Automatic drilling system for sea area exploration

Abstract

The invention relates to the technical field of sea area drilling, in particular to an automatic drilling system for sea area exploration. The data analysis module is used for determining a drilling parameter correction type based on whether the real-time drilling parameters are abnormally changed or not and whether the stability parameters of the real-time drilling platform meet the vibration conditions of the drilling platform or not; the drilling parameter correction module comprises a real-time correction unit and a delay correction starting unit; the real-time correction unit is used for correcting the drilling parameters in real time based on the real-time drilling parameter deviation value or predicting the stability degree of the drilling platform after a first preset duration; the delay correction starting unit is used for correcting the drilling parameters in a delay manner or stopping drilling; the delay correction module is used for determining a prediction opening threshold value for performing drilling parameter delay correction or correcting the stability degree of the drilling platform by using a trend pre-judgment correction method based on whether the stability degree of the drilling platform is a regular change or not; the stability of the drilling platform and the drilling parameters are comprehensively analyzed, and the drilling parameters are corrected to improve the drilling precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sea drilling, and in particular to an automatic drilling system for sea exploration. BACKGROUND

[0002] Traditional sea drilling technology has many obvious limitations when facing complex marine environments. The complexity of the marine environment is reflected in many aspects, such as sea waves, ocean currents, tides and other factors, which can cause the drilling platform to be in a state of continuous vibration. This not only seriously affects the positioning accuracy of the drilling equipment, but also greatly increases the difficulty of parameter control during drilling. When the vibration amplitude of the platform is too large, the drilling equipment may deviate from its position, causing the drill bit to deviate from the predetermined trajectory, thereby affecting the quality of core sampling and the accuracy of the judgment of the underground geological structure. In addition, the properties of different sea areas are very different, and the traditional drilling equipment may not be able to adjust the drilling parameters in time, resulting in excessive wear of the drill bit and low drilling efficiency.

[0003] However, the prior art has the problem of low drilling precision and efficiency due to the lack of analysis of the influence of drilling geology and drilling platform stability on drilling working parameters during sea drilling. SUMMARY

[0004] To this end, the present application provides an automatic drilling system for sea exploration, which overcomes the problem of low drilling precision and efficiency due to the lack of analysis of the influence of drilling geology and drilling platform stability on drilling working parameters during sea drilling in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides an automatic drilling system for sea exploration, comprising:

[0006] a data acquisition module for acquiring real-time cuttings return data, real-time drilling parameter data and real-time drilling platform stability parameter data;

[0007] a data analysis module connected to the data acquisition module, for determining the drilling parameter correction type based on whether the real-time drilling parameters have abnormal changes and whether the real-time drilling platform stability parameters meet the drilling platform vibration conditions;

[0008] a drilling parameter correction module connected to the data analysis module, comprising,

[0009] a real-time correction unit for determining real-time correction of drilling parameters based on real-time drilling parameter deviation values or predicting the stability of the drilling platform after a first predetermined time based on the drilling parameter correction type;

[0010] a delay correction starting unit, connected with the real-time correction unit, configured to determine to correct the drilling parameter in delay or stop drilling based on a predicted stability degree of the drilling platform after a first preset time length;

[0011] a delay correction module, connected with the drilling parameter correction module, configured to determine to correct the drilling parameter in delay by a trend prediction correction method or correct a predicted starting threshold of the stability degree of the drilling platform based on whether the stability degree of the drilling platform is changing regularly;

[0012] an adjusting module, connected with the drilling parameter correction module and the delay correction module respectively, configured to determine whether to calibrate the detection sensor of the stability degree of the drilling platform based on whether the drilling parameter corrected in delay is corrected at least twice within a second preset time length after the drilling parameter is corrected in delay.

[0013] Further, the data analysis module determines the drilling parameter correction type based on whether the real-time drilling parameter changes abnormally and whether the real-time drilling platform stability parameter meets the drilling platform vibration condition, wherein,

[0014] if the real-time drilling parameter changes abnormally and the real-time drilling platform stability parameter does not meet the drilling platform vibration condition, the data analysis module determines that the drilling parameter correction type is the real-time correction type;

[0015] if the real-time drilling parameter changes abnormally and the real-time drilling platform stability parameter meets the drilling platform vibration condition, the data analysis module determines that the drilling parameter correction type is the delay correction type.

[0016] Further, the data analysis module determines that the real-time drilling parameter changes abnormally based on a comparison result that the change rate of at least two real-time drilling parameters is greater than a corresponding preset change rate, and determines that the real-time drilling platform stability parameter meets the drilling platform vibration condition based on that the real-time drilling platform stability degree is greater than a first preset stability degree and the difference between the real-time drilling platform stability degree and the last drilling platform stability degree is positive.

[0017] Further, the data analysis module calculates the stability degree of the drilling platform based on the vibration frequency and the maximum inclination angle of the drilling platform.

[0018] Further, the real-time correction unit determines to correct the drilling parameter in real time based on the real-time drilling parameter deviation value or predicts the stability degree of the drilling platform after a first preset time length based on the drilling parameter correction type, wherein,

[0019] if the drilling parameter correction type is the real-time correction type, the real-time correction unit determines to correct the drilling parameter in real time based on the real-time drilling parameter deviation value;

[0020] If the drilling parameter correction type is a delay correction type, the real-time correction unit determines a stability degree of the drilling platform after a first preset time period.

[0021] Further, the delay correction starting unit determines to correct the drilling parameter by delay or to stop drilling based on the predicted stability degree of the drilling platform after the first preset time period, wherein,

[0022] If the predicted stability degree of the drilling platform after the first preset time period is less than or equal to a preset predicted stability degree, the delay correction starting unit determines to correct the drilling parameter by delay.

[0023] If the predicted stability degree of the drilling platform after the first preset time period is greater than the preset predicted stability degree, the delay correction starting unit determines to stop drilling.

