Methods, devices, equipment, media, and procedures for determining operating parameters during controlled pressure drilling.

Abstract

This invention discloses a method, apparatus, equipment, medium, and program for determining operating parameters during controlled pressure drilling. The method includes: inputting logging data at the current moment into a residual prediction model to obtain the residual operating parameters at the current moment; calculating the theoretical value of the bottom hole pressure at the current moment based on the inlet flow rate and a first bottom hole pressure calculation model; calculating the theoretical value of the outlet flow rate at the current moment based on the inlet flow rate and outlet flow rate calculation model; determining the bottom hole pressure at the current moment based on the theoretical value of the bottom hole pressure and the bottom hole pressure residual; and determining the outlet flow rate at the current moment based on the theoretical value of the outlet flow rate and the outlet flow rate residual. This solution solves the problem of low accuracy in predicting operating parameters during controlled pressure drilling, automatically adapting to changes such as increased well depth and altered drilling fluid properties, fundamentally eliminating false alarms caused by physical model drift, and improving the accuracy of operating parameter prediction.

Description

Technical Field

[0001] This invention relates to the field of oil and gas drilling technology, and in particular to a method, apparatus, equipment, electronic device, storage medium, and computer program product for determining operating parameters during controlled pressure drilling. Background Technology

[0002] As exploration and development extend to deep wells, ultra-deep wells, and complex geological environments such as high temperature and high pressure, drilling operations face severe safety risks and technical challenges. The traditional "post-incident handling" model, such as shutting in the well after discovering a blowout, is no longer sufficient to meet the pursuit of safety and efficiency in ultra-deep and ultra-high pressure environments. Therefore, it is urgent to establish a monitoring system for operating parameters during the drilling process to achieve a leap from passive response to proactive early warning.

[0003] Existing technologies primarily rely on empirical formulas to set fixed physical parameters for predicting operating conditions, neglecting the changes in drilling fluid rheology and friction characteristics brought about by increasing well depth. This leads to a gradual distortion of the predicted operating conditions as well depth increases. For example, the bottom hole pressure prediction method in patent document CN114737948A constructs an input vector based on the controlled-pressure drilling data and the input parameters of the choke valve opening adjustment model. Constraints are established based on the correlation between constraint parameters and the choke valve opening. The choke valve opening adjustment model is trained using these constraints, a neural network, and historical controlled-pressure drilling data from completed reference wells. The input vector is then input into the choke valve opening adjustment model to obtain the predicted choke valve opening. This predicted choke valve opening is then input into the bottom hole pressure calculation model to obtain the predicted bottom hole pressure. Furthermore, existing operating condition parameter prediction methods typically model only a single parameter, lacking multi-variable joint physical constraints. This results in a high false alarm rate under complex operating conditions and makes it difficult to capture true fluid intrusion or leakage characteristics.

[0004] Therefore, there is a need for a method to determine operating parameters that can adaptively identify physical parameters, automatically adapt to changes such as increased well depth and altered drilling fluid properties, accurately separate normal physical fluctuations caused by pump switching from monitoring data, and fundamentally eliminate false alarms caused by physical model drift. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, medium, and program for determining operating parameters during controlled pressure drilling, in order to solve the problem of low accuracy in predicting operating parameters during controlled pressure drilling. By jointly predicting the outlet flow residual and the bottom hole pressure residual through a residual prediction model, the bottom hole pressure and outlet flow can be obtained. It can automatically adapt to changes such as increased well depth and changes in drilling fluid properties, fundamentally eliminating false alarms caused by physical model drift and improving the accuracy of operating parameter prediction.

[0006] According to one aspect of the present invention, a method for determining operating parameters during controlled pressure drilling is provided, the method comprising: The logging data at the current moment is acquired and input into a pre-trained residual prediction model to obtain the residual of the operating parameters at the current moment; the residual of the operating parameters includes the outlet flow rate residual and the bottom hole pressure residual. Based on the current inlet flow rate and the pre-built first bottom hole pressure calculation model, calculate the theoretical value of the bottom hole pressure at the current moment; based on the current inlet flow rate and the pre-built outlet flow rate calculation model, calculate the theoretical value of the outlet flow rate at the current moment. The bottom pressure at the current moment is determined based on the theoretical value of the bottom pressure and the bottom pressure residual. The outlet flow rate at the current moment is determined based on the theoretical value of the outlet flow rate and the outlet flow rate residual.

[0007] According to another aspect of the present invention, an apparatus for determining operating parameters during controlled-pressure drilling is provided, the apparatus comprising: The residual determination module is used to acquire the logging data at the current moment, input the logging data at the current moment into the pre-trained residual prediction model, and obtain the operating condition parameter residuals at the current moment; the operating condition parameter residuals include the outlet flow rate residuals and the bottom hole pressure residuals; The theoretical value determination module is used to calculate the theoretical value of the bottom hole pressure at the current moment based on the current inlet flow rate and the pre-built first bottom hole pressure calculation model, and to calculate the theoretical value of the outlet flow rate at the current moment based on the current inlet flow rate and the pre-built outlet flow rate calculation model. The operating condition parameter determination module is used to determine the bottom hole pressure at the current moment based on the theoretical value of the bottom hole pressure and the bottom hole pressure residual, and to determine the outlet flow rate at the current moment based on the theoretical value of the outlet flow rate and the outlet flow rate residual.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining operating parameters during controlled-pressure drilling as described in any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for determining operating parameters during controlled-pressure drilling as described in any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method for determining operating parameters during controlled-pressure drilling as described in any embodiment of the present invention.

