A method and system for adjusting parameters of a geothermal well while drilling

Abstract

The application discloses a geothermal well while-drilling perforating parameter adjustment method and system, and belongs to the technical field of oil and gas exploitation. The method comprises the following steps: acquiring multi-channel real-time data of a drilling tool perforating section to form same-period data; performing noise reduction and completion preprocessing on the same-period data; calculating a confidence weight for each sensing channel; performing weighted fusion on the channel data in combination with the confidence weight; constructing a lithology identification model; constructing a multi-objective optimization function in combination with characteristic parameters; solving the multi-objective optimization function to acquire optimal perforating control parameters, and adjusting a nozzle according to the optimal perforating control parameters. The geothermal well while-drilling perforating parameter adjustment method provided by the application forms a complete intelligent closed-loop control system through real-time acquisition, preprocessing, characteristic calculation, lithology identification, optimization control and execution of multi-channel data. Not only can the efficiency and safety of geothermal well perforating operation be improved, but also complex working conditions under different stratum conditions can be coped with.

Description

Technical Field

[0001] This application belongs to the field of oil and gas extraction technology, and specifically relates to a method and system for adjusting perforation parameters while drilling geothermal wells. Background Technology

[0002] Geothermal well perforation technology is one of the key processes in geothermal resource extraction. It primarily promotes the flow of geothermal fluids and enhances the thermal recovery efficiency of the geothermal system by creating holes in the wellbore. Meanwhile, with the development of sensor technology, Measurement While Drilling (MWD) and Logging While Drilling (LWD) technologies have been widely applied in geothermal well operations. These technologies, by deploying sensors on the drill bit or drill string, collect downhole physical data (such as pressure, temperature, flow rate, vibration acceleration, etc.) in real time, providing a foundation for real-time monitoring and control.

[0003] Although modern geothermal well perforation technology has made progress in some aspects, current perforation parameters often rely on experience or pre-set formation types, lacking a real-time dynamic adjustment mechanism. This makes it impossible to make adaptive adjustments to complex formation environments during actual construction. Furthermore, existing optimization methods mostly focus on single-objective optimization, neglecting the complexity of multi-objective optimization. For example, borehole depth efficiency, borehole wall stability, and heat transfer performance typically need to be considered in optimization, but current technologies struggle to find the optimal balance among multiple objectives.

[0004] Therefore, overcoming the shortcomings of the existing technology is an urgent problem to be solved in this technical field. Summary of the Invention

[0005] To address the above problems, this application provides a method for adjusting perforation parameters while drilling in geothermal wells, comprising the following steps: Periodically acquire multi-channel real-time data of the drill bit perforation section, and unify the multi-channel real-time data into the same sampling period based on depth and time alignment processing to form data of the same period; Noise reduction and completion preprocessing are performed on data from the same period to obtain channel data; Calculate the confidence weight for each sensing channel based on the channel data; The channel data is weighted and fused by combining confidence scores to obtain fused data, and the feature parameters of the fused data are extracted. A lithology identification model is constructed based on characteristic parameters, and the stratigraphic category, estimated values ​​of unmeasurable state variables, and identification uncertainty are output. Based on formation type, estimated values ​​of unmeasurable state variables and identification uncertainty, a multi-objective optimization function for pore depth efficiency, pore wall stability and heat transfer performance is constructed by combining characteristic parameters. The multi-objective optimization function is solved using nonlinear programming to obtain the optimal perforation control parameters, and the nozzle is adjusted based on the optimal perforation control parameters.

[0006] Furthermore, the multi-channel real-time data includes bottom hole pressure, annular pressure, bottom hole temperature, drilling fluid flow rate, vibration acceleration, logging-while-drilling parameters, and microseismic signals from multiple channels.

[0007] Furthermore, the noise reduction and completion preprocessing includes: Denoising and filtering processes are applied to multi-channel real-time data, as well as anomaly detection and removal, to obtain stable data. A state estimation method is used to predict and complete missing data in stationary data, and the channel data is output after noise reduction and completion preprocessing.

[0008] Furthermore, the formula for calculating the confidence weight is:

[0009] Where, σ i Let S be the standard deviation of the channel, f be the normalized composite scoring function, and S be the standard deviation of the channel. i T represents the stability index. i C represents the temperature drift compensation result. i Redundant channel consistency, w i This indicates the confidence weight.