[0024] Further, the delay correction module determines to correct the drilling parameter by delay with a trend prediction correction method or to correct a prediction starting threshold of the stability degree of the drilling platform based on whether the stability degree of the drilling platform is regular change, wherein,

[0025] If the stability degree of the drilling platform is regular change, the delay correction module determines to correct the drilling parameter by delay with the trend prediction correction method.

[0026] If the stability degree of the drilling platform is irregular change, the delay correction module determines to correct the prediction starting threshold of the stability degree of the drilling platform.

[0027] The prediction starting threshold is a first preset stability degree.

[0028] Further, the delay correction module determines that the stability degree of the drilling platform is regular change based on a comparison result that a variance of the stability degree of the drilling platform in a plurality of continuous periods is less than a preset variance.

[0029] Further, a correction amount of the first preset stability degree is positively correlated with the variance of the stability degree of the drilling platform in the plurality of continuous periods.

[0030] Further, the adjustment module determines whether to calibrate a detection sensor of the stability parameter of the drilling platform based on whether at least two times of delay correction are performed within a second preset time period after the drilling parameter is corrected by delay, wherein,

[0031] If at least two times of delay correction are performed within the second preset time period after the drilling parameter is corrected by delay, the adjustment module determines to calibrate the detection sensor of the stability parameter of the drilling platform.

[0032] Compared with the prior art, the beneficial effects of the present application are that the present application clearly divides two types of scenes of real-time correction and delayed correction based on the combination logic of real-time drilling parameter anomaly and platform vibration condition, avoids the safety hazards caused by improper correction from the root, triggers real-time correction when the parameter is abnormal but the platform is not vibrating, quickly responds to parameter problems such as stratum mutation, avoids abnormal expansion, and at the same time, because the platform is stable, the correction operation will not aggravate the equipment or structural burden; when the platform meets the vibration condition, delayed correction is triggered, considering the time delay from detecting that the platform is vibrating to adjusting the drilling parameter, the delayed correction can synchronize the actual vibration state of the platform and the adjustment of the drilling parameter; only when the change rate of at least two real-time drilling parameters is greater than the corresponding preset change rate, the abnormality is determined, avoiding that the normal fluctuation of a single parameter is misjudged as abnormality, and reducing invalid correction; accurate abnormality judgment and reasonable correction type selection can maximize drilling efficiency on the premise of safety, indirectly reduce engineering cost, avoid unnecessary downtime caused by misjudgment of abnormality, or fault downtime caused by missed judgment of abnormality.

[0033] Further, the real-time correction unit of the present application dynamically selects the correction operation based on the correction type, realizes accurate matching of the correction strategy and the operation scene, directly starts the parameter correction process for the real-time correction type, quickly responds to problems such as stratum mutation, and avoids abnormal accumulation; for the delayed correction type, the future stability is predicted in priority, if the stability is insufficient to support the correction of the drilling parameter, the platform needs to be stable before correction, avoiding that forcibly adjusting the parameter when vibrating aggravates the structural risk, if the stability is sufficient to support the correction of the drilling parameter, the delayed correction can synchronize the actual vibration state of the drilling platform and the correction of the drilling parameter, improving the drilling precision, ensuring quick response when there is no risk, and eliminating blind operation when there is high risk, so that the correction action always matches the safe operation state; combining feedback control (PID / PI) and feedforward compensation avoids the hysteresis problem of traditional single feedback control, after combining the two, the original correction instruction can eliminate the current deviation and avoid future risks in advance, greatly reducing the duration of parameter fluctuation.

[0034] Further, the present application predicts the stability degree of the drilling platform after a first preset time period instead of relying on the current state. When the predicted stability degree is greater than a preset predicted stability degree, the drilling is directly stopped, meaning that the system predicts that the platform will break through the safe and stable threshold within a future time period. At this time, the drilling is stopped in advance, which can cut off the additional load of the drilling operation on the platform before the risk actually occurs. If the platform is still unstable in the future, forced correction may cause additional stress on the platform due to parameter adjustment, further amplifying the inclination or vibration. Through accurate prediction of the stability degree, the correction time is accurately selected. When the predicted stability degree is less than or equal to the preset predicted stability degree, the drilling parameter is corrected with a delay, which can solve the parameter abnormalities accumulated in the early stage through parameter adjustment, and can also synchronize the actual vibration state of the drilling platform with the drilling parameter adjustment, improving the drilling accuracy. Through accurate prediction and hierarchical decision-making, the balance between safety and efficiency is achieved. The drilling is stopped only when the predicted stability degree exceeds the safety value, avoiding the over-conservatism of stopping the drilling due to slight vibration, and cutting off the operation only when there is a real structural risk. The delay correction is performed when the stability is predicted, which avoids the risk of immediate correction and does not cause footage loss due to stopping the drilling.

[0035] Further, the present application divides the fluctuation nature of the stability degree of the drilling platform into two categories: regular changes (such as periodic vibration caused by sea waves and tides, with fixed period and amplitude) and irregular changes (such as irregular vibration caused by sudden gusts and transient equipment failures, without fixed pattern). For regular changes, the trend prediction correction method is used. By extracting the dominant period, separating the trend item and the period item, and predicting the future fluctuation curve, the correction amount is applied in advance, so that the correction effect is synchronized with the fluctuation peak, solving the problem of lagging correction after the fluctuation occurs. For irregular changes, the prediction threshold is adjusted. Irregular fluctuations usually mean that the current environment or equipment state has changed suddenly. The original threshold may not be suitable (such as frequent false triggering of correction according to the original threshold). At this time, the threshold is adjusted to adapt the new fluctuation characteristics, which can accurately control predictable regular fluctuations and flexibly respond to unpredictable sudden fluctuations, greatly improving the correction adaptability in complex environments. The system can still make reliable judgments when sudden disturbances occur, greatly improving the robustness. The trend prediction correction method can offset the fluctuation impact through early correction without interrupting the operation, avoiding footage loss due to waiting for the fluctuation to subside. The dynamic correction threshold can reduce false triggering of correction and reduce the impact of frequent parameter adjustment on drilling efficiency. The two modes work together to ensure platform stability and reduce invalid operations, achieving double optimization of safety and efficiency.