[0011] The technical solution of this invention involves acquiring the logging data at the current moment, inputting the logging data at the current moment into a pre-trained residual prediction model, and obtaining the residuals of the operating parameters at the current moment. These residuals include the outlet flow rate residual and the bottom hole pressure residual. Based on the inlet flow rate at the current moment and a pre-built first bottom hole pressure calculation model, the theoretical value of the bottom hole pressure at the current moment is calculated. Similarly, based on the inlet flow rate at the current moment and a pre-built outlet flow rate calculation model, the theoretical value of the outlet flow rate at the current moment is calculated. Based on the theoretical value of the bottom hole pressure at the current moment and the bottom hole pressure residual, the bottom hole pressure at the current moment is determined. Finally, based on the theoretical value of the outlet flow rate at the current moment and the outlet flow rate residual, the outlet flow rate at the current moment is determined. This technical solution solves the problem of low accuracy in predicting operating parameters during pressure controlled drilling. By jointly predicting the outlet flow rate residual and the bottom hole pressure residual using a residual prediction model, the bottom hole pressure and outlet flow rate are obtained. This automatically adapts to changes such as increased well depth and altered drilling fluid properties, fundamentally eliminating false alarms caused by physical model drift and improving the accuracy of operating parameter prediction.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart of a method for determining operating parameters during controlled pressure drilling according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a method for determining operating parameters during controlled pressure drilling according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a device for determining operating parameters during pressure-controlled drilling according to Embodiment 3 of the present invention; Figure 4This is a schematic diagram of the structure of an electronic device for implementing the method of determining operating parameters during controlled-pressure drilling according to an embodiment of the present invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 used interchangeably where appropriate so that the embodiments of the invention 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 non-exclusive inclusion; for example, a process, method, system, 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. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0017] Example 1 Figure 1 This invention provides a flowchart of a method for determining operating parameters during controlled pressure drilling, according to Embodiment 1. This embodiment is applicable to controlled pressure drilling scenarios, particularly for predicting operating parameters such as bottom hole pressure and outlet flow rate during controlled pressure drilling. This method can be executed by a device for determining operating parameters during controlled pressure drilling. This device can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes: S110. Obtain the logging data at the current moment, input the logging data at the current moment into the pre-trained residual prediction model, and obtain the operating condition parameter residuals at the current moment; the operating condition parameter residuals include the outlet flow residuals and the bottom hole pressure residuals.

[0018] This solution can be executed by electronic devices such as computers and servers. These devices can communicate with the logging system at the target well site to obtain logging data at the current moment. The logging data may include one or more of the following: drill bit depth, well depth, vertical depth, drill bit vertical depth, drill bit pressure, drilling speed, hook load, rotary table speed, torque, standpipe pressure, inlet flow rate, outlet flow rate, casing pressure, PWD depth, PWD vertical depth, PWD pressure, and PWD flow rate.

[0019] Well logging systems typically employ multiple sensors, and the data acquired by these sensors may vary in acquisition methods and formats. Electronic equipment can standardize the acquired well logging data by performing actions such as unifying naming and data formatting to facilitate subsequent data processing. To avoid temporal discrepancies caused by varying acquisition frequencies of different sensors, electronic equipment can unify the frequency of data from different sensors within the well logging data and resample data from sensors with lower acquisition frequencies to obtain well logging data with a uniform acquisition frequency, continuous temporal flow, and no missing values.

[0020] Understandably, abnormal drilling conditions such as gas intrusion, overflow, and lost circulation can be identified through operating parameters. These parameters include bottom hole pressure and outlet flow rate. When gas intrusion occurs in formations with narrow safety pressure windows, the migration of the intruding gas will cause abnormal fluctuations in bottom hole pressure. In the early stages of gas intrusion, when the gas volume is small, the bottom hole pressure will initially decrease slightly. As the gas expands, the bottom hole pressure will fluctuate significantly. If the bottom hole pressure continues to decrease and exceeds the normal range, gas intrusion or overflow is highly likely, requiring timely pressure control measures. If the bottom hole pressure suddenly drops sharply, the outlet flow rate suddenly decreases sharply, or even there is no flow, lost circulation may have occurred, with a large amount of drilling fluid leaking into the formation. Loss of circulation will cause a rapid decrease in the fluid column pressure within the wellbore, resulting in a sharp drop in bottom hole pressure. Electronic equipment can predict the operating parameters at the current moment based on the logging data.

[0021] To enable the operating condition parameter prediction model to automatically adapt to changes such as increased well depth and altered drilling fluid properties, and to accurately isolate normal physical fluctuations caused by pump switching from the logging data, the electronic equipment can automatically focus on and amplify subtle early signs of abnormal operating conditions. The electronic system can use a residual prediction model to predict the residuals of the operating conditions at the current moment based on the logging data, and then derive the operating conditions based on these residuals. Specifically, the outlet flow rate residual can be the difference between the theoretical and measured outlet flow rate, and the bottom hole pressure residual can be the difference between the theoretical and measured bottom hole pressure.

