Marine fine pressure control well drilling intelligent control system based on AI technology

Abstract

The invention belongs to the field of marine drilling, relates to a data analysis technology, and aims to solve the problem that control parameters cannot be reasonably set when set numerical analysis results of the same control parameter are inconsistent in the prior art, in particular to an intelligent control system for marine fine pressure control drilling based on an AI technology. Comprising a parameter control module, a compensation control module, a protection adjustment module and a protection optimization module which are connected in sequence. The parameter control module is used for performing parameter control analysis on the seabed drilling equipment; a plurality of control groups are generated, deviation coefficients of the control groups are calculated, and set optimization values are marked through the deviation coefficients; the set optimization value is sent to a compensation control module; according to the method, the problem of control instruction conflict caused by multi-source monitoring parameters is effectively solved, meanwhile, the wellbore blockage risk caused by control lag is avoided, and the safety and control precision of deep sea drilling operation are improved.

Description

Technical Field

[0001] The present invention belongs to the field of offshore drilling, involves data analysis technology, and specifically is an intelligent control system for offshore fine pressure control drilling based on AI technology. Background Art

[0002] The intelligent control system for offshore fine pressure control drilling is a high-end technical system for drilling operations in deep sea or complex formations, aiming to ensure drilling safety, improve efficiency and reduce risks by real-time monitoring and dynamic regulation of wellbore pressure; the intelligent control system for offshore fine pressure control drilling is a key technology for deepwater oil and gas development, and its intelligent and automated level directly determines the operation safety.

[0003] The invention patent with the publication number of CN115822550B discloses an intelligent control system for offshore fine pressure control drilling. This control system helps to reduce the difficulty of data acquisition and the work complexity of technicians during offshore fine pressure control drilling, realize the effective utilization of various parameters, and improve the accuracy and operation efficiency of control instructions; however, the undersea drilling environment is complex, and there may be significant differences in the set values obtained by analyzing the same control parameter from different perspectives. The prior art cannot rationally set the control parameters in this case, resulting in high risks for undersea drilling.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent control system for offshore fine pressure control drilling based on AI technology, which is used to solve the problem that the prior art cannot rationally set the control parameters when the analysis results of the set values of the same control parameter are contradictory;

[0006] The technical problem that the present invention needs to solve is: how to provide an intelligent control system for offshore fine pressure control drilling based on AI technology that can rationally set the control parameters when the analysis results of the set values of the same control parameter are contradictory.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent control system for offshore fine pressure control drilling based on AI technology includes a parameter control module, a compensation control module, a protection adjustment module, and a protection optimization module connected in sequence;

[0009] The parameter control module is used to perform parameter control analysis on undersea drilling equipment: generate several control groups and calculate the deviation coefficients of the control groups, mark the set optimization values through the deviation coefficients; and send the set optimization values to the compensation control module;

[0010] The compensation control module is used to perform calibration compensation control analysis on subsea drilling equipment: before controlling the control parameters, generate a compensation optimization value by setting an optimization value, and set the numerical value of the control parameters through the compensation optimization value;

[0011] The protection adjustment module is used to perform adjustment analysis on the hydrate formation critical point of subsea drilling equipment: collect temperature data, fluid data, and external data of subsea drilling equipment, input the collected temperature data, fluid data, and external data into the LSTM neural network model for hydrate formation critical point analysis and obtain the critical point threshold; if the real-time parameters under the current wellbore conditions reach the critical point threshold, mark the current moment as the injection moment, and adjust the protection liquid concentration and injection volume at the injection moment;

[0012] The protection optimization module is used to perform optimization analysis on the protection liquid injection process of subsea drilling equipment.