[0036] Further, the adjustment module of the present application triggers sensor calibration based on correction frequency, and timely discovers correction failure caused by data distortion, guarantees decision reliability from the source, and the stability parameters of the drilling platform depend on sensor collection, and the sensor is easily affected by salt spray corrosion, vibration interference and electromagnetic interference in the sea environment, leading to data drift, data distortion will cause repeated correction of the system but cannot solve the problem, the traditional system lacks real-time monitoring of the reliability of the sensor, the adjustment module of the present application reverses the data reliability through the correction frequency, realizes the early warning of sensor calibration, if at least two times of delay correction occur within the second preset time period after delay correction, it is indicated that the correction does not achieve the expected effect, and calibration is directly triggered, at this time the adjustment module determines that the sensor may be misaligned, and starts the calibration process (such as comparison with the standby sensor, zero point calibration), and eliminates the influence of data distortion. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 FIG. 1 is a structural schematic diagram of an automatic drilling system for sea exploration of the present application;

[0038] Figure 2 FIG. 2 is a structural schematic diagram of a drilling parameter correction module in the automatic drilling system for sea exploration of the present application;

[0039] Figure 3 FIG. 3 is a work flow diagram of a data analysis module in the automatic drilling system for sea exploration of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose and advantages of the present application clearer and more apparent, the present application will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0041] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0042] In addition, it should be further pointed out that in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection" and "connection" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integrally connected; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or the communication inside two elements. Those skilled in the art can understand the specific meaning of the above terms in the present application according to the specific circumstances.

[0043] Please refer to Figures 1-3 as shown, Figure 1 FIG. 1 is a structural schematic diagram of an automatic drilling system for sea exploration of the present application;Figure 2 It is a structural schematic view of a drilling parameter correction module in an automatic drilling system for sea area exploration of the present application; Figure 3 It is a working flow chart of a data analysis module in an automatic drilling system for sea area exploration of the present application.

[0044] An automatic drilling system for sea area exploration of an embodiment of the present application comprises:

[0045] A data acquisition module is used to acquire real-time cuttings return data, real-time drilling parameter data and real-time drilling platform stability parameter data;

[0046] A data analysis module is connected with the data acquisition module and is used to determine a drilling parameter correction type based on whether real-time drilling parameters have abnormal changes and whether real-time drilling platform stability parameters meet drilling platform vibration conditions;

[0047] A drilling parameter correction module is connected with the data analysis module and comprises,

[0048] A real-time correction unit is used to determine real-time correction of drilling parameters based on real-time drilling parameter deviation values or prediction of the stability degree of the drilling platform after a first preset time length based on the drilling parameter correction type;

[0049] A delay correction opening unit is connected with the real-time correction unit and is used to determine delay correction of drilling parameters or stopping of drilling based on the predicted stability degree of the drilling platform after the first preset time length;

[0050] A delay correction module is connected with the drilling parameter correction module and is used to determine whether to perform drilling parameter delay correction by trend prediction correction method or to open the prediction threshold of correction of the stability degree of the drilling platform based on whether the stability degree of the drilling platform is regular change;

[0051] An adjustment module is connected with the drilling parameter correction module and the delay correction module respectively and is used to determine whether to calibrate the detection sensor of the stability degree of the drilling platform based on whether the detection sensor of the stability degree of the drilling platform is performed at least twice within a second preset time length after delay correction of drilling parameters.

[0052] In the embodiment of the present application, the real-time cuttings return data includes but is not limited to "cuttings lithology data, cuttings particle size data and cuttings weight data"; the real-time drilling parameter data includes but is not limited to "real-time drilling pressure data, real-time drilling rotation speed data and real-time torque data"; and the real-time drilling platform stability parameter data includes but is not limited to "real-time drilling platform three-dimensional vibration data, real-time drilling platform inclination angle data and platform displacement deviation data".

[0053] Specifically, the data analysis module determines the drilling parameter correction type based on whether the real-time drilling parameter has an abnormal change and whether the real-time drilling platform stability parameter meets the drilling platform vibration condition, wherein,

[0054] If the real-time drilling parameter has an abnormal change and the real-time drilling platform stability parameter does not meet the drilling platform vibration condition, the data analysis module determines that the drilling parameter correction type is a real-time correction type.

[0055] If the real-time drilling parameter has an abnormal change and the real-time drilling platform stability parameter meets the drilling platform vibration condition, the data analysis module determines that the drilling parameter correction type is a delayed correction type.

[0056] If the real-time drilling parameter does not have an abnormal change, the data analysis module determines that the drilling parameter does not need to be corrected.

[0057] Specifically, the data analysis module determines that the real-time drilling parameter has an abnormal change based on a comparison result that the change rate of at least two real-time drilling parameters is greater than a corresponding preset change rate, and determines that the real-time drilling platform stability parameter meets the drilling platform vibration condition based on the real-time drilling platform stability degree being greater than a first preset stability degree and the difference between the real-time drilling platform stability degree and the last drilling platform stability degree being positive.

[0058] Specifically, the data analysis module calculates the stability degree of the drilling platform based on the vibration frequency and the maximum inclination angle of the drilling platform.