[0022] S120. Calculate the theoretical value of the bottom hole pressure at the current moment based on the inlet flow rate at the current moment and the pre-built first bottom hole pressure calculation model. Calculate the theoretical value of the outlet flow rate at the current moment based on the inlet flow rate at the current moment and the pre-built outlet flow rate calculation model.

[0023] It's easy to understand that under steady-state conditions, the bottom hole pressure and inlet flow rate are exponentially related, while under transient conditions, the change in fluid volume is directly proportional to the change in bottom hole pressure. To calculate the theoretical values ​​of the operating parameters, the electronic equipment can construct a first bottom hole pressure calculation model based on the correlation between bottom hole pressure and inlet flow rate, and a second model for calculating outlet flow rate based on the correlation between fluid volume change and bottom hole pressure change.

[0024] In this scheme, the first bottom hole pressure calculation model is determined based on the exponential relationship between bottom hole pressure and inlet flow rate under steady-state conditions; the outlet flow rate calculation model is determined based on the positive correlation between fluid volume change and bottom hole pressure change under transient conditions.

[0025] Based on the above scheme, the first bottom hole pressure calculation model is expressed as follows: ; express The pressure at the bottom of the well at any given moment. express Ingress traffic at any given moment Indicates power. Indicates the coefficient of friction. The friction coefficient and the hydrostatic pressure are obtained by fitting the bottom hole pressure and inlet flow rate at multiple historical moments under steady-state conditions. The export flow calculation model is expressed as follows: ; express The outflow at any given moment express Ingress traffic at any given moment Indicates the fluid storage coefficient. express The change in bottom hole pressure at any given time; the fluid storage coefficient is obtained by fitting the bottom hole pressure, inlet flow rate, and outlet flow rate at multiple historical moments under transient conditions.

[0026] In a feasible scheme, the historical time in steady state satisfies the condition that the change in bottom hole pressure is less than a first pressure threshold and the inlet flow rate is greater than a preset flow rate threshold; the historical time in transient state satisfies the condition that the change in bottom hole pressure is greater than or equal to a second pressure threshold and the inlet flow rate is greater than a preset flow rate threshold; the first pressure threshold is less than the second pressure threshold.

[0027] In this plan, express The change in bottom hole pressure at any given time. ,in, express The pressure at the bottom of the well at any given moment. express The bottom hole pressure at each historical moment. Electronic equipment can pre-calculate the changes in bottom hole pressure at each historical moment. Based on these changes and the inlet flow rate, it can determine whether each historical moment represents a steady-state or transient state. In a specific example, a historical moment in a steady-state state should satisfy... , The historical moments in the transient state should satisfy the following: , ,in, .

[0028] After dividing the state at each historical moment, the electronic equipment can use the bottom hole pressure and inlet flow rate at each historical moment under steady-state conditions as sample points to fit the exponential relationship between bottom hole pressure and inlet flow rate, obtaining the friction coefficient and hydrostatic column pressure, and thus deriving the first bottom hole pressure calculation model. Specifically, the electronic equipment can fit the exponential relationship between bottom hole pressure and inlet flow rate based on the least squares method, letting... , , The value of is determined based on the drilling fluid type and flow regime, and the objective loss function is expressed as . Setting the partial derivative of the target loss function with respect to the friction coefficient to 0, we obtain the friction coefficient and the hydrostatic pressure. The value of the friction coefficient can be expressed as: The value of the hydrostatic column pressure can be expressed as: , This represents the average bottom hole pressure at each historical moment under steady-state conditions. Indicates the sample point index. Indicates the number of sample points. This represents the average inflow rate at each historical moment under steady-state conditions.

[0029] Electronic equipment can calculate the change in flow volume at each historical time point based on the outflow and inflow rates. Specifically, express The change in flow volume at any given time. , express The outflow at any given moment express The inlet flow rate at any given time. The electronic equipment can use the flow rate volume change and bottom hole pressure at each historical moment in the transient state as sample points, and fit the proportional relationship between the fluid volume change and the bottom hole pressure change based on the least squares method to obtain the fluid storage coefficient, and then obtain the outlet flow rate calculation model.

[0030] After obtaining the first bottomhole pressure calculation model, the electronic equipment can input the current inlet flow rate into the first bottomhole pressure calculation model to calculate the theoretical value of the bottomhole pressure at the current moment. After obtaining the outlet flow rate calculation model, the electronic equipment can input the current inlet flow rate into the outlet flow rate calculation model to calculate the theoretical value of the outlet flow rate at the current moment.

[0031] S130. Determine the bottom pressure at the current moment based on the theoretical value of the bottom pressure and the bottom pressure residual. Determine the outlet flow rate at the current moment based on the theoretical value of the outlet flow rate and the outlet flow rate residual.

