A method and device for predicting downhole parameters by dynamically updating surface parameters

Abstract

This specification provides a method and device for predicting downhole parameters by dynamically updating ground parameters. Obtain target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be detected; use a multi-target network prediction model to determine the target feature data corresponding to the downhole feature based on the target first ground feature data of the target well in the area to be detected; wherein the multi-target network prediction model is trained based on the second ground feature data in the historical sample data, the downhole feature data in the historical sample data, and the second ground feature prediction value and the downhole feature prediction value, and the first ground feature and the second ground feature are the correlation between the ground feature and the downhole feature determined according to the historical sample data, and the ground feature is split; according to the target feature data, determine the drilling strategy for the target well. Thus, based on the prediction of the downhole feature data, the efficiency and accuracy of the drilling strategy determination are improved.

Description

Technical Field

[0001] This specification belongs to the field of oil production technology, and in particular to a method and device for predicting downhole parameters by dynamically updating surface parameters. Background Art

[0002] Currently, oil and gas exploration and development are expanding beyond conventional resources into complex resources such as deep and ultra-deep formations. Under complex geological conditions, downhole parameter data is susceptible to interference from downhole temperature and pressure, resulting in significant noise and distortion. Furthermore, downhole measurement equipment is expensive and difficult to maintain. Consequently, existing downhole characteristic data measurement equipment and methods are difficult to widely adopt and cannot accurately obtain downhole parameter data, resulting in inefficient and inaccurate determination of oil and gas well drilling strategies.

[0003] To address the above issues, no effective solutions have been proposed so far. Summary of the Invention

[0004] This specification provides a method and device for dynamically updating ground parameters to predict downhole parameters, which avoids the problem of poor efficiency and accuracy in determining drilling strategies due to the inability to accurately obtain downhole characteristic data, thereby optimizing drilling operations and improving drilling speed and efficiency.

[0005] This specification provides a method for predicting downhole parameters using dynamically updated surface parameters, including:

[0006] receiving a processing request for a drilling strategy for a target well in the area to be inspected;

[0007] In response to the processing request, obtaining target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be inspected;

[0008] A multi-objective network prediction model is used to determine target feature data corresponding to the downhole feature based on the target first ground feature data of the target well in the area to be detected; wherein, the multi-objective network prediction model is trained based on the second ground feature data corresponding to the second ground feature in the historical sample data, the downhole feature data corresponding to the downhole feature in the historical sample data, and the second ground feature prediction value and the downhole feature prediction value, the second ground feature prediction value and the downhole feature prediction value are obtained by processing the multi-objective network prediction model according to the first ground feature data corresponding to the first ground feature in the historical sample data, the first ground feature and the second ground feature are obtained by splitting the ground feature based on the correlation between the ground feature and the downhole feature determined according to the historical sample data; and the drilling strategy for the target well is determined based on the target feature data.

[0009] In one embodiment, before determining the target feature data corresponding to the downhole feature based on the target first surface feature data of the target well in the area to be detected using the multi-target network prediction model, the method further includes:

[0010] Acquiring the historical sample data; wherein the historical sample data includes the ground feature data corresponding to the ground feature and the downhole feature data corresponding to the downhole feature;

[0011] Splitting the surface feature into the first surface feature and the second surface feature according to the correlation between the surface feature and the downhole feature;

[0012] Determining the second ground feature prediction value and the downhole feature prediction value based on the first ground feature data using an initial multi-objective network prediction model;

[0013] determining whether the initial multi-objective network prediction model converges based on the second ground feature prediction value, the second ground feature data, the downhole feature data, and the downhole feature prediction value;

[0014] When the initial multi-objective network prediction model converges, a multi-objective network prediction model is obtained; wherein, the multi-objective network prediction model is used to determine the downhole characteristic data of the target well in the area to be detected for formulating a drilling strategy based on the target first ground characteristic data of the target well in the area to be detected.

[0015] In one embodiment, determining whether the initial multi-objective network prediction model converges based on the second ground feature prediction value, the second ground feature data, the downhole feature data, and the downhole feature prediction value includes:

[0016] A loss value is determined based on a preset loss function, the loss weight corresponding to the second ground feature, the loss weight corresponding to the downhole feature, the second ground feature prediction value, the second ground feature data, the downhole feature data and the downhole feature prediction value, and based on the loss value, it is determined whether the initial multi-objective network prediction model converges, wherein the loss weight corresponding to the downhole feature is greater than the loss weight corresponding to the second ground feature.

[0017] In one embodiment, the method further comprises:

[0018] When a model update period is reached, obtaining incremental sample data within the model update period;

[0019] According to the incremental sample data, the multi-objective network prediction model is updated.

[0020] In one embodiment, the downhole feature data corresponding to the downhole feature in the incremental sample data has not been acquired, and the ground feature data corresponding to the second ground feature has been acquired, and the model updating process of the multi-objective network prediction model based on the incremental sample data includes:

[0021] The parameters of the hidden layer in the multi-objective network prediction model are updated according to the ground feature data corresponding to the first ground feature and the second ground feature in the incremental sample data.

[0022] In one embodiment, splitting the surface feature into a first surface feature and a second surface feature according to the correlation between the surface feature and the downhole feature includes:

[0023] According to the correlation between the ground features and the downhole features, the ground features among the ground features whose correlation is greater than a preset correlation threshold are determined as the second ground features, and the ground features among the ground features whose correlation is not greater than the preset correlation threshold are determined as the first ground features.

[0024] In one embodiment, before splitting the surface feature into the first surface feature and the second surface feature according to the correlation between the surface feature and the downhole feature, the method further includes:

[0025] Based on the surface feature data and the downhole feature data, the correlation between the surface feature and the downhole feature is determined according to the following formula:

[0026]

[0027] Among them, r xy is the correlation between the Xth surface feature and the Yth downhole feature, Cov(X,Y) is the covariance between the Xth surface feature and the Yth downhole feature, σ X and σ Y are respectively the standard deviations of the Xth surface feature and the Yth downhole feature.

[0028] This specification provides a device for predicting downhole parameters by dynamically updating surface parameters, including:

[0029] A request receiving module, configured to receive a request for processing a drilling strategy for a target well in the area to be inspected;

[0030] a request response module, configured to obtain, in response to the processing request, target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be detected;

[0031] a model prediction module, configured to determine target feature data corresponding to a downhole feature based on target first surface feature data of a target well in the area to be detected using a multi-target network prediction model; wherein the multi-target network prediction model is trained based on second surface feature data corresponding to a second surface feature in historical sample data, downhole feature data corresponding to the downhole feature in the historical sample data, and a second surface feature prediction value and a downhole feature prediction value; the second surface feature prediction value and the downhole feature prediction value are obtained by processing the multi-target network prediction model based on the first surface feature data corresponding to the first surface feature in the historical sample data; the first surface feature and the second surface feature are obtained by splitting the surface feature based on the correlation between the surface feature and the downhole feature determined based on the historical sample data;

[0032] A strategy determination module is used to determine a drilling strategy for the target well based on the target characteristic data.