[0059] The corresponding preset change rate in the embodiment of the application is the average value of the real-time drilling parameter change rate corresponding to the stratigraphic mutation occurring several times under the same drilling conditions (including but not limited to "the same drilling tool, the same geological parameters, and the same drilling tool working mode"); the first preset stability degree is the average value of the stability degree when the drilling platform is unstable and the drilling parameter needs to be adjusted several times under the same drilling conditions (not more than the safe and stable degree of the drilling platform, if more than that, stop drilling directly), for example, from the drilling log of the project in the past year, 12 historical cases that meet the conditions are selected, the vibration frequency and the maximum inclination angle of each case are recorded, and the corresponding stability degree is calculated, and the average value is taken as the first preset stability degree, the stability degree is the sum of the ratio of the vibration frequency to the preset vibration frequency and the ratio of the maximum inclination angle to the preset inclination angle, the preset vibration frequency is the maximum vibration frequency allowed by the drilling platform (the first several natural frequencies of the drilling platform are obtained by modal analysis (such as the overall swing frequency of the platform, the torsional frequency, the local structure vibration frequency), the maximum allowable vibration frequency (f_max) must be far away from any one order natural frequency of the platform to prevent resonance amplification effect from causing structural damage, the requirement should not be within ±10%-15% of the natural frequency, finally f_max should be less than the lowest one order natural frequency, or greater than the highest one order natural frequency), the preset inclination angle is the maximum inclination angle allowed by the drilling platform (the precise model of the drilling platform is established by finite element analysis (FEA), the stress of the key support structure (such as the leg, the locking device, the deck girder) gradually increases with the increase of the inclination angle under the action of the maximum design load, when the maximum equivalent stress (such as Von Mises stress) of the key part reaches 2 / 3 of the yield strength of the platform structure steel material (i.e. the safety factor is 1.5) when the platform is inclined to a certain angle, the angle is the maximum allowable inclination angle based on the structural integrity), the maximum inclination angle is the maximum angle deviation value generated in the three-dimensional space when the drilling platform (such as the land drilling rig base, the offshore drilling platform deck, and the main structure bearing the drilling equipment) is inclined relative to the horizontal plane during real-time drilling operation, but the above values are not limited thereto, and those skilled in the art can adjust them according to the actual situation.

[0060] The present application is based on the combination logic of real-time drilling parameter anomaly and platform vibration condition, which clearly divides two types of scenes of real-time correction and delayed correction, and avoids the safety hazards caused by improper correction from the root. When the parameter is abnormal but the platform is not vibrating, real-time correction is triggered to quickly respond to parameter problems such as sudden changes in the formation, avoid abnormal expansion, and at the same time, because the platform is stable, the correction operation will not aggravate the equipment or structural burden; when the platform meets the vibration condition, delayed correction is triggered, considering the time delay from detecting that the platform is vibrating to adjusting the drilling parameters, the delayed correction can synchronize the actual vibration state of the platform with the adjustment of the drilling parameters; only when the change rate of at least two real-time drilling parameters is greater than the corresponding preset change rate, the abnormality is determined, avoiding the normal fluctuation of a single parameter being misjudged as abnormal and reducing invalid correction; accurate abnormality judgment and reasonable correction type selection can maximize drilling efficiency under the premise of safety, indirectly reduce engineering cost, avoid unnecessary downtime caused by misjudgment of abnormality, or fault downtime caused by missed abnormality.

[0061] Specifically, the real-time correction unit determines to correct the drilling parameter based on the real-time drilling parameter deviation value in real time or to predict the stability of the drilling platform after a first preset time length based on the drilling parameter correction type,

[0062] If the drilling parameter correction type is a real-time correction type, the real-time correction unit determines to correct the drilling parameter based on the real-time drilling parameter deviation value in real time;

[0063] If the drilling parameter correction type is a delayed correction type, the real-time correction unit determines to predict the stability of the drilling platform after a first preset time length.

[0064] In the embodiment of the present application, the real-time correction unit determines to correct the drilling parameter based on the real-time drilling parameter deviation value in real time, which includes calculating the real-time drilling parameter deviation value, which is the weighted sum of the deviation values of the change rates of the real-time drilling parameters that have abnormally changed from their corresponding preset change rates after standardization processing, based on the above calculated comprehensive real-time drilling parameter deviation value, using proportional-integral (PI) or proportional-integral-derivative (PID) algorithm to generate a basic correction amount (such as a drilling pressure adjustment amount, a rotation speed adjustment amount); based on the comprehensive deviation value and the cuttings return data prediction, an original correction instruction containing feedback and feedforward compensation is generated; and after rate limiting and amplitude limiting of the original correction instruction, the final safety correction instruction is output to the drilling execution mechanism to complete the real-time correction; the first preset time length (T_pre) refers to the time span of the system predicting the future platform state, and its value should be greater than the total time (T_response) required for the drilling parameter adjustment instruction to fully appear at the downhole bit, T_response mainly includes the execution mechanism action time and the downhole drilling tool response time.