[0013] Furthermore, the generation process of the control group includes: marking the control parameters of subsea drilling equipment as control object i, where i = 1, 2, …, n, and n is a positive integer. Control object i includes throttle valve opening, drilling fluid density pump, sulfur scavenger dosage, etc. Mark the environmental parameters of offshore drilling as monitoring object e, where e = 1, 2, …, m, and m is a positive integer; Monitoring objects include wellbore temperature gradient, sea current velocity, hydrogen sulfide concentration, bottom hole pressure fluctuation, etc. Each control object i corresponds to one or more monitoring objects e. A control group is formed by control object i and the corresponding monitoring object e. It can be understood that when control object i is the throttle valve opening, the wellbore temperature gradient (when high temperature causes the viscosity of drilling fluid to decrease, the throttle valve opening needs to be increased to compensate for pressure loss), sea current velocity (when strong sea current intensifies the vibration of the riser, trigger fine adjustment of the throttle valve to suppress pressure fluctuation), hydrogen sulfide concentration (when the concentration exceeds the standard, the self-drilling fluid circulation rate), and bottom hole pressure fluctuation (when the pressure deviation exceeds ±0.2 MPa of the threshold, the throttle valve responds within 10 s and cooperates with the drilling fluid density pump for adjustment) in monitoring object e all correspond to the throttle valve opening. Then, a control group is formed by the throttle valve opening, wellbore temperature gradient, sea current velocity, hydrogen sulfide concentration, and bottom hole pressure fluctuation. Within this control group, the wellbore temperature gradient, sea current velocity, hydrogen sulfide concentration, and bottom hole pressure fluctuation all correspond to a theoretical setting value of the throttle valve opening.

[0014] Further, the process of obtaining the deviation coefficient of the control group includes: arranging the monitoring objects e in the control group in the order of decreasing response priority to obtain a priority sequence. The response priority represents the priority degree of the control timeliness of the corresponding parameter. For example, the priority sequence of the monitoring object e in the control group corresponding to the throttle valve opening is hydrogen sulfide concentration - bottom hole pressure fluctuation - wellbore temperature gradient - sea current velocity. Analyze the real-time monitoring values of the monitoring object e to obtain the set value SZie of the control object i, and then calculate the variance of the set values SZie of the control object i corresponding to all monitoring objects e to obtain the deviation coefficient.

[0015] Further, the specific process of marking the set optimization value includes: comparing the deviation coefficient with a preset deviation threshold: if the deviation coefficient is less than the deviation threshold, sum up all the set values SZie and take the average to obtain the set optimization value; if the deviation coefficient is greater than or equal to the deviation threshold, sequentially set the set values SZie as the set optimization value in the order of the priority sequence. The set value SZie with a later ranking needs to be set after the previous monitoring object e is stable.

[0016] Further, the process of generating the compensation optimization value includes: obtaining the displayed value and the actual value of the control object i, marking the difference between the displayed value and the actual value as the compensation value of the control object i, and marking the sum of the set optimization value and the compensation value of the control object i as the compensation optimization value of the control object i.

[0017] Further, the process of temperature data acquisition includes: obtaining the temperature and pressure values of each section of the wellbore / pipeline through a temperature sensor; the process of fluid data acquisition includes: detecting the gas concentration, water content, and supersaturation in the fluid composition; the process of external data acquisition includes: obtaining the seawater temperature and flow velocity in the area where the wellbore is located.

[0018] Further, the specific process of the protection optimization module for optimizing the analysis of the protection liquid injection process of the subsea drilling equipment includes: generating an optimization conversion ratio. After the critical point threshold is output by the subsequent LSTM neural network model, mark the product of the critical point threshold and the optimization conversion ratio as the critical point optimization value, compare the real-time parameters of the current wellbore working condition with the critical point optimization value, and mark the subsequent injection time.

[0019] Further, the process of generating the optimization conversion ratio includes: marking the time difference between the effective time after adjusting the protection liquid concentration and injection volume and the injection time as the time difference value, marking the injection optimization time, the injection optimization time is before the injection time and the time difference with the injection time is also the time difference value, and marking the ratio of the real-time parameters at the injection optimization time to the critical point threshold as the optimization conversion ratio.

[0020] The present invention has the following beneficial effects:

[0021] 1. Effectively solve the problem of control instruction conflicts caused by multi-source monitoring parameters. Dynamically select parameter optimization strategies through deviation coefficients to ensure the rationality and consistency of control instructions. At the same time, realize the real-time prediction of the hydrate formation critical point and the pre-judgment optimization of the injection timing of the protective fluid, avoid the risk of wellbore blockage caused by control lag, and improve the safety and control accuracy of deep-sea drilling operations.

[0022] 2. Solve the problem of unreasonable setting caused by the single angle of control parameter setting in the existing technology. By establishing a dynamic correlation relationship between control parameters and environmental parameters, reduce the parameter setting differences under different analysis dimensions, and thus reduce the risks of blowout or equipment damage caused by parameter deviation in subsea drilling operations.