[0033] This specification also provides an electronic device, including a processor and a memory for storing processor-executable instructions, wherein when the processor executes the instructions, a method for predicting downhole parameters by dynamically updating surface parameters is implemented.

[0034] This specification also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed, implement a method for predicting downhole parameters by dynamically updating surface parameters.

[0035] A method for predicting downhole parameters based on dynamically updated surface parameters provided in this specification receives a processing request for a drilling strategy for a target well in a to-be-detected area; in response to the processing request, obtains target first surface feature data corresponding to a first surface feature in the surface feature data of the target well in the to-be-detected area; and uses a multi-objective network prediction model to determine target feature data corresponding to a downhole feature based on the target first surface feature data of the target well in the to-be-detected area; wherein the multi-objective network prediction model is trained based on second surface feature data corresponding to a second surface feature in historical sample data, downhole feature data corresponding to the downhole feature in the historical sample data, and a second surface feature prediction value and a downhole feature prediction value, the second surface feature prediction value and the downhole feature prediction value being obtained by processing the multi-objective network prediction model based on the first surface feature data corresponding to the first surface feature in the historical sample data, the first surface feature and the second surface feature being obtained by splitting the surface feature based on the correlation between the surface feature and the downhole feature determined based on the historical sample data; and determining a drilling strategy for the target well based on the target feature data. In this way, since the multi-objective network prediction model is trained based on the second ground feature data corresponding to the second ground feature in the historical sample data, the downhole feature data corresponding to the downhole feature in the historical sample data, and the second ground feature prediction value and the downhole feature prediction value, and the first ground feature and the second ground feature are the correlation between the ground feature and the downhole feature determined according to the historical sample data, and the ground feature is split. Therefore, when the return frequency of the downhole feature data corresponding to the downhole feature in the historical sample data is not high, the second ground feature data corresponding to the second ground feature in the historical sample data can be used to assist in training the multi-objective network prediction model, thereby improving the training effect of the model and making the model prediction more accurate and real-time. Furthermore, the multi-objective network prediction model can quickly and accurately determine the target feature data corresponding to the downhole feature of the target well, so as to determine the drilling strategy for the target well based on the target feature data, thereby avoiding the problem of poor determination efficiency and accuracy of the drilling strategy due to the inability to accurately obtain downhole feature data, thereby optimizing drilling operations and improving drilling speed and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of this specification, the following is a brief introduction to the drawings required for use in the embodiments. The drawings described below are only some of the embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0037] Figure 1This is a flowchart of a method for predicting downhole parameters by dynamically updating surface parameters provided by an embodiment of this specification;

[0038] Figure 2 This is a schematic diagram of downhole characteristic prediction effect provided by an embodiment of this specification;

[0039] Figure 3 This is a schematic diagram of correlation analysis between surface features and downhole features provided by an embodiment of this specification;

[0040] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of this specification;

[0041] Figure 5 This is a schematic diagram of the structure of a device for dynamically updating surface parameters to predict downhole parameters provided by an embodiment of this specification;

[0042] Figure 6 This is a schematic diagram of a method for updating a downhole parameter prediction model in real time using surface parameters, provided by an embodiment of this specification;

[0043] Figure 7 This is a schematic diagram of another idea of ​​using surface parameters to update downhole parameter prediction model in real time, provided by an embodiment of this specification;

[0044] Figure 8 This is a schematic diagram of updating a multi-objective network prediction model provided by an embodiment of this specification;

[0045] Figure 9 This is a long short-term memory network structure diagram provided by an embodiment of this specification. DETAILED DESCRIPTION

[0046] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0047] Real-time monitoring and analysis of downhole parameters can optimize drilling operations, improve drilling speed and efficiency, and reduce drilling costs. Furthermore, accurate downhole characteristic data helps develop more scientific drilling strategies, increases drilling success rates, and ensures the efficient development and utilization of oil and gas resources. Therefore, downhole characteristic data is not only crucial for ensuring the safety of drilling operations but also plays an indispensable role in improving drilling efficiency and economic benefits.

[0048] Research on downhole characteristic prediction has made considerable progress. Numerous researchers have employed data-driven models based on drilling big data, achieving excellent prediction results. Common parameter prediction methods include time series analysis based on historical data, multivariate regression models utilizing surface parameters, and comprehensive assessment models incorporating expert experience. These methods have significantly improved the accuracy of downhole characteristic prediction, providing strong support for drilling operations.

[0049] However, existing downhole feature prediction models still have some major problems. First, most models are static models, lack adaptability, and cannot be adjusted according to real-time changes in the environment. As a result, the model's prediction results in practical applications often lag behind the actual situation, making it difficult to cope with complex and changing geological conditions. Second, the accuracy of existing models is insufficient to meet the requirements of efficient and safe drilling operations. Especially in complex environments such as deep, ultra-deep layers and deep ocean waters, model prediction errors will increase significantly, affecting the safety and efficiency of drilling operations. Therefore, how to achieve dynamic updating of downhole feature models in response to drilling conditions and wellbore status is a key approach to accurately characterizing downhole features.

[0050] In response to the root cause of the above-mentioned problem, this specification considers that according to the correlation between the ground feature and the downhole feature, the ground feature can be quickly and accurately split into a first ground feature and a second ground feature with a high correlation with the downhole feature. Secondly, based on the first ground feature data, the predicted value of the second ground feature and the predicted value of the downhole feature are determined by using a multi-objective network prediction model. On the one hand, the downhole feature can be quickly predicted based on the ground feature in real time and accurately, thereby improving the characterization accuracy of the downhole feature and helping on-site personnel to understand the downhole situation in real time and accurately. On the other hand, the multi-objective network prediction model can be assisted in optimizing according to the predicted value of the second ground feature, thereby improving the training effect of the model and making the model prediction more accurate and real-time. Finally, according to the predicted value of the downhole feature, the drilling strategy for the target well is determined, which avoids the problem of poor efficiency and accuracy in determining the drilling strategy due to the inability to accurately obtain downhole feature data, and can optimize drilling operations and improve drilling speed and efficiency.

