Downhole parameter prediction method and apparatus

Abstract

The application discloses a downhole parameter prediction method and device, and the method comprises the following steps: acquiring a downhole parameter prediction model and a loss function thereof for predicting downhole parameters, which are constructed by using multi-source data; constructing a mechanism model of the downhole parameters, embedding the mechanism model into the loss function of the downhole parameter prediction model to obtain a loss function based on physical constraints; performing reverse propagation update on model parameters through optimization training to obtain a mechanism data fusion intelligent prediction model of downhole parameters; and predicting downhole parameters by using the intelligent prediction model of downhole parameters to obtain a prediction result. By using the application, the dependence of an intelligent model on data driving can be reduced, and the stability and accuracy of a prediction result can be improved.

Description

Technical Field

[0001] The present invention relates to the field of exploration technology, and in particular to a downhole parameter prediction method and device. Background Art

[0002] As my country's oil and gas exploration and development continues to deepen, the focus and types of exploration and development are rapidly expanding toward unconventional oil and gas resources, such as deep, ultra-deep, and low-permeability formations. Due to the high temperatures and pressures in deep formations, the narrow safety density window makes flooding, gas intrusion, and other complex situations highly susceptible to occur. Accurate prediction and real-time monitoring of downhole engineering parameters are critical to ensuring the safety of deep, high-temperature, and high-pressure drilling. Existing mechanistic models for downhole parameter prediction suffer from high model complexity, lengthy calculation times, and insufficient accuracy under complex geological and engineering conditions. Furthermore, the durability and reliability of costly downhole measurement equipment in high-temperature, high-pressure environments pose challenges.

[0003] In recent years, the advantages of artificial intelligence algorithms and technologies in the oil and gas sector have gradually become apparent, and they have been applied to various scenarios, including operating condition diagnosis and parameter optimization. However, current intelligent models are data-driven, and their establishment is extremely dependent on the quality and quantity of sample data. Accurate models require multiple training sessions based on a large amount of high-quality, representative data. Due to the limited sample data during drilling and the significant differences in data from different drilling processes, existing data-driven intelligent models have poorly stable predictions for downhole parameters, and their application in drilling also faces challenges in real-time performance and generalization. Summary of the Invention

[0004] The present invention provides a downhole parameter prediction method and device to reduce the dependence of an intelligent model on data driving and improve the stability and accuracy of prediction results.

[0005] To this end, the present invention provides the following technical solutions:

[0006] A downhole parameter prediction method, the method comprising:

[0007] Obtaining a downhole parameter prediction model and its loss function constructed using multi-source data for predicting downhole parameters;

[0008] Constructing a mechanism model for the downhole parameters, and embedding the mechanism model into the loss function of the downhole parameter prediction model to obtain a loss function based on physical constraints;

[0009] The model parameters are updated through back propagation through optimization training to obtain an intelligent downhole parameter prediction model that integrates mechanism data.

[0010] The downhole parameter intelligent prediction model is used to predict the downhole parameters to obtain prediction results.

[0011] Optionally, the method further comprises constructing the downhole parameter prediction model in the following manner:

[0012] Acquire multi-source data and generate a multi-source data set; the multi-source data includes any one or more of the following data: well logging data, well logging data, and drilling data;

[0013] Preprocessing the data in the multi-source data set to obtain a downhole key parameter feature set;

[0014] The downhole key parameter feature set is used to train a downhole parameter prediction model and its loss function.

[0015] Optionally, the logging data includes any one or more of the following data: well depth, bit pressure, rotary table torque, rotation speed, mechanical penetration rate, pump pressure, total pool volume, inlet density, outlet density, hook load, pump stroke, equivalent density;

[0016] The logging data includes any one or more of the following data: natural gamma, spontaneous potential, acoustic transit time, deep lateral resistivity curve, shallow lateral resistivity, density or neutron;

[0017] The drilling data includes any one or more of the following data: natural gamma, natural potential, well diameter, apparent resistivity, deep lateral resistivity curve, shallow lateral resistivity curve, acoustic wave, density, neutron, etc.