[0023] 3. Can more accurately identify the risk of hydrate formation, trigger the protective fluid injection mechanism in advance when the wellbore working conditions are close to the critical point, avoid the problem of lag response caused by incomplete parameter monitoring, and thus effectively reduce the potential risk of hydrate blocking the wellbore or pipeline.

[0024] 4. Effectively solve the problem of lag in the injection of the protective fluid. By dynamically correcting the critical point threshold and combining the time difference compensation mechanism, ensure that the protective fluid is adjusted before the wellbore working conditions reach the actual danger threshold, significantly reduce the risk of hydrate formation and improve the timeliness of injection control. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 It is the system block diagram of Embodiment 1 of the present invention;

[0027] Figure 2 It is the method flow chart of Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0029] In the prior art, the intelligent control system for ocean fine pressure control drilling is a key technology for deepwater oil and gas development, which ensures drilling safety by real-time monitoring and dynamic regulation of wellbore pressure. However, the undersea drilling environment is complex, and there may be significant differences in the set values obtained from different perspectives for the same control parameter. The prior art cannot rationally set the control parameter in this situation, resulting in a high risk of undersea drilling. For example, in the deep-sea high-pressure and low-temperature environment, the wellbore pressure control parameters may produce conflicting analysis results due to factors such as temperature gradient and fluid composition differences, and it is difficult for traditional systems to coordinate the conflicts between multi-source data.

[0030] To solve the above problems, a control method that can coordinate multi-dimensional parameter conflicts and achieve dynamic optimization is needed. Through analysis, it is found that the parameter setting conflict stems from the differential influence of different monitoring objects on the same control parameter, and a priority ranking mechanism needs to be established to eliminate the contradiction. At the same time, the dynamic change of the hydrate formation critical point requires the system to have real-time prediction ability, and it is necessary to make a comprehensive judgment by combining environmental parameters and fluid states. In addition, the lag of the protection fluid injection timing may cause potential safety hazards, and a pre-judgment mechanism needs to be established to optimize the injection moment.

[0031] Example 1: As Figure 1 shown, this application proposes an intelligent control system for ocean fine pressure control drilling based on AI technology, including a parameter control module, a compensation control module, a protection adjustment module, and a protection optimization module connected in sequence. The parameter control module generates a control group and calculates the deviation coefficient, and marks the set optimization value through the deviation coefficient; the compensation control module generates a compensation optimization value for parameter setting; the protection adjustment module collects multi-dimensional data and inputs it into the LSTM model to analyze the critical point threshold, and adjusts the protection fluid parameters when the real-time parameter reaches the threshold; the protection optimization module generates an optimization conversion ratio to adjust the critical point threshold.

[0032] Among them, the deviation coefficient of the parameter control module refers to the variance value of the set values of the control object corresponding to multiple monitoring objects, which can be specifically realized through the variance calculation formula and is used to quantify the comprehensive influence degree of different monitoring parameters on the same control object. The compensation optimization value of the compensation control module refers to the superimposed value of the deviation between the set optimization value and the displayed value, which can be specifically realized by calculating the difference between the actual value collected by the sensor and the feedback value of the control system, and is used to eliminate the equipment execution error. The critical point threshold of the protection adjustment module refers to the boundary value of the hydrate formation condition predicted by the LSTM neural network, which can be specifically realized by training the model with multi-dimensional data such as temperature, pressure, and fluid composition, and is used to dynamically judge the trigger condition for protection fluid injection. The optimization conversion ratio of the protection optimization module refers to the ratio of the injection moment pre-judgment parameter to the critical point threshold, which can be specifically realized by modeling the historical effective time difference data and is used to trigger the protection fluid injection action in advance.

[0033] Specifically, the parameter control module associates control parameters with environmental parameters to form control groups, and evaluates the dispersion degree of parameter settings through variance calculation. When the deviation coefficient is lower than the threshold, the average value is used as the optimization value, and when it is higher than the threshold, it is set step by step according to the priority sequence. The compensation control module superimposes the device execution error compensation value to form the final control instruction. The protection regulation module collects wellbore temperature, fluid composition, and seawater environment data in real time, inputs the trained LSTM model to predict the critical point, and immediately triggers the protection liquid concentration regulation when the real-time pressure or temperature reaches the predicted threshold. The protection optimization module establishes an optimization conversion ratio based on the historical effective time difference, and adjusts the critical point trigger value in advance in subsequent predictions to synchronize the protection liquid injection action with the working condition changes.