[0051] See Figure 1 As shown, the embodiment of this specification provides a method for predicting downhole parameters by dynamically updating surface parameters, wherein the method is specifically applied to the server side. When implemented, the method may include the following contents:

[0052] S101: receiving a request for processing a drilling strategy for a target well in an area to be inspected;

[0053] S102: In response to the processing request, obtaining target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be inspected;

[0054] S103: Utilizing a multi-objective network prediction model, target feature data corresponding to a downhole feature is determined based on target first surface feature data of a target well in the area to be inspected; wherein the multi-objective network prediction model is trained based on second surface feature data corresponding to a second surface feature in historical sample data, downhole feature data corresponding to the downhole feature in the historical sample data, and a second surface feature prediction value and a downhole feature prediction value; the second surface feature prediction value and the downhole feature prediction value are obtained by processing the multi-objective network prediction model based on the first surface feature data corresponding to the first surface feature in the historical sample data; the first surface feature and the second surface feature are obtained by splitting the surface feature based on the correlation between the surface feature and the downhole feature determined based on the historical sample data;

[0055] S104: Determine a drilling strategy for the target well based on the target characteristic data.

[0056] The above-mentioned drilling strategy may refer to a series of technical measures and operational plans formulated during the oil and gas exploration and development process to achieve safe, economical and efficient drilling goals.

[0057] The above-mentioned ground characteristic data may include characteristic data such as logging parameters, drilling fluid parameters and drill bit parameters, among which the drilling fluid parameters may include parameters such as density and temperature; the logging parameters may include parameters such as standpipe pressure, flow rate, pump stroke, drill bit position, and bit pressure; the drill bit parameters may include parameters such as nozzle size, nozzle combination, and number of blades.

[0058] Downhole characteristics may include downhole equivalent circulating density (ECD), downhole pressure, and other characteristics. ECD represents the equivalent density at a certain depth when drilling fluid is circulated. It is usually expressed as the static density of the drilling fluid plus the additional pressure generated by the circulation.

[0059] Among the above three parameters (i.e., logging parameters, drilling fluid parameters, and drill bit parameters), multiple parameters that have an impact on the liquid column stability, pressure distribution, and circulatory pressure loss process of the target well and that affect the downhole characteristics can be selected as the surface characteristics of the target well. For example, the surface characteristics can include measured depth, torsion, bending moment, drill bit position, well depth, drilling time, hook load, surface drilling pressure, surface torque, surface speed, pump stroke, temperature, and standpipe pressure. Surface characteristic data corresponding to these multiple surface characteristics can be obtained.

[0060] The first and second surface characteristics may be obtained by splitting the surface characteristics based on the correlation between the surface characteristics and the downhole characteristics determined based on the historical sample data. For example, based on the correlation between the surface characteristics and the downhole characteristics determined based on the historical sample data, the standpipe pressure and temperature among the surface characteristics may be used as the second surface characteristic data, and the remaining parameters (i.e., measured depth, torsion, bending moment, drill bit position, well depth, drilling time, hook load, surface weight on bit, surface torque, surface rotational speed, and pump stroke) may be used as the first surface parameters.

[0061] Based on the above embodiment, since the multi-objective network prediction model is trained based on the second ground feature data corresponding to the second ground feature in the historical sample data, the downhole feature data corresponding to the downhole feature in the historical sample data, and the second ground feature prediction value and the downhole feature prediction value, and the first ground feature and the second ground feature are the correlation between the ground feature and the downhole feature determined according to the historical sample data, and the ground feature is split. Therefore, when the return frequency of the downhole feature data corresponding to the downhole feature in the historical sample data is not high, the second ground feature data corresponding to the second ground feature in the historical sample data can be used to assist in training the multi-objective network prediction model, thereby improving the training effect of the model and making the model prediction more accurate and real-time. Furthermore, the multi-objective network prediction model can quickly and accurately determine the target feature data corresponding to the downhole feature of the target well, so as to determine the drilling strategy for the target well based on the target feature data, thereby avoiding the problem of poor determination efficiency and accuracy of the drilling strategy due to the inability to accurately obtain downhole feature data, thereby optimizing drilling operations and improving drilling speed and efficiency.

[0062] In some embodiments, before determining the target feature data corresponding to the downhole feature based on the target first surface feature data of the target well in the area to be inspected using the multi-target network prediction model, the method may further include the following steps when implemented:

[0063] S1: Acquire the historical sample data; wherein the historical sample data includes the surface feature data corresponding to the surface feature and the downhole feature data corresponding to the downhole feature;

[0064] S2: splitting the surface feature into the first surface feature and the second surface feature according to the correlation between the surface feature and the downhole feature;

[0065] S3: using the initial multi-objective network prediction model, determining the second ground feature prediction value and the downhole feature prediction value according to the first ground feature data;

[0066] S4: determining whether the initial multi-objective network prediction model converges based on the second ground feature prediction value, the second ground feature data, the downhole feature data, and the downhole feature prediction value;

[0067] S5: When the initial multi-objective network prediction model converges, a multi-objective network prediction model is obtained.

[0068] In some embodiments, before splitting the surface feature into the first surface feature and the second surface feature based on the correlation between the surface feature and the downhole feature, the specific implementation may include:

[0069] Acquire initial historical sample data, and perform anomaly detection processing on the initial historical sample data;

[0070] In the case that abnormal data exists in the initial historical sample data, the initial historical sample data is preprocessed to obtain the historical sample data.

[0071] When performing anomaly detection on the initial historical sample data, outlier detection can be performed based on the standard deviation of the initial historical sample data using the 3σ method (3SigmaRule). Specifically, assuming that the feature data in the initial historical sample data (i.e., the surface feature data and the downhole feature data) are normally distributed, if the mean difference of the feature data exceeds 3 times the standard deviation, it is determined that abnormal data exists in the initial historical sample data.

[0072] When preprocessing the initial historical sample data, the missing values ​​of continuous feature data in the initial historical sample data can be filled with the mean value of the feature data using the mean value of the feature data through mean interpolation. In addition, a smoothing filter method can be used to perform polynomial fitting on the local feature data to estimate the trend of the feature data, thereby achieving a smoothing effect, effectively removing noise and retaining the signal trend.

[0073] Finally, after the above preprocessing operations, the initial multi-objective network prediction model can be trained and tested using the historical sample data. For example, the historical sample data can be split in a ratio of 70%:30%. Specifically, the first 140,000 samples of the historical sample data can be used as training data, and the last 60,000 samples of the historical sample data can be used as test data to test the performance of the trained multi-objective network prediction model.

[0074] Among them, the above-mentioned initial multi-objective network prediction model can be constructed based on the temporal characteristics of the downhole characteristic data, using a long short-term memory network algorithm (Long Short Term Memory, LSTM), a gated recurrent unit (Gated Recurrent Unit, GRU) or other deep learning algorithms suitable for time series data prediction.