[0065] The real-time correction unit extracts the parameters that have abnormal changes, i.e., the WOB and the torque. The deviation of the change rate of each parameter is calculated, i.e., the WOB change rate deviation ΔV_wob=|ΔWOB / Δt|-V_wob_preset=1.2-0.5=0.7 kN / s, and the torque change rate deviation ΔV_torque=|ΔTorque / Δt|-V_torque_preset=0.17-0.1=0.07 kN·m / s. The deviations are normalized (for example, divided by the respective preset change rate), the normalized WOB deviation ΔV_wob_norm=0.7 / 0.5=1.4, and the normalized torque deviation ΔV_torque_norm=0.07 / 0.1=0.7. Dynamic weight distribution is performed. Since the cuttings data simultaneously indicate that the formation is becoming harder (the sand content is increasing), the system automatically assigns a higher weight (for example, 0.7, which can be determined by a regression model trained by historical data) to the WOB deviation, because the WOB is the most direct parameter for responding to the change in formation hardness. The weight of the torque is correspondingly reduced (for example, 0.3). The weighted sum is calculated to obtain the comprehensive real-time drilling parameter deviation value (B), i.e., B=(0.7*1.4)+(0.3*0.7)=0.98+0.21=1.19. An original correction instruction is generated, and feedback control (PID algorithm) is performed, with the comprehensive deviation value B=1.19 as the input of the PID controller. After algorithm calculation (assuming that the integral term and the differential term are calculated in this period), a basic WOB increase instruction is output, for example: ΔWOB_feedback=+25 kN. Feedforward control (based on cuttings prediction) is performed. The cuttings data (increased particle size and hardened lithology) are strong precursors that the formation will become harder. According to the historical data model, the feedforward control unit predicts that if no intervention is made, the torque will continue to rise and the drilling speed will decrease. Therefore, a feedforward compensation amount is generated, i.e., a stronger WOB increase instruction and a preemptive RPM fine-tuning instruction, for example: ΔWOB_feedforward=+15 kN, ΔRPM_feedforward=+5 RPM (slightly increase the RPM to help break harder rocks). The original correction instruction is synthesized, and the final WOB adjustment amount ΔWOB_total=ΔWOB_feedback+ΔWOB_feedforward=+40 kN and the final RPM adjustment amount ΔRPM_total=ΔRPM_feedforward=+5 RPM are obtained. The torque is not directly controlled, but is indirectly managed by adjusting the WOB and the RPM. The maximum allowed single adjustment amount of the WOB is 50 kN, and +40 kN is within the allowed range. The RPM adjustment +5 RPM is also within the safe range. The WOB change rate needs to be less than 5 kN / s. Assuming that the control period is 2 seconds, 40 kN / 2 s=20 kN / s, which is far beyond the allowed value. To prevent impact on the equipment, the current instruction is split into four consecutive sub-instructions, each of which is output in a period of 0.5 seconds) output +10kN of WOB adjustment, smoothly reach the target value within 2 seconds; the RPM adjustment is output at one time; the smoothed safety correction instruction (Delta WOB = +10kN / 0.5s, Delta RPM = +5 RPM) is sent to the drilling execution mechanism (WOB servo system and top drive variable frequency system).

[0066] The real-time correction unit of the present application dynamically selects the correction operation based on the correction type, realizes accurate matching of the correction strategy and the operation scene, directly starts the parameter correction process for the real-time correction type, quickly responds to problems such as stratum mutation, and avoids abnormal accumulation; for the delay correction type, the future stability degree is predicted in priority, if the stability degree is not sufficient to support the correction of drilling parameters, the platform needs to be stable before correction, so as to avoid forcibly adjusting parameters to aggravate the structure risk when vibrating, if the stability degree is sufficient to support the correction of drilling parameters, the delay correction can be synchronized with the actual vibration state of the drilling platform and the correction of drilling parameters, thereby improving the drilling precision, ensuring quick response in the risk-free state, eliminating blind operation in the high-risk state, and matching the correction action with the operation safety state at all times; the feedback control (PID / PI) is combined with the feedforward compensation, thereby avoiding the hysteresis problem of the traditional single feedback control, after the combination of the two, the original correction instruction can eliminate the current deviation and avoid future risks in advance, and the duration of parameter fluctuation is greatly reduced.

[0067] Specifically, the delay correction starting unit determines the delay correction drilling parameter or stops drilling based on the predicted stability degree of the drilling platform after the first preset time length.

[0068] If the predicted stability degree of the drilling platform after the first preset time length is less than or equal to the preset predicted stability degree, the delay correction starting unit determines the delay correction drilling parameter.

[0069] If the predicted stability degree of the drilling platform after the first preset time length is greater than the preset predicted stability degree, the delay correction starting unit determines to stop drilling.

[0070] The preset predicted stability degree in the embodiment of the present application is the safety stability degree of the drilling platform, and the value is 2, but the above value is not limited thereto, and a person skilled in the art can adjust it according to the actual situation.

[0071] The stability degree of the drilling platform after the first preset time period in the embodiment of the application comprises pre-off-line calculation and generation of motion response amplitude operator (RAO) database and hydrodynamic coefficient database covering various drafts and load states of the platform using professional hydrodynamic software (such as AQWA and WAMIT); a large amount of historical data (environmental data, platform motion data and vibration data) is collected, and an LSTM or other machine learning prediction model is trained off-line, and after the training is completed, the model is lightened and converted into a format (such as TensorRT and ONNX) suitable for high-speed reasoning; the environmental data and platform state data at the current time are collected; the system does not perform complex CFD or full-time domain simulation. Instead, the RAO under the current working condition is directly interpolated and queried from the pre-generated RAO database, the simplified prediction wave spectrum (regarded as linear superposition of multiple regular waves) is combined with the RAO, and the rigid body motion trend (such as the motion amplitude at the center of gravity) of the platform at the future T_pre time is quickly calculated by linear superposition; the rigid body motion trend predicted by the simplified model, the current platform state and the real-time environmental data are input into the trained lightened LSTM model, the LSTM model is not predicted from zero, but based on the result of the simplified model, an accurate correction is output, which is mainly used to predict the high-frequency vibration and nonlinear response part which the prediction mechanism model is not good at; the prediction result of the simplified mechanism model is fused with the correction output of the data-driven model, and finally the stability degree prediction value at the future T_pre time is obtained, which is high-precision and meets the real-time requirement.