[0010] Furthermore, the calculation formula for fused data is as follows:

[0011] In the formula, X i Let X be the channel data of the i-th channel after noise reduction and completion preprocessing. f Indicates fused data, w i This indicates the confidence weight.

[0012] Furthermore, the characteristic parameters include effective erosion power density, cooling margin, brittleness index, erosion index, and thermo-hydraulic-mechanical coupling derivatives.

[0013] Furthermore, calculating the confidence weight for each sensing channel based on channel data specifically includes: Acquire stability indicators, temperature drift compensation results, and redundancy channel consistency of multi-channel data; The confidence weight of each sensing channel is calculated by combining the stability index of multi-channel data, temperature drift compensation results, and redundancy channel consistency.

[0014] Furthermore, the sampling period is 1-5 seconds.

[0015] A geothermal well perforation parameter adjustment system while drilling is also disclosed, the system comprising: The acquisition unit is used to periodically acquire multi-channel real-time data of the perforation section of the drill string, and to unify the multi-channel real-time data into the same sampling period based on depth and time alignment processing to form data of the same period; The preprocessing unit is used to perform noise reduction and completion preprocessing on data from the same period to obtain channel data; The weighting unit is used to calculate the confidence weight for each sensing channel based on the channel data. The extraction unit is used to perform weighted fusion of channel data with confidence weights to obtain fused data, and to extract feature parameters of the fused data; The model building unit is used to build a lithology identification model based on feature parameters and output the stratigraphic category, estimated values ​​of unmeasurable state variables, and identification uncertainty. The function construction unit is used to construct a multi-objective optimization function for borehole depth efficiency, borehole wall stability and heat transfer performance based on formation type, estimated values ​​of unmeasurable state variables and identification uncertainty, combined with characteristic parameters. The adjustment unit is used to solve a multi-objective optimization function using nonlinear programming to obtain the optimal perforation control parameters, and then adjusts the nozzle based on these parameters. Furthermore, the extraction unit extracts characteristic parameters from the fused data, including effective erosion power density, cooling margin, brittleness index, erosion index, and thermo-hydraulic-mechanical coupling derivatives.

[0016] Compared with the prior art, this application has the following advantages: The perforation parameter adjustment method for geothermal wells proposed in this application forms a complete intelligent closed-loop control system through real-time acquisition, preprocessing, feature calculation, lithology identification, optimization control, and execution of multi-channel data. By integrating multi-channel real-time data processing, feature parameter extraction, lithology identification, and multi-objective optimization techniques, it provides an efficient, intelligent, and dynamically adaptable method for adjusting perforation parameters to changes in formation. This method not only improves the efficiency and safety of geothermal well perforation operations but also copes with complex operating conditions under different formations, ensuring long-term stable operational performance and providing technical support for the efficient exploitation of geothermal resources.

[0017] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures pointed out in the description and the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic flowchart of the method for adjusting perforation parameters while drilling in a geothermal well, according to an embodiment of the present invention, is shown. Figure 2 A system block diagram of the geothermal well perforation parameter adjustment system in an embodiment of the present invention is shown. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] This invention provides a method and system for adjusting perforation parameters while drilling in geothermal wells. Figure 1 A schematic flowchart of the geothermal well perforation parameter adjustment method in an embodiment of the present invention is shown. Figure 1 In China, the method for adjusting perforation parameters while drilling geothermal wells includes the following steps: S1. Periodically acquire multi-channel real-time data of the perforation section of the drill string, and unify the multi-channel real-time data into the same sampling period based on depth and time alignment processing to form data of the same period. The sampling period is unified to 1-5 seconds.

[0022] Among them, the multi-channel real-time data includes the bottom hole pressure P acquired by sensors through multiple channels. b Annular pressure P a Bottom hole temperature T b Drilling fluid flow rate Q f Vibration acceleration av, logging-while-drilling parameters (including resistivity R) t (Sound wave time difference Δt), microseismic signal Ms; All sensor data is first converted into a unified ground standard time via a downhole clock or surface synchronization signal; The real-time well depth D(t) as it changes over time is obtained using a depth sensor on the drill string.