[0075] In some embodiments, the method of determining whether the initial multi-objective network prediction model converges based on the second ground feature prediction value, the second ground feature data, the downhole feature data, and the downhole feature prediction value may further include the following when implemented:

[0076] A loss value is determined based on a preset loss function, the loss weight corresponding to the second ground feature, the loss weight corresponding to the downhole feature, the second ground feature prediction value, the second ground feature data, the downhole feature data and the downhole feature prediction value, and based on the loss value, it is determined whether the initial multi-objective network prediction model converges, wherein the loss weight corresponding to the downhole feature is greater than the loss weight corresponding to the second ground feature.

[0077] Specifically, the preset loss function can be expressed as a weighted sum of the mean square error (MSE) of each feature data. Taking the downhole feature as ECD and the second feature as temperature and standpipe pressure as an example, the preset loss function can be expressed as follows:

[0078] loss = loss(ECD) + mse(temperature) + mse(standpipe pressure)

[0079] Among them, loss is the loss value.

[0080] In order to ensure that the weight distribution between different feature data is the optimal value, different weight ratios can be set for different feature data. Specifically, it can be expressed according to the following formula:

[0081] loss = σ1loss(ECD) + σ2mse(temperature) + σ3mse(standpipe pressure)

[0082] Among them, σ1 represents the loss weight corresponding to the downhole characteristic, σ2 represents the loss weight corresponding to the second surface characteristic temperature, and σ3 represents the loss weight corresponding to the second surface characteristic standpipe pressure.

[0083] Furthermore, to ensure that the multi-objective network prediction model ultimately prioritizes the downhole feature's predictive performance, the downhole feature's penalty weight can be greater than the corresponding penalty weight for the second surface feature. Furthermore, a penalty factor can be set to ensure a balanced weight distribution between the downhole feature and the second surface feature, preventing one feature from excessively impacting model performance.

[0084] Furthermore, the selection of loss weights can be performed using a Bayesian optimization algorithm to search for optimal hyperparameters. The Bayesian optimization algorithm constructs a Gaussian process model based on known hyperparameter combinations and their corresponding training loss values ​​in each iteration, and, under the guidance of this Gaussian process model, selects the next set of hyperparameter combinations that may perform better for trial. This process iterates multiple times within the specified hyperparameter search space until the hyperparameter combination that optimizes model performance is found (i.e., the loss weight corresponding to the downhole feature, and the loss weight corresponding to the second surface feature).

[0085] Based on the above embodiment, the optimized multi-objective network prediction model can significantly improve the prediction accuracy of downhole characteristics after introducing the second ground feature. Figure 2 As shown in the figure, the addition of the second surface feature (such as standpipe pressure and temperature) not only effectively improves the prediction accuracy of downhole characteristics (such as ECD), but also corrects the prediction fluctuation of the multi-objective network prediction model, making the model more robust and reliable.

[0086] In some embodiments, the method may further include the following when implemented:

[0087] S1: When a model update period is reached, obtaining incremental sample data within the model update period;

[0088] S2: performing model update processing on the multi-objective network prediction model according to the incremental sample data.

[0089] In some embodiments, the model updating process of the multi-objective network prediction model based on the incremental sample data may include:

[0090] The incremental update technology is used to perform model update processing on the multi-objective network prediction model according to the incremental sample data.

[0091] Among them, the above-mentioned incremental update technology can be a data-driven model optimization method. Its core idea is to use the newly input incremental sample data to perform small updates on the multi-objective network prediction model without restarting the entire multi-objective network prediction model training.

[0092] Specifically, the incremental update technology described above is used to dynamically adjust the multi-objective network prediction model and to verify the relationship between downhole characteristics and a second surface feature in real time. By continuously monitoring the measured characteristic data of both surface and downhole characteristics, the multi-objective network prediction model continuously receives the latest surface feature data feedback. Based on the incremental sample data added in real time from the field, the multi-objective network prediction model can then make timely fine-tuning of the loss weights for the neuron state, downhole characteristics, and the second surface feature.

[0093] Furthermore, when incremental sample data enters the multi-objective network prediction model, the states of the neurons in its hidden layer can be updated first. The multi-objective network prediction model can use the incremental sample data to adjust the neuron weights, thereby making the model's representation in its internal feature space more consistent with the dynamics of the current environment. During this incremental update process, the multi-objective network prediction model can only update influential feature data, reducing computational overhead and the resource consumption of retraining the entire multi-objective network prediction model.

[0094] In addition, incremental sample data can also be used to synchronously adjust the shared layers in the model and the dedicated layers of each feature to ensure that after each update, the multi-objective network prediction model's understanding of the relationship between downhole features and second surface features can accurately fit the current downhole environment. Among them, the second surface features can not only play a role in auxiliary prediction, but also provide more accurate data support for downhole features through incremental sample data. Especially in complex and changing downhole environments, the effective auxiliary correction of the second surface features can help the model perceive downhole conditions more keenly, improving the adaptability of the multi-objective network prediction model and the accuracy of the prediction results.

[0095] Based on the above approach, compared with traditional batch training methods, the incremental update technology can gradually absorb new data features and dynamically optimize the weights of the multi-objective network prediction model, thereby avoiding a sudden drop in the performance of the multi-objective network prediction model or "overfitting". In addition, it can also quickly reflect data changes, ensuring that the multi-objective network prediction model always has efficient and accurate prediction capabilities.

[0096] In some embodiments, the downhole feature data corresponding to the downhole feature in the incremental sample data has not been acquired, and the ground feature data corresponding to the second ground feature has been acquired. The method of performing model updating processing on the multi-objective network prediction model based on the incremental sample data may further include the following when implemented:

[0097] The parameters of the hidden layer in the multi-objective network prediction model are updated according to the ground feature data corresponding to the first ground feature and the second ground feature in the incremental sample data.

[0098] Specifically, when the downhole feature data corresponding to the downhole feature in the incremental sample data and the ground feature data corresponding to the second ground feature have both been acquired, the following may also be included based on the ground feature data corresponding to the first ground feature and the second ground feature in the incremental sample data:

[0099] The relationship ratio between the downhole feature and the second surface feature is dynamically adjusted according to the incremental sample data.

[0100] Furthermore, when the data feature change of the second ground feature is greater than a preset threshold (such as a sudden fluctuation in the temperature of the second ground feature, resulting in the difference between the true value of the temperature at the current moment and the true value of the temperature at the next moment being greater than the preset threshold), the multi-objective network prediction model will automatically increase the loss weight of the second ground feature related to temperature to ensure that the downhole feature can be corrected in real time in each update, thereby improving the overall prediction accuracy of the multi-objective network prediction model.