[0072] The application predicts the stability degree of the drilling platform after the first preset time period instead of relying on the current state. When the predicted stability degree is greater than the preset prediction stability degree, the drilling is directly stopped, which means that the system predicts that the platform will break through the safe and stable threshold within a future time period. At this time, the drilling operation is stopped in advance to cut off the additional load of the drilling operation on the platform before the risk actually occurs. If the platform is still unstable in the future, forced correction may cause additional stress on the platform due to parameter adjustment, further amplifying the inclination or vibration. The prediction of the stability degree accurately selects the correction time. When the predicted stability degree is less than or equal to the preset prediction stability degree, the drilling parameter is corrected with a delay, which can solve the parameter abnormalities accumulated in the early stage through parameter adjustment, and can also synchronize the actual vibration state of the drilling platform with the drilling parameter adjustment, improving the drilling precision. The balance between safety and efficiency is achieved through accurate prediction and hierarchical decision-making. The drilling is stopped only when the predicted stability degree exceeds the safety value, avoiding the over-conservatism of stopping the drilling due to slight vibration, and cutting off the operation only when there is a real structural risk. The stability is predicted and the correction is performed with a delay, which avoids the risk of immediate correction and does not cause footage loss due to shutdown.

[0073] Specifically, the delay correction module determines to correct the drilling parameter delay or to correct the prediction opening threshold of the drilling platform stability degree by the trend prediction correction method based on whether the drilling platform stability degree is regular change, wherein,

[0074] If the drilling platform stability degree is regular change, the delay correction module determines to correct the drilling parameter delay by the trend prediction correction method.

[0075] If the drilling platform stability degree is irregular change, the delay correction module determines to correct the prediction opening threshold of the drilling platform stability degree.

[0076] The prediction opening threshold is a first preset stability degree.

[0077] Specifically, the delay correction module determines that the drilling platform stability degree is regular change based on the comparison result that the variance of the drilling platform stability degree in a plurality of continuous periods is less than a preset variance.

[0078] The drilling parameter delay correction in the trend prediction correction method in the embodiment of the application includes: using autocorrelation analysis or fast Fourier transform (FFT) to extract the dominant period (denoted as T cycle) of the stability fluctuation; calculating the autocorrelation function of the real-time data of continuous M periods (M≥5, for example, the sea wave period is usually 8-15 seconds, and 40-75 stable degree data points are collected for 40-75 seconds), and the time difference corresponding to the peak value of the function is the dominant period (for example, the peak value appears at 10 seconds, which indicates that the fluctuation period is 10 seconds); converting the time-domain stability data into a frequency-domain signal, and the frequency reciprocal corresponding to the frequency-domain peak value is the dominant period, which can exclude high-frequency noise interference (such as transient vibration of equipment); using a sliding average method or a polynomial fitting to separate the long-term trend item and the periodic fluctuation item from the original stability data; for example, the stability data of a certain period is S(t)=0.2t+1.5sin(2πt / T cycle)+ε (t is time, 0.2t is the trend item that slowly rises with the tide, 1.5sin(2πt / T cycle) is the periodic fluctuation item, and ε is a small noise); the periodic fluctuation is filtered by a 5-point sliding average to obtain a smooth trend item S_trend(t); the original data is subtracted from the trend item to obtain a pure periodic fluctuation item S_cycle(t); the separated periodic fluctuation item S_cycle(t) is used to calculate key characteristic parameters and store them as a regular fluctuation feature library: the amplitude A is the difference between the maximum value and the minimum value of the fluctuation item (for example, A=3, which indicates that the stability fluctuation amplitude is 3 in the period); the phase shift φ is the time difference between the fluctuation starting point and the standard sinusoidal wave (for example, φ=π / 4, which indicates that the fluctuation peak value appears T cycle / 8 earlier than the standard period); the attenuation coefficient k, if the amplitude slowly decreases with time (for example, the energy of the sea wave decreases), then k is a positive number (for example, k=0.05, indicating that the amplitude is attenuated by 5% per cycle); combined with the quantized fluctuation characteristics, a time series prediction model is used to predict the stability level in the future first preset time + parameter response time (to ensure that the prediction covers the effective period of the correction instruction); according to the linear / nonlinear characteristics of the fluctuation law, an appropriate prediction model is selected, if the fluctuation shows a linear trend + fixed period (such as the stability level change caused by uniform tidal), a seasonal autoregressive integrated moving average model (SARIMA) is used, the dominant period T_cycle is taken as the seasonal parameter, the stability level data of the previous 3 complete periods (including trend items and period items) are input to train the model, and the prediction value S_pred(t) of the future 1-2 periods is output; if the fluctuation shows a nonlinear trend + period change (such as the fluctuation of sea waves with slowly increasing amplitude over time), a long short-term memory network (LSTM) is used, the historical stability level value, the real-time sea wave height and the wind speed are taken as the input features, the model is trained to learn the nonlinear mapping relationship, and the continuous change curve of the stability level in the future period is predicted; in order to reduce the cumulative error, the prediction is updated once every 5 seconds (1 / 5 of the sampling frequency); the actual stability level data of the latest 5 seconds is collected, compared with the prediction value at the same period, and the error ΔS_err = |actual value-prediction value| is calculated; if ΔS_err>10%×target stability level (the target stability level is usually 80% of the first preset stability level, such as the first preset stability level is 5, then the target value is 4), the S_pred(t) of the remaining prediction period is corrected based on the error (such as the error is positive, the subsequent prediction value is uniformly adjusted by 0.8xAS_err, avoid error amplification); according to the predicted stability degree trend, calculate the correction amount to be applied in advance, and accurately control the correction time, ensure that the correction effect is synchronized with the fluctuation peak; set the correction target stability S_target, calculate the deviation of the stability from the target value in the future prediction period, AS(t)=S_pred(t)-S_target; if AS(t)>0, it means that the predicted stability is higher than the target value (platform vibration is intensified, and the drilling pressure / rotation speed needs to be reduced to reduce vibration feedback); if AS(t)<0, it means that the predicted stability is lower than the target value (the platform is too stable, and the drilling pressure / rotation speed can be appropriately increased to improve drilling efficiency); based on historical drilling data, a quantitative mapping relationship between stability deviation and drilling parameter correction amount is established (by multiple linear regression or neural network fitting), drilling pressure correction amount AP=k_PxAS(t), k_P is the drilling pressure sensitivity coefficient (measured by experiment, such as k_P=-6 kN / unit AS, which means that for every increase of 1 in AS, the drilling pressure needs to be reduced by 6 kN); rotation speed correction amount AR=k_RxAS(t): k_R is the rotation speed sensitivity coefficient (such as k_R=-3 r / min / unit AS, which means that for every increase of 1 in AS, the rotation speed needs to be reduced by 3 r / min); torque correction amount AT: indirectly controlled through adjustment of drilling pressure and rotation speed (torque is positively correlated with drilling pressure and rotation speed, and does not need to be calculated directly); considering the physical response time t_response of drilling parameter adjustment (such as drilling pressure adjustment needs to take effect in 10-15 seconds, and rotation speed adjustment needs to take effect in 5-10 seconds), calculate the leading correction time t_lead, t_lead=1.2xt_response (1.2 is a safety factor to ensure that the correction takes effect in advance), for example, if t_response=10 seconds, then t_lead=12 seconds; if the predicted stability reaches the peak value AS=2 at the 30th second, the correction instruction is issued at the 18th second (30-12), and the corrected parameter at the 30th second exactly offsets the fluctuation peak, so that the actual stability is maintained near S_target.