[0034] Compared with the prior art, the existing system uses the simple weighted average method when dealing with multi-source parameter conflicts, cannot identify the priority relationship between parameters, and easily leads to contradictory control instructions. This solution identifies the parameter dispersion degree through the deviation coefficient, establishes a hierarchical setting mechanism, and effectively coordinates the mutual influence of multi-dimensional parameters. The prior art relies on fixed thresholds to judge the timing of protection liquid injection and is difficult to adapt to dynamic environmental changes. This solution predicts the critical point in real time through the LSTM model, combines the optimization conversion ratio to realize the prediction of the injection moment, and significantly improves the control timeliness.

[0035] Through the above technical solutions, this application can effectively solve the problem of conflicting control instructions caused by multi-source monitoring parameters, dynamically select parameter optimization strategies through the deviation coefficient, and ensure the rationality and consistency of control instructions. At the same time, it realizes the real-time prediction of the hydrate formation critical point and the prediction optimization of the protection liquid injection timing, avoids the risk of wellbore blockage caused by control lag, and improves the safety and control accuracy of deep-sea drilling operations.

[0036] Mark the control parameters of the subsea drilling equipment as control object i, where i = 1, 2, …, n, and n is a positive integer. Mark the environmental parameters of the offshore drilling as monitoring object e, where e = 1, 2, …, m, and m is a positive integer. Each control object i corresponds to one or more monitoring objects e, and a control group is formed by the control object i and the corresponding monitoring object e.

[0037] Among them, the control object i refers to the parameters that need to be dynamically adjusted in the subsea drilling equipment, such as wellbore pressure, drilling fluid flow rate, or bit rotation speed. Specifically, data can be collected in real time through pressure sensors, flow meters, or rotation speed sensors. The monitoring object e refers to the environmental parameters related to drilling safety, such as seawater temperature, flow rate, or formation pressure. Specifically, temperature sensors, flow meters, or pressure sensors can be used for monitoring. The control group consists of the control object i and its associated monitoring object e, and is used to establish the dynamic association relationship between control parameters and environmental parameters, thereby avoiding the one-sidedness of single-parameter analysis.

[0038] Specifically, when generating the control group, the control parameters are first divided into independent control objects according to functional categories. For example, the wellbore pressure is divided into a control object i, and the drilling fluid flow rate is divided into another control object i. Subsequently, according to the actual requirements of the drilling operation, environmental monitoring parameters associated with each control object i are assigned. For example, the wellbore pressure control object i can be associated with monitoring objects e such as seawater temperature and flow rate. Through this grouping method, the adjustment of control parameters can be bound to real-time environmental changes. For example, when the seawater flow rate suddenly increases, the wellbore pressure control parameters associated with it are preferentially adjusted, thereby realizing the dynamic optimization of parameter settings.

[0039] Compared with the prior art, the setting of control parameters in the prior art is usually based on single-dimensional data only. For example, it is only adjusted according to the historical data of the wellbore pressure, ignoring the real-time impact of environmental parameters on the control effect. In this solution, by constructing a control group, the environmental monitoring parameters are associated with the equipment control parameters, enabling the parameter settings to comprehensively consider multi-dimensional dynamic changes. For example, when the seawater temperature fluctuates, the associated drilling fluid flow rate parameters can be adjusted synchronously, thereby avoiding control deviations caused by environmental mutations.

[0040] Through the above technical solution, this application can solve the problem of unreasonable parameter settings caused by the single angle of control parameter setting in the prior art. By establishing a dynamic association relationship between control parameters and environmental parameters, the parameter setting differences under different analysis dimensions are reduced, thereby reducing the risks of blowout or equipment damage caused by parameter deviations in subsea drilling operations.

[0041] The process of obtaining the deviation coefficient of the control group includes arranging the monitoring objects e in the control group in descending order of response priority to obtain a priority sequence, analyzing the set value SZie of the control object i based on the real-time monitoring values of the monitoring objects e, and then calculating the variance of the set values SZie of the control object i corresponding to all monitoring objects e to obtain the deviation coefficient.