[0101] In some embodiments, the method of splitting the surface feature into a first surface feature and a second surface feature according to the correlation between the surface feature and the downhole feature may further include the following steps when implemented:

[0102] According to the correlation between the ground features and the downhole features, the ground features among the ground features whose correlation is greater than a preset correlation threshold are determined as the second ground features, and the ground features among the ground features whose correlation is not greater than the preset correlation threshold are determined as the first ground features.

[0103] For example, the preset correlation threshold may be 0.8, and the surface feature (such as temperature and riser pressure) whose absolute value of correlation between the surface feature and the downhole feature is greater than or equal to 0.8 and less than the maximum correlation value 1 is used as the second surface feature, while the surface feature whose absolute value of correlation between the surface feature and the downhole feature is less than 0.8 and greater than the minimum correlation value 0 is used as the first surface feature.

[0104] In some embodiments, before splitting the surface feature into the first surface feature and the second surface feature according to the correlation between the surface feature and the downhole feature, the method may further include the following steps when implemented:

[0105] Based on the surface feature data and the downhole feature data, the correlation between the surface feature and the downhole feature is determined according to the following formula:

[0106]

[0107] Among them, r xyis the correlation between the Xth surface feature and the Yth downhole feature, Cov(X,Y) is the covariance between the Xth surface feature and the Yth downhole feature, σ X and σ Y are respectively the standard deviations of the Xth surface feature and the Yth downhole feature.

[0108] The Pearson correlation coefficient can be a statistical measure that can quantify the strength of the linear relationship between two variables, and its value (i.e., the correlation between the surface feature and the downhole feature) ranges from -1 to 1. Specifically, a value of 1 indicates that there is a perfect positive linear correlation between the two variables; a value of -1 indicates that there is a perfect negative linear correlation between the two variables; and a value of 0 indicates that there is no linear correlation between the two variables.

[0109] For further information, see Figure 3 As shown in the correlation analysis heat map, the darker the color in the figure, the higher the absolute value of the Pearson correlation coefficient, the higher the correlation between the ground features and the underground features, and the existence of a significant correlation. During the feature selection process, in order to maintain the independence between the features, those features that show a high correlation with each other are eliminated. For example, the correlation coefficient between the entrance density and the exit density is 1, and the correlation between the two is large. One of the two needs to be eliminated to avoid the problem of multicollinearity.

[0110] Based on the above embodiment, by evaluating the Pearson correlation coefficient between the ground features and the downhole features, it is possible to effectively identify features that have a significant impact on the prediction target, while excluding those redundant or low-correlation features, thereby optimizing the feature set of the multi-objective network prediction model and improving the performance and explanatory power of the model.

[0111] As can be seen from the above, an embodiment of this specification provides a method for dynamically updating ground parameters to predict downhole parameters, which receives a processing request for a drilling strategy for a target well in an area to be detected; in response to the processing request, obtains target first ground feature data corresponding to a first ground feature in the ground feature data of the target well in the area to be detected; uses a multi-objective network prediction model to determine target feature data corresponding to the downhole feature based on the target first ground feature data of the target well in the area to be detected; wherein the multi-objective network prediction model is trained based on second ground feature data corresponding to a second ground feature in historical sample data, downhole feature data corresponding to the downhole feature in the historical sample data, and a second ground feature prediction value and a downhole feature prediction value, the second ground feature prediction value and the downhole feature prediction value are obtained by processing the multi-objective network prediction model according to the first ground feature data corresponding to the first ground feature in the historical sample data, the first ground feature and the second ground feature are the correlation between the ground feature and the downhole feature determined according to the historical sample data, and the ground feature is split; based on the target feature data, the drilling strategy for the target well is determined. In this way, since the multi-objective network prediction model is trained based on the second ground feature data corresponding to the second ground feature in the historical sample data, the downhole feature data corresponding to the downhole feature in the historical sample data, and the second ground feature prediction value and the downhole feature prediction value, and the first ground feature and the second ground feature are the correlation between the ground feature and the downhole feature determined according to the historical sample data, and the ground feature is split. Therefore, when the return frequency of the downhole feature data corresponding to the downhole feature in the historical sample data is not high, the second ground feature data corresponding to the second ground feature in the historical sample data can be used to assist in training the multi-objective network prediction model, thereby improving the training effect of the model and making the model prediction more accurate and real-time. Furthermore, the multi-objective network prediction model can quickly and accurately determine the target feature data corresponding to the downhole feature of the target well, so as to determine the drilling strategy for the target well based on the target feature data, thereby avoiding the problem of poor determination efficiency and accuracy of the drilling strategy due to the inability to accurately obtain downhole feature data, thereby optimizing drilling operations and improving drilling speed and efficiency.

[0112] See Figure 4 As shown, an embodiment of this specification also provides a specific electronic device, wherein the electronic device includes a network communication port 401, a processor 402 and a memory 403, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0113] The network communication port 401 may be used to receive a request for processing a drilling strategy for a target well in the area to be inspected.

[0114] The processor 402 can be specifically used to respond to the processing request, obtain the target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be detected; use the multi-target network prediction model to determine the target feature data corresponding to the downhole feature based on the target first ground feature data of the target well in the area to be detected; wherein the multi-target network prediction model is based on the second ground feature data corresponding to the second ground feature in the historical sample data, the downhole feature data corresponding to the downhole feature in the historical sample data, and the second ground feature prediction value and the downhole feature prediction value. The second ground feature prediction value and the downhole feature prediction value are obtained by processing the multi-target network prediction model according to the first ground feature data corresponding to the first ground feature in the historical sample data. The first ground feature and the second ground feature are obtained by splitting the ground feature according to the correlation between the ground feature and the downhole feature determined according to the historical sample data; and determine the drilling strategy for the target well according to the target feature data.

[0115] The memory 403 may be specifically used to store corresponding instruction programs.

[0116] Based on the above method, the relevant structural performance of electronic equipment can be effectively utilized, the data processing speed of electronic equipment can be improved, and a method for predicting downhole parameters by dynamically updating ground parameters can be efficiently realized.

[0117] In this embodiment, the network communication port 401 can be a virtual port that is bound to different communication protocols, thereby being capable of sending or receiving 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.

[0118] In this embodiment, the processor 402 may be implemented in any suitable manner. For example, the processor may take the form of a microprocessor or a processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, an embedded microcontroller, etc. This specification is not intended to limit this.

[0119] In this embodiment, the memory 403 may include multiple levels. In a digital system, anything that can store binary data can be a memory. In an integrated circuit, a circuit with a storage function that has 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.

