Well drilling optimization decision-making method, device and equipment based on underground parameter regulation and control

Abstract

The embodiment of the invention relates to the technical field of drilling engineering, in particular to a drilling optimization decision-making method, device and equipment based on underground parameter regulation, and the method comprises the steps: obtaining drilling data which comprises underground engineering data and ground logging data; according to the well drilling data, the mechanical drilling speed, the mechanical specific energy and the complex working condition index of well drilling are calculated, and the complex working condition index is used for representing the vibration grade and the abrasion degree of a drill bit; by taking maximization of the mechanical drilling speed and minimization of the mechanical specific energy as targets and taking the condition that the complex working condition index meets the risk working condition constraint as a condition, an optimization model is constructed; according to the optimization model, underground engineering data are optimized, and the underground engineering data at least comprise underground bit pressure data and underground rotating speed data; and underground engineering parameters are regulated and controlled according to the optimized underground engineering data. By obtaining the underground engineering data and carrying out optimization decision making according to the underground engineering data, the problem of well-ground transmission deviation caused by dependence on ground logging data is fundamentally solved.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of drilling engineering technology, specifically to a drilling optimization decision-making method, apparatus, and equipment based on downhole parameter control. Background Technology

[0002] Drilling is an indispensable and crucial link in oil and gas exploration and development, accounting for approximately 30% to 80% of the total exploration and development cost. Currently, as oil and gas exploration and development gradually shifts towards deep, ultra-deep, deepwater, and unconventional complex reservoirs, these areas have become important directions for current and future oil and gas resource replacement. However, these resources generally have poor occurrence conditions, complex geological environments, and harsh downhole conditions, posing severe challenges to the efficiency, safety, and quality of drilling operations. Therefore, the task of reducing drilling costs and increasing efficiency is urgent, necessitating the development of transformative new methods and technologies.

[0003] With the widespread application of complex well structures such as ultra-deep wells and extended reach wells, the frequent alternation of formation lithology, the difficulty in controlling the wellbore trajectory, and the significant increase in drill string friction and torque have made it difficult to effectively transmit the drilling pressure applied from the surface to the bottom of the well. This has become a key bottleneck restricting the speed and efficiency of deep and unconventional oil and gas drilling. Insufficient drilling pressure leads to inadequate rock breaking efficiency, while excessively high or fluctuating drilling pressure can easily cause abnormal drill bit wear and severe drill string vibration, and in severe cases, even induce downhole failures such as stuck pipe. Therefore, achieving accurate characterization and precise control of downhole drilling parameters is an important foundation for improving drilling efficiency and ensuring safety.

[0004] Currently, drilling parameter optimization methods can be mainly divided into two categories: the first is the traditional optimization method based on statistics or rock breaking mechanisms, which establishes empirical or theoretical relationships between mechanical drilling rate and drilling parameters in different formations or well sections to screen for the optimal parameter combination; the second is the drilling parameter optimization method based on intelligent algorithms, which establishes a nonlinear mapping between surface logging parameters and rock breaking efficiency indicators (such as mechanical drilling rate) through data-driven models, and uses optimization algorithms to inversely recommend drilling parameters. Although the methodology is constantly evolving, the mainstream solutions in the industry still generally take surface logging parameters (such as surface drilling pressure, rotary table speed, pump displacement, etc.) as the core of optimization, and formulate parameter optimization strategies by analyzing their correlation with drilling performance indicators.

[0005] However, existing methods have significant technical limitations: surface parameters need to be transmitted to the downhole operating area via drill string, drilling fluid, and other media. During this process, they are affected by complex factors such as drill string deformation, hydraulic losses, high-temperature and high-pressure environments, and abrupt changes in lithology, leading to significant deviations between surface parameters and actual downhole operating parameters. This makes optimization methods centered on surface parameters essentially indirect extrapolations of actual downhole conditions. Surface parameters such as drilling pressure and torque are difficult to effectively transmit to the well bottom, making it difficult to accurately match actual downhole conditions and rock-breaking requirements. This easily leads to a disconnect between optimization strategies and actual downhole conditions and needs, not only limiting drilling speed-up effects but also potentially exacerbating wellbore instability and stuck pipe risks due to parameter mismatch, thus hindering the improvement of overall drilling performance. Summary of the Invention

[0006] The purpose of the embodiments in this specification is to provide a drilling optimization decision-making method, device, and equipment based on downhole parameter control, so as to overcome the problems of existing methods that are difficult to accurately match the actual downhole working conditions and the optimization strategy being out of touch with actual needs.

[0007] To solve the above-mentioned technical problems, the specific technical solutions of the embodiments in this specification are as follows: On the one hand, the embodiments of this specification provide a drilling optimization decision-making method based on downhole parameter control, including: Acquire drilling data, which includes downhole engineering data and surface logging data; Based on the drilling data, the drilling speed, mechanical energy, and complex condition index are calculated. The complex condition index is used to characterize the vibration level and wear degree of the drill bit. An optimization model is constructed with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the condition that the complex working condition index meets the risk working condition constraint. Based on the optimization model, the downhole engineering data is optimized, and the downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data; Adjust downhole engineering parameters based on optimized downhole engineering data.

[0008] Furthermore, the acquisition of drilling data includes: Acquire downhole engineering data at the drill bit location; the downhole engineering data shall include at least downhole torque data and internal and external annular pressure data; Acquire surface logging data; the surface logging data includes at least surface drilling pressure data, rotary table rotation speed data, pump displacement data, and hook load data; The drilling data is obtained by spatiotemporally aligning the downhole engineering data and the surface logging data.

[0009] Furthermore, the calculation of the mechanical drilling rate includes: Based on the drilling data, determine the drilling parameters that affect the rock-breaking efficiency of the drill bit; the rock-breaking parameters that affect the rock-breaking efficiency of the drill bit include at least downhole drilling pressure, downhole torque, downhole rotation speed, inner and outer annular pressure, pump displacement, and hook load; Based on the drilling parameter data that affect the rock-breaking efficiency of the drill bit, the mechanical drilling rate is calculated using a preset mechanical drilling rate prediction model; the mechanical drilling rate prediction model is used to characterize the mapping relationship between the drilling parameters that affect the rock-breaking efficiency of the drill bit and the mechanical drilling rate.

[0010] Furthermore, the calculation of the mechanical specific energy of the well includes: Based on the drill bit's size data, the static rock-breaking factor of the drill bit is calculated; the static rock-breaking factor is negatively correlated with the drill bit's size. Based on downhole drilling pressure data, downhole torque data, downhole rotation speed data, drill bit size data, and the mechanical drilling rate data, the dynamic friction factor of the drill bit is calculated; the dynamic friction factor is positively correlated with downhole torque and downhole rotation speed; the dynamic friction factor is negatively correlated with downhole drilling pressure, drill bit size, and mechanical drilling rate. The mechanical specific energy of the well is calculated based on the downhole drilling pressure data, the static rock-breaking factor of the drill bit, and the dynamic friction factor.

[0011] Furthermore, the calculation of the drilling complexity index includes: Based on downhole rotation speed data, drill bit size data, and mechanical drilling rate data, the formation's drill resistance strength is calculated; the drill resistance strength is positively correlated with drill bit size and downhole rotation speed; and negatively correlated with mechanical drilling rate. Based on the mechanical specific energy and the formation's drill resistance strength, the drilling complexity index is calculated.

[0012] Furthermore, the condition that the complex operating condition index satisfies the risk operating condition constraint includes: The conditions are that the internal and external annular pressures meet the overflow and leakage risk constraints, the complex working condition index meets the wear and vibration risk constraints, and the downhole drilling pressure and downhole drilling speed meet the engineering risk constraints.

[0013] Furthermore, the construction of the optimization model includes: Based on drilling stage data, the weighting coefficients for the mechanical drilling rate and mechanical specific energy are determined; Based on the weighting coefficients, a multi-objective optimization function is constructed with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy.

[0014] Furthermore, optimizing the downhole engineering data according to the optimization model includes: According to the preset intelligent optimization algorithm, the multi-objective optimization function is solved to obtain multiple combinations of downhole engineering parameters of downhole drilling pressure and downhole rotation speed. Each combination of downhole engineering parameters corresponds to an optimization scheme for downhole engineering data. From the multiple combinations of downhole engineering parameters, one or more candidate combinations of downhole engineering parameters that meet the risk condition constraints are selected; The one or more candidate combinations of downhole engineering parameters are sorted, and the optimal combination of downhole engineering parameters is selected. Optimize downhole engineering data based on the optimal combination of downhole drilling pressure and downhole rotation speed.

[0015] Furthermore, adjusting the downhole engineering parameters based on the optimized downhole engineering data includes: Based on the optimized downhole engineering data, generate downhole control commands; Adjust downhole engineering parameters according to the downhole control commands.

[0016] On another front, embodiments of this specification provide a drilling optimization decision-making device based on downhole parameter control, comprising: The acquisition module is used to acquire drilling data, which includes downhole engineering data and surface logging data. The calculation module is used to calculate the drilling speed, mechanical energy, and complex working condition index of the well based on the drilling data. The complex working condition index is used to characterize the vibration level and wear degree of the drill bit. A construction module is used to build an optimization model with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the complex working condition index satisfying the risk working condition constraint as a condition; The optimization module is used to optimize downhole engineering data according to the optimization model. The downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data. The control module is used to adjust downhole engineering parameters based on optimized downhole engineering data.

[0017] On the other hand, a computer device is provided, including a memory for storing computer programs and a processor for executing the computer programs to implement the above-mentioned drilling optimization decision-making method based on downhole parameter control.

[0018] As can be seen from the technical solutions provided in the embodiments of this specification above, these embodiments can acquire drilling data, including downhole engineering data and surface logging data; based on the drilling data, calculate the mechanical drilling rate, mechanical specific energy, and complex operating condition index, whereby the complex operating condition index characterizes the vibration level and wear degree of the drill bit; construct an optimization model with the goal of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the complex operating condition index satisfying risk operating condition constraints; optimize the downhole engineering data based on the optimization model, whereby the downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data; and adjust the downhole engineering parameters based on the optimized downhole engineering data. By acquiring and making optimization decisions based on downhole engineering data, the well-to-surface transmission deviation problem caused by the reliance on surface logging data in existing technologies is fundamentally overcome. The mechanical drilling rate, mechanical specific energy, and complex operating condition index on which the optimization model is based are all calculated based on actual downhole operating conditions, ensuring that the optimization objectives and constraints closely align with actual production. This ensures that the optimized parameter combination accurately matches the actual downhole requirements, avoiding decision-making disconnect caused by parameter distortion, thereby significantly improving the rate of drilling and reducing ineffective energy consumption. Furthermore, by maximizing the rate of drilling and minimizing the specific energy of the machine as parallel objectives, and using the complex operating condition index as a hard constraint, a multi-objective constrained optimization model was constructed. This model forces the optimization algorithm to automatically find the optimal balance between efficiency and energy consumption within a safe range. This overcomes the limitations of traditional single-objective optimization or ignoring safety constraints, enabling the final solution to simultaneously consider drilling speed improvement, cost reduction, and safety assurance, achieving system-level synergistic optimization rather than a one-sided improvement in local indicators. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below.

[0020] Figure 1 This is a flowchart of a drilling optimization decision-making method based on downhole parameter control, provided in the embodiments of this specification; Figure 2 This is a schematic diagram of the overall logic flow of a drilling optimization decision-making method based on downhole parameter control provided in the embodiments of this specification; Figure 3 This is a field schematic diagram of a drilling optimization decision-making method based on downhole parameter control provided in the embodiments of this specification; Figure 4 This is a schematic diagram of the structural composition of a drilling optimization decision-making device based on downhole parameter control, provided in the embodiments of this specification; Figure 5 This is a schematic diagram of the structural composition of the computer device provided in the embodiments of this specification. Detailed Implementation

[0021] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0022] It should be noted that the terms "first," "second," etc., used in this specification, claims, and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0023] Figure 1 This is a flowchart illustrating a drilling optimization decision-making method based on downhole parameter control, as provided in the embodiments of this specification. Figure 2 This is a schematic diagram of the overall logic flow of a drilling optimization decision-making method based on downhole parameter control, provided in the embodiments of this specification. In specific implementation, it includes the following steps: S101: Acquire drilling data, which includes downhole engineering data and surface logging data.

[0024] In some embodiments, step S101 may specifically include: acquiring downhole engineering data at the drill bit; the downhole engineering data may include at least downhole torque data and annular pressure data; acquiring surface logging data; the surface logging data may include at least surface drilling pressure data, rotary table rotation speed data, pump displacement data, and hook load data; and performing spatiotemporal alignment of the downhole engineering data and the surface logging data to obtain the drilling data.

[0025] In some embodiments, downhole engineering data can be a series of physical parameters that reflect the actual working state of the bottom hole assembly, directly measured by a sensor array mounted on a specific tool (i.e., a downhole engineering parameter measurement sub) closest to the drill bit on the drill string. This measurement sub can integrate multiple high-precision sensors to form a near-bit measurement system.

[0026] In some embodiments, during drilling operations, the measurement system can perform real-time measurements at a preset high frequency (e.g., 1 time / second). The acquired raw signals can be transmitted to the surface control system in real-time or near real-time via downhole communication technologies such as mud pulse telemetry, electromagnetic waves, or high-speed wired drill pipe.

[0027] In some embodiments, downhole drilling pressure data may include axial forces acting directly on the drill bit, measured in kilonewtons. This data can be measured by downhole pressure sensors and reflects the core power input during rock breaking operations.

[0028] In some embodiments, downhole torque data can be the rotational resistance torque generated by the drill bit when breaking rock, measured in kilonewtons per meter. This data can be measured by a downhole torque sensor and directly characterizes the difficulty of rock breaking and the working condition of the drill bit.

[0029] In some embodiments, the downhole rotational speed data can be the actual rotational speed of the drill bit itself, measured in revolutions per minute. In the presence of a downhole motor, this speed differs from the rotational speed of the surface rotary table.

[0030] In some embodiments, the annular pressure data can be the fluid pressure inside the drill string (inner annulus) and between the drill string and the wellbore (outer annulus), measured in megapascals (MPa). This data is crucial for monitoring wellbore pressure balance and preventing complex conditions such as overflows and lost circulation.

[0031] By directly acquiring the mechanical parameters at the drill bit, the signal attenuation, lag, and distortion problems caused by factors such as friction, vibration, compression, and torsional deformation during the transmission of surface parameters in a drill string thousands of meters long are completely avoided. This provides high-fidelity first-hand data reflecting the actual downhole working conditions for subsequent optimization and control, laying the physical foundation for precise optimization of downhole parameter control methods.

[0032] In some embodiments, surface logging data may be a series of parameters collected by a sensor system installed on surface equipment at the well site to monitor the overall drilling operation status. This data reflects the energy input and overall response of the surface equipment to the downhole system.

[0033] In some embodiments, the ground data acquisition system can synchronously record signals from devices such as winch sensors, pump sensors, rotary encoders, and pressure transmitters, and perform preliminary digital processing and storage.

[0034] In some embodiments, the surface drilling pressure data can be the axial force applied to the top of the drill string at the wellhead, calculated from the hook load and the weight of the drill string.

[0035] In some embodiments, the turntable rotation speed data can be the actual drive speed of the ground turntable.

[0036] In some embodiments, pump displacement data can be the volumetric flow rate of drilling fluid delivered into the well by the drilling pump, which is related to wellbore cleaning and downhole power.

[0037] In some embodiments, the hook load data can be the load borne by the hook suspending the entire drill string system, used to calculate the ground drilling pressure and determine the tripping and tripping conditions.

[0038] Surface data reflects control commands and equipment status on the surface, providing indispensable information for analyzing command-response relationships, evaluating equipment efficiency, and conducting overall system energy consumption analysis. By comparing and analyzing surface data with downhole data, the energy transmission efficiency of the entire drill string system can be assessed, and significant differences between surface and downhole data can aid in diagnosing systemic problems such as drill string friction and wellbore cleanliness.

[0039] In some embodiments, spatiotemporal alignment can resolve the issues of time asynchrony and depth mismatch between downhole and surface data due to differences in physical location and transmission delay.

[0040] Specifically, time alignment can be achieved by synchronizing the two types of data streams using a unified time reference (such as a GPS clock). Considering the latency in downhole data uploads, latency compensation needs to be performed based on the transmission rate and well depth to ensure that the data reception time recorded on the surface is corrected to the actual time when the downhole data occurred.

[0041] Depth alignment associates each data point with its corresponding precise well depth. By integrating logging depth, drill string length, and mechanical drilling rate, all parameters are mapped uniformly to a depth-time coordinate system, ensuring that at any given well depth point, corresponding downhole and surface parameters can be found.

[0042] In some embodiments, drilling data can be a standardized dataset that is multi-dimensional, highly consistent, and formed after spatiotemporal alignment, integrating real downhole responses and surface control commands.

[0043] Spatiotemporal alignment can eliminate inherent spatiotemporal distortions in data, enabling parameters such as downhole torque and surface rotational speed, downhole drilling pressure and surface drilling pressure to be accurately correlated within the same spatiotemporal framework for analysis. Furthermore, spatiotemporal data alignment is a prerequisite for constructing high-precision mechanical drilling rate prediction models and calculating indicators such as mechanical specific energy. Only when data is precisely matched in time and space can the established model truly reflect the inherent laws of the drilling system, thereby outputting effective optimization decisions.

[0044] S102: Based on the drilling data, calculate the drilling speed, mechanical energy, and complex operating condition index. The complex operating condition index is used to characterize the vibration level and wear degree of the drill bit.

[0045] In some embodiments, calculating the mechanical rate of drilling in step S102 may specifically include: determining drilling parameter data affecting the rock-breaking efficiency of the drill bit based on the drilling data; the rock-breaking parameters affecting the rock-breaking efficiency of the drill bit include at least downhole drilling pressure, downhole torque, downhole rotational speed, inner and outer annular pressure, pump displacement, and hook load; calculating the mechanical rate of drilling using a preset mechanical rate of drilling prediction model based on the drilling parameter data affecting the rock-breaking efficiency of the drill bit; the mechanical rate of drilling prediction model is used to characterize the mapping relationship between the drilling parameters affecting the rock-breaking efficiency of the drill bit and the mechanical rate of drilling.

[0046] In some embodiments, drilling parameters affecting the rock-breaking efficiency of the drill bit may include variables that directly or indirectly affect the bottom-hole rock-breaking process. The following core parameters can be extracted from spatiotemporally aligned fused drilling data to form the model input feature set.

[0047] In some embodiments, downhole drilling pressure can be an effective axial force acting directly on the drill bit, and is a direct source of rock-breaking energy.

[0048] In some embodiments, downhole torque can be the torque that reflects the drill bit's resistance to rock breaking and frictional resistance, characterizing the difficulty of rock breaking.

[0049] In some embodiments, the downhole rotational speed can be the actual rotational speed of the drill bit, which determines the cutting frequency.

[0050] In some embodiments, the internal and external annular pressures can affect the bottom hole stress environment and cuttings transport, indirectly affecting rock breaking efficiency.

[0051] In some embodiments, pump displacement can affect bottomhole hydraulic energy and cuttings cleaning effectiveness, which is crucial for preventing repeated drill bit cutting.

[0052] In some embodiments, the hook load can reflect the total load of the drilling system and can be used to help determine the overall stress state of the drill string.

[0053] By integrating direct downhole measurement data with surface control parameters, the model is provided with a complete information set that includes both the actual downhole response and surface control commands, fundamentally avoiding model bias caused by incomplete or inaccurate input features. The selected parameters cover key mechanical and hydraulic factors in the rock-breaking process, making the model not only dependent on data correlation but also implicitly containing drilling engineering mechanisms, thus improving the model's physical rationality and extrapolation capabilities.

[0054] In some embodiments, the preset mechanical drilling rate prediction model can be an intelligent model pre-trained with a large amount of historical drilling data, which can couple the complex nonlinear mapping relationship between drilling parameters and mechanical drilling rate. This model is preferably an advanced architecture capable of handling sequence dependencies and system structure relationships, such as a temporal neural network (e.g., LSTM, GRU) or a graph neural network (GNN).

[0055] In some embodiments, the multidimensional drilling parameter dataset that affects the rock-breaking efficiency of the drill bit, as determined above, can be input into the deployed mechanical drilling rate prediction model in time series order. The model internally performs forward propagation calculations through its multi-layer network structure and activation functions, ultimately outputting a continuous, real-time mechanical drilling rate prediction value.

[0056] Compared to traditional linear regression or empirical formulas, pre-defined mechanical drilling rate prediction models can capture the subtle, dynamic, and nonlinear interactions between parameters in complex downhole systems, thus achieving faster and more accurate estimation of mechanical drilling rate, and even possessing a certain degree of predictability before changes in operating conditions. Neural network-based models possess powerful learning and adaptive capabilities, adapting to changes in formations, drill string combinations, and operating conditions as drilling progresses, exhibiting superior generalization performance compared to fixed-coefficient models, and providing reliable support for decision-making in unknown blocks or complex conditions. Furthermore, the mechanical drilling rate predicted by the model can serve as core real-time feedback for measuring drilling efficiency, directly fed into subsequent optimization modules, becoming a key objective in the multi-objective optimization function, thus forming the cornerstone of an intelligent decision-making-execution-feedback closed loop.

[0057] In some embodiments, calculating the mechanical specific energy of the well in step S102 above may specifically include: calculating the static rock-breaking factor of the drill bit based on the drill bit size data; the static rock-breaking factor is negatively correlated with the drill bit size; calculating the dynamic friction factor of the drill bit based on downhole drilling pressure data, downhole torque data, downhole rotational speed data, drill bit size data, and the mechanical drilling rate data; the dynamic friction factor is positively correlated with downhole torque and downhole rotational speed; the dynamic friction factor is negatively correlated with downhole drilling pressure, drill bit size, and mechanical drilling rate; and calculating the mechanical specific energy of the well based on the downhole drilling pressure data, the static rock-breaking factor of the drill bit, and the dynamic friction factor.

[0058] In some embodiments, the static rock-breaking factor can characterize the basic pressure required per unit drill bit area to overcome rock strength under ideal, static conditions, and its dimension is force / area. It can be related to the geometry of the drill bit and reflects the inherent ability of the drill string to convert drilling pressure into rock-breaking static pressure.

[0059] In some embodiments, the drill bit dimensions may include the drill bit diameter. The drill bit cross-sectional area can then be calculated, which serves as the reference area for calculating static pressure.

[0060] In some embodiments, the static rock-breaking factor is proportional to the drill bit size. That is, the larger the drill bit size, the larger its total cross-sectional area, and the smaller the pressure per unit area (static rock-breaking factor) required to produce the same static pressure intensity. The cross-sectional area can be calculated based on the input drill bit diameter, and the value of the static rock-breaking factor can be determined accordingly.

[0061] By introducing a static rock-breaking factor, the influence of drill bit size, a fixed geometric property, on rock-breaking efficiency is isolated, allowing subsequent analysis to focus more on the dynamic process and enhancing the model's interpretability. The static rock-breaking factor constitutes the theoretical lower limit of mechanical specific energy that cannot be eliminated through operational optimization, helping to determine the gap between the current energy consumption level and the ideal state.

[0062] In some embodiments, the dynamic friction factor can characterize the intensity of all additional energy losses caused by friction, shearing, grinding, and hydraulic conditions, in addition to static crushing, during the rock-breaking process of a drill bit rotating. It is a comprehensive efficiency loss index.

[0063] In some embodiments, the dynamic friction factor can be determined as a function of multiple real-time downhole parameters. Specifically, real-time data including downhole torque and downhole rotational speed can be retrieved, their product being proportional to the power consumed by rotary rock breaking. Higher power means greater frictional losses, thus the dynamic friction factor is positively correlated with it. Downhole bit pressure, bit size, and the calculated rate of penetration (RLP) can also be obtained. The product of bit pressure and bit size can be approximated as a measure of rock breaking scale, while the calculated RLP represents the effective output of rock breaking. Under the same frictional losses, a larger rock breaking scale and higher efficiency result in lower frictional losses per unit volume of rock. Therefore, the dynamic friction factor is negatively correlated with these three parameters.

[0064] By independently quantifying the main energy loss component during drilling—dynamic friction loss—it becomes clear how much energy is used for effective rock breaking and how much is wasted on non-productive friction. Abnormal increases in the dynamic friction factor (such as due to drill bit mud buildup, ball tooth wear, or encountering abrasive formations) or abnormal decreases (such as due to drill bit slippage or cutting tooth failure) are early and sensitive signals for judging the drill bit's working condition and complex downhole conditions.

[0065] In some embodiments, mechanical specific energy can be the total mechanical energy consumed in breaking a unit volume of rock, which can evaluate the overall efficiency of drilling energy utilization; the lower the value, the higher the efficiency.

[0066] In some embodiments, the two factors calculated above can be combined with the downhole drilling pressure (WOB). The mechanical energy specificity (MSE) can be represented as: MSE = WOB (static rock breaking factor + dynamic friction factor).

[0067] This decomposition of static rock breaking and dynamic friction results in a MSE that is no longer a vague, black-box value. It clearly reveals the composition of total energy consumption and indicates the specific direction for energy efficiency optimization—whether to optimize drilling pressure distribution or focus on reducing friction losses. This decompositional calculation method provides richer gradient information for multi-objective optimization algorithms. The optimization algorithm can not only pursue the minimization of total MSE but also selectively adjust parameters to prioritize the suppression of abnormal dynamic friction factors, thereby achieving smarter and more precise downhole parameter control and fundamentally improving the economy and safety of the drilling process.

[0068] In some embodiments, calculating the drilling complexity index in step S102 may specifically include: calculating the formation's drill resistance strength based on downhole rotation speed data, drill bit size data, and the mechanical drilling rate data; the drill resistance strength is positively correlated with drill bit size and downhole rotation speed; the drill resistance strength is negatively correlated with the mechanical drilling rate; and calculating the drilling complexity index based on the mechanical specific energy and the formation's drill resistance strength.

[0069] In some embodiments, formation drill resistance strength characterizes the formation's overall ability to resist drill bit penetration and fracturing. Its physical properties are analogous to the equivalent stiffness of a material, and its unit is force / length (e.g., kN / mm). It comprehensively reflects the rock's strength, hardness, plasticity, and abrasiveness.

[0070] In some embodiments, real-time downhole rotation speed data and drill bit size data can be acquired, which together define the drill bit's theoretical rock-breaking profile and cutting frequency. Drill resistance is positively correlated with this, because facing harder formations requires higher rotation speeds and / or larger drill bits to maintain a certain level of rock-breaking efficiency.

[0071] In some embodiments, the solved mechanical drilling rate is the actual output of rock-breaking efficiency. Drill resistance is negatively correlated with it because, under the same drilling parameters, the harder and stiffer the formation, the lower the mechanical drilling rate typically is.

[0072] In some embodiments, the formula for calculating formation drill resistance strength can be expressed as: DS∝(NDb) / ROP. Wherein, DS, N, Db, and ROP represent formation drill resistance strength, downhole rotation speed, drill bit size, and mechanical drilling rate, respectively. This formula indicates that the higher the equivalent stiffness required to maintain a unit mechanical drilling rate, the stronger the formation's drill resistance.

[0073] Formation drill resistance transforms the mechanical properties of a formation from static, laboratory-measured attributes into a dynamic index that changes in real time during the drilling process and can be directly calculated on-site, providing crucial formation environmental information for system optimization. Abrupt changes in formation drill resistance are sensitive indicators for identifying formation interfaces (such as transitioning from soft formations to hard interlayers); abnormally high values ​​may foreshadow complex downhole conditions such as stick-slip vibrations, serving as an early warning system.

[0074] In some embodiments, the complex condition index can be a ratio factor, i.e. a dimensionless comprehensive index, which can reveal the working health status of the drill bit itself in isolation by stripping away the influence of formation factors.

[0075] In some embodiments, the mechanical specific energy (MSE) calculated above can be correlated with the formation drill resistance (DS). The calculation formula can be expressed as: RF = MSE / DS. Substituting the expressions for MSE and DS, the formula can be simplified to a more direct form: RF ∝ T / WOB, where T is the downhole torque and WOB is the downhole drill pressure. This reveals that the essence of this index is the torque-drill pressure ratio.

[0076] Since the RF index effectively filters out the interference of formation changes (characterized by DS) and total rock breaking energy consumption (characterized by MSE), its changes directly point to abnormal mechanical behavior of the drilling tool.

[0077] In some embodiments, based on the linkage trend analysis of RF and WOB, drill bit vibration early warning and drill bit wear diagnosis can be achieved.

[0078] In some embodiments, when the RF value and WOB value increase simultaneously, it indicates that the drill bit has failed to penetrate the formation smoothly, and a large amount of energy is consumed in non-productive collisions and friction, thus indicating that drill bit vibration exists.

[0079] In some embodiments, when the RF value decreases while the WOB value increases, it indicates that the drill bit cutting teeth are worn and even if the drilling pressure is increased, it cannot be effectively converted into cutting torque, thus indicating that there is drill bit wear.

[0080] In some embodiments, the calculated RF value can be directly used as a hard constraint condition input into the subsequent optimization model, enabling the optimization algorithm to automatically avoid parameter danger zones that may cause severe vibration or accelerate drill bit wear. This transforms safety control from a passive consequence response to an active, forward-looking avoidance, achieving a qualitative leap in the drilling process from efficiency optimization to safety-efficiency synergistic optimization.

[0081] S103: With the goal of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the condition that the complex working condition index meets the risk working condition constraint, construct an optimization model.

[0082] In some embodiments, risk condition constraints can be boundary conditions that must be strictly adhered to during the optimization process; any parameter combination that violates these conditions will be directly excluded. Risk condition constraints can be defined by a complexity condition index.

[0083] In some embodiments, one or more safety thresholds can be set for the complex operating condition index RF. For example, an upper limit threshold RF_max can be set for RF, which is determined based on extensive historical data, experimental or theoretical analysis, to define the acceptable risk boundary of drill bit vibration and wear. This constraint can be mathematically expressed as: RF ≤ RF_max. During optimization, this constraint acts as a hard constraint, and any candidate parameter combination that results in RF > RF_max will be deemed an infeasible solution.

[0084] By using the complex operating condition index as a constraint, all known high-risk areas are proactively removed from the search space of the optimization algorithm. This allows optimization decisions to avoid potentially dangerous parameters that could cause severe vibrations, accelerate drill bit damage, or lead to complex downhole conditions from the outset, achieving a fundamental shift in safety management from post-event alarms to pre-event prevention. The final recommended combination of optimization parameters is the most efficient solution obtained under the premise of absolutely meeting safety red lines. This greatly improves the feasibility and reliability of the optimization scheme in field applications and reduces the probability of downhole failures caused by inappropriate parameters.

[0085] In some embodiments, step S103 above, which uses the condition that the complex operating condition index meets the risk operating condition constraints, may specifically include: the condition that the inner and outer annular pressures meet the overflow and leakage risk constraints, the complex operating condition index meets the wear and vibration risk constraints, and the downhole drilling pressure and downhole drilling speed meet the engineering risk constraints.

[0086] Specifically, the aforementioned risk conditions constraints may include overflow and leakage risk constraints, wear and vibration risk constraints, and engineering risk constraints.

[0087] In some embodiments, overflow and lost circulation risk constraints can be used to prevent two major safety incidents: overflow (formation fluid inflow into the wellbore) and lost circulation (drilling fluid loss into the formation). A pre-set annular pressure safety window can be established, with the lower limit being the minimum permissible annular pressure to prevent overflow and the upper limit being the maximum permissible annular pressure to prevent lost circulation.

[0088] In some embodiments, when searching for parameters, the optimization algorithm can predict or calculate the wellbore pressure profile corresponding to the candidate parameter combination in real time and ensure that it is within a preset safety window.

[0089] In some embodiments, wear and vibration risk constraints can be used to control tool and machinery risks such as drill string vibration and drill bit wear. An upper limit threshold (RF_max) can be set for the Complexity Index (RF).

[0090] In some embodiments, for each candidate combination of downhole drilling pressure and rotation speed, the corresponding RF prediction model can be invoked for calculation, and RF ≤ RF_max is required.

[0091] In some embodiments, engineering risk constraints can be used to ensure that the optimized parameters are within the physical capabilities of the surface and downhole equipment, including the upper and lower limits of downhole drilling pressure and downhole rotation speed, which are determined by the technical specifications of equipment such as drill bits, drill pipes, and top drives.

[0092] By transforming the three major risk categories into hard constraints in the optimization model, proactive and automated safety management is achieved. The optimization algorithm actively avoids all known risk areas from the outset, fundamentally eliminating the possibility of unsafe parameter combinations being recommended, thus elevating drilling safety from passive post-event alerts to proactive pre-event prevention. The final optimized parameter combination absolutely meets well control safety, tool safety, and equipment capability limitations, greatly improving the executability and success rate of the optimization scheme in the field, laying a reliable safety foundation for unmanned and automated drilling.

[0093] In some embodiments, step S103 may specifically include: determining the weighting coefficients of the mechanical drilling rate and mechanical specific energy based on drilling stage data; and constructing a multi-objective optimization function based on the weighting coefficients, with the goal of maximizing the mechanical drilling rate and minimizing the mechanical specific energy.

[0094] In some embodiments, maximizing the mechanical rate of penetration (ROP) corresponds to the pursuit of drilling efficiency. By maximizing ROP, the aim is to shorten the drilling cycle and directly reduce time-related costs.

[0095] In some embodiments, minimizing mechanical specific energy (MSE) corresponds to the efficiency and energy consumption goals of drilling operations. By minimizing MSE, the aim is to improve the energy utilization efficiency of rock breaking, reduce energy consumption per unit footage, and reduce non-productive wear of the drill string.

[0096] In some embodiments, drilling stage data can be a set of parameters used to identify and classify the drilling process, including at least: real-time well depth, geological steering data (such as gamma rays and resistivity curves), formation pressure monitoring data, mechanical drilling rate trends, and torque vibration characteristics. These data collectively constitute the basis for determining the current stage of the drilling operation.

[0097] In some embodiments, a weight configuration strategy corresponding to different drilling stages can be pre-set. This strategy explicitly specifies the weight values ​​or weight ratio ranges of the two optimization objectives at a specific stage. Therefore, once the current drilling stage is identified, the corresponding weight configuration strategy can be invoked, and appropriate weight coefficients can be assigned to the rate of penetration (ROP) and mechanical energy specificity (MSE), thereby constructing a multi-objective optimization function.

[0098] Specifically, the two objective functions can be normalized and then linearly combined with different weight coefficients to form a single comprehensive objective function. The preferences of different drilling stages (such as emphasizing efficiency in vertical well sections and safety and stability in horizontal well sections) can be reflected by adjusting the weights.

[0099] Pareto optimization can also be used to retain both objectives and seek a set of non-dominated solutions (Pareto solution set), in which it is impossible to improve one objective without making the other objective worse by changing the parameters.

[0100] Compared to traditional single-objective optimization methods, this dual-objective model forces the optimization algorithm to find the optimal balance between drilling speed and efficiency, avoiding the overall performance degradation caused by unilaterally pursuing a single indicator, and achieving a leap from local optima to system optima. It provides a more scientific mathematical description of drilling parameter optimization that aligns with engineering efficiency, ensuring that the final optimized solution is the optimal choice that comprehensively considers production efficiency.

[0101] In some embodiments, the above objectives and constraints can be mathematically integrated to form a complete model representation. For example, the optimization model can be characterized as follows: Objective: Min (-aROP+bMSE) (equivalent to Max ROP and Min MSE); Constraints: RF≤RF_max; Decision variables: downhole drilling pressure WOB, downhole rotation speed N; where a and b are weighting coefficients that can be dynamically adjusted according to engineering requirements.

[0102] By unifying the goals of drilling optimization—speeding up, reducing costs, and ensuring safety—within a rigorous mathematical framework, this approach provides a clear search direction and insurmountable safety boundaries for subsequent intelligent optimization algorithms (such as particle swarm optimization and genetic algorithms). Furthermore, the optimization model is dynamic, with its inputs (ROP, MSE, RF) calculated in real time. Therefore, the model itself can adaptively update as downhole conditions change, continuously outputting the optimal parameters best suited to the current geological environment and drill string status.

[0103] S104: Optimize the downhole engineering data according to the optimization model. The downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data.

[0104] In some embodiments, the downhole engineering data mentioned above includes at least downhole drill pressure data and downhole rotation speed data. Based on this, step S104 may specifically include: solving the multi-objective optimization function according to a preset intelligent optimization algorithm to obtain multiple combinations of downhole engineering parameters for drill pressure and rotation speed, each combination corresponding to an optimization scheme for downhole engineering data; selecting one or more candidate downhole engineering parameter combinations that satisfy risk condition constraints from the multiple combinations; sorting the one or more candidate downhole engineering parameter combinations and selecting the optimal downhole engineering parameter combination; and optimizing the downhole engineering data based on the optimal combination of downhole drill pressure and rotation speed.

[0105] In some embodiments, the combination of downhole engineering parameters can be a specific pair of values ​​consisting of the decision variables of the optimization problem—namely, downhole drilling pressure and downhole rotation speed. Each combination represents a specific operational option to be chosen.

[0106] In some embodiments, intelligent optimization algorithms (such as improved particle swarm optimization (PSO) or genetic algorithm (GA) can be used to solve multi-objective optimization functions, thereby generating multiple sets of parameter combinations. The execution process may specifically include: Initialization: Within the allowable engineering range of downhole drilling pressure and downhole rotation speed, the algorithm randomly or according to specific rules generates a certain number (e.g., 200) of initial parameter combinations to form the initial population. Each parameter combination is regarded as a particle or individual.

[0107] Iterative search: The algorithm simulates the process of evolution or swarm intelligence based on its internal rules (such as inertia weights and learning factors). In each iteration, it updates and generates new parameter combinations based on the fitness evaluation results, gradually approaching the optimal region.

[0108] Compared to traditional exhaustive or grid-based methods, intelligent algorithms can perform efficient searches combining directional and random approaches within a vast parameter space. This allows them to cover a wider range of possible solutions with less computational cost, significantly improving optimization efficiency and meeting the timeliness requirements of real-time drilling optimization. Furthermore, the algorithm's built-in randomness and collaborative mechanisms enable it to escape local optima, thus increasing its chances of finding globally optimal or near-optimal parameter combinations and enhancing the quality of the optimization scheme.

[0109] In some embodiments, for each parameter combination generated by the algorithm during the search process, it can be substituted into a multi-objective optimization function to calculate its corresponding predicted complex working condition index in real time. Subsequently, constraint condition judgment is performed, that is, only those parameter combinations that satisfy RF≤RF_max are retained and marked as candidate downhole engineering parameter combinations; all combinations that do not satisfy this constraint are immediately eliminated.

[0110] By eliminating all potentially high-risk parameter solutions early in the optimization process, subsequent ranking and decision-making are ensured to occur only within an absolutely safe region, fundamentally preventing the possibility of unsafe solutions being recommended. Furthermore, by preemptively removing a large number of invalid or dangerous solutions, the effective search space is reduced, allowing subsequent ranking calculations to focus resources on the analysis of high-quality solutions. This accelerates decision-making and guarantees the absolute safety of the final output.

[0111] In some embodiments, the above ranking can be based on the overall performance of the optimization objective, evaluating the merits of all candidate parameter combinations.

[0112] In some embodiments, a multi-attribute decision-making method (such as TOPSIS, or the approximation-to-ideal-solution ranking method) can be used to finely rank the selected candidate combinations. Specifically, the comprehensive objective function value, which takes into account both the rate of drilling and the specific energy of the machine, can be calculated for each candidate combination. The TOPSIS method can rank the candidates by calculating the relative distances between each candidate solution and the ideal optimal solution (the best solution for all objectives) and the ideal worst solution (the worst solution for all objectives). The candidate solution that is closest to the ideal optimal solution and furthest from the ideal worst solution is the optimal combination of downhole engineering parameters.

[0113] Methods such as TOPSIS avoid subjective judgment and select the best-performing solution from multiple high-performing candidate solutions through rigorous mathematical calculations, ensuring the scientific validity of the recommended parameters. The final optimal solution not only stays within safety constraints but also achieves the best balance between efficiency and energy consumption.

[0114] In some embodiments, the optimized downhole engineering data may be the optimal downhole drilling pressure setting and the optimal downhole rotation speed setting determined by the above process.

[0115] In some embodiments, the specific values ​​in the optimal downhole engineering parameter combinations selected through sorting can be determined as the final instruction data used to guide on-site control within the current optimization cycle.

[0116] By generating clear, explicit, and quantifiable control objectives, precise inputs are provided for the next stage of direct parameter regulation, serving as the output point of the entire intelligent decision-making process. The complex optimization model solution process is ultimately translated into concrete values ​​that can be understood and executed by field equipment.

[0117] S105: Adjust downhole engineering parameters based on optimized downhole engineering data.

[0118] In some embodiments, step S105 may specifically include: generating downhole control commands based on optimized downhole engineering data; and adjusting downhole engineering parameters based on the downhole control commands.

[0119] In some embodiments, after receiving the optimization results, the ground control center does not directly issue these values, but instead converts them into control commands for specific actuators. Specifically, refer to... Figure 3 For downhole drilling pressure (DBP) control, the optimal DBP value can be translated into commands for the top drive lowering speed and the winch control system. By precisely controlling the drill string lowering speed and hook load, the actual DBP at the drill bit is indirectly, but target-oriented, adjusted to near the optimal value. For downhole rotational speed control, the optimal downhole rotational speed data can be translated into setting commands for the top drive or downhole motor speed. The issuance of commands takes into account the dynamic relationship between surface rotational speed and downhole rotational speed, such as slippage, to ensure that the bottomhole rotational speed reaches the target.

[0120] By using downhole parameters as the ultimate control target, the well-to-surface transmission deviation problem caused by using surface parameters as control setpoints in the traditional method is overcome, enabling more direct and precise control over the working conditions in the core rock-breaking area.

[0121] In some embodiments, the actuators may be devices that receive downhole control commands and directly drive equipment movements, including a drill pressure controller and a top drive speed controller. The generated control commands can be rapidly transmitted to the corresponding actuators via an industrial real-time network or a dedicated control system. These actuators adjust their outputs (such as motor torque and speed, hydraulic system pressure, etc.) in real time according to the commands, driving the drilling rig equipment (top drive, winch) to perform corresponding actions, thereby initiating changes to the actual downhole engineering parameters.

[0122] Automated execution avoids compromised results due to human error or misunderstanding, ensuring that the optimization plan can be fully and accurately implemented downhole.

[0123] In some embodiments, after the control command is issued, the system can initiate a feedback loop: real-time downhole drilling pressure and real-time downhole rotation speed parameters after control can be continuously collected via the downhole measurement sub in step S101. The collected actual values ​​can be compared with the optimized target values ​​in real time to calculate the deviation. Allowable deviation thresholds can be preset (e.g., drilling pressure deviation ±5kN, rotation speed deviation ±2 rpm). If all real-time parameter deviations are within the threshold range, the current control is deemed effective, and the existing command is maintained. If any parameter deviation continues to exceed the threshold, or if a sudden change occurs in the downhole operating conditions (manifested as abnormal mechanical specific energy MSE or complex operating condition index RF), a re-optimization mechanism is immediately triggered, i.e., automatically jumping to step S103, reconstructing and solving the optimization model based on the latest downhole data, generating a new set of optimal parameters more suitable for the current operating conditions, and immediately updating the control command.

[0124] This closed-loop feedback enables the drilling system to cope with time-varying factors such as formation changes and drill string wear, ensuring that the drilling process remains in an optimal or near-optimal state at all times. Through real-time feedback and proactive adjustments, it can automatically suppress internal and external disturbances and has strong fault tolerance and self-recovery capabilities for unforeseen changes in operating conditions, greatly improving the stability and success rate of the entire drilling operation.

[0125] In some embodiments, calculating the mechanical specific energy of the well based on the downhole drilling pressure data, the static rock-breaking factor of the drill bit, and the dynamic friction factor in step S102 may specifically include: calculating the mechanical specific energy of the well using the following formula based on the downhole drilling pressure data, the static rock-breaking factor of the drill bit, and the dynamic friction factor: ; In the formula, MSE is the mechanical specific energy of drilling. MPa ; The static rock-breaking factor of the drill bit; The dynamic friction factor of the drill bit; The diameter of the drill bit. mm ; The coefficient of friction is dimensionless. The cross-sectional area of ​​the drill bit. mm 2 WOB stands for drill pressure at the drill bit. kN N is the drill bit rotation speed. rpm ; T This refers to the drill bit torque. kNm ROP stands for RPM (Rate of Pi) in mechanical drilling. m / h ; and These are preset constant coefficients.

[0126] The aforementioned mechanical energy specificity (MSE) calculation formula directly uses the measured bit bit pressure (WOB) and bit torque (T) as inputs, fundamentally avoiding the energy transfer loss and signal distortion problems associated with traditional methods that use surface parameters. This allows the calculated MSE to accurately reflect the actual energy consumption during the rock breaking process at the bottom of the well, providing a highly reliable data foundation for optimization decisions and significantly improving the accuracy and effectiveness of the optimization results.

[0127] Furthermore, through the dynamic friction coefficient Achieve self-sensing of operating conditions. This is achieved by defining the friction coefficient as a dynamic variable. Rather than a fixed empirical constant, the friction coefficient is defined as a condition health factor that reflects the downhole working conditions in real time. Abnormal changes in the friction coefficient can directly indicate complex downhole conditions. For example, an abnormally high value may indicate drill bit mud buildup, balling, or encountering highly abrasive formations; an abnormally low value may indicate drill bit wear or decreased cutting efficiency. By incorporating the dynamic friction coefficient into the MSE calculation, the entire mechanical energy specificity model becomes an intelligent model capable of self-sensing and adapting to changes in downhole conditions, rather than a rigid static formula.

[0128] The above formula for calculating mechanical specific energy decouples the total mechanical specific energy into two components with clear mechanisms: among which, the static rock-breaking term... The basic static pressure required to overcome rock strength is negatively correlated with drill bit area. Dynamic friction term. It characterizes the energy loss during the rotary rock-breaking process, taking into account the effects of friction, rotational speed, and rock-breaking efficiency.

[0129] This structure not only provides the total energy consumption value but also clearly reveals the composition and sources of energy consumption, determining whether low energy efficiency stems primarily from rock breaking itself or frictional losses. This provides a clear optimization path for subsequent optimization algorithms. For example, if the dynamic friction term accounts for too high a proportion, the optimization focus should be on adjusting parameters to reduce frictional losses, thereby achieving more precise and intelligent parameter control.

[0130] The aforementioned mechanical energy specificity calculation formula is not a simple mathematical equivalence. Its core lies in creating an intelligent energy efficiency assessment model that can accurately sense, diagnose in real time, and has clear physical meaning by introducing a dynamic friction coefficient and a clear mechanistic structure. This provides crucial technical support for the entire downhole parameter intelligent control system to achieve a leap from indirect speculation to direct sensing, and from experience-driven to a dual-driven approach of mechanism and data.

[0131] In some embodiments, calculating the drilling complexity index based on the mechanical specific energy and the formation's drill resistance in step S102 may specifically include: calculating the drilling complexity index using the following formula based on the mechanical specific energy and the formation's drill resistance: ; In the formula, RF is the complex working condition index of the drill bit; WOB is the pressure on the drill bit. kN ; is the dynamic friction factor of the drill bit; DS is the formation's drill resistance strength; DOC is the depth of penetration per drill bit revolution. m ; The diameter of the drill bit. mm ; The cross-sectional area of ​​the drill bit. mm 2 N is the drill bit rotation speed. rpm T represents the drill bit torque. kNm ROP stands for RPM (Rate of Pi) in mechanical drilling. m / h ; , and These are preset constant coefficients.

[0132] The final simplified form of the calculation formula for the above complex working condition index This indicates that the index is essentially a torque-to-pressure ratio standardized by drill bit size. In its derivation, the numerator (MSE) includes the total energy consumption, while the denominator (DS, drill resistance) characterizes the overall strength of the formation. Through this ratio calculation, the influence of formation variations (reflected in DS) is effectively eliminated from the total signal.

[0133] This allows the Complex Condition Index to purely reflect the working condition and health of the drill bit itself. Regardless of whether the formation is soft or hard, abnormal changes in the Complex Condition Index mainly point to problems with the drill bit itself, such as drill bit vibration, wear, or mud buildup, rather than formation changes. This enables accurate positioning of complex conditions and greatly reduces the false alarm rate.

[0134] The final formula The RF value measures the level of torque required to generate a unit of drill pressure. In efficient and healthy rock-breaking conditions, torque and drill pressure maintain a stable and reasonable ratio, with the RF value within the normal range. Once this balance is broken, the RF value undergoes characteristic changes. An abnormally high RF value indicates that greater torque is required to achieve the same drill pressure, which usually signifies drill bit vibration (energy wasted on non-productive impacts), mud pockets, or encountering extremely abrasive formations. An abnormally low RF value indicates that even with increased drill pressure, torque cannot increase accordingly, strongly suggesting that the drill bit cutting teeth are worn and dulled, losing their effective rock-breaking ability.

[0135] The above formula provides a solid theoretical basis for the diagnostic logic based on the linkage trend of RF and WOB described in step S102: When both RF and WOB increase simultaneously: it is determined to be drill bit vibration. Because vibration leads to energy waste and a surge in torque, the numerator in the above formula increases much faster than the denominator, resulting in an increase in RF. When RF decreases while WOB increases: it is determined to be drill bit wear. Because wear leads to a decrease in cutting efficiency and weak torque growth, the RF value will inevitably decrease when the denominator increases.

[0136] Although the derivation process involves multiple parameters, the final formula simplifies to only relate to three core downhole directly measurable parameters (downhole torque, downhole drilling pressure, and drill bit diameter). This results in minimal computational burden, enabling real-time updates at a very high frequency, perfectly adapting to the rapidly changing downhole conditions and the real-time requirements of closed-loop control. It reduces reliance on intermediate calculations and excessive parameters, lowers the risk of error accumulation, and improves the overall robustness and reliability of the monitoring system.

[0137] This complex working condition index calculation formula, through ingenious mathematical construction, creates a sensitive indicator that can filter out formation interference, has clear physical meaning, and is directly related to the drill bit's health status. It not only achieves accurate perception of complex downhole working conditions but also provides an indispensable and reliable quantitative basis for subsequent automated risk diagnosis and intelligent safety constraint control.

[0138] In some embodiments, the process of sorting the one or more candidate downhole engineering parameter combinations and selecting the optimal downhole engineering parameter combination in step S104 may further include: obtaining multiple candidate downhole engineering parameter combinations that meet risk constraints; constructing a decision attribute set, wherein the decision attribute set includes at least: optimization target values ​​characterizing efficiency and energy consumption, robustness indicators characterizing parameter stability, and control amplitude indicators characterizing the degree of parameter change; assigning weights to each attribute in the decision attribute set based on the current drilling stage or operating condition; using the decision attribute set and corresponding weights to perform multi-attribute decision sorting on the multiple candidate downhole engineering parameter combinations; and selecting the optimal downhole engineering parameter combination based on the sorting results.

[0139] In some embodiments, the decision attribute set can be a multi-dimensional evaluation index system established for comprehensively evaluating combinations of candidate parameters. It includes multiple key attributes from different engineering perspectives, ensuring the comprehensiveness and scientific nature of the final decision.

[0140] In some embodiments, the following three attribute values ​​can be calculated for each candidate parameter combination: optimization target value, robustness index, and adjustment range index.

[0141] The optimization target value is directly derived from the calculation results of the aforementioned multi-objective optimization model and is a weighted evaluation value that integrates mechanical drilling rate and mechanical specific energy. It characterizes the theoretical comprehensive performance of efficiency and energy consumption of this parameter combination.

[0142] Robustness metrics can be used to assess the stability of a parameter combination when faced with minor disturbances. Their calculation can be based on the mathematical properties of the point on the surface of the objective function, for example, by calculating the gradient or eigenvalues ​​of the Hessian matrix at that point to determine whether it lies in a flat plateau (good robustness) or a steep ridge (poor robustness). A highly robust parameter combination will not exhibit drastic performance fluctuations when subjected to minor geological changes or measurement noise.

[0143] The control amplitude index quantifies the degree of change required to adjust from the currently executed parameters to a candidate parameter combination. It can be calculated as the norm of the difference between the candidate parameter and the current parameter. Excessive control amplitude may exceed the equipment's response capacity or cause instability in the downhole system; therefore, this index is crucial for ensuring a smooth transition during the drilling process.

[0144] By introducing robustness and controllability indicators, the decision-making process no longer blindly relies on an abstract comprehensive score, but comprehensively considers the feasibility, stability, and smoothness of the scheme in field implementation, making the final selected scheme more in line with the actual working conditions underground.

[0145] In some embodiments, appropriate importance coefficients can be assigned to each attribute in the decision attribute set based on the core tasks and risk preferences of different drilling operation stages. Weight configuration templates corresponding to different drilling stages can be pre-stored. When a specific stage is identified or received, the corresponding template is automatically invoked. For example, the conventional high-efficiency drilling stage is given a higher weight to the optimization target value to maximize the speed-up and cost-reduction effect. The complex formation crossing stage increases the weight of robustness indicators, prioritizing operational safety and wellbore stability, even at the expense of some efficiency. The critical equipment performance or operational condition recovery stage increases the weight of control amplitude indicators to ensure smooth parameter transitions and avoid equipment shocks or system oscillations.

[0146] By endowing the decision-making system with strategic thinking and adaptive capabilities, the optimization system can adjust its decision preferences according to different operating conditions, and its output can proactively align with strategic objectives at different stages. Furthermore, through flexible weight configuration, conflicting objectives can be precisely balanced in different scenarios.

[0147] In some embodiments, multi-attribute decision ranking can be achieved by using mathematical methods to comprehensively evaluate and rank the performance of each candidate combination across all attributes.

[0148] In some embodiments, data normalization can be performed to eliminate the influence of different attribute dimensions. Further, a weighted normalization matrix is ​​constructed, which involves multiplying each attribute value by the dynamic weight determined in the previous step. Next, the ideal solution and the negative ideal solution are determined, where the ideal solution is the set of optimal values ​​for each attribute, and the negative ideal solution is the set of worst values ​​for each attribute. The distance between each candidate combination and the ideal and negative ideal solutions can be calculated, and the relative closeness to the ideal solution can be obtained. The higher the closeness, the better the overall performance of the combination. The candidate combination with the highest closeness is selected as the final optimization scheme.

[0149] The final determined optimal combination of downhole engineering parameters is a point that achieves the best balance between efficiency, robustness, and operational stability within safety constraints and under the current drilling stage strategy. It is not only a mathematically excellent solution but also an engineeringally intelligent solution, greatly increasing the probability of the optimized solution succeeding on the first attempt.

[0150] The following is a specific embodiment of this specification: 1. Data collection.

[0151] A downhole engineering parameter measurement sub (including pressure, temperature, torque sensors, etc.) is deployed in the drill string assembly. The acquisition frequency is set to 1 time / second. The data is uploaded to the ground control center in real time through the mud pulse transmission module (transmission rate 2-4bps). The uploaded parameters include: drill bit pressure, torque, rotation speed, inner and outer annular pressure, triaxial vibration, etc. Data is collected synchronously using ground sensors.

[0152] 2. Data preprocessing.

[0153] Downhole engineering parameters are acquired from the downhole engineering parameter measurement system, including but not limited to drill pressure, torque, rotational speed, and annular pressure. Surface logging parameters are obtained from the surface parameter measurement device, including but not limited to surface drill pressure, rotary table rotational speed, pump displacement, and hook load. The acquired data undergoes preprocessing, including but not limited to outlier detection, missing value completion, and standardization / normalization. Surface and downhole data are processed separately in 1-second windows. Outliers are removed using the 3σ criterion, missing data is completed using linear interpolation, and the data is normalized using Min-Max standardization.

[0154] 3. Fusion of surface logging and downhole engineering data.