[0018] Optionally, preprocessing the data to obtain a downhole key parameter feature set includes:

[0019] Use any one or more methods including outlier removal, linear regression interpolation, and sliding average filtering to screen out abnormal and noisy data in the well;

[0020] Use variance selection method to select feature parameters;

[0021] Calculating correlation coefficients between different feature parameters, and determining candidate feature parameters based on the correlation coefficients;

[0022] Determining effective feature parameters among the candidate feature parameters using a non-parametric method in statistics;

[0023] Perform one-hot encoding on the non-time series feature parameters to obtain the encoded non-time series feature parameters;

[0024] The encoded non-time-series characteristic parameters are fused with the effective characteristic parameters to generate a downhole key parameter feature set.

[0025] Optionally, the training of a downhole parameter prediction model using the downhole key parameter feature set includes:

[0026] Using the downhole key parameter feature set to train a candidate downhole parameter prediction model;

[0027] A model parameter optimization test is performed on the candidate downhole parameter model to determine a downhole parameter prediction model.

[0028] Optionally, performing a model parameter optimization test on the candidate downhole parameter prediction model includes:

[0029] Select any one or more of the following as evaluation indicators of model prediction effect: root mean square error RMSE, average relative error δ, maximum relative error δ max , training time.

[0030] Optionally, the mechanism model includes any one or more of the following: a direct and inverse proportional response relationship model, a string force balance model, and a multiphase flow model.

[0031] Optionally, embedding the mechanism model into the loss function of the downhole parameter prediction model to obtain a loss function based on physical constraints includes:

[0032] The input parameters of the mechanism model are expressed as physical functions of downhole parameters to obtain a loss function based on physical constraints.

[0033] Optionally, the downhole parameters include any one or more of the following: bottom hole torque, bit pressure, and equivalent density.

[0034] A downhole parameter prediction device, comprising:

[0035] A model determination module is used to obtain a downhole parameter prediction model and its loss function for predicting downhole parameters constructed using multi-source data;

[0036] A correction module, configured to construct a mechanism model for the downhole parameters, and embed the mechanism model into the loss function of the downhole parameter prediction model to obtain a loss function based on physical constraints;

[0037] The model optimization module is used to back-propagate and update the model parameters through optimization training to obtain an intelligent downhole parameter prediction model that integrates mechanism data;

[0038] The prediction module is used to predict the downhole parameters using the downhole parameter intelligent prediction model to obtain prediction results.

[0039] Optionally, the device further comprises: a model building module for building the downhole parameter prediction model; the model building module comprises:

[0040] A data acquisition unit is used to acquire multi-source data and generate a multi-source data set; the multi-source data includes any one or more of the following data: well logging data, well logging data, and drilling data;

[0041] A data processing unit, configured to pre-process the data in the multi-source data set to obtain a downhole key parameter feature set;

[0042] A training unit is used to train the downhole key parameter feature set to obtain a downhole parameter prediction model and its loss function.

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the above-mentioned downhole parameter prediction method.

[0044] The downhole parameter prediction method and device provided by the present invention pre-construct a downhole parameter prediction model to predict downhole parameters, and by adding mechanism constraints, deeply fuse data and mechanism, train a downhole parameter intelligent prediction model that fuses mechanism data, and use this model to realize downhole parameter prediction under mechanism constraints, thereby effectively improving the accuracy, stability and generalization of the model, and improving the stability and accuracy of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of constructing a downhole parameter prediction model in the implementation of the present invention;

[0046] Figure 2 is a histogram of distance correlation coefficients of 14 time series feature parameters in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of a downhole parameter prediction model according to an embodiment of the present invention;

[0048] Figure 4 is a flow chart of a downhole parameter prediction method provided by an embodiment of the present invention;

[0049] Figure 5 Schematic diagram of the training process of the intelligent prediction model for downhole engineering parameters based on mechanism data fusion in an embodiment of the present invention;

[0050] Figure 6 This is a schematic structural diagram of a downhole parameter prediction device provided by an embodiment of the present invention;

[0051] Figure 7 It is a structural diagram of the model building module in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0053] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The embodiments cannot be described one by one here, but the embodiments of the present invention are not limited to the following embodiments.