[0032] After obtaining the theoretical value of the bottom hole pressure at the current moment, the electronic equipment can use the sum of the theoretical value of the bottom hole pressure at the current moment and the bottom hole pressure residual output by the residual prediction model at the current moment as the bottom hole pressure at the current moment. Similarly, after obtaining the theoretical value of the outlet flow rate at the current moment, the electronic equipment can use the sum of the theoretical value of the outlet flow rate at the current moment and the outlet flow rate residual output by the residual prediction model at the current moment as the outlet flow rate at the current moment.

[0033] The technical solution of this invention involves acquiring the logging data at the current moment, inputting the logging data at the current moment into a pre-trained residual prediction model, and obtaining the residuals of the operating parameters at the current moment. These residuals include the outlet flow rate residual and the bottom hole pressure residual. Based on the inlet flow rate at the current moment and a pre-built first bottom hole pressure calculation model, the theoretical value of the bottom hole pressure at the current moment is calculated. Similarly, based on the inlet flow rate at the current moment and a pre-built outlet flow rate calculation model, the theoretical value of the outlet flow rate at the current moment is calculated. Based on the theoretical value of the bottom hole pressure at the current moment and the bottom hole pressure residual, the bottom hole pressure at the current moment is determined. Finally, based on the theoretical value of the outlet flow rate at the current moment and the outlet flow rate residual, the outlet flow rate at the current moment is determined. This technical solution solves the problem of low accuracy in predicting operating parameters during pressure controlled drilling. By jointly predicting the outlet flow rate residual and the bottom hole pressure residual using a residual prediction model, the bottom hole pressure and outlet flow rate are obtained. This automatically adapts to changes such as increased well depth and altered drilling fluid properties, fundamentally eliminating false alarms caused by physical model drift and improving the accuracy of operating parameter prediction.

[0034] Example 2 Figure 2This is a flowchart illustrating a method for determining operating parameters during controlled-pressure drilling, as provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2 As shown, the method includes: S210. Obtain the logging data at the current moment, use the logging data at the current moment as the feature vector of the current moment, and combine it with the feature vectors of a preset number of historical moments within a preset time sliding window to form a feature matrix. Input the matrix into a bidirectional long short-term memory network to obtain the bidirectional fused features of the current moment.

[0035] In this scheme, the residual prediction model is a model built based on bidirectional long short-term memory network and self-attention mechanism.

[0036] Optionally, the bidirectional long short-term memory network includes a forward long short-term memory structure and a backward long short-term memory structure; The forward long short-term memory structure outputs the positive feature at the current moment, and the backward long short-term memory structure outputs the negative feature at the current moment; the bidirectional fused feature is obtained by concatenating the positive feature at the current moment with the negative feature at the current moment.

[0037] Positive features are output from the forward long short-term memory structure in the bidirectional long short-term memory network. The forward long short-term memory structure is used to capture the evolution trend of the feature matrix. Positive features can be represented as: , express The feature vector at time step, express The forward hidden layer state vector at time 1. This indicates forward long short-term memory structure operations.

[0038] The inverse feature is output by the inverse long short-term memory structure in the bidirectional long short-term memory unit. The inverse long short-term memory structure is used to capture the backtracking dependencies of the feature matrix. The inverse feature can be represented as: , express The feature vector at time step, express The inverse hidden layer state vector at time 1. This indicates reverse long short-term memory structure operations.

[0039] After obtaining the positive and negative features at the current moment, the electronic device can concatenate the positive and negative features at the current moment to obtain the bidirectional fused features at the current moment. The bidirectional fused features can be represented as: .

[0040] S220. Based on the self-attention mechanism, calculate the attention energy score of the current moment and the historical moments within the current time sliding window according to the bidirectional fusion characteristics of the current moment and the bidirectional fusion characteristics of each historical moment within the current time sliding window.

[0041] The self-attention mechanism quantifies the geometric projection relationship between the bidirectional fused features at the current time step and the bidirectional fused features at a historical time step by calculating the dot product of the two. The dot product of the bidirectional fused features at the current time step and the bidirectional fused features at a historical time step is the attention energy score of the current time step and the historical time step. The magnitude of the attention energy score directly reflects the degree of influence of the feature evolution at a certain historical time step on the feature at the current time step.

[0042] Specifically, the formula for calculating attention energy score can be expressed as: , ; The length of the time sliding window is indicated by the attention energy score, which represents the degree of matching between the bidirectional fusion features at the current moment and the bidirectional fusion features at historical moments within the current time window. The larger the attention energy score, the stronger the correlation between the two.

[0043] S230. Based on the attention energy scores of each historical moment within the current time sliding window, determine the residual of the operating parameters at the current moment; the residual of the operating parameters includes the outlet flow residual and the bottom hole pressure residual.

[0044] After obtaining the attention energy scores of the current time and each historical time within the current time sliding window, the electronic device can extract features from the attention energy scores of the current time and each historical time within the current time sliding window to obtain the residual operating parameters of the current time.