[0155] First, filters such as Savitzky-Golay are used for smoothing and noise reduction to preserve the global macroscopic trend of parameter changes. Then, based on well depth and standard time, surface parameters (such as surface drilling pressure) and downhole parameters (such as drilling pressure at the drill bit) are mapped to the same time / depth point.

[0156] 4. Downhole condition monitoring module.

[0157] It primarily characterizes the rock-breaking state of downhole parameters, employing a mechanism-data fusion method to calculate mechanical drilling rate, mechanical specific energy, ratio factor, etc., enabling real-time calculation based on the constructed dataset and accurately characterizing the downhole state.

[0158] 5. Construction of multi-objective optimization model.

[0159] With the goals of maximizing mechanical drilling rate and minimizing mechanical specific energy, risk constraints (critical internal and external annular pressure values ​​corresponding to overflow and well leakage risks, and wear and drill string vibration conditions corresponding to ratio factors) and engineering parameter constraints (ensuring that drilling pressure and rotation speed can reach the actual output range of the equipment) are introduced. At the same time, a multi-objective function is constructed using a weighted method or Pareto optimization, and the weight of each objective is dynamically adjusted according to the drilling stage (efficiency is emphasized in vertical well sections, and safety is emphasized in horizontal well sections).

[0160] The optimization function can be set as follows: ; In the formula, These are the weighting coefficients for each indicator (the weighting coefficients can be adjusted automatically). It is the normalization coefficient for each indicator.

[0161] 6. Downhole parameter optimization methods.

[0162] An improved particle swarm optimization algorithm is used to solve the multi-objective function. The specific parameters and process are as follows: Algorithm parameters: Number of particles = 200, Number of iterations = 100, Inertia weight = 0.7, Learning factor c1 = c2 = 2; Solution process: Initialize the particle swarm: Each particle corresponds to a set of downhole drilling pressure and rotation speed combinations (e.g., WOB=90kN, N=85r / min). Risk constraint elimination: Remove 12 invalid combinations, including WOBd=300kN (exceeding engineering constraints) and RF=16 (exceeding risk constraints); TOPSIS sorting: The remaining 38 effective combinations are sorted according to the objective function value, and the optimal combination is selected as: WOB=105kN, N=90r / min; Optimization result verification: Substituting into the mechanical drilling rate prediction model, we get ROP = 14.5 m / h (meets the target); substituting into the MSE formula, we get MSE = 1680 MPa (meets the target); RF = 14.2 ft / in (meets the risk constraint).

[0163] 7. Downhole parameter control strategies and closed-loop control.

[0164] Control command issued: Convert WOB (downhole drilling pressure) = 105kN, N (downhole rotation speed) = 90r / min into control commands: Downhole drilling pressure controller: Adjusts the lowering speed of the top drive, winch, etc., and the load of the hook to increase the drilling pressure at the drill bit from the current 95kN to 105kN; Top drive speed controller: Increases the turntable speed from the current 80 r / min to 90 r / min; Ground pump displacement: Maintain at 30L / s (no adjustment required); Closed-loop feedback adjustment: Ten minutes after adjustment, real-time data was collected: WOBd = 103kN (deviation -2kN, within the allowable threshold ±5kN), N = 89r / min (deviation -1r / min, allowable threshold ±2r / min), ROP = 14.3m / h, MSE = 17.0MPa, RF = 14.5ft / in; Deviation judgment: All parameter deviations are within the threshold and no adjustment is required; If subsequent changes occur in the downhole working conditions, step 6 is executed again to optimize and obtain WOB = 110kN, N = 92r / min, and the control command is updated.

[0165] This method allows for direct control of downhole parameters, providing timely and comprehensive decision support for field engineers.

[0166] As can be seen from the drilling optimization decision-making method based on downhole parameter control provided in the embodiments of this specification above, the embodiments of this specification can acquire drilling data, including downhole engineering data and surface logging data; based on the drilling data, the mechanical drilling rate, mechanical specific energy, and complex operating condition index are calculated, with the complex operating condition index used to characterize the vibration level and wear degree of the drill bit; with the goal of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the complex operating condition index satisfying the risk operating condition constraints, an optimization model is constructed; based on the optimization model, the downhole engineering data is optimized, including at least downhole drilling pressure data and downhole rotation speed data; based on the optimized downhole engineering data, the downhole engineering parameters are controlled. By acquiring and making optimization decisions based on downhole engineering data, the well-to-surface transmission deviation problem caused by the reliance on surface logging data in existing technologies is fundamentally overcome. The mechanical drilling rate, mechanical specific energy, and complex operating condition index on which the optimization model is based are all calculated based on actual downhole operating conditions, making the optimization objectives and constraints closely aligned with actual production. This ensures that the optimized parameter combination accurately matches the actual downhole requirements, avoiding decision-making disconnect caused by parameter distortion, thereby significantly improving the rate of drilling and reducing ineffective energy consumption. Furthermore, by maximizing the rate of drilling and minimizing the specific energy of the machine as parallel objectives, and using the complex operating condition index as a hard constraint, a multi-objective constrained optimization model was constructed. This model forces the optimization algorithm to automatically find the optimal balance between efficiency and energy consumption within a safe range. This overcomes the limitations of traditional single-objective optimization or ignoring safety constraints, enabling the final solution to simultaneously consider drilling speed improvement, cost reduction, and safety assurance, achieving system-level synergistic optimization rather than a one-sided improvement in local indicators.

[0167] Based on the above-described drilling optimization decision-making method based on downhole parameter control, this specification also proposes embodiments of a drilling optimization decision-making device based on downhole parameter control. For example... Figure 4 As shown, the drilling optimization decision-making device 400 based on downhole parameter control may specifically include the following modules: The acquisition module 401 is used to acquire drilling data, which includes downhole engineering data and surface logging data.

[0168] The calculation module 402 is used to calculate the drilling mechanical rate of penetration, mechanical specific energy and complex working condition index based on the drilling data. The complex working condition index is used to characterize the vibration level and wear degree of the drill bit.

[0169] The construction module 403 is used to construct an optimization model with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the condition that the complex working condition index meets the risk working condition constraints.

[0170] The optimization module 404 is used to optimize downhole engineering data according to the optimization model. The downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data.

[0171] The control module 405 is used to adjust the downhole engineering parameters based on the optimized downhole engineering data.

[0172] In some embodiments, the acquisition module 401 described above can be specifically used for: Acquire downhole engineering data at the drill bit location; the downhole engineering data shall include at least downhole torque data and internal and external annular pressure data; Acquire surface logging data; the surface logging data includes at least surface drilling pressure data, rotary table rotation speed data, pump displacement data, and hook load data; The drilling data is obtained by spatiotemporally aligning the downhole engineering data and the surface logging data.

[0173] In some embodiments, the computing module 402 described above can be specifically used for: Based on the drilling data, determine the drilling parameters that affect the rock-breaking efficiency of the drill bit; the rock-breaking parameters that affect the rock-breaking efficiency of the drill bit include at least downhole drilling pressure, downhole torque, downhole rotation speed, inner and outer annular pressure, pump displacement, and hook load; Based on the drilling parameter data that affect the rock-breaking efficiency of the drill bit, the mechanical drilling rate is calculated using a preset mechanical drilling rate prediction model; the mechanical drilling rate prediction model is used to characterize the mapping relationship between the drilling parameters that affect the rock-breaking efficiency of the drill bit and the mechanical drilling rate.

[0174] In some embodiments, the computing module 402 described above can also be used for: Based on the drill bit's size data, the static rock-breaking factor of the drill bit is calculated; the static rock-breaking factor is negatively correlated with the drill bit's size. Based on downhole drilling pressure data, downhole torque data, downhole rotation speed data, drill bit size data, and the mechanical drilling rate data, the dynamic friction factor of the drill bit is calculated; the dynamic friction factor is positively correlated with downhole torque and downhole rotation speed; the dynamic friction factor is negatively correlated with downhole drilling pressure, drill bit size, and mechanical drilling rate. The mechanical specific energy of the well is calculated based on the downhole drilling pressure data, the static rock-breaking factor of the drill bit, and the dynamic friction factor.

[0175] In some embodiments, the computing module 402 described above can also be used for: Based on downhole rotation speed data, drill bit size data, and mechanical drilling rate data, the formation's drill resistance strength is calculated; the drill resistance strength is positively correlated with drill bit size and downhole rotation speed; and negatively correlated with mechanical drilling rate. Based on the mechanical specific energy and the formation's drill resistance strength, the drilling complexity index is calculated.

[0176] In some embodiments, the above-described building module 403 can be specifically used for: The conditions are that the internal and external annular pressures meet the overflow and leakage risk constraints, the complex working condition index meets the wear and vibration risk constraints, and the downhole drilling pressure and downhole drilling speed meet the engineering risk constraints.

[0177] In some embodiments, the above-described construction module 403 can also be used for: Based on drilling stage data, the weighting coefficients for the mechanical drilling rate and mechanical specific energy are determined; Based on the weighting coefficients, a multi-objective optimization function is constructed with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy.

[0178] In some embodiments, the optimization module 404 described above can be specifically used for: Based on the preset intelligent optimization algorithm, the multi-objective optimization function is solved to obtain multiple combinations of downhole engineering parameters of downhole drilling pressure and downhole rotation speed. Each combination of downhole engineering parameters corresponds to an optimization scheme for downhole engineering data. From the multiple combinations of downhole engineering parameters, one or more candidate combinations of downhole engineering parameters that meet the risk condition constraints are selected; The one or more candidate combinations of downhole engineering parameters are sorted, and the optimal combination of downhole engineering parameters is selected. Optimize downhole engineering data based on the optimal combination of downhole drilling pressure and downhole rotation speed.