[0042] Among them, the priority sequence refers to the order formed by arranging the monitoring objects e according to the response priority. Specifically, it can be implemented by using a preset priority rule or an algorithm dynamically adjusted based on environmental parameters, and is used to determine the processing order of the influence of different monitoring objects on the control parameters. The set value SZie refers to the parameter setting value corresponding to the control object i under the real-time data of the monitoring object e. Specifically, it can be calculated by collecting real-time monitoring values through sensors and combining a preset mapping relationship or regression model. The deviation coefficient is a quantitative index that reflects the degree of dispersion of the set values of the same control object i under different monitoring objects e through variance calculation. Specifically, the variance formula in statistics can be used to calculate the numerical dispersion degree of multiple SZie.

[0043] Specifically, after generating the priority sequence, the real-time monitoring data of each monitoring object e is input into the analysis model and converted into the set value SZie of the corresponding control object i through a preset algorithm or mapping relationship. Subsequently, for the same control object i, multiple corresponding SZie are extracted and variance calculation is performed, and the variance result is defined as the deviation coefficient. For example, when the control object is the wellbore pressure, the monitoring objects may include the seabed flow velocity, temperature, and fluid composition. After the SZie corresponding to each monitoring object is generated through independent analysis, the variance calculation can reflect the dispersion degree of different monitoring objects with respect to the pressure set value.

[0044] Compared with the prior art, the prior art does not consider the numerical dispersion problem of the same control parameter under different monitoring dimensions, resulting in a risk of parameter setting conflicts. This solution quantifies the dispersion degree through variance calculation and determines the processing order in combination with the priority sequence, enabling the parameter setting process to preferentially process the data of high-priority monitoring objects and simultaneously judging the rationality of parameter setting through the deviation coefficient.

[0045] The specific process of marking the set optimization value includes: comparing the deviation coefficient with a preset deviation threshold: if the deviation coefficient is less than the deviation threshold, the sum of all set values is averaged to obtain the set optimization value; if the deviation coefficient is greater than or equal to the deviation threshold, the set values are sequentially set as the set optimization value according to the order of the priority sequence, and the set values with a later ranking need to be set after the previous monitoring object is stable.

[0046] Among them, the deviation coefficient is a quantitative index reflecting the fluctuation degree of the set value of the control parameter, which can be specifically realized by calculating the variance of the set values corresponding to each monitoring object and is used to evaluate the stability of the control parameter setting.

[0047] The deviation threshold is a preset reference value for determining whether the parameter setting is stable, which can be specifically realized by using the critical value obtained from the statistical analysis of historical operation data and is used to divide the applicable conditions of the parameter optimization strategy.

[0048] The priority sequence is the operation order formed by sorting the monitoring objects according to the response priority, which can be specifically realized by setting the weight coefficients of different monitoring parameters and is used to determine the sequence logic of parameter adjustment.

[0049] Specifically, when the deviation coefficient of the control group is lower than the preset threshold, it indicates that the set values corresponding to each monitoring object fluctuate less. At this time, the average value of each set value is used as the optimization value to achieve the equalization processing of parameter setting. When the deviation coefficient exceeds the threshold, it indicates that there are significant parameter fluctuations. At this time, the parameters are set step by step according to the priority order of the monitoring objects, and the adjustment of subsequent parameters needs to wait until the operating state of the previous monitoring object is stable before execution, so as to avoid system oscillations caused by simultaneous adjustment of multiple parameters.

[0050] Compared with the prior art, the prior art lacks an effective integration mechanism for different analysis results of the same control parameter, resulting in a risk of parameter setting conflicts. In this solution, the degree of parameter fluctuation is quantitatively evaluated by the deviation coefficient, and the average optimization or step-by-step optimization strategy is dynamically selected according to the evaluation results, which not only ensures the parameter setting efficiency in the low-fluctuation scenario but also realizes the adjustment stability in the high-fluctuation scenario.

[0051] The generation process of the compensated optimization value includes: obtaining the displayed value and the actual value of the control object i, marking the difference between the displayed value and the actual value as the compensation value of the control object i, and marking the sum of the set optimization value and the compensation value of the control object i as the compensated optimization value of the control object i.

[0052] Among them, the displayed value refers to the data displayed by the control object on the device operation interface or in the sensor, and specifically can be implemented by the values collected by real-time monitoring devices such as pressure sensors and flow meters and transmitted to the control system.

[0053] Among them, the actual value refers to the parameter state that actually exists in the physical environment of the control object, and specifically can be implemented by secondary verification through an independent calibration device or a redundant measurement device.

[0054] Among them, the compensation value refers to the error amount between the displayed value and the actual value, and specifically can be implemented by a difference calculation module to compare the two in real time and generate a correction parameter.