[0120] The embodiment of the present specification also provides a computer-readable storage medium based on the above-mentioned method of dynamically updating ground parameters to predict downhole parameters, wherein the computer-readable storage medium stores computer program instructions, which, when executed, implement the following: receiving a processing request for a drilling strategy for a target well in a to-be-detected area; in response to the processing request, obtaining target first ground feature data corresponding to a first ground feature in the ground feature data of the target well in the to-be-detected area; using a multi-objective network prediction model, determining target feature data corresponding to a downhole feature based on the target first ground feature data of the target well in the to-be-detected area; wherein the multi-objective network prediction model is based on historical The second ground feature data corresponding to the second ground feature in the historical sample data, the downhole feature data corresponding to the downhole feature in the historical sample data, and the second ground feature prediction value and the downhole feature prediction value are trained, the second ground feature prediction value and the downhole feature prediction value are obtained by processing the first ground feature data corresponding to the first ground feature in the historical sample data by the multi-objective network prediction model, the first ground feature and the second ground feature are obtained by splitting the ground feature according to the correlation between the ground feature and the downhole feature determined according to the historical sample data; according to the target feature data, the drilling strategy for the target well is determined.

[0121] In this embodiment, the storage medium includes, but is not limited to, random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD), or memory card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured in accordance with the standards specified by the communication protocol for network connection communication.

[0122] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other implementations and will not be repeated here.

[0123] See Figure 5At the software level, the embodiments of this specification also provide a device for dynamically updating surface parameters to predict downhole parameters. The device may specifically include the following structural modules:

[0124] The request receiving module 501 is used to receive a request for processing a drilling strategy for a target well in the area to be inspected;

[0125] The request response module 502 is configured to obtain target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be inspected in response to the processing request;

[0126] The model prediction module 503 is used to determine the target feature data corresponding to the downhole feature based on the target first surface feature data of the target well in the area to be detected using a multi-target network prediction model; wherein the multi-target network prediction model is trained based on the second surface feature data corresponding to the second surface feature in the historical sample data, the downhole feature data corresponding to the downhole feature in the historical sample data, and the second surface feature prediction value and the downhole feature prediction value; the second surface feature prediction value and the downhole feature prediction value are obtained by processing the multi-target network prediction model based on the first surface feature data corresponding to the first surface feature in the historical sample data; the first surface feature and the second surface feature are obtained by splitting the surface feature based on the correlation between the surface feature and the downhole feature determined based on the historical sample data;

[0127] The strategy determination module 504 determines a drilling strategy for the target well according to the target characteristic data.

[0128] In some embodiments, before the above-mentioned model prediction module 503, during specific implementation, the historical sample data is obtained; wherein, the historical sample data includes the ground feature data corresponding to the ground feature, and the downhole feature data corresponding to the downhole feature; a feature splitting module is used to split the ground feature into the first ground feature and the second ground feature according to the correlation between the ground feature and the downhole feature; using the initial multi-objective network prediction model, the second ground feature prediction value and the downhole feature prediction value are determined according to the first ground feature data; a convergence determination module is used to determine whether the initial multi-objective network prediction model converges according to the second ground feature prediction value, the second ground feature data, the downhole feature data and the downhole feature prediction value; when the initial multi-objective network prediction model converges, a multi-objective network prediction model is obtained; wherein, the multi-objective network prediction model is used to determine the downhole feature data of the target well in the target area to be detected for formulating a drilling strategy according to the target first ground feature data of the target well in the target area to be detected.

[0129] In some embodiments, the above-mentioned convergence determination module is specifically implemented to determine the loss value based on a preset loss function, the loss weight corresponding to the second ground feature, the loss weight corresponding to the downhole feature, the second ground feature prediction value, the second ground feature data, the downhole feature data and the downhole feature prediction value, and determine whether the initial multi-objective network prediction model converges based on the loss value, wherein the loss weight corresponding to the downhole feature is greater than the loss weight corresponding to the second ground feature.

[0130] In some embodiments, the device further includes, when a model update cycle is reached, obtaining incremental sample data within the model update cycle; and a model update module for performing model update processing on the multi-objective network prediction model based on the incremental sample data.

[0131] In some embodiments, the downhole feature data corresponding to the downhole feature in the incremental sample data has not been obtained, and the ground feature data corresponding to the second ground feature has been obtained. When the above-mentioned model updating module is specifically implemented, the parameters of the hidden layer in the multi-objective network prediction model are updated according to the ground feature data corresponding to the first ground feature and the second ground feature in the incremental sample data.

[0132] In some embodiments, when the above-mentioned feature splitting module is specifically implemented, based on the correlation between the ground features and the downhole features, the ground features among the ground features whose correlation is greater than a preset correlation threshold are determined as the second ground features, and the ground features among the ground features whose correlation is not greater than the preset correlation threshold are determined as the first ground features.

[0133] In some embodiments, before the feature splitting module is implemented, the correlation between the surface feature and the downhole feature is determined according to the following formula based on the surface feature data and the downhole feature data:

[0134]

[0135] Among them, r xy is the correlation between the Xth surface feature and the Yth downhole feature, Cov(X,Y) is the covariance between the Xth surface feature and the Yth downhole feature, σ X and σ Y are respectively the standard deviations of the Xth surface feature and the Yth downhole feature.

[0136] It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described in terms of functions and are divided into various modules and described separately. Of course, when implementing this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the module that implements the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] As can be seen from the above, a dynamically updated ground parameter prediction device for downhole parameters provided in the embodiment of this specification, first, can quickly and accurately split the ground feature into a first ground feature and a second ground feature with a high correlation with the downhole feature according to the correlation between the ground feature and the downhole feature. Secondly, a multi-objective network prediction model is used to determine the predicted value of the second ground feature and the predicted value of the downhole feature based on the first ground feature data. On the one hand, the downhole feature can be quickly and accurately predicted based on the ground feature in real time, thereby improving the characterization accuracy of the downhole feature and helping on-site personnel to understand the downhole situation in real time and accurately. On the other hand, the predicted value of the second ground feature can be used to assist in optimizing the multi-objective network prediction model, thereby improving the training effect of the model and making the model prediction more accurate and real-time.

[0138] In a specific scenario example, a method and device for predicting downhole parameters by dynamically updating ground parameters provided in this specification can be applied to solve the problem that most existing downhole prediction models in the drilling process use single-task learning, the model cannot obtain timely feedback on changes in downhole data for updating, and is difficult to adapt to the changing complex downhole environment, resulting in low accuracy in predicting downhole characteristic data. The method aims to ensure the immediacy and accuracy of the downhole characteristic data prediction model, improve the characterization accuracy of downhole characteristic data, and help on-site personnel understand the downhole situation in real time and accurately, thereby avoiding the problem of poor efficiency and accuracy in determining the drilling strategy due to the inability to accurately obtain downhole characteristic data, and can optimize drilling operations and improve drilling speed and efficiency. The specific implementation process may include the following.