[0179] In some embodiments, the control module 405 can be specifically used for: Based on the optimized downhole engineering data, generate downhole control commands; Adjust downhole engineering parameters according to the downhole control commands.

[0180] As can be seen from the drilling optimization decision-making device based on downhole parameter control provided in the embodiments of this specification, the embodiments of this specification can acquire drilling data, including downhole engineering data and surface logging data; based on the drilling data, calculate the mechanical drilling rate, mechanical specific energy, and complex operating condition index, whereby the complex operating condition index characterizes the vibration level and wear degree of the drill bit; construct an optimization model with the goal of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the complex operating condition index satisfying the risk operating condition constraints; optimize the downhole engineering data based on the optimization model, whereby the downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data; and adjust the downhole engineering parameters based on the optimized downhole engineering data. By acquiring and making optimization decisions based on downhole engineering data, the well-to-surface transmission deviation problem caused by the reliance on surface logging data in existing technologies is fundamentally overcome. The mechanical drilling rate, mechanical specific energy, and complex operating condition index on which the optimization model is based are all calculated based on actual downhole operating conditions, ensuring that the optimization objectives and constraints closely align with actual production. This ensures that the optimized parameter combination accurately matches the actual downhole requirements, avoiding decision-making disconnect caused by parameter distortion, thereby significantly improving the rate of drilling and reducing ineffective energy consumption. Furthermore, by maximizing the rate of drilling and minimizing the specific energy of the machine as parallel objectives, and using the complex operating condition index as a hard constraint, a multi-objective constrained optimization model was constructed. This model forces the optimization algorithm to automatically find the optimal balance between efficiency and energy consumption within a safe range. This overcomes the limitations of traditional single-objective optimization or ignoring safety constraints, enabling the final solution to simultaneously consider drilling speed improvement, cost reduction, and safety assurance, achieving system-level synergistic optimization rather than a one-sided improvement in local indicators.

[0181] This specification also provides a computer device for a drilling optimization decision-making method based on downhole parameter control, including a processor and a memory for storing processor-executable instructions. Specifically, the processor can perform the following tasks according to the instructions: acquiring drilling data, including downhole engineering data and surface logging data; calculating the drilling speed, mechanical energy specificity, and complexity index based on the drilling data, where the complexity index characterizes the vibration level and wear degree of the drill bit; constructing an optimization model with the goal of maximizing the drilling speed and minimizing the mechanical energy specificity, and with the complexity index satisfying risk condition constraints; optimizing the downhole engineering data based on the optimization model, where the downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data; and controlling the downhole engineering parameters based on the optimized downhole engineering data.

[0182] To execute the above instructions more accurately, please refer to... Figure 5As shown in the embodiments of this specification, another specific computer device 500 is also provided, wherein the computer device 500 includes a network communication port 501, a processor 502 and a memory 503, and the above structures are connected by internal cables so that the various structures can perform specific data interaction.

[0183] The processor 502 can be specifically used for: acquiring drilling data, including downhole engineering data and surface logging data; calculating the mechanical drilling rate, mechanical specific energy, and complex operating condition index based on the drilling data, wherein the complex operating condition index is used to characterize the vibration level and wear degree of the drill bit; constructing an optimization model with the goal of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the complex operating condition index satisfying the risk operating condition constraint; optimizing the downhole engineering data based on the optimization model, wherein the downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data; and adjusting the downhole engineering parameters based on the optimized downhole engineering data.

[0184] The memory 503 can be used to store the corresponding instruction program.

[0185] In this embodiment, the network communication port 501 can be a virtual port bound to different communication protocols, thereby enabling the sending or receiving of different data. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. Furthermore, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM or CDMA; it can also be a Wi-Fi chip; or it can be a Bluetooth chip.

[0186] In this embodiment, the processor 502 can be implemented in any suitable manner. For example, the processor can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, etc. This specification is not limiting.

[0187] In this embodiment, the memory 503 includes volatile memory and non-volatile memory. The memory 503 can include multiple layers. In digital systems, anything that can store binary data can be a memory; in integrated circuits, a circuit with storage function but no physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0188] Furthermore, embodiments of this specification also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described... Figure 1 The instructions for the method shown.

[0189] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0190] It should also be understood that, in the embodiments of this specification, the terms and / or are merely descriptions of the relationships between related objects, indicating that three relationships may exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this specification generally indicates that the preceding and following related objects have an "or" relationship.

[0191] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0192] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0193] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0194] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational tasks to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The task is a function specified in one or more boxes.

[0195] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A drilling optimization decision-making method based on downhole parameter control, characterized in that, include: Acquire drilling data, which includes downhole engineering data and surface logging data; Based on the drilling data, the drilling speed, mechanical energy, and complex condition index are calculated. The complex condition index is used to characterize the vibration level and wear degree of the drill bit. An optimization model is constructed with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the condition that the complex working condition index meets the risk working condition constraint. Based on the optimization model, the downhole engineering data is optimized, and the downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data; Adjust downhole engineering parameters based on optimized downhole engineering data.

2. The method according to claim 1, characterized in that, The acquisition of drilling data includes: Acquire downhole engineering data at the drill bit location; the downhole engineering data shall include at least downhole torque data and internal and external annular pressure data; Acquire surface logging data; the surface logging data includes at least surface drilling pressure data, rotary table rotation speed data, pump displacement data, and hook load data; The drilling data is obtained by spatiotemporally aligning the downhole engineering data and the surface logging data.

3. The method according to claim 1, characterized in that, The calculation of the mechanical drilling rate includes: Based on the drilling data, determine the drilling parameters that affect the rock-breaking efficiency of the drill bit; the rock-breaking parameters that affect the rock-breaking efficiency of the drill bit include at least downhole drilling pressure, downhole torque, downhole rotation speed, inner and outer annular pressure, pump displacement, and hook load; Based on the drilling parameter data that affect the rock-breaking efficiency of the drill bit, the mechanical drilling rate is calculated using a preset mechanical drilling rate prediction model; the mechanical drilling rate prediction model is used to characterize the mapping relationship between the drilling parameters that affect the rock-breaking efficiency of the drill bit and the mechanical drilling rate.

4. The method according to claim 1, characterized in that, The calculation of the mechanical specific energy of the well includes: Based on the drill bit's size data, the static rock-breaking factor of the drill bit is calculated; the static rock-breaking factor is negatively correlated with the drill bit's size. Based on downhole drilling pressure data, downhole torque data, downhole rotation speed data, drill bit size data, and the mechanical drilling rate data, the dynamic friction factor of the drill bit is calculated; the dynamic friction factor is positively correlated with downhole torque and downhole rotation speed; the dynamic friction factor is negatively correlated with downhole drilling pressure, drill bit size, and mechanical drilling rate. The mechanical specific energy of the well is calculated based on the downhole drilling pressure data, the static rock-breaking factor of the drill bit, and the dynamic friction factor.

5. The method according to claim 1, characterized in that, The calculation of the complex operating condition index for drilling includes: Based on downhole rotation speed data, drill bit size data, and mechanical drilling rate data, the formation's drill resistance strength is calculated; the drill resistance strength is positively correlated with drill bit size and downhole rotation speed; and negatively correlated with mechanical drilling rate. Based on the mechanical specific energy and the formation's drill resistance strength, the drilling complexity index is calculated.

6. The method according to claim 1, characterized in that, The condition that the complex operating condition index meets the risk operating condition constraint includes: The conditions are that the internal and external annular pressures meet the overflow and leakage risk constraints, the complex working condition index meets the wear and vibration risk constraints, and the downhole drilling pressure and downhole drilling speed meet the engineering risk constraints.

7. The method according to claim 1, characterized in that, The construction of the optimization model includes: Based on drilling stage data, the weighting coefficients for the mechanical drilling rate and mechanical specific energy are determined; Based on the weighting coefficients, a multi-objective optimization function is constructed with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy.

8. The method according to claim 7, characterized in that, The optimization of downhole engineering data based on the optimization model includes: Based on the preset intelligent optimization algorithm, the multi-objective optimization function is solved to obtain multiple combinations of downhole engineering parameters of downhole drilling pressure and downhole rotation speed. Each combination of downhole engineering parameters corresponds to an optimization scheme for downhole engineering data. From the multiple combinations of downhole engineering parameters, one or more candidate combinations of downhole engineering parameters that meet the risk condition constraints are selected; The one or more candidate combinations of downhole engineering parameters are sorted, and the optimal combination of downhole engineering parameters is selected. Optimize downhole engineering data based on the optimal combination of downhole drilling pressure and downhole rotation speed; The adjustment of downhole engineering parameters based on optimized downhole engineering data includes: Based on the optimized downhole engineering data, generate downhole control commands; Adjust downhole engineering parameters according to the downhole control commands.

9. A drilling optimization decision-making device based on downhole parameter control, characterized in that, include: The acquisition module is used to acquire drilling data, which includes downhole engineering data and surface logging data. The calculation module is used to calculate the drilling speed, mechanical energy, and complex working condition index of the well based on the drilling data. The complex working condition index is used to characterize the vibration level and wear degree of the drill bit. A construction module is used to build an optimization model with the objectives of maximizing the mechanical drilling rate and minimizing the mechanical specific energy, and with the complex working condition index satisfying the risk working condition constraint as a condition; The optimization module is used to optimize downhole engineering data according to the optimization model. The downhole engineering data includes at least downhole drilling pressure data and downhole rotation speed data. The control module is used to adjust downhole engineering parameters based on optimized downhole engineering data.

10. A computer device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the method of any one of claims 1-8.

Images