[0055] Among them, the compensated optimization value refers to the final set value of the control parameter after error correction, and specifically can be implemented by an adder to perform a superposition operation on the set optimization value and the compensation value.

[0056] Specifically, during the control parameter setting process, the displayed value may deviate due to sensor drift, environmental interference, or transmission delay. By obtaining the actual value and calculating the compensation value, the influence of system errors on control accuracy can be eliminated. The set optimization value is the initial control parameter generated based on the analysis of environmental parameters, and the compensated optimization value obtained by superimposing the compensation value will be output as the final execution instruction to the subsea drilling equipment. For example, when the displayed value of the pressure control parameter is 10 MPa and the actual value is 9.8 MPa, the compensation value of 0.2 MPa will be superimposed on the set optimization value to ensure that the control instruction matches the actual working condition.

[0057] Compared with the prior art, the prior art only relies on a single data source for parameter setting and does not consider the systematic deviation between the device display value and the true value. By introducing a compensation value calculation mechanism, the present application can dynamically correct the control parameter setting error. For example, in the patent with the publication number CN115822550B, the control parameters are directly generated using the monitoring data without involving an error compensation link, while the present application effectively avoids the problem of control inaccuracy caused by device errors through the double verification of the displayed value and the actual value.

[0058] Through the above technical solution, the present application solves the problem of drilling risk caused by the deviation of control parameter setting in the prior art. By generating a compensation optimization value in real time, it can ensure the accurate matching of control parameters with the actual working conditions. For example, in wellbore pressure control, the application of the compensation optimization value can reduce the pressure fluctuation range to within the safety threshold, thus avoiding hydrate formation or blowout accidents caused by parameter setting errors.

[0059] The process of temperature data acquisition includes: obtaining the temperature and pressure values of each section of the wellbore / pipeline through temperature sensors; the process of fluid data acquisition includes: detecting the gas concentration, water content, and supersaturation in the fluid composition; the process of external data acquisition includes: obtaining the seawater temperature and flow rate in the area where the wellbore is located; specifically, the temperature data acquisition obtains the temperature and pressure distribution of each section of the wellbore through a distributed sensor network to form a thermodynamic state profile; the fluid data acquisition synchronously detects the gas concentration, water content, and supersaturation in the fluid through multiple types of sensors to reflect the phase stability of the fluid inside the wellbore in real time; the external data acquisition obtains the seawater temperature and flow rate around the wellbore through marine environment monitoring equipment to evaluate the impact of the external environment on the wellbore heat exchange. The above three types of data are integrated and input into the LSTM neural network model, and a dynamic prediction model of the hydrate generation critical point is established through temporal feature learning. When the real-time parameters reach the critical point threshold, the system triggers the decision-making logic for the injection time of the protective fluid and dynamically adjusts the concentration and injection volume of the protective fluid according to the fluid composition and environmental parameters.

[0060] The specific process of the protection optimization module for optimizing the analysis of the protective fluid injection process of the subsea drilling equipment includes generating an optimization conversion ratio. After the subsequent LSTM neural network model outputs the critical point threshold, the product of the critical point threshold and the optimization conversion ratio is marked as the critical point optimization value, and the real-time parameters of the current working condition of the wellbore are compared with the critical point optimization value to mark the subsequent injection time. The generation process of the optimization conversion ratio includes marking the time difference between the effective time after adjusting the protective fluid concentration and injection volume and the injection time as the time difference value, marking the injection optimization time, the injection optimization time is before the injection time and the time difference with the injection time is also the time difference value, and marking the ratio of the real-time parameters at the injection optimization time to the critical point threshold as the optimization conversion ratio.

[0061] Among them, the optimization conversion ratio refers to the adjustment coefficient established through the dynamic relationship between the historical adjustment effective time difference and the critical point threshold. Specifically, it can be achieved by calculating the ratio of the time difference value to the real-time parameter, and is used to introduce a dynamic correction factor based on the critical point threshold. The optimized critical point value refers to the adjustment result of the original critical point threshold based on the optimization conversion ratio, and can be specifically achieved through multiplication operations, and is used to trigger the protective liquid injection action in advance. The optimized injection time refers to the starting time point of the protective liquid injection preset according to the effective time difference, and can be specifically achieved through the calculation of advancing the time difference value, and is used to reserve the response period required for the protective liquid to take effect.