[0023] After completing time alignment and depth alignment, bivariate interpolation is used to unify all channel data to the same sampling time period t in the (t, D) two-dimensional space. s With the same depth step size d s Generate a multi-channel synchronous data matrix: (1); Where n is the number of channels, x i (t s d s ) indicates that the i-th channel at time t s With depth d s The alignment value; This represents a multi-channel synchronous data matrix, i.e., data in the same period.

[0024] By performing the aforementioned depth-time alignment processing, multi-channel downhole data with different sampling rates, different installation locations, and response delays can be mapped to a unified time-depth coordinate system. This ensures the comparability and synchronization of data from each channel in subsequent fusion, feature extraction, and optimization calculations, significantly improving the accuracy and stability of the perforation parameter adjustment model.

[0025] During the perforation process in geothermal wells, real-time downhole multi-channel data is often affected by factors such as sensor accuracy, downhole environmental disturbances, and signal transmission interference, resulting in noise interference, abnormal data, and missing data. Directly using unprocessed data will significantly reduce the reliability and optimization effect of subsequent models.

[0026] S2. Perform noise reduction and completion preprocessing on the data in the same period to obtain channel data; The noise types included in the data of the same period include high-frequency random noise (such as vibration interference), low-frequency drift (such as thermal drift of temperature sensors), electromagnetic interference pulses, etc. Low-pass filters are used for stable signals such as pressure and flow rate, band-pass filters are used for vibration signals to remove DC drift and high-frequency noise, and threshold denoising is used for microseismic signals to retain the waveform characteristics of the main events.

[0027] Anomaly types include single-point jumps, drift segments, and distortion segments; a statistical threshold method is used, and data points are judged as anomalies when they deviate from the mean by more than a set multiple of the standard deviation; a sliding window Z-score method is used to determine the degree of anomaly of the data within the window; based on multi-channel consistency detection, when the deviation of a channel from the redundant channel exceeds a set threshold, it is judged as anomaly; data points judged as anomalies are marked as missing. Missing data includes data lost due to sensor offline, data packet loss, or abnormal removal; Kalman filtering is used to predict missing values ​​based on historical states and inputs; collaborative prediction and completion are performed using multiple regression models or machine learning models based on redundant channels; and spline interpolation or local polynomial fitting is used to smoothly complete short-term continuous missing segments.

[0028] Noise reduction and completion preprocessing includes: Denoising and filtering processes are applied to multi-channel real-time data, as well as anomaly detection and removal, to obtain stable data. A state estimation method is used to predict and complete missing data in stationary data, and the channel data is output after noise reduction and completion preprocessing.

[0029] The above preprocessing steps suppress signal interference from the high-noise environment downhole; eliminate sudden erroneous measurements to avoid misleading the model; and restore missing information to maintain the continuity and availability of the data sequence.

[0030] S3. Calculate the confidence weight for each sensing channel i based on the channel data.

[0031] Specifically, the stability index S based on the channel data after noise reduction and completion preprocessing. i Temperature drift compensation result T i and redundancy channel consistency C i Calculate the confidence weight w for each sensing channel. i ; The formula for calculating confidence weights is: (2); In the formula, σ i Let S be the standard deviation of the channel, f be the normalized composite scoring function, and S be the standard deviation of the channel. i T represents the stability index. i C represents the temperature drift compensation result. i Redundant channel consistency, w i This indicates the confidence weight.

[0032] S4. Combine the confidence weights to perform weighted fusion of the channel data to obtain fused data, and extract the feature parameters of the fused data; Among them, fused data X f The calculation formula is: (3); In the formula, X i Let X be the channel data of the i-th channel after noise reduction and completion preprocessing. f Indicates fused data, w i This indicates the confidence weight.

[0033] Correspondingly, fused data Xf This includes: pressure P f Traffic Q f Temperature T f Vibration acceleration a f Microseismic event parameters m f ; Meanwhile, characteristic parameters include effective erosion power density P e Cooling margin M c Brittleness index B i Abrasion Index A b And the thermo-hydraulic-mechanical coupling derivative H thm ; The specific calculation process for the effective erosion power density Pe is as follows: (4); In the formula, ρ f The density of drilling fluid is expressed in units of (kg / m³), Q f v represents flow rate (m³ / s). f A represents the jet velocity (m / s). f This represents the nozzle outlet cross-sectional area (m²).

[0034] Cooling margin M c The calculation formula is as follows: (5); In the formula, T max T represents the maximum temperature (°C) that the formation material can withstand. op,f Indicates the current bottom hole operating temperature (°C), T f Indicates the temperature (°C) of the drilling fluid or other fluid.

[0035] Brittleness index B i The calculation formula is as follows: (6); In the formula, σ c σ represents the uniaxial compressive strength of rock (MPa). t This represents the tensile strength of the rock (MPa).

[0036] Abrasion Index A b The calculation formula is as follows: (7); In the formula, ΔP represents the pressure drop in the flow channel (Pa), L represents the length of the jet's path (m), and ρ f V represents the density of drilling fluid (kg / m³). f This indicates the jet velocity (m / s).

[0037] Thermo-hydraulic-mechanical coupling derivative Hthm The calculation formula is as follows: (8); In the formula, T f p represents temperature (°C). f σ represents pressure (Pa). h σ represents horizontal stress (MPa). v This represents the vertical stress (MPa).

[0038] S5. Construct a lithology identification model based on characteristic parameters, and input the effective erosion power density P. e Cooling margin M c Brittleness index B i Abrasion Index A b And the thermo-hydraulic-mechanical coupling derivative H thm The system outputs the formation category, estimated values ​​of unmeasurable state variables, and identification uncertainty. The formation category and state variables are used for subsequent perforation parameter optimization and safety constraint control. Correspondingly, the input data expression is: (9); Among them, P e Indicates effective erosion power density, M c Indicates cooling margin, B i Indicates the brittleness index, A b Indicates the abrasion index, H thm This represents the thermo-hydraulic-mechanical coupling derived quantity, and F represents the input data; Output data expression: (10); in, Indicates the type of strata (such as sandstone, limestone, basalt, etc.). Represents the estimated value of unmeasurable state variables, U conf denoted by , g(F) represents the identification uncertainty, and g(F) represents the output data.

[0039] S6. Based on the formation type, estimated values ​​of unmeasurable state variables, and identification uncertainty, and combined with a multi-objective optimization function constructed from characteristic parameters that includes borehole depth efficiency, borehole wall stability, and heat transfer performance, the control parameters include nozzle orifice diameter, jet pressure, jet angle, pore density, and operation duration. The nozzle is adjusted according to the control parameters.

[0040] Define the perforation control parameters as follows: (11); In the formula, d n Indicates nozzle orifice diameter (mm), p j θ represents the jet pressure (MPa).j Indicates the injection angle, ρ h t represents pore density (pores / m). o The value indicates the duration of the operation (in seconds), and C indicates the definition of the perforation control parameters.

[0041] The objective function F(C) is a set of functions of the control parameters, expressed as: (12); In the formula, f d (C) represents the hole depth efficiency function, reflecting the ability to form an effective hole depth per unit time; f s (C) represents the hole wall stability function, reflecting the hole wall's ability to maintain structural integrity under the current stress field and erosion load; f h (C) represents the heat transfer performance function, which inversely maps the contribution of the pores to heat conduction and fluid exchange.

[0042] Among them, the hole depth efficiency f d (C) measures the ability to form an effective hole depth per unit time. The calculation formula is: (13); Where: η d The erosion efficiency coefficient is determined based on the formation type and nozzle performance; α represents the pressure weighting factor, and β represents the flow rate weighting factor, set according to experimental data or experience; Q f t represents the flow rate (determined by the nozzle orifice diameter and injection velocity); o f represents the duration of the task. d (C) represents the hole depth efficiency.

[0043] Hole wall stability f s (C) is an important target in perforation operations, usually measured by the stress on the wellbore under the action of the jet. The calculation formula is: (14); Where, σ t (C) represents the equivalent tangential stress on the wellbore under jet action; σ h f represents the minimum horizontal stress in the formation (estimated from unmeasurable state variables); s (C) indicates the stability of the pore wall.

[0044] heat exchange performance f h (C) is a parameter used to evaluate the heat conduction and heat exchange efficiency after perforation. The calculation formula is: (15); Where: k eff Indicates the effective thermal conductivity; A c (C) represents the effective heat exchange area; Rth (C) represents thermal resistance; f h (C) indicates heat exchange performance.

[0045] Furthermore, the optimal perforation control parameters are solved using nonlinear programming methods; Multiple objective functions are weighted and combined into a single objective function for optimization. (16); Among them, w d w s w h f represents the weight coefficients of the objective function. s (C) represents the stability of the hole wall, f d (C) represents the hole depth efficiency, f h (C) indicates heat exchange performance.

[0046] After solving for the optimal perforation control parameter C, it is transmitted to the downhole perforation actuator according to the actual operation requirements, and the actual nozzle diameter, jet pressure, injection angle, orifice density and operation duration are adjusted to achieve the optimal perforation effect.

[0047] This invention provides a method for adjusting perforation parameters while drilling in geothermal wells. By performing noise reduction, anomaly detection, missing data completion, and confidence weighting on multi-channel real-time downhole data, it effectively improves the quality of downhole data and reduces errors caused by sensor noise, abnormal interference, and missing data. This significantly improves the accuracy and reliability of the data, providing a more stable input for subsequent feature extraction and optimization, reducing control parameter errors caused by inaccurate data, and enhancing the overall system stability.

[0048] Based on weighted fusion data, the calculated characteristic parameters encompass formation hydraulic, thermal, and mechanical properties, comprehensively reflecting formation fracturing, temperature control capabilities, stability, and heat transfer efficiency. Comprehensive evaluation of these characteristic parameters provides a more complete decision-making basis for perforation operations, enabling more accurate assessment of perforation risks and efficiency in different formations, ensuring efficient perforation operations across various formations. Combined with the characteristic parameters input into the lithology identification model, intelligent formation identification can automatically adjust perforation parameters based on real-time data, enhancing the adaptability of perforation operations and adjusting the range of operating parameters according to uncertainty, ensuring safe and efficient operations even in uncertain environments. Balancing and optimizing multiple objectives maximizes perforation efficiency while effectively ensuring borehole stability and heat transfer, guaranteeing the long-term stable operation of geothermal wells. The optimized parameters can be dynamically adjusted according to different formation conditions, significantly improving the safety, stability, and efficiency of operations.

[0049] The method of this invention forms a complete intelligent closed-loop control system through real-time acquisition, preprocessing, feature calculation, lithology identification, optimization control, and execution of multi-channel data. By integrating multi-channel real-time data processing, feature parameter extraction, lithology identification, and multi-objective optimization techniques, it provides an efficient, intelligent, and dynamically adaptable method for adjusting perforation parameters to adapt to formation changes. This method not only improves the efficiency and safety of geothermal well perforation operations but also copes with complex working conditions under different formations, ensuring long-term stable operational performance and providing technical support for the efficient exploitation of geothermal resources.

[0050] At the same time, refer to Figure 2 The present invention also discloses a geothermal well perforation parameter adjustment system, the adjustment system comprising: The acquisition unit is used to periodically acquire multi-channel real-time data of the perforation section of the drill string, and to unify the multi-channel real-time data into the same sampling period based on depth and time alignment processing to form data of the same period; The preprocessing unit is used to perform noise reduction and completion preprocessing on data from the same period to obtain channel data; The weighting unit is used to calculate the confidence weight for each sensing channel based on the channel data. The extraction unit is used to perform weighted fusion of channel data with confidence weights to obtain fused data, and to extract feature parameters of the fused data; The model building unit is used to build a lithology identification model based on feature parameters and output the stratigraphic category, estimated values ​​of unmeasurable state variables, and identification uncertainty. The function construction unit is used to construct a multi-objective optimization function for borehole depth efficiency, borehole wall stability and heat transfer performance based on formation type, estimated values ​​of unmeasurable state variables and identification uncertainty, combined with characteristic parameters. The adjustment unit is used to solve a multi-objective optimization function using a nonlinear programming method to obtain the optimal perforation control parameters, and then adjusts the nozzle based on the optimal perforation control parameters.

[0051] Among them, the feature parameters extracted by the extraction unit from the fused data include effective erosion power density, cooling margin, brittleness index, erosion index, and thermo-hydraulic-mechanical coupling derivative.

[0052] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection, an electrical connection, or a connection that allows for communication; they may refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of these terms in this invention according to the specific circumstances.

[0053] It should be understood that all terms used to indicate orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and should not be construed as a limitation of the present invention.