[0054] In response to the problem that existing intelligent models rely too much on data-driven methods, resulting in poor stability of prediction results in applications during drilling, an embodiment of the present invention provides a downhole parameter prediction method and device, which predicts downhole parameters based on a pre-constructed downhole parameter prediction model, and then constructs a loss function based on the downhole prediction parameters and the corresponding downhole measured parameters, and embeds physical constraints in the loss function. Through optimization training, a downhole parameter intelligent prediction model with mechanism data fusion is obtained, and the downhole parameter intelligent prediction model with mechanism data fusion is used to predict the downhole parameters to obtain prediction results.

[0055] It should be noted that the downhole parameter prediction model may be an existing model or a model constructed by collecting corresponding data.

[0056] First, a process of constructing a downhole parameter prediction model provided in an embodiment of the present invention is described in detail below.

[0057] like Figure 1 FIG. 1 is a flow chart of constructing a downhole parameter prediction model in the implementation of the present invention, which includes the following steps:

[0058] Step 101: Acquire multi-source data and generate a multi-source data set.

[0059] The multi-source data may come from multiple wells and may include but is not limited to drilling data, well logging data, mud logging data, etc. Among them:

[0060] The logging data mainly include: well inclination data table, engineering parameter table, drilling fluid performance table, drill bit record table, cuttings description record table, etc. The data therein include but are not limited to any one or more of the following data: well depth, bit pressure, rotary table torque, rotation speed, mechanical penetration rate, pump pressure, total pool volume, inlet density, outlet density, hook load, pump stroke, equivalent density, etc.

[0061] The logging data includes but is not limited to any one or more of the following data: natural gamma, natural potential, well diameter, apparent resistivity, deep lateral resistivity curve, shallow lateral resistivity curve, acoustic wave, density, neutron, etc.

[0062] The drilling data include but are not limited to any one or more of the following data: well deviation data, drilling fluid performance data, drill bit record data, cuttings description record data, etc. Among them:

[0063] The drilling fluid performance data include but are not limited to any one or more of the following data: funnel viscosity (unit: s), plastic viscosity (unit: mPa·s), dynamic shear force (unit: Pa), drilling fluid system, etc.;

[0064] The drill bit record data includes but is not limited to any one or more of the following data: drill bit size, drill bit model, freshness at entry into the well (unit %), freshness at exit from the well (unit %), weight on bit (unit kN), rotation speed (unit r / min), drill bit water hole, drilling tool assembly information, etc.;

[0065] The rock cutting description record data includes but is not limited to any one or more of the following data: information such as layer position, well section, lithology and oil, gas and water description, and the lithology and oil, gas and water description information includes numerical and text information such as rock cutting shape, maximum particle size, minimum particle size, average particle size, sorting, and roundness.

[0066] The multi-source data may include structured data and unstructured data; moreover, the data may be of numerical type or text type, which is not limited in this embodiment of the present invention.

[0067] To this end, these data also need to be preprocessed, which may include but is not limited to unifying the sampling frequency, format conversion, and other processing.

[0068] For example, the sampling frequency of well deviation data, drilling fluid performance data, drill bit log data, and cuttings description log data can be converted to sampling every 1 meter. For example, well deviation data can be interpolated with well trajectory data using a cubic spline curve interpolation method to convert it to sampling one point every 1 meter.

[0069] After unifying the sampling frequencies of various types of data, due to the inconsistency of different data types, it is necessary to establish corresponding data extraction and processing methods for specific data types.

[0070] For example, well deviation data and engineering parameters are all numerical data. After unifying the sampling frequency to 1m, they can be directly read using the Pandas module in Python, which facilitates subsequent data splicing operations.

[0071] For example, if drilling fluid system data is in text format, it can be roughly categorized into three broad types: water-based, oil-based, and gas-based. Water-based drilling fluids include non-dispersible, dispersed, polymer, low-solids, calcium-treated, and saturated brine drilling fluids; gas-based drilling fluids include air and foam drilling fluids. Each category can be mapped to a corresponding numeric value, effectively mapping text data to numeric data.

[0072] For another example, drill bit model data is stored in the drill tool assembly information in text form, and information is extracted according to the actual drill bit type, such as PDC drill bit.

[0073] After preprocessing the multi-source data, a multi-source dataset can be generated. For example, well deviation, engineering parameters, drilling fluid properties, drill bit records, and cuttings description records can be spliced ​​together based on well depth to form a comprehensive mud logging parameter dataset.