[0062] Specifically, when the LSTM neural network model outputs the hydrate formation critical point threshold, the optimization conversion ratio is dynamically calculated and applied to generate the optimized critical point value. The real-time wellbore parameters are continuously compared with the optimized critical point value. If the real-time parameter reaches this optimized value, the injection time mark is triggered. At this time, the protective liquid injection action is advanced to be executed at the optimized injection time, so that the protective liquid completes the adjustment of the concentration and injection volume before the actual critical condition is reached, thereby avoiding the risk of hydrate formation caused by the delay in taking effect.

[0063] The generation process of the optimization conversion ratio includes marking the time difference value as the time difference between the effective time after the adjustment of the protective liquid concentration and injection volume and the injection time, marking the optimized injection time, where the optimized injection time is before the injection time and the time difference from the injection time is also the time difference value, and marking the ratio of the real-time parameter at the optimized injection time to the critical point threshold as the optimization conversion ratio.

[0064] Among them, the time difference value refers to the time interval required for the adjustment operation of the protective liquid concentration or injection volume to take effect from the execution. Specifically, it can be achieved by using the timer module to record the time difference between the execution time of the adjustment instruction and the stable time of the sensor feedback parameter. This feature is used to quantify the response delay characteristics of the protective liquid adjustment operation.

[0065] Among them, the optimized injection time refers to the optimal starting time point of the protective liquid adjustment operation calculated based on the time difference value. Specifically, it can be determined by advancing the time difference period based on the injection time. This feature is used to establish a dynamic time correlation between the protective liquid adjustment operation and the critical point threshold.

[0066] Among them, the optimization conversion ratio refers to the dynamic proportional coefficient between the real-time working condition parameters at the optimized injection time and the critical point threshold. Specifically, it can be achieved by performing ratio operations on the wellbore temperature and pressure data collected in real time and the critical point threshold output by the LSTM model. This feature is used to construct a dynamic matching mechanism between the protective liquid injection timing and the change of working condition parameters.

[0067] Specifically, during the optimization of the injection of the protective fluid, first, the time difference from the execution to the effectiveness of the operation of adjusting the concentration or injection volume of the protective fluid is recorded as the time difference value through historical data. After the LSTM neural network model outputs the critical point threshold of the current working condition, the system automatically advances the injection moment by the time length of the time difference value, which is marked as the injection optimization moment when the operation of adjusting the protective fluid needs to be started. At this time, by collecting the wellbore temperature and pressure parameters at the injection optimization moment in real time, a ratio operation is performed with the critical point threshold to generate an optimization conversion ratio. This conversion ratio is applied to the dynamic correction of the subsequent critical point threshold, so that the operation of adjusting the protective fluid can complete the preparation for taking effect in advance before the actual working condition reaches the critical point threshold.

[0068] Embodiment 2: As Figure 2 shown, the intelligent control method for ocean fine pressure control drilling based on AI technology includes the following steps:

[0069] Step 1: Conduct parameter control analysis on subsea drilling equipment: A control group is composed of a control object i and the corresponding monitoring object e. The variance of the set values SZie of all monitoring objects e corresponding to the control object i in the control group is calculated to obtain a deviation coefficient, and the value of the control object i is controlled through the deviation coefficient;

[0070] Step 2: Conduct calibration compensation control analysis on subsea drilling equipment: The compensation optimization value is obtained from the displayed value and the actual value of the control object, and the parameter setting of the control object i is performed through the compensation optimization value;

[0071] Step 3: Conduct adjustment analysis on the hydrate formation critical point of subsea drilling equipment: Temperature data collection, fluid data collection, and external data collection are carried out on subsea drilling equipment. The collected temperature data, fluid data, and external data are input into the LSTM neural network model for hydrate formation critical point analysis to obtain the critical point threshold; the injection moment is marked through the critical point threshold;

[0072] Step 4: Conduct optimization analysis on the injection process of the protective fluid for subsea drilling equipment: The time difference between the effective moment after adjusting the concentration and injection volume of the protective fluid and the injection moment is marked as the time difference value, and the critical point optimization value is marked through the time difference value.

[0073] The intelligent control system for ocean fine pressure control drilling based on AI technology, when working,

[0074] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the structure of the invention or exceed the scope defined by this claim book, they should all fall within the protection scope of the present invention.

[0075] In the description of this specification, the descriptions referring to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0076] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific embodiments. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An intelligent control system for ocean fine pressure control drilling based on AI technology, characterized in that, It includes a parameter control module, a compensation control module, a protection adjustment module, and a protection optimization module connected in sequence; The parameter control module is used to perform parameter control analysis on the subsea drilling equipment: generate several control groups and calculate the deviation coefficients of the control groups, mark the set optimization values through the deviation coefficients; send the set optimization values to the compensation control module; The compensation control module is used to perform calibration compensation control analysis on the subsea drilling equipment: before controlling the control parameters, generate compensation optimization values through the set optimization values, and perform numerical setting on the control parameters through the compensation optimization values; The protection adjustment module is used to perform adjustment analysis on the hydrate formation critical point of the subsea drilling equipment: collect temperature data, fluid data, and external data of the subsea drilling equipment, input the collected temperature data, fluid data, and external data into the LSTM neural network model for hydrate formation critical point analysis and obtain the critical point threshold; If the real-time parameters under the current wellbore condition reach the critical point threshold, mark the current moment as the injection moment, and adjust the protection liquid concentration and injection volume at the injection moment; The protection optimization module is used to perform optimization analysis on the protection liquid injection process of the subsea drilling equipment.

2. The intelligent control system for ocean fine pressure-controlled drilling based on AI technology according to claim 1, wherein The generation process of the control group includes: marking the control parameters of the subsea drilling equipment as the control object i, i = 1, 2,..., n, where n is a positive integer, and marking the environmental parameters of the offshore drilling as the monitoring object e, e = 1, 2,..., m, where m is a positive integer; each control object i corresponds to one or more monitoring objects e, and a control group is formed by the control object i and the corresponding monitoring object e.

3. The intelligent control system for marine fine pressure-controlled drilling based on AI technology according to claim 2, characterized in that, The process of obtaining the deviation coefficient of the control group includes: arranging the monitoring objects e in the control group in the order of decreasing response priority to obtain a priority sequence, analyzing the set value SZie of the control object i based on the real-time monitoring values of the monitoring objects e, and then calculating the variance of the set values SZie of all the monitoring objects e corresponding to the control object i to obtain the deviation coefficient.

4. The intelligent control system for ocean fine pressure control drilling based on AI technology according to claim 3, wherein The specific process of marking the set optimization value includes: comparing the deviation coefficient with the preset deviation threshold: if the deviation coefficient is less than the deviation threshold, sum and average all the set values SZie to obtain the set optimization value; if the deviation coefficient is greater than or equal to the deviation threshold, set the set values SZie as the set optimization value in the order of the priority sequence, and the set value SZie with a later ranking needs to be set after the previous monitoring object e is stable.

5. The intelligent control system for ocean fine managed pressure drilling based on AI technology according to claim 4, characterized in that, The generation process of the compensation optimization value includes: obtaining the displayed value and the actual value of the control object i, marking the difference between the displayed value and the actual value as the compensation value of the control object i, and marking the sum of the set optimization value and the compensation value of the control object i as the compensation optimization value of the control object i.

6. The intelligent control system for ocean fine pressure control drilling based on AI technology according to claim 5, characterized in that, The process of temperature data collection includes: obtaining the temperature and pressure values of each section of the wellbore / pipeline through temperature sensors; the process of fluid data collection includes: detecting the gas concentration, water content, and supersaturation in the fluid composition; the process of external data collection includes: obtaining the seawater temperature and flow rate in the area where the wellbore is located.

7. The intelligent control system for marine fine pressure control drilling based on AI technology according to claim 6, characterized in that, The specific process of the protection optimization module for optimizing the analysis of the protection liquid injection process of subsea drilling equipment includes: generating an optimization conversion ratio. After the critical point threshold is output by the subsequent LSTM neural network model, the product of the critical point threshold and the optimization conversion ratio is marked as the critical point optimization value, and the real-time parameters of the current wellbore working condition are compared with the critical point optimization value and the subsequent injection moments are marked.

8. The intelligent control system for ocean fine pressure control drilling based on AI technology according to claim 7, characterized in that, The generation process of the optimization conversion ratio includes: marking the time difference between the effective moment after adjusting the protection liquid concentration and injection volume and the injection moment as the time difference value, marking the injection optimization moment, where the injection optimization moment is before the injection moment and the time difference from the injection moment is also the time difference value, and marking the ratio of the real-time parameters of the injection optimization moment to the critical point threshold as the optimization conversion ratio.

Images