[0079] The preset variance in the embodiment of the application can be determined by the following method: from the historical drilling logs of the same drilling conditions, at least 10 times of stability data verified as regular changes (such as periodic vibration caused by sea waves, and no sudden interference is confirmed afterwards) are screened, the variance of the stability is calculated, and the maximum variance upper limit of the regular fluctuation is determined; for each regular fluctuation case, the stability values of M consecutive cycles (M≥5, such as 40 stability data points for 40 seconds of sea wave cycles of 8 seconds) are collected at a sampling frequency of 1 time / second; the stability variance of each case is calculated according to the statistical variance formula, the variances of all 10 regular cases are counted, and the maximum value among them is taken as the preset variance, but the above value is not limited thereto, and those skilled in the art can adjust it according to the actual situation.

[0080] The application classifies the fluctuation nature of the drilling platform stability into two categories, regular changes (such as periodic vibration caused by sea waves and tides, the fluctuation has a fixed period and amplitude) and irregular changes (such as irregular vibration caused by sudden gusts and transient equipment failure, the fluctuation has no fixed pattern). For regular changes, the trend prediction correction method is used. By using the periodicity of the fluctuation, the dominant period is extracted, the trend item and the periodic item are separated, the future fluctuation curve is predicted, and the correction amount is applied in advance, so that the correction effect is synchronized with the fluctuation peak, and the lag problem of correction after the fluctuation occurs is solved. For irregular changes, the prediction threshold is corrected. Irregular fluctuation usually means that the current environment or equipment state has changed suddenly, and the original threshold may not be suitable (such as frequent false triggering of correction according to the original threshold). At this time, the threshold is adjusted, and the judgment standard is adapted to the new fluctuation characteristics. It can accurately control the predictable regular fluctuation and flexibly cope with unpredictable sudden fluctuation, greatly improving the correction adaptability in complex environment. The system can still make reliable judgments when sudden interference occurs, greatly improving the robustness. The trend prediction correction method can offset the fluctuation influence by early correction without interrupting the operation, and avoid the footage loss caused by waiting for the fluctuation to subside. The dynamic correction threshold can reduce false triggering of correction and reduce the impact of frequent parameter adjustment on drilling efficiency. The two modes cooperate to ensure platform stability and reduce invalid operations, achieving double optimization of safety and efficiency.

[0081] Specifically, the correction amount of the first preset stability degree is positively correlated with the variance of the stability degree of the drilling platform in a plurality of continuous periods.

[0082] In the embodiment of the application, the correction amount of the first preset stability degree is the product of a proportional coefficient and the current first preset stability degree. The proportional coefficient can be determined by the following method. The relative deviation rate of variance (R) is calculated. The relative deviation rate of variance is used to quantify the multiple relationship between the severity of the current irregular fluctuation and the reference level of the historical regular fluctuation. R=(σ_current²-σ_preset²) / σ_preset²; σ_current² represents the variance of the stability degree of the drilling platform calculated in a plurality of continuous periods; σ_preset² represents the preset variance (the upper limit of the variance of the historical regular fluctuation); in order to prevent excessive correction in extreme abnormal conditions, the relative deviation rate R is input into a saturation function (such as a hyperbolic tangent function tanh) for compression processing, which is mapped to the range of (-1, 1) to ensure the stability of the system; the proportional coefficient λ is determined by the saturated relative deviation rate R_saturated and a maximum allowed adjustment amplitude (λ_max); λ=R_saturated*λ_max; λ_max is a pre-set constant, representing the maximum adjustment ratio allowed by a single correction (for example, λ_max=0.2, that is, the current threshold is adjusted by ±20% at most in a single correction). Its specific value is determined by historical data simulation debugging.

[0083] Specifically, the adjustment module determines whether to calibrate the detection sensor of the drilling platform stability parameter based on whether at least two time delay corrections are performed within a second preset time period after the drilling parameter is corrected.

[0084] If at least two time delay corrections are performed within the second preset time period after the drilling parameter is corrected, the adjustment module determines to calibrate the detection sensor of the drilling platform stability parameter.

[0085] In the embodiment of the present application, the second preset time period is the average interval of two time delay corrections under the same drilling condition for several times, but the above value is not limited thereto, and a person skilled in the art can adjust it according to the actual situation.