[0074] Step 102 : pre-process the data in the multi-source data set to obtain a downhole key parameter feature set.

[0075] The preprocessing of the data mainly includes:

[0076] (1) The data is processed by outlier removal, linear regression interpolation, sliding average filtering, etc. to screen out downhole abnormal data and noise data, reduce the impact of downhole noise on the collected data, and improve the density and quality of data samples.

[0077] (2) Use variance selection method to select feature parameters.

[0078] The smaller the variance, the less feature information there is. To this end, a variance threshold can be set to calculate the variance of each feature parameter, and feature parameters that are smaller than the variance threshold can be deleted.

[0079] (3) Calculate the correlation coefficients between different feature parameters and determine candidate feature parameters based on the correlation coefficients.

[0080] For example, we can combine the three correlation coefficients, namely the Pearson correlation coefficient, the Spearman correlation coefficient, and the distance correlation coefficient, to analyze the linear relationship between features. Based on the theoretical connection between features, we can use a correlation coefficient of 0.6 as the threshold for feature selection.

[0081] In a non-limiting embodiment, the distance correlation coefficient between different feature parameters can be calculated using the following formula:

[0082]

[0083] in, is the distance covariance of X, Y; is the distance variance of X; is the distance variance of Y; R n (X,Y) is the distance correlation coefficient of X and Y.

[0084] Of course, other methods may also be used to calculate the correlation between different characteristic parameters, which is not limited in this embodiment of the present invention.

[0085] If the correlation coefficient of two characteristic parameters is less than a set correlation coefficient threshold (for example, set to 0.6), it is considered that the two characteristic parameters are unrelated.

[0086] The correlation coefficients between all different feature parameters are calculated in sequence, and then the feature parameters with higher correlation can be selected as candidate feature parameters, and irrelevant feature parameters can be deleted.

[0087] Figure 2 A histogram showing distance correlation coefficients of 14 time series feature parameters in an embodiment of the present invention is shown.

[0088] (4) Using non-parametric methods in statistics, valid feature parameters among the candidate feature parameters are determined, thereby further screening the candidate feature parameters.

[0089] Using nonparametric statistical methods, such as the chi-square test and the mutual information method, the independence of the target feature and other features is calculated to determine the effective features among the candidate feature parameters. The mutual information method is a filtering feature selection algorithm. In feature selection, mutual information is a measure of the degree of mutual dependence between a feature and a label class. The larger the mutual information value, the greater the degree of mutual dependence between the feature and the label class.

[0090] (5) Normalize the effective feature parameters.

[0091] Considering that the scale differences of various features in the original data may be large, which can easily cause gradient problems, we can further normalize the maximum and minimum values ​​of the selected effective feature parameters to eliminate the influence of dimension, avoid gradient problems, and speed up model training.

[0092] The specific formula for normalization is as follows:

[0093]

[0094] Where x′ i is the result of normalization of the i-th variable; x i is the i-th variable; min(x i ) is the minimum value of the i-th variable; max(x i ) is the maximum value of the i-th variable.

[0095] It should be noted that the effective feature parameters screened out by (2)-(4) above are time series data feature parameters.

[0096] (6) Perform one-hot encoding on the non-time series data feature parameters to obtain the encoded non-time series feature parameters.

[0097] For example, one-hot encoding can be performed on non-time-series data such as drilling tool assembly, drilling fluid type, and drill bit type. For example, the drilling fluid system can be divided into water-based, oil-based, and gas-based drilling fluids, and they can be coded as [0, 0, 1], [0, 1, 0], [1, 0, 0] respectively; the drill bit type can be divided into PDC and roller, and they can be coded as [0, 1], [1, 0] respectively; the drilling tool assembly can be divided into pendulum, full-hole, and tower drilling tool assembly, and they can be coded as [0, 0, 1], [0, 1, 0], [1, 0, 0] respectively.

[0098] (7) The encoded non-time series feature parameters are fused with the normalized effective feature parameters to generate a downhole key parameter feature set.

[0099] For example, in a non-limiting embodiment, the encoded non-time-series feature parameters may be combined with normalized effective feature parameters to generate a downhole key parameter feature set.

[0100] Step 103: Use the downhole key parameter feature set to train and obtain a downhole parameