azimuths, and import it into the adaptive control model to perform equipment jitter compensation on the wellhead skid-mounted equipment to generate equipment jitter compensation data.

[0105] In the embodiments of the present invention, by using the Daubechies 4 wavelet basis, which has good smoothness and is suitable for analyzing equipment vibration data. The decomposition level is set to 5 layers to capture the detailed information of equipment jitter. The sampling rate of the equipment vibration data is set to 1 kHz to ensure the capture of high-frequency jitter characteristics. After processing the data using wavelet transform, time series characteristics such as the jitter amplitude and frequency of the equipment are extracted to generate equipment jitter time series data. The autoregressive integrated moving average (ARIMA) model is used to perform time series prediction on standard sea area environmental monitoring data (such as wave height, period, direction, etc.) to extract the changing trend of the waves. The model order is set to (p = 1, d = 1, q = 1), that is, one difference processing is performed, using an autoregressive term with one lag period and a moving average term with one lag period. The sampling frequency of the wave data is 30 minutes, which is sufficient to capture the changing trend of the waves on a relatively large time scale. The trend data extracted by the ARIMA model includes the increasing and decreasing trend of the waves, period changes, direction changes, etc. The least squares method is used to perform direction fitting on the equipment jitter time series data and the wave changing trend data to determine the relationship between the two. The direction fitting will be used to extract the influence direction of the waves on the equipment. The input variables for the fitting are the equipment jitter amplitude and the wave height, and the output variable is the equipment influence direction. By fitting the linear relationship between the equipment jitter and the wave changes using the least squares method, the equipment influence direction data is obtained. The clustering algorithm (such as the K-means algorithm) is used to analyze the obtained equipment influence direction data to mark the direction where the equipment is most strongly affected by the waves. The influence direction data is clustered into two groups, corresponding to the strong wave direction data and the weak wave direction data respectively. The center point of the clustering represents the intensity of the influence direction. The direction of the clustering center is the strong wave direction, and the others are the weak wave directions. The number of clusters K = 2, that is, it is clustered into two categories: the strong wave direction and the weak wave direction. The multi-scale wavelet analysis based on wavelet transform is used to calculate the wave fluctuation amplitudes in the strong wave direction and the weak wave direction. This method can more accurately capture the wave fluctuation characteristics in different directions. Applying the same wavelet transform method as in step S21, wavelet decomposition is performed on each direction data to extract the wave fluctuation amplitude. Five-layer wavelet decomposition is performed on each direction data to capture the details of the fluctuations. The fluctuation amplitudes of each direction are calculated and synthesized to obtain the comprehensive wave fluctuation amplitude of each direction. According to the wave fluctuation amplitudes in different directions, the comprehensive wave fluctuation amplitude is calculated to generate the wave fluctuation amplitude data for the strong and weak directions. Based on the wave fluctuation amplitude data of the associated directions, the genetic algorithm (GA) is used to optimize the control parameters of the wellhead skid-mounted equipment, such as the vibration suppression frequency, equipment load, etc. By encoding the control parameters, crossover, mutation, and selection operations are used to iteratively optimize the control scheme to find the best equipment response strategy. Minimize the vibration amplitude and load fluctuation of the equipment to improve the stability and response ability of the equipment.The population size of the genetic algorithm is 50, the number of iterations is 100, the crossover probability is 0.7, and the mutation probability is 0.1. The optimized control parameters are imported into the Adaptive Control Model to adjust the working state of the wellhead skid-mounted equipment in real time to resist the jitter caused by the waves. Based on the output of the control algorithm, the working state of the equipment is adjusted to perform jitter compensation and maintain the stable operation of the equipment. Through the real-time adjustment of the adaptive control model, equipment jitter compensation data is generated, including the load of the equipment under different wave conditions and vibration suppression control data.

[0106] Preferably, step S23 includes the following steps:

[0107] Step S231: Evaluate the mutual information of the strong wave azimuth data and the weak wave azimuth data to generate a wave azimuth similarity measurement result;

[0108] Step S232: Calculate the fluctuation amplitudes of the strong wave azimuth data and the weak wave azimuth data respectively to obtain the strong wave fluctuation amplitude and the weak wave fluctuation amplitude;

[0109] Step S233: Use the wave azimuth similarity measurement result to perform amplitude fluctuation superposition calculation on the strong wave fluctuation amplitude and the weak wave fluctuation amplitude to obtain the comprehensive wave fluctuation amplitude of the associated azimuth. The formula for the amplitude fluctuation superposition calculation is as follows:

[0110] A total =W strong ·(ρ strong,weak ·A strong )+W weak ·((1-ρ strong,weak )·A weak );

[0111] Where, A total is the comprehensive wave fluctuation amplitude of the associated azimuth, A strong is the fluctuation amplitude of the strong wave, A weak is the fluctuation amplitude of the weak wave, ρ strong,weak is the azimuth similarity measurement between the strong wave and the weak wave, W strong is the fluctuation weight of the strong wave, and W weak is the fluctuation weight of the weak wave.

[0112] In the embodiment of the present invention, the similarity of the strong wave azimuth data and the weak wave azimuth data is evaluated by using mutual information. Mutual information measures the degree of association between two variables. The larger the value, the closer the relationship between the two. Formula: Among them, p(x, y) is the joint probability distribution, and p(x) and p(y) are the marginal probability distributions of X and Y respectively. The strong sea wave azimuth data and the weak sea wave azimuth data are discretized, and probability estimation is performed using the frequency distribution. Based on the calculated mutual information I(X, Y), a similarity measure is obtained, which reflects the directional correlation between the strong sea waves and the weak sea waves. The calculated mutual information result I(X, Y) is converted into a similarity measure, and the value range is [0, 1]. The closer to 1, the more similar the azimuths are. For the strong sea wave and weak sea wave data, the standard deviation can be used as a measure of the fluctuation amplitude, which reflects the change amplitude of the data on the time axis. According to the sea wave azimuth similarity measure and their respective fluctuation amplitudes, the given weighted formula is used to superimpose the fluctuation amplitudes of the two: A total = W strong ·(ρ strong,weak ·A strong ) + W weak ·((1 - ρ strong,weak )·A weak ); where A total is the comprehensive sea wave fluctuation amplitude of the associated azimuth, A strong is the fluctuation amplitude of the strong sea waves, A weak is the fluctuation amplitude of the weak sea waves, ρ strong,weak is the azimuth similarity measure between the strong sea waves and the weak sea waves, W strong is the fluctuation weight of the strong sea waves, and W weak is the fluctuation weight of the weak sea waves. The superimposed comprehensive sea wave fluctuation amplitude can accurately reflect the combined influence of different sea wave azimuths and provide a basis for the subsequent control model.

[0113] Preferably, the device control optimization algorithm designed based on the comprehensive sea wave fluctuation amplitude of the associated azimuth includes:

[0114] Defining device control parameters based on the comprehensive sea wave fluctuation amplitude of the associated azimuth, where the device control parameters include the hydraulic pressure and the moving speed of the wellhead skid-mounted equipment;

[0115] Constructing an adjustment formula according to the hydraulic pressure and the moving speed of the wellhead skid-mounted equipment, where the hydraulic pressure adjustment formula is as follows:

[0116] P new = P base ×(1 + k pressure ·A total );

[0117] Among them, P new is the adjusted hydraulic pressure, P base is the basic hydraulic pressure, k pressure is the adjustment coefficient of the hydraulic pressure, and A total is the comprehensive sea wave fluctuation amplitude;

[0118] The formula for adjusting the movement speed is as follows:

[0119] V new = V base ×(1 + V speed ·A total );

[0120] Among them, V new is the adjusted hydraulic pressure, V base is the basic hydraulic pressure, k speed is the adjustment coefficient of the movement speed, A total is the comprehensive wave fluctuation amplitude;

[0121] Using PID control to adaptively adjust the hydraulic pressure adjustment formula and the movement speed adjustment formula to generate an optimized equipment control algorithm.

[0122] In the embodiment of the present invention, the hydraulic pressure (P) and the movement speed (V) are two important control parameters of the wellhead skid-mounted equipment, which directly affect the operation stability of the equipment and the ability to cope with wave changes. According to the comprehensive wave fluctuation amplitude and the basic hydraulic pressure, a hydraulic pressure adjustment formula is established. Formula: P new = P base ×(1 + k pressure ·A total ); Among them, P new is the adjusted hydraulic pressure, P base is the basic hydraulic pressure, k pressure is the adjustment coefficient of the hydraulic pressure, A total is the comprehensive wave fluctuation amplitude; Based on the real-time monitored comprehensive wave fluctuation amplitude A total , combined with the hydraulic pressure adjustment coefficient k pressure , dynamically adjust the hydraulic pressure. k pressure is an empirical coefficient, which can be calibrated through experimental data or obtained through an optimization algorithm to adapt to different sea conditions. According to the comprehensive wave fluctuation amplitude and the basic movement speed, a movement speed adjustment formula is established. Formula: V new = V base ×(1 + V speed ·A total ); Among them, V new is the adjusted hydraulic pressure, V base is the basic hydraulic pressure, k speed is the adjustment coefficient of the movement speed, A total is the comprehensive wave fluctuation amplitude; Based on the comprehensive wave fluctuation amplitude A total , the movement speed of the wellhead skid-mounted equipment is adjusted in real time. k speedis an adjustment coefficient, similar to the hydraulic pressure adjustment coefficient, which can be adjusted through experiments, simulations, or online learning. Use PID control to dynamically adjust the hydraulic pressure to ensure that the equipment remains stable under the influence of wave fluctuations. Similarly, use PID control for the movement speed to ensure the stability and responsiveness during the equipment movement. In practical applications, the coefficients of PID control can be adaptively adjusted according to real-time sea condition data and equipment status: through optimization methods such as online learning or genetic algorithms, dynamically adjust the PID coefficients to improve the adaptability to different sea conditions. When the errors of hydraulic pressure and movement speed are large, the PID controller will enhance the response; when the errors are small, reduce the response speed to ensure the stable operation of the equipment during the change of sea waves. Integrate the adjustment formulas of hydraulic pressure and movement speed and the PID controller to design a fully adaptive equipment control optimization algorithm. According to the comprehensively calculated wave fluctuation amplitude in real time and the hydraulic pressure and movement speed adjusted by PID control, perform real-time adjustment and optimization of the equipment. This control algorithm can effectively cope with wave fluctuations and ensure the stable and efficient operation of the wellhead skid-mounted equipment under complex sea conditions.

[0123] As an example of the present invention, refer to Figure 3 shown, in this example, step S3 includes:

[0124] Step S31: Extract historical data from the standard sea area environmental monitoring data to obtain historical sea condition data; construct a wave prediction model based on the historical sea condition data, and use the wave prediction model to predict the waves of the standard sea area environmental monitoring data to generate wave prediction data;

[0125] Step S32: Perform equipment impact early warning on the equipment jitter compensation data according to the wave prediction data to generate equipment impact early warning data; perform compensation response adjustment on the equipment jitter compensation data through the equipment impact early warning data to generate equipment jitter compensation response data, where the compensation response adjustment includes compensation time adjustment and compensation coefficient adjustment;

[0126] Step S33: Import the equipment jitter compensation response data into the adaptive control model for equipment adaptive jitter control to generate equipment adaptive control data;

[0127] Step S34: Design redundant nodes for the wellhead skid-mounted equipment status data to obtain equipment redundant control nodes; perform equipment exception fault tolerance control on the wellhead skid-mounted equipment status data based on the equipment redundant control nodes to generate equipment standby control data.

[0128] In the embodiments of the present invention, historical sea condition data is extracted from a standard sea area environmental monitoring system, mainly including variables such as wave height, wave period, wave direction, and tide. The data extraction process can be docked with the historical data warehouse through a real-time data interface to obtain sea condition records for a past period (such as sea condition records for the past 6 months, 1 year, or 10 years). Based on the extracted historical sea condition data, a wave prediction model is constructed using a machine learning model (such as a support vector machine, random forest, or deep learning model) or traditional statistical methods (such as ARIMA, Kalman filtering). The historical data is denoised, standardized, and missing data is filled. Using the sliding window method, the historical sea condition data is converted into time series data to ensure that the model can identify the changing trend of sea conditions. The model is trained using past data, and its accuracy is evaluated through means such as cross-validation and error analysis. The optimal prediction model (such as a long short-term memory network LSTM, suitable for time series prediction) is selected for long-term and short-term wave predictions. The trained wave prediction model is used to predict the standard sea area environmental monitoring data, and wave prediction data for a future period is output. The prediction data includes key sea condition indicators such as wave height, wave period, and wave direction in the future time period. According to the generated wave prediction data, combined with the operating state data of the wellhead skid-mounted equipment (such as equipment vibration, pressure, speed, etc.), the impact of future waves on the equipment is evaluated. Using a multi-factor analysis model, comprehensively considering the frequency and amplitude of the waves and the dynamic response characteristics of the equipment, equipment impact warning data is generated. When the warning value exceeds the threshold, a warning signal is issued to indicate the existing equipment jitter risk. According to the wave prediction data and equipment impact warning, the time of jitter compensation (i.e., the equipment response time) is dynamically adjusted. The adjustment formula can be adjusted based on the wave period of the predicted waves and the response time of the equipment: Tcomp = Tbase × (1 + ktime·Awave); where: Tcomp is the adjusted compensation time; Tbase is the basic compensation time; ktime is the compensation time adjustment coefficient; Awave is the wave amplitude of the waves (or the comprehensive fluctuation amplitude). According to the changing trend of the waves, the compensation coefficient is adjusted to ensure that the equipment can return to the normal working state in a timely manner. The compensation coefficient adjustment formula is as follows: Ccomp = Cbase × (1 + kcomp·Awave); where: Ccomp is the adjusted compensation coefficient; Cbase is the basic compensation coefficient; kcomp is the compensation coefficient adjustment coefficient; Awave is the wave amplitude of the waves. According to the adjusted compensation time and compensation coefficient, equipment jitter compensation response data is generated for subsequent use by the adaptive control system. The equipment jitter compensation response data is imported into the adaptive control model. This model can be a dynamic adjustment system based on PID control, which can automatically adjust the control strategy according to the real-time sea conditions and equipment status. The key point of adaptive control is to be able to automatically adjust equipment parameters such as hydraulic pressure and movement speed according to the real-time data, historical data, and warning data of wave fluctuations, reduce equipment jitter, and ensure the stable operation of the equipment.Through the adaptive control model, the control parameters of the wellhead skid-mounted equipment are adjusted in real time to generate equipment adaptive control data for optimizing the working state of the equipment. To improve the reliability and fault tolerance of the system, redundant control nodes need to be designed in the equipment control system. The design of redundant nodes can be achieved by setting multiple independent control modules or backup sensors to ensure that when the main control system fails, the redundant nodes can take over the control function and keep the equipment running normally. Based on the equipment redundant control nodes, the status data of the wellhead skid-mounted equipment is monitored in real time to detect whether there are any abnormalities (such as equipment failures, sensor failures, etc.). Once an abnormality is detected, the system will perform fault tolerance processing through the redundant nodes, that is, restore the equipment function through the backup control system. The fault tolerance control includes automatically switching to the backup node, monitoring the abnormal situation in real time, and adjusting the control mode of the equipment according to the type of abnormality. Based on the data of the equipment redundant control nodes, backup control data is generated. The backup control data will be enabled when the main system of the equipment fails to ensure that the equipment continues to run normally.

[0129] Preferably, the equipment abnormal fault tolerance control based on the equipment redundant control nodes for the wellhead skid-mounted equipment status data includes:

[0130] Extract the wellhead skid-mounted equipment status data for equipment pressure, equipment flow rate, and equipment temperature, and perform abnormal detection on the equipment pressure, equipment flow rate, and equipment temperature based on the preset equipment status threshold. When no abnormality is detected, the node of the equipment redundant control node is put into sleep mode;

[0131] When an abnormality is detected, the abnormal impact identification of the wellhead skid-mounted equipment status data is performed to generate an equipment abnormal impact identification result, where the equipment abnormal impact identification result includes a core equipment abnormal impact identification result and a peripheral equipment abnormal impact identification result, and the peripheral equipment abnormal impact identification result is excluded;

[0132] According to the core equipment abnormal impact identification result, the node of the equipment redundant control node is activated, and based on the activated equipment redundant control node, the core equipment abnormal impact identification result is subjected to backup control to generate equipment backup control data, where the formula for backup control is as follows:

[0133] C backup =(f redundant (D backup ,C current ));

[0134] In the formula, C backup is the backup control data, f redundant is the calculation function for the redundant node to generate control data, D backup is the backup data of the redundant control node, and C current is the control data under the current equipment status.

[0135] In the embodiments of the present invention, by extracting the real-time status data of the wellhead skid-mounted equipment, the following three main indicators are focused on: the hydraulic system pressure inside the equipment is obtained in real time through a pressure sensor, the liquid flow rate of the equipment is monitored through a flow sensor, and the operating temperature of the equipment is obtained through a temperature sensor to ensure that the equipment does not overheat. The extracted equipment status data is compared with the preset equipment status threshold, and the following steps are executed: If the equipment pressure exceeds the preset safety range (such as the maximum pressure value or the minimum pressure value), it is considered that an abnormality has occurred; if the change range of the flow rate exceeds the set threshold or the actual flow rate exceeds the specified range, it is determined that the flow rate is abnormal; if the temperature exceeds the set safety upper limit or is lower than the lower limit, it is detected that the temperature is abnormal. If the equipment status is within the normal range (that is, no abnormality is detected), the system will put the redundant control nodes of the equipment into the sleep state, stop the activation operation of the redundant control nodes, and reduce the consumption of redundant resources. When an abnormality is detected, it is necessary to analyze the status data of the wellhead skid-mounted equipment to identify the specific impact of the abnormality on the equipment. According to the working principle and operating status of the equipment, the impact on the core equipment (such as hydraulic pumps, drive motors, etc.) is identified. The failure of these equipment will directly affect the normal operation of the system. Analyze the auxiliary equipment (such as sensors, cooling systems, etc.) connected to the core equipment, check whether these equipment are abnormal, and if they are abnormal, perform troubleshooting to avoid the activation of redundant control nodes. During the process of identifying the impact of equipment abnormalities, the system will exclude the impact of peripheral equipment irrelevant to the redundant control system to ensure that the activation of redundant control nodes is only for core equipment abnormalities and avoid misoperations. According to the identification result of the impact of core equipment abnormalities, if the core equipment has an abnormality (such as too high pressure, too low flow rate, etc.), the redundant control node is activated. The activated redundant control node will intervene in the equipment control system, take over the control function of the abnormal equipment, ensure the continuous operation of the equipment and reduce the impact of abnormalities. The redundant control node is used to control the core equipment through a preset standby control formula and generate standby control data: C backup =(f redundant (D backup ,C current )); In the formula, C backup is the standby control data, f redundant is the calculation function for the redundant node to generate control data, D backup is the standby data of the redundant control node, C currentIt is the control data under the current device state. According to the generated backup control data, the redundant control node performs real-time control adjustment on the core device to ensure that the device can smoothly transition to the redundant control state in case of faults or anomalies. The execution of the backup control includes adjusting key control parameters such as the hydraulic pressure, movement speed, and temperature of the device to ensure that the device can continue to operate without being severely damaged. Once the redundant control node takes over the control, the system will automatically execute the exception tolerance mechanism, including switching to the backup device and adjusting the control parameters. The system will monitor the state of the device through the redundant control node and adjust the control strategy in real time to reduce the impact of the core device's failure on the system. After the core device resumes normal operation, the redundant control node will release the control right and return to the operation mode of the main control system. The system will put the redundant node into the sleep state for future abnormal situations.

[0136] Preferably, step S4 includes the following steps:

[0137] Step S41: Package the device adaptive control data and the device backup control data to generate a device control log; upload the device control log to the cloud platform for data storage to generate a device control storage log;

[0138] Step S42: Visualize the data of the device control storage log to generate a device control storage report for performing the control optimization operation of the wellhead skid-mounted equipment.

[0139] In the embodiments of the present invention, by extracting the control data of the wellhead skid-mounted equipment from the adaptive control model, these data reflect the state of the equipment after adaptive adjustment under the current sea conditions (such as hydraulic pressure, movement speed, etc.). Extract the backup control data from the redundant control system, and record the control data generated by the redundant control nodes during equipment anomalies (such as redundant node activation, standby equipment scheduling, etc.). Package these two types of data in a preset format (such as JSON, XML, etc.), ensuring that the data contains necessary meta-information, such as timestamp, equipment identifier, control parameter values, operation types, etc. This packaging process facilitates subsequent data storage, querying, and analysis. After packaging, generate an equipment control log file to record the control information and redundant control situation during the entire operation process of the equipment. Upload the generated equipment control log to the cloud platform through a network interface. During the upload process, ensure the security and integrity of data transmission, and use an encrypted transmission protocol (such as HTTPS) for data transmission. During the upload process, either batch upload or real-time upload can be adopted, and the specific choice depends on the generation frequency of the equipment control data and the receiving capacity of the cloud platform. After receiving the equipment control log, the cloud platform stores the data and generates an equipment control storage log to record meta-information such as the storage location, time, and equipment identifier of the log. The purpose of storing the log is to provide reliable historical data support for subsequent analysis and optimization. By analyzing the data of the equipment control storage log stored in the cloud platform, perform data visualization processing to help equipment operators or managers quickly understand the equipment status, control effects, and optimization potential. Based on the visualization results of the equipment control storage log, generate an equipment control storage report, and the report content includes: the execution status of equipment adaptive control and standby control, the variation range of control parameters, analyze indicators such as the response time of redundant control nodes and the effectiveness of standby control, evaluate the impact of waves on equipment jitter and the timeliness of equipment response according to the wave change trend and equipment adjustment data, and propose equipment control optimization suggestions based on the data analysis results, such as hydraulic pressure adjustment optimization, redundant control strategy optimization, etc.

[0140] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0141] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control optimization method for wellhead skid-mounted equipment on an offshore platform, characterized in that: The following steps are involved: Step S1: Acquire marine environment monitoring data and wellhead skid-mounted equipment status data; A dynamic model based on sea conditions is established based on marine environmental monitoring data, and the status data of the wellhead skid-mounted equipment is imported into the dynamic model based on sea conditions for control linkage modeling to generate an adaptive control model; Step S2: confirm the impact of the equipment-wave jitter of the marine environment monitoring data on the status data of the wellhead skid-mounted equipment, and design an equipment control optimization algorithm based on the impact of the equipment-wave jitter; import the equipment control optimization algorithm into the adaptive control model to perform equipment jitter compensation on the wellhead skid-mounted equipment, and generate equipment jitter compensation data; Step S3: performing sea wave prediction on the marine environment monitoring data to generate sea wave prediction data; Perform advance response compensation on the equipment jitter compensation data according to the wave prediction data to generate equipment jitter compensation response data; import the equipment jitter compensation response data into the adaptive control model to perform equipment jitter control to generate equipment adaptive control data and equipment standby control data; Step S4: The equipment adaptive control data and the equipment standby control data are stored and visualized in the cloud, thereby generating an equipment control storage report to perform wellhead skid-mounted equipment control optimization operations.

2. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using sensors to obtain marine environment monitoring data and wellhead skid-mounted equipment status data; Step S12: preprocessing the marine environment monitoring data to generate standard marine environment monitoring data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization; Step S13: Performing environmental change analysis on the standard sea area environmental monitoring data through edge computing equipment to generate sea area environmental change data; Step S14: extract the wave height, period, direction and frequency from the marine environment change data to establish a dynamic model based on the sea conditions, and import the wellhead skid-mounted equipment status data into the dynamic model based on the sea conditions for control linkage modeling to generate an adaptive control model.

3. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 2 is characterized in that: Importing the status data of the wellhead skid-mounted equipment into the dynamic model based on sea conditions for control linkage modeling includes: Import the wellhead skid-mounted equipment status data into the dynamic model based on sea conditions to screen the affected equipment status and obtain the status data of key equipment components; Analyze the dynamic response characteristics of the equipment based on the status data of key components of the equipment and the dynamic model based on sea conditions, and generate the equipment sea condition response characteristic data; According to the equipment sea condition response characteristic data, the model equipment mobility is adjusted for the sea condition-based dynamic model to generate an adaptive control model.

4. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing equipment jitter timing analysis on the wellhead skid-mounted equipment status data to generate equipment jitter timing data; extracting the sea wave change trend from the standard sea environment monitoring data based on the equipment jitter timing data to obtain sea wave change trend data; Step S22: performing directional fitting on the device jitter time series data and the wave change trend data to generate device impact azimuth data; extracting the maximum impact azimuth from the device impact azimuth data and marking it as strong wave azimuth data, and marking the remaining impact azimuths as weak wave azimuth data; Step S23: calculating the wave-associated fluctuation amplitude for the strong wave azimuth data and the weak wave azimuth data to obtain the comprehensive wave fluctuation amplitude of the associated azimuth; Step S24: designing an equipment control optimization algorithm based on the comprehensive wave fluctuation amplitude of the associated orientation, and performing equipment jitter compensation on the wellhead skid-mounted equipment according to the equipment control optimization algorithm imported into the adaptive control model to generate equipment jitter compensation data.

5. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 4 is characterized in that: Step S23 includes the following steps: Step S231: Evaluate the mutual information of the strong wave position data and the weak wave position data to generate a wave position similarity measurement result; Step S232: respectively calculating the fluctuation amplitudes of the strong wave azimuth data and the weak wave azimuth data to obtain the strong wave fluctuation amplitude and the weak wave fluctuation amplitude; Step S233: Using the wave orientation similarity measurement result, the amplitude fluctuation superposition calculation is performed on the strong wave fluctuation amplitude and the weak wave fluctuation amplitude to obtain the comprehensive wave fluctuation amplitude of the associated orientation, wherein the amplitude fluctuation superposition calculation formula is as follows: total =W strong ·(ρ strong,weak ·A strong )+W weak ·((1-ρ strong,weak )·A weak ); Among them, A total is the comprehensive wave amplitude of the associated direction, A strong is the amplitude of strong waves, A weak is the amplitude of weak waves, ρ strong,weak is the azimuth similarity measure between strong waves and weak waves, W strong is the fluctuation weight of strong waves, W weak is the fluctuation weight of weak waves.

6. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 4, characterized in that: The equipment control optimization algorithm for comprehensive wave amplitude design based on associated orientation includes: The equipment control parameters are defined based on the comprehensive sea wave amplitude of the associated orientation, wherein the equipment control parameters include the hydraulic pressure and movement speed of the wellhead skid-mounted equipment; The adjustment formula is constructed according to the hydraulic pressure and movement speed of the wellhead skid-mounted equipment, where the hydraulic pressure adjustment formula is as follows: P new =P base ×(1+k pressure ·A total ); Among them, P new is the adjusted hydraulic pressure, P base is the basic hydraulic pressure, k pressure A is the adjustment coefficient of hydraulic pressure. total is the comprehensive wave amplitude; The motion speed adjustment formula is as follows: V new =V base ×(1+V speed ·A total ); Among them, V new is the adjusted hydraulic pressure, V base is the basic hydraulic pressure, k speed is the adjustment coefficient of the movement speed, A total is the comprehensive wave amplitude; PID control is used to adaptively adjust the hydraulic pressure regulation formula and the motion speed regulation formula to generate an equipment control optimization algorithm.

7. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: extracting historical data from the standard sea environment monitoring data to obtain historical sea condition data; constructing a wave prediction model based on the historical sea condition data, and using the wave prediction model to perform wave prediction on the standard sea environment monitoring data to generate wave prediction data; Step S32: performing equipment impact warning on the equipment jitter compensation data according to the wave prediction data to generate equipment impact warning data; performing compensation response adjustment on the equipment jitter compensation data according to the equipment impact warning data to generate equipment jitter compensation response data, wherein the compensation response adjustment includes compensation time adjustment and compensation coefficient adjustment; Step S33: importing the device jitter compensation response data into the adaptive control model to perform device adaptive jitter control and generate device adaptive control data; Step S34: Design redundant nodes for the wellhead skid-mounted equipment status data to obtain equipment redundant control nodes; perform equipment abnormality fault-tolerant control on the wellhead skid-mounted equipment status data based on the equipment redundant control nodes to generate equipment standby control data.

8. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 7, characterized in that: The equipment abnormal fault tolerance control of the wellhead skid-mounted equipment status data based on the equipment redundancy control node includes: Extract the status data of the wellhead skid-mounted equipment to measure the equipment pressure, equipment flow and equipment temperature, and perform abnormal detection on the equipment pressure, equipment flow and equipment temperature based on the preset equipment status threshold. When no abnormality is detected, the equipment redundant control node is put into node hibernation; When an abnormality is detected, the abnormal impact identification is performed on the wellhead skid-mounted equipment status data to generate equipment abnormal impact identification results, where the equipment abnormal impact identification results include core equipment abnormal impact identification results and edge equipment abnormal impact identification results, and the edge equipment abnormal impact identification results are excluded; The device redundant control node is activated according to the abnormal impact identification result of the core device, and the abnormal impact identification result of the core device is controlled according to the activated device redundant control node to generate device backup control data, wherein the backup control formula is as follows: C backup =(f redundant (D backup ,C current )); In the formula, C backup is the standby control data, f redundant The computation function that generates control data for redundant nodes, D backup is the backup data of the redundant control node, C current It is the control data of the current device status.

9. The control optimization method for wellhead skid-mounted equipment for offshore platforms according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: encapsulate the device adaptive control data and the device standby control data to generate a device control log; upload the device control log to the cloud platform for data storage to generate a device control storage log; Step S42: Visualize the data of the equipment control storage log to generate an equipment control storage report to perform wellhead skid-mounted equipment control optimization operations.

10. A wellhead skid-mounted equipment control optimization system for an offshore platform, characterized in that: Used to execute the wellhead skid-mounted equipment control optimization method for an offshore platform as claimed in claim 1, the wellhead skid-mounted equipment control optimization system for an offshore platform comprises: The control model building module is used to obtain marine environment monitoring data and wellhead skid-mounted equipment status data; a dynamic model based on sea conditions is established based on the marine environment monitoring data, and the wellhead skid-mounted equipment status data is imported into the dynamic model based on sea conditions for control linkage modeling to generate an adaptive control model; The jitter compensation module is used to confirm the impact of the equipment-wave jitter of the marine environment monitoring data on the status data of the wellhead skid-mounted equipment, and to design the equipment control optimization algorithm based on the impact of the equipment-wave jitter; the equipment control optimization algorithm is imported into the adaptive control model to perform equipment jitter compensation on the wellhead skid-mounted equipment and generate equipment jitter compensation data; The response compensation module is used to predict the sea waves based on the marine environment monitoring data and generate the sea wave prediction data; perform early response compensation on the equipment jitter compensation data according to the sea wave prediction data and generate the equipment jitter compensation response data; import the equipment jitter compensation response data into the adaptive control model to perform equipment jitter control and generate the equipment adaptive control data and equipment standby control data; The control data storage module is used to store and visualize the equipment adaptive control data and equipment backup control data in the cloud, so as to generate equipment control storage reports to perform wellhead skid-mounted equipment control optimization operations.

Images