[0139] See Figure 6As shown, in some embodiments, a method process for updating downhole parameters (i.e., downhole characteristics) in real time using surface parameters (i.e., surface characteristics) is used. Specifically, in combination with prior mechanism knowledge and data correlation analysis, a second surface feature that is highly correlated with the target downhole parameter (i.e., downhole characteristic) is selected from the surface parameters (i.e., surface characteristics, such as logging parameters, drilling fluid parameters, and drill bit parameters, etc.) as a sub-task (i.e., riser pressure and temperature) for mechanism data driving, and real-time verification (i.e., incremental update technology) is performed to dynamically update the multi-objective network prediction model and predict the downhole parameters (i.e., downhole characteristics).

[0140] Based on the above embodiment, first, combining prior mechanism knowledge with data correlation analysis, surface parameters that are highly correlated with the target downhole parameters are selected as sub-tasks. This helps the model to adjust weights in real time according to changes in surface parameters to make the target result prediction more accurate; then, a multi-objective network prediction model is established, and the difference between the predicted value and the true value of the sub-task is used to update the neural weights in the shared hidden layer of the model in real time, thereby achieving high-precision dynamic prediction of downhole parameters. Finally, using incremental update technology, based on the returned measured values ​​of downhole parameters, the main-sub-task relationship in the multi-objective network prediction model is updated online to ensure the real-time perception of the downhole environment by the multi-objective network prediction model. This method can accurately and quickly predict downhole parameters, improve the safety and efficiency of the drilling process, and can also timely warn of potential risks and prevent the occurrence of downhole accidents. It has broad application prospects.

[0141] See Figure 7 As shown, in some embodiments, specifically, by performing correlation analysis on the surface parameters (i.e., surface features), according to the correlation between the surface parameters (i.e., surface features) and the downhole parameters (i.e., downhole features), the sub-task (i.e., the second surface feature) is screened out, and then combined with the main task (i.e., downhole features, such as downhole equivalent circulation density ECD), a multi-objective network prediction model is used to update the predicted downhole parameters in real time through the surface parameters.

[0142] Based on the above embodiments, firstly, the method of updating downhole parameters by real-time verification of the multi-objective network prediction model using ground parameters is used, so that the multi-objective network prediction model's ability to instantly perceive the downhole environment is improved. In this case, the prediction results of the downhole target parameters by the multi-objective network prediction model are the results after the weights are updated based on the real-time environment. Secondly, the prediction accuracy of the multi-objective network prediction model is improved: this method takes into account the shared information and common feature space between different parameters, and makes full use of the complementarity between different tasks. At the same time, the use of ground parameters not only effectively improves the prediction accuracy of the multi-objective network prediction model on downhole parameters, but also further ensures the generalizability of the multi-objective network prediction model.

[0143] See Figure 8As shown, in some embodiments, a multi-objective network prediction model performs supervised learning on a secondary task by acquiring surface parameters in real time. The model continuously updates the prediction results of the secondary task and feeds prediction errors back into the model's shared neural parameters for real-time correction, allowing the model to continuously adjust itself to changes in surface parameters. The real-time nature of surface data allows the model to capture changes in the wellbore environment and, in turn, update the predictions of the primary task's downhole parameters in real time, maintaining high accuracy and flexibility.

[0144] In some embodiments, the multi-target network prediction model can be constructed based on the Long Short Term Memory (LSTM) network. Specifically, the Long Short Term Memory (LSTM) network is a variant of the recurrent neural network, and its structure is as follows: Figure 9 As shown, it is specifically designed to address the problem of long sequence dependencies. Traditional recurrent neural networks are prone to vanishing or exploding gradients when processing long sequences, making it difficult to learn long-term dependencies. To address this challenge, the Long Short-Term Memory (LSTM) network introduces a special structure that allows the network to selectively remember or forget information in long sequences. Each unit in the LSTM network includes three modules: a forget gate, an input gate, and an output gate.

[0145] Specifically, when the LSTM network unit is running, the state information h of the previous layer i-1 First, it will pass through the first forget gate, which will control whether to forget the state information h from the previous layer with a certain probability. i-1 , whose expression is as follows.

[0146] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0147] Among them, h i-1 is the output of the previous stage, x i is the input of the current stage, σ is the sigmiod activation function, W f is the weight matrix of the forget gate, b f is the bias of the forget gate.

[0148] Next, the data comes to the input gate layer, which has the same calculation input as the forget gate. By comprehensively considering the hidden layer state h of the previous stage i-1 And the input x at this moment i , and then decide which information should enter the cell state; for the information found to be worth remembering through the forget gate, this information is recorded and converted into a format that can be used for cell state updates.

[0149] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0150]

[0151] Among them, W i is the weight matrix of the input gate, b i is the bias of the input gate, W C is the weight matrix of the candidate memory, b C is the bias of the candidate memory.

[0152] The next step is to update the newly acquired information of this unit into the "backup" of the long short-term memory network, that is, the cell state C of the previous stage t-1 Updated to C t .

[0153]

[0154] Finally, the sigmoid activation function of the output gate is used to determine the output result based on the current state of the LSTM unit.

[0155] o t =σ(W o *[h t-1 ,x t ]+b o )

[0156] h t =o t *tanh(C t )

[0157] Among them, W o represents the weight matrix of the output gate, b o is the bias of the output gate.

[0158] In some embodiments, analysis of the relationship between the downhole ECD parameter and various engineering parameters yields the following two conclusions: First, the downhole ECD parameter increases with increases in backpressure pump flow, drilling fluid density, and drilling fluid viscosity. Second, from the perspective of traditional momentum conservation, a partial derivative relationship exists between the downhole ECD and the well depth input parameter, which can be expressed using a mechanistic formula.

[0159] Therefore, under the condition of mechanism constraints, the downhole ECD prediction problem can be regarded as a constrained nonlinear programming problem. Its expression is as follows:

[0160]

[0161] Among them, P pre Denotes the predicted pressure, P pre represents the true pressure, n represents the number of samples, represents the partial derivative of a variable.

[0162] The loss function plays a crucial role in neural networks. It is a key metric for measuring the difference between a model's predictions and the true values. During neural network training, the model's parameters are adjusted by minimizing the loss function, bringing the model's predictions closer to the true values, thereby improving the model's accuracy and generalization capabilities.

[0163] During neural network training, the value of the loss function is the goal of model optimization. By calculating the gradient of the loss function and using optimization algorithms such as gradient descent to update the model parameters, the loss function is gradually reduced. When the loss function reaches its minimum or converges to a smaller value, the model training process ends, and the model has achieved good predictive capabilities.

[0164] In summary, the loss function plays an important role in measuring model performance and guiding model optimization in neural networks. It directly affects the model's training results and ultimate prediction accuracy. Therefore, in the design and training of neural networks, it is crucial to select an appropriate loss function and properly adjust its parameters.

[0165] Therefore, in the process of integrating mechanism knowledge into the neural network, this example embeds mechanism knowledge into the neural network by changing the form of the loss function. The specific design of the loss function of the multi-objective network prediction model is as follows:

[0166]

[0167] Among them, P pre Denotes the predicted pressure, P true represents the real pressure, n represents the number of samples, λ1, λ2, λ3, λ4 represent weight parameters, represents the partial derivative of a variable.

[0168] Although this specification provides the method operation steps as described in the embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the device or client product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. Words such as first and second are used to represent names and do not represent any particular order.

[0169] Those skilled in the art will also appreciate that, in addition to implementing the controller in pure computer-readable program code, it is entirely possible to implement the same functionality by logically programming the method steps in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, and the like. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered structures within the hardware component. Alternatively, the devices for implementing various functions can be considered both software modules implementing the method and structures within the hardware component.

[0170] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that this specification can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of this specification can essentially be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of this specification.

[0171] Although the present specification has been described through embodiments, those skilled in the art will appreciate that there are many modifications and variations to the present specification without departing from the spirit of the present specification. It is intended that the appended claims include these modifications and variations without departing from the spirit of the present specification.

Claims

1. A method for predicting downhole parameters by dynamically updating surface parameters, characterized in that: include: receiving a processing request for a drilling strategy for a target well in the area to be inspected; In response to the processing request, obtaining target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be inspected; Acquiring historical sample data; wherein the historical sample data includes ground feature data corresponding to ground features and downhole feature data corresponding to downhole features; Splitting the surface feature into a first surface feature and a second surface feature according to a correlation between the surface feature and the downhole feature; Determining the second ground feature prediction value and the downhole feature prediction value based on the first ground feature data using an initial multi-objective network prediction model; Determining a loss value based on a preset loss function, a loss weight corresponding to the second surface feature, a loss weight corresponding to the downhole feature, a predicted value of the second surface feature, the second surface feature data, the downhole feature data, and the predicted value of the downhole feature, and determining whether the initial multi-objective network prediction model has converged based on the loss value, wherein the loss weight corresponding to the downhole feature is greater than the loss weight corresponding to the second surface feature; When the initial multi-objective network prediction model converges, obtaining a multi-objective network prediction model; Utilizing a multi-objective network prediction model, target feature data corresponding to a downhole feature is determined based on target first surface feature data of a target well in the area to be detected; wherein the multi-objective network prediction model is trained based on second surface feature data corresponding to a second surface feature in historical sample data, downhole feature data corresponding to the downhole feature in the historical sample data, and a second surface feature prediction value and a downhole feature prediction value; the second surface feature prediction value and the downhole feature prediction value are obtained by processing the multi-objective network prediction model based on the first surface feature data corresponding to the first surface feature in the historical sample data; the first surface feature and the second surface feature are obtained by splitting the surface feature based on the correlation between the surface feature and the downhole feature determined based on the historical sample data; A drilling strategy for the target well is determined based on the target characteristic data.

2. A method for predicting downhole parameters by dynamically updating surface parameters according to claim 1, characterized in that: The method further comprises: When a model update period is reached, obtaining incremental sample data within the model update period; According to the incremental sample data, the multi-objective network prediction model is updated.

3. The method for predicting downhole parameters by dynamically updating surface parameters according to claim 2, characterized in that: The downhole feature data corresponding to the downhole feature in the incremental sample data has not been acquired, and the ground feature data corresponding to the second ground feature has been acquired, and the multi-objective network prediction model is updated based on the incremental sample data, including: The parameters of the hidden layer in the multi-objective network prediction model are updated according to the ground feature data corresponding to the first ground feature and the second ground feature in the incremental sample data.

4. A method for predicting downhole parameters by dynamically updating surface parameters according to claim 3, characterized in that: The step of splitting the surface feature into a first surface feature and a second surface feature according to the correlation between the surface feature and the downhole feature includes: According to the correlation between the ground features and the downhole features, the ground features among the ground features whose correlation is greater than a preset correlation threshold are determined as the second ground features, and the ground features among the ground features whose correlation is not greater than the preset correlation threshold are determined as the first ground features.

5. The method for predicting downhole parameters by dynamically updating surface parameters according to claim 4, characterized in that: Before splitting the surface feature into the first surface feature and the second surface feature according to the correlation between the surface feature and the downhole feature, the method further includes: Based on the surface feature data and the downhole feature data, the correlation between the surface feature and the downhole feature is determined according to the following formula: Among them, r xy is the correlation between the Xth surface feature and the Yth downhole feature, Cov(X,Y) is the covariance between the Xth surface feature and the Yth downhole feature, σ X and σ Y are respectively the standard deviations of the Xth surface feature and the Yth downhole feature.

6. A device for predicting downhole parameters by dynamically updating surface parameters, the device being used to execute the method for predicting downhole parameters by dynamically updating surface parameters according to any one of claims 1 to 5, characterized in that: include: A request receiving module, configured to receive a request for processing a drilling strategy for a target well in the area to be inspected; a request response module, configured to obtain, in response to the processing request, target first ground feature data corresponding to the first ground feature in the ground feature data of the target well in the area to be detected; a model prediction module, configured to determine target feature data corresponding to a downhole feature based on target first surface feature data of a target well in the area to be detected using a multi-target network prediction model; wherein the multi-target network prediction model is trained based on second surface feature data corresponding to a second surface feature in historical sample data, downhole feature data corresponding to the downhole feature in the historical sample data, and a second surface feature prediction value and a downhole feature prediction value; the second surface feature prediction value and the downhole feature prediction value are obtained by processing the multi-target network prediction model based on the first surface feature data corresponding to the first surface feature in the historical sample data; the first surface feature and the second surface feature are obtained by splitting the surface feature based on the correlation between the surface feature and the downhole feature determined based on the historical sample data; A strategy determination module is used to determine a drilling strategy for the target well based on the target characteristic data.

7. An electronic device, characterized in that: The method comprises a processor and a memory for storing processor-executable instructions, wherein when the processor executes the instructions, the method realizes the steps of the method for predicting downhole parameters by dynamically updating surface parameters as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method for predicting downhole parameters by dynamically updating surface parameters as described in any one of claims 1 to 5 are implemented.

Images