[0045] Based on the above scheme, the residual operating parameters at the current moment are determined according to the attention energy scores of the current moment and each historical moment within the current time sliding window, including: Input the attention energy scores of the current time and each historical time within the current time sliding window into a preset activation function to obtain the attention weight coefficients matched for each historical time within the current time sliding window. The semantic features of the current time sliding window are obtained by weighting the bidirectional fusion features of each historical moment using the attention weight coefficients matched at each historical moment. Global average pooling is applied to the semantic features of the current time sliding window to obtain a global feature summary of the current time sliding window; A linear regression mapping is performed on the global feature summary of the current time sliding window to obtain the residual of the operating parameters at the current time.

[0046] In this embodiment, the electronic device can exponentially process the attention energy score through an activation function. On the one hand, this can amplify the score difference, making strong signals stronger and weak noise weaker. On the other hand, it can ensure that the sum of the weights of all historical moments within the current time sliding window is strictly equal to 1, thus adaptively ignoring background noise and focusing on key time segments containing residuals of abnormal operating condition parameters.

[0047] Specifically, the activation function can be the Softmax function, with the expression: ; This represents the attention weight coefficient. , indicating a historical moment In assessing the importance of the current operating condition. This represents an exponential function with the natural constant as its base. Utilizing the non-linear properties of this exponential function, the difference between different attention energy scores can be widened, highlighting key signals. This indicates the time index in the current time sliding window. This indicates the length of the time sliding window.

[0048] After obtaining the attention weight coefficients matched at each historical moment, the electronic device can use these attention weight coefficients to weight the bidirectional fusion features of each historical moment to obtain the semantic features of the current time sliding window. The semantic features of the current time sliding window can be represented as follows: ; This indicates the time index in the current time sliding window. Indicates the length of the time sliding window. This represents a historical moment in the current time sliding window. Matching attention weight coefficients, This represents a historical moment in the current time sliding window. Its bidirectional fusion characteristics.

[0049] To prevent overfitting, electronic devices can perform global average pooling on the semantic features of the current time sliding window to compress the features along the time dimension and extract a global feature summary for the current time sliding window. The global feature summary of the current time sliding window can be represented as: , This represents the global average pooling function. This represents the semantic features of the current time-based sliding window.

[0050] The global feature summary of the current time sliding window is input into the linear regressor to obtain the residuals of the operating parameters at the current time step. Specifically, the fully connected layer can act as a linear regressor to map the high-dimensional feature space back to the one-dimensional physical space for residual prediction of the operating parameters. The prediction results of the operating parameter residuals can be expressed as: ; This represents the weight matrix of the fully connected layer. This represents a global feature summary of the current time-sliding window. This represents the bias term of the fully connected layer, used to correct the intercept of linear regression.

[0051] S240. Calculate the theoretical value of the bottom hole pressure at the current moment based on the inlet flow rate at the current moment and the pre-built first bottom hole pressure calculation model. Calculate the theoretical value of the outlet flow rate at the current moment based on the inlet flow rate at the current moment and the pre-built outlet flow rate calculation model.

[0052] S250. Determine the bottom pressure at the current moment based on the theoretical value of the bottom pressure and the bottom pressure residual. Determine the outlet flow rate at the current moment based on the theoretical value of the outlet flow rate and the outlet flow rate residual.

[0053] In one feasible approach, the residual prediction model is trained using historical logging data as input and historical mining parameter residuals as labels. The bottom hole pressure residual at a historical moment is the difference between the theoretical bottom hole pressure calculated by the first bottom hole pressure calculation model and the reference bottom hole pressure calculated by the second bottom hole pressure calculation model. The residual of the outflow at a historical moment is the difference between the theoretical value of the outflow calculated by the outflow calculation model and the measured value of the outflow obtained by logging.

[0054] The electronic equipment can acquire logging data from multiple historical moments, and can also obtain measured values ​​of outlet flow rate at each historical moment through the logging system. Since the bottom hole pressure value is obtained directly through measurement, the electronic equipment can calculate the theoretical value of bottom hole pressure at each historical moment based on the first bottom hole pressure calculation model, and calculate the reference value of bottom hole pressure at each historical moment based on the second bottom hole pressure calculation model. It should be noted that the reference value of bottom hole pressure calculated by the second bottom hole pressure calculation model is closer to the actual bottom hole pressure value than the theoretical value of bottom hole pressure calculated by the first bottom hole pressure calculation model. In other words, the bottom hole pressure calculated by the second bottom hole pressure calculation model is more accurate than that calculated by the first bottom hole pressure calculation model.

[0055] The electronic device can use the difference between the theoretical bottom-hole pressure calculated by the first bottom-hole pressure calculation model and the reference bottom-hole pressure calculated based on the second bottom-hole pressure calculation model as the bottom-hole pressure residual, and the difference between the theoretical outlet flow calculated by the outlet flow calculation model and the measured outlet flow obtained from logging as the outlet flow residual.

[0056] Understandably, electronic devices use logging data from each historical moment as input data for the residual prediction model, and use the residuals of the mining parameters from each historical moment as labels to train the residual prediction model, thus obtaining a residual prediction model that can be used to predict the residuals of the operating parameters in future moments.

[0057] Based on the above scheme, the second bottom hole pressure calculation model divides the well structure into finite element parts, and performs bottom hole pressure numerical simulation on each finite element element to obtain the bottom hole pressure reference value based on the mass conservation equation and the momentum conservation equation.