[0086] The adjustment module of the present application triggers sensor calibration based on correction frequency, discovers correction failure caused by data distortion in time, guarantees decision reliability from the source, and depends on sensor collection for the stability parameter of the drilling platform. In the sea environment, the sensor is easily affected by salt mist corrosion, vibration interference and electromagnetic interference, leading to data drift. Data distortion will cause the system to repeatedly correct but cannot solve the problem. The traditional system lacks real-time monitoring of the reliability of the sensor. The adjustment module of the present application reverses the data reliability through the correction frequency, realizes the early warning of sensor calibration, and if at least two time delay corrections occur within the second preset time period after the time delay correction, it means that the correction does not achieve the expected effect, and directly triggers calibration. At this time, the adjustment module determines that the sensor may be misaligned, starts the calibration process (such as comparison with the standby sensor, zero point calibration), and eliminates the influence of data distortion.

[0087] The technical scheme of the present application has been described in combination with the preferred embodiments shown in the drawings, but a person skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. A person skilled in the art can make equivalent changes or replacements to related technical features without deviating from the principles of the present application, and the technical scheme after the changes or replacements will fall within the protection scope of the present application.

Claims

1. An automated drilling system for marine exploration, characterized in that: include: A data acquisition module is used to collect real-time cuttings return data, real-time drilling parameter data, and real-time drilling platform stability parameter data; a data analysis module connected to the data acquisition module, configured to determine a drilling parameter correction type based on whether abnormal changes occur in the real-time drilling parameters and whether the real-time drilling platform stability parameters meet the drilling platform vibration conditions; A drilling parameter correction module, connected to the data analysis module, includes: A real-time correction unit, configured to determine, based on the drilling parameter correction type, whether to correct the drilling parameter in real time based on the real-time drilling parameter deviation value or to predict the stability of the drilling platform after a first preset time period; a time-delay correction starting unit, connected to the real-time correction unit, for determining a time-delay correction of drilling parameters or stopping drilling based on a predicted stability of the drilling platform after a first preset time period; a delay correction module connected to the drilling parameter correction module, configured to determine, based on whether the stability of the drilling platform changes regularly, whether to perform drilling parameter delay correction using a trend prediction correction method or to correct a predicted threshold for the stability of the drilling platform; An adjustment module is connected to the drilling parameter correction module and the delay correction module respectively, and is used to determine whether to calibrate the detection sensor of the drilling platform stability parameter based on whether at least two delay corrections are performed within a second preset time length after the delay correction of the drilling parameter.

2. The automated drilling system for marine exploration according to claim 1, characterized in that: The data analysis module determines the drilling parameter correction type based on whether the real-time drilling parameters have abnormal changes and whether the real-time drilling platform stability parameters meet the drilling platform vibration conditions, wherein: If the real-time drilling parameters change abnormally and the real-time drilling platform stability parameters do not meet the drilling platform vibration conditions, the data analysis module determines that the drilling parameter correction type is a real-time correction type; If the real-time drilling parameters change abnormally and the real-time drilling platform stability parameters meet the drilling platform vibration condition, the data analysis module determines that the drilling parameter correction type is a delayed correction type.

3. The automated drilling system for marine exploration according to claim 2, characterized in that: The data analysis module determines that an abnormal change has occurred in the real-time drilling parameter based on a comparison result that the change rate of at least two real-time drilling parameters is greater than the corresponding preset change rate. The data analysis module determines that the real-time drilling platform stability parameter meets the drilling platform vibration condition based on the fact that the real-time drilling platform stability is greater than a first preset stability and the difference between the real-time drilling platform stability and the previous drilling platform stability is a positive value.

4. The automated drilling system for marine exploration according to claim 3, characterized in that: The data analysis module calculates the stability of the drilling platform based on the vibration frequency and the maximum inclination angle of the drilling platform.

5. The automated drilling system for marine exploration according to claim 4, characterized in that: The real-time correction unit determines whether to correct the drilling parameters in real time using the real-time drilling parameter deviation value or predict the stability of the drilling platform after a first preset time period based on the drilling parameter correction type, wherein: If the drilling parameter correction type is a real-time correction type, the real-time correction unit determines to correct the drilling parameter in real time based on the real-time drilling parameter deviation value; If the drilling parameter correction type is a delayed correction type, the real-time correction unit determines and predicts the stability of the drilling platform after a first preset time period.

6. The automated drilling system for marine exploration according to claim 5, characterized in that: The delay correction start unit determines the delay correction drilling parameters or stops drilling based on the predicted stability of the drilling platform after the first preset time period, wherein, If the predicted stability of the drilling platform after the first preset time period is less than or equal to the preset predicted stability, the delay correction starting unit determines the delay correction drilling parameters; If the predicted stability of the drilling platform after the first preset time period is greater than the preset predicted stability, the delay correction starting unit determines to stop drilling.

7. The automated drilling system for marine exploration according to claim 6, characterized in that: The delay correction module determines whether the stability of the drilling platform changes regularly by using the trend prediction correction method to perform drilling parameter delay correction or to correct the prediction start threshold of the drilling platform stability, wherein: If the stability of the drilling platform changes regularly, the delay correction module determines to perform drilling parameter delay correction using a trend prediction correction method; If the drilling platform stability changes irregularly, the delay correction module determines a prediction start threshold for correcting the drilling platform stability; The prediction start threshold is a first preset stability level.

8. The automated drilling system for marine exploration according to claim 7, characterized in that: The delay correction module determines that the stability of the drilling platform changes regularly based on a comparison result that the variance of the stability of the drilling platform in several consecutive periods is less than a preset variance.

9. The automated drilling system for marine exploration according to claim 8, characterized in that: The correction amount of the first preset stability level is positively correlated with the variance of the stability level of the drilling platform in a plurality of consecutive cycles.

10. The automated drilling system for marine exploration according to claim 9, characterized in that: The adjustment module determines whether to calibrate the detection sensor of the drilling platform stability parameter based on whether at least two delay corrections are performed within a second preset time period after the delay correction of the drilling parameter, wherein: If at least two delay corrections are performed within a second predetermined time period after the delay correction of the drilling parameters, the adjustment module determines a detection sensor for calibrating the drilling platform stability parameter.

Images