[0054] Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for adjusting perforation parameters while drilling a geothermal well, characterized in that, Includes the following steps: Periodically acquire multi-channel real-time data of the perforation section of the drill bit, and unify the multi-channel real-time data into the same sampling period based on depth and time alignment processing to form data of the same period; Noise reduction and completion preprocessing are performed on data from the same period to obtain channel data; Calculate the confidence weight for each sensing channel based on the channel data; The channel data is weighted and fused by combining confidence scores to obtain fused data, and the feature parameters of the fused data are extracted. A lithology identification model is constructed based on characteristic parameters, and the stratigraphic category, estimated values ​​of unmeasurable state variables, and identification uncertainty are output. Based on the aforementioned formation type, estimated values ​​of unmeasurable state variables, and identification uncertainty, a multi-objective optimization function concerning borehole depth efficiency, borehole wall stability, and heat transfer performance is constructed by combining characteristic parameters. The multi-objective optimization function is solved using nonlinear programming to obtain the optimal perforation control parameters, and the nozzle is adjusted based on the optimal perforation control parameters.

2. The method for adjusting perforation parameters while drilling in geothermal wells according to claim 1, characterized in that, The multi-channel real-time data includes bottom hole pressure, annular pressure, bottom hole temperature, drilling fluid flow rate, vibration acceleration, logging-while-drilling parameters, and microseismic signals from multiple channels.

3. The method for adjusting perforation parameters while drilling in geothermal wells according to claim 2, characterized in that, The noise reduction and completion preprocessing includes: Denoising and filtering processes are applied to multi-channel real-time data, as well as anomaly detection and removal, to obtain stable data. A state estimation method is used to predict and complete missing data in stationary data, and the channel data is output after noise reduction and completion preprocessing.

4. The method for adjusting perforation parameters while drilling in geothermal wells according to claim 3, characterized in that, The formula for calculating the confidence weight is as follows: Where, σ i Let S be the standard deviation of the channel, f be the normalized composite scoring function, and S be the standard deviation of the channel. i T represents the stability index. i C represents the temperature drift compensation result. i Redundant channel consistency, w i This indicates the confidence weight.

5. The method for adjusting perforation parameters while drilling in geothermal wells according to claim 4, characterized in that, The calculation formula for the fused data is: In the formula, X i Let X be the channel data of the i-th channel after noise reduction and completion preprocessing. f Indicates fused data, w i This indicates the confidence weight.

6. The method for adjusting perforation parameters while drilling in geothermal wells according to claim 5, characterized in that, The characteristic parameters include effective erosion power density, cooling margin, brittleness index, erosion index, and thermo-hydraulic-mechanical coupling derivative.

7. The method for adjusting perforation parameters while drilling in geothermal wells according to claim 3, characterized in that, The calculation of confidence weights for each sensing channel based on channel data specifically includes: Acquire stability indicators, temperature drift compensation results, and redundancy channel consistency of multi-channel data; The confidence weight of each sensing channel is calculated by combining the stability index of multi-channel data, temperature drift compensation results, and redundancy channel consistency.

8. The method for adjusting perforation parameters while drilling in geothermal wells according to claim 1, characterized in that, The sampling period is 1-5 seconds.

9. A perforation parameter adjustment system for geothermal wells during drilling, characterized in that, The regulating system includes: The acquisition unit is used to periodically acquire multi-channel real-time data of the perforation section of the drill bit, and to unify the multi-channel real-time data into the same sampling period based on depth and time alignment processing to form data of the same period; The preprocessing unit is used to perform noise reduction and completion preprocessing on data from the same period to obtain channel data; The weighting unit is used to calculate the confidence weight for each sensing channel based on the channel data. The extraction unit is used to perform weighted fusion of channel data with confidence weights to obtain fused data, and to extract feature parameters of the fused data; The model building unit is used to build a lithology identification model based on feature parameters and output the stratigraphic category, estimated values ​​of unmeasurable state variables, and identification uncertainty. The function construction unit is used to construct a multi-objective optimization function concerning borehole depth efficiency, borehole wall stability and heat transfer performance based on the formation type, estimated values ​​of unmeasurable state variables and identification uncertainty, combined with characteristic parameters. The adjustment unit is used to solve a multi-objective optimization function using a nonlinear programming method to obtain the optimal perforation control parameters, and then adjusts the nozzle based on the optimal perforation control parameters.

10. The geothermal well perforation parameter adjustment system according to claim 9, characterized in that, The extraction unit extracts characteristic parameters from the fused data, including effective erosion power density, cooling margin, brittleness index, abrasion index, and thermo-hydraulic-mechanical coupling derivatives.

Images