[0058] The electronic device can construct a second bottom-hole pressure calculation model based on numerical simulation. Specifically, it can establish a geometric model of the wellbore based on the wellbore structure, formation parameters, and fluid properties. The finite element method (FEM) is used to divide the geometric model into numerous interconnected finite element elements, achieving discretization of the computational domain. The mass conservation equation describes that the difference in fluid mass flowing into and out of the control volume per unit time equals the increment of fluid mass within that control volume, ensuring mass balance during fluid flow. The momentum conservation equation describes that the sum of all external forces acting on the fluid equals the rate of change of fluid momentum, allowing calculation of the dynamic effects of gravity, friction, and pressure gradients during fluid flow. The electronic device can discretize the continuous mass and momentum conservation equations on each finite element element, transforming them into a system of algebraic equations. Given initial and boundary conditions, such as wellhead pressure and inlet flow rate, the system of algebraic equations is solved using numerical iteration methods to obtain the pressure, velocity, and other parameter distributions on each finite element element, thereby extracting the bottom-hole pressure reference value.

[0059] After obtaining the operating parameters at the current moment, the electronic equipment can draw operating parameter change curves based on the operating parameters at the historical moment and the current moment, so as to intuitively display the changing trend of the operating parameters, timely identify early signs of abnormal operating conditions such as gas intrusion, overflow and well leakage, and provide risk warnings to ensure construction safety during controlled pressure drilling.

[0060] This technical solution utilizes a bidirectional long short-term memory network and an attention mechanism to deeply mine the residuals of operating parameters at historical moments, solving the problem of information forgetting in long-sequence monitoring. It also has the potential to automatically focus on and amplify subtle early signs of anomalies even under strong background noise interference. The residual prediction model trained based on deep learning has transfer and generalization capabilities in cross-well applications across different blocks and well types, effectively reducing the deployment difficulty and maintenance cost of operating parameter prediction models.

[0061] Example 3 Figure 3 This is a schematic diagram of a device for determining operating parameters during pressure-controlled drilling, provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: The residual determination module 310 is used to acquire the logging data at the current moment, input the logging data at the current moment into the pre-trained residual prediction model, and obtain the operating condition parameter residuals at the current moment; the operating condition parameter residuals include the outlet flow rate residuals and the bottom hole pressure residuals. The theoretical value determination module 320 is used to calculate the theoretical value of the bottom hole pressure at the current moment based on the inlet flow rate at the current moment and the pre-built first bottom hole pressure calculation model, and to calculate the theoretical value of the outlet flow rate at the current moment based on the inlet flow rate at the current moment and the pre-built outlet flow rate calculation model. The operating condition parameter determination module 330 is used to determine the bottom pressure at the current time based on the theoretical value of the bottom pressure and the bottom pressure residual at the current time, and to determine the outlet flow rate at the current time based on the theoretical value of the outlet flow rate and the outlet flow rate residual at the current time.

[0062] In this scheme, the first bottom hole pressure calculation model is determined based on the exponential relationship between bottom hole pressure and inlet flow rate under steady-state conditions; the outlet flow rate calculation model is determined based on the positive correlation between fluid volume change and bottom hole pressure change under transient conditions.

[0063] Based on the above scheme, the first bottom hole pressure calculation model is expressed as follows: ; express The pressure at the bottom of the well at any given moment. express Ingress traffic at any given moment Indicates power. Indicates the coefficient of friction. The friction coefficient and the hydrostatic pressure are obtained by fitting the bottom hole pressure and inlet flow rate at multiple historical moments under steady-state conditions. The export flow calculation model is expressed as follows: ; express The outflow at any given moment express Ingress traffic at any given moment Indicates the fluid storage coefficient. express The change in bottom hole pressure at any given time; the fluid storage coefficient is obtained by fitting the bottom hole pressure, inlet flow rate, and outlet flow rate at multiple historical moments under transient conditions.

[0064] Optionally, in steady state, the historical time point satisfies that the bottom hole pressure change is less than a first pressure threshold and the inlet flow rate is greater than a preset flow rate threshold; in transient state, the historical time point satisfies that the bottom hole pressure change is greater than or equal to a second pressure threshold and the inlet flow rate is greater than a preset flow rate threshold; the first pressure threshold is less than the second pressure threshold.

[0065] In this embodiment, the residual prediction model is a model built based on bidirectional long short-term memory network and self-attention mechanism.

[0066] Based on the above scheme, the residual determination module 310 includes: The fusion feature generation unit is used to take the current logging data as the feature vector of the current time, and combine it with the feature vectors of a preset number of historical times within a preset time sliding window to form a feature matrix, which is then input into a bidirectional long short-term memory network to obtain the bidirectional fusion feature of the current time. The energy score calculation unit is used to calculate the attention energy score of the current moment and the historical moments within the current time sliding window based on the bidirectional fusion characteristics of the current moment and the bidirectional fusion characteristics of each historical moment within the current time sliding window, according to the self-attention mechanism. The residual determination unit is used to determine the residual of the operating parameters at the current moment based on the attention energy scores of the current moment and each historical moment within the current time sliding window.

[0067] Based on the aforementioned scheme, the residual determination unit is specifically used for: Input the attention energy scores of the current time and each historical time within the current time sliding window into a preset activation function to obtain the attention weight coefficients matched for each historical time within the current time sliding window. The semantic features of the current time sliding window are obtained by weighting the bidirectional fusion features of each historical moment using the attention weight coefficients matched at each historical moment. Global average pooling is applied to the semantic features of the current time sliding window to obtain a global feature summary of the current time sliding window; A linear regression mapping is performed on the global feature summary of the current time sliding window to obtain the residual of the operating parameters at the current time.

[0068] In this embodiment, the bidirectional long short-term memory network includes a forward long short-term memory structure and a backward long short-term memory structure; The forward long short-term memory structure outputs the positive feature at the current moment, and the backward long short-term memory structure outputs the negative feature at the current moment; the bidirectional fused feature is obtained by concatenating the positive feature at the current moment with the negative feature at the current moment.

[0069] In one feasible approach, the residual prediction model is trained using historical logging data as input and historical mining parameter residuals as labels. The bottom hole pressure residual at a historical moment is the difference between the theoretical bottom hole pressure calculated by the first bottom hole pressure calculation model and the reference bottom hole pressure calculated by the second bottom hole pressure calculation model. The residual of the outflow at a historical moment is the difference between the theoretical value of the outflow calculated by the outflow calculation model and the measured value of the outflow obtained by logging.

[0070] Based on the above scheme, the second bottom hole pressure calculation model divides the well structure into finite element parts, and performs bottom hole pressure numerical simulation on each finite element element to obtain the bottom hole pressure reference value based on the mass conservation equation and the momentum conservation equation.

[0071] Optionally, the logging data includes bit depth, well depth, vertical depth, bit vertical depth, drilling pressure, drilling speed, hook load, rotary table speed, torque, stand pressure, inlet flow rate, outlet flow rate, casing pressure, PWD depth, PWD vertical depth, PWD pressure, and PWD flow rate.

[0072] The device for determining operating parameters during controlled pressure drilling provided in this embodiment of the invention can execute the method for determining operating parameters during controlled pressure drilling provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0073] Example 4 Figure 4 A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0074] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory communicatively connected to the at least one processor 411. The memory may be a read-only memory (ROM) 412, a random access memory (RAM) 413, etc. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0075] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0076] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as methods for determining operating parameters during controlled-pressure drilling.

[0077] In some embodiments, the method for determining operating parameters during controlled pressure drilling can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the method for determining operating parameters during controlled pressure drilling described above can be performed. Alternatively, in other embodiments, processor 411 can be configured to perform the method for determining operating parameters during controlled pressure drilling by any other suitable means (e.g., by means of firmware).

[0078] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0079] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other device for determining operating parameters during programmable controlled-pressure drilling, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0080] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0082] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0083] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0084] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0085] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining operating parameters during controlled pressure drilling, characterized in that, The method includes: The logging data at the current moment is acquired and input into a pre-trained residual prediction model to obtain the residual of the operating parameters at the current moment; the residual of the operating parameters includes the outlet flow rate residual and the bottom hole pressure residual. Based on the current inlet flow rate and the pre-built first bottom hole pressure calculation model, calculate the theoretical value of the bottom hole pressure at the current moment; based on the current inlet flow rate and the pre-built outlet flow rate calculation model, calculate the theoretical value of the outlet flow rate at the current moment. Determine the bottom pressure at the current moment based on the theoretical value of the bottom pressure and the bottom pressure residual; determine the outlet flow rate at the current moment based on the theoretical value of the outlet flow rate and the outlet flow rate residual. The first bottom hole pressure calculation model is determined based on the exponential relationship between bottom hole pressure and inlet flow rate under steady-state conditions; the outlet flow rate calculation model is determined based on the positive correlation between fluid volume change and bottom hole pressure change under transient conditions. The first bottom hole pressure calculation model is expressed as follows: ; express The pressure at the bottom of the well at any given moment. express Ingress traffic at any given moment Indicates power. Indicates the coefficient of friction. The friction coefficient and the hydrostatic pressure are obtained by fitting the bottom hole pressure and inlet flow rate at multiple historical moments under steady-state conditions. The export flow calculation model is expressed as follows: ; express The outflow at any given moment Indicates the fluid storage coefficient. express The change in bottom hole pressure at any given time; the fluid storage coefficient is obtained by fitting the bottom hole pressure, inlet flow rate, and outlet flow rate at multiple historical moments under transient conditions; In steady-state conditions, the historical time point satisfies the following conditions: the change in bottom hole pressure is less than a first pressure threshold, and the inlet flow rate is greater than a preset flow rate threshold. In transient conditions, the historical time point satisfies the following conditions: the change in bottom hole pressure is greater than or equal to a second pressure threshold, and the inlet flow rate is greater than a preset flow rate threshold. The first pressure threshold is less than the second pressure threshold.

2. The method according to claim 1, characterized in that, The residual prediction model is based on a bidirectional long short-term memory network and a self-attention mechanism.

3. The method according to claim 2, characterized in that, The step of inputting the current logging data into a pre-trained residual prediction model to obtain the current operating condition parameter residuals includes: The current logging data is used as the feature vector of the current moment, and together with the feature vectors of a preset number of historical moments within a preset time sliding window, a feature matrix is ​​formed and input into a bidirectional long short-term memory network to obtain the bidirectional fused features of the current moment. Based on the self-attention mechanism, the attention energy scores of the current moment and each historical moment within the current time sliding window are calculated according to the bidirectional fusion characteristics of the current moment and the bidirectional fusion characteristics of each historical moment within the current time sliding window. Based on the attention energy scores of the current moment and each historical moment within the current time sliding window, determine the residual of the operating parameters at the current moment.

4. The method according to claim 3, characterized in that, Based on the attention energy scores of the current moment and each historical moment within the current time sliding window, determine the residuals of the operating parameters at the current moment, including: Input the attention energy scores of the current time and each historical time within the current time sliding window into a preset activation function to obtain the attention weight coefficients matched for each historical time within the current time sliding window. The semantic features of the current time sliding window are obtained by weighting the bidirectional fusion features of each historical moment using the attention weight coefficients matched at each historical moment. Global average pooling is applied to the semantic features of the current time sliding window to obtain a global feature summary of the current time sliding window; A linear regression mapping is performed on the global feature summary of the current time sliding window to obtain the residual of the operating parameters at the current time.

5. The method according to claim 3, characterized in that, The bidirectional long short-term memory network includes a forward long short-term memory structure and a backward long short-term memory structure; The forward long short-term memory structure outputs the positive features at the current moment, and the backward long short-term memory structure outputs the negative features at the current moment. The bidirectional fusion feature is obtained by concatenating the positive feature at the current moment with the negative feature at the current moment.

6. The method according to claim 2, characterized in that, The residual prediction model is trained using historical logging data as input and historical mining parameter residuals as labels. The bottom hole pressure residual at a historical moment is the difference between the theoretical bottom hole pressure calculated by the first bottom hole pressure calculation model and the reference bottom hole pressure calculated by the second bottom hole pressure calculation model. The residual of the outflow at a historical moment is the difference between the theoretical value of the outflow calculated by the outflow calculation model and the measured value of the outflow obtained by logging.

7. The method according to claim 6, characterized in that, The second bottom hole pressure calculation model divides the well structure into finite element parts and performs a bottom hole pressure numerical simulation on each finite element element based on the mass conservation equation and the momentum conservation equation to obtain the bottom hole pressure reference value.

8. The method according to claim 1, characterized in that, The logging data includes bit depth, well depth, bit vertical depth, bit pressure, bit speed, hook load, rotary table speed, torque, stand pressure, inlet flow rate, outlet flow rate, casing pressure, PWD depth, PWD vertical depth, PWD pressure, and PWD flow rate.

9. A device for determining operating parameters during controlled pressure drilling, characterized in that, The device includes: The residual determination module is used to acquire the logging data at the current moment, input the logging data at the current moment into the pre-trained residual prediction model, and obtain the operating condition parameter residuals at the current moment; the operating condition parameter residuals include the outlet flow rate residuals and the bottom hole pressure residuals; The theoretical value determination module is used to calculate the theoretical value of the bottom hole pressure at the current moment based on the current inlet flow rate and the pre-built first bottom hole pressure calculation model, and to calculate the theoretical value of the outlet flow rate at the current moment based on the current inlet flow rate and the pre-built outlet flow rate calculation model. The operating condition parameter determination module is used to determine the bottom hole pressure at the current moment based on the theoretical value of the bottom hole pressure and the bottom hole pressure residual, and to determine the outlet flow rate at the current moment based on the theoretical value of the outlet flow rate and the outlet flow rate residual. The first bottom hole pressure calculation model is determined based on the exponential relationship between bottom hole pressure and inlet flow rate under steady-state conditions; the outlet flow rate calculation model is determined based on the positive correlation between fluid volume change and bottom hole pressure change under transient conditions. The first bottom hole pressure calculation model is expressed as follows: ; express The pressure at the bottom of the well at any given moment. express Ingress traffic at any given moment Indicates power. Indicates the coefficient of friction. The friction coefficient and the hydrostatic pressure are obtained by fitting the bottom hole pressure and inlet flow rate at multiple historical moments under steady-state conditions. The export flow calculation model is expressed as follows: ; express The outflow at any given moment Indicates the fluid storage coefficient. express The change in bottom hole pressure at any given time; the fluid storage coefficient is obtained by fitting the bottom hole pressure, inlet flow rate, and outlet flow rate at multiple historical moments under transient conditions; In steady-state conditions, the historical time point satisfies the following conditions: the change in bottom hole pressure is less than a first pressure threshold, and the inlet flow rate is greater than a preset flow rate threshold. In transient conditions, the historical time point satisfies the following conditions: the change in bottom hole pressure is greater than or equal to a second pressure threshold, and the inlet flow rate is greater than a preset flow rate threshold. The first pressure threshold is less than the second pressure threshold.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining operating parameters during controlled-pressure drilling as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for determining operating parameters during controlled-pressure drilling as described in any one of claims 1-8.

12. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements a method for determining operating parameters during controlled-pressure drilling according to any one of claims 1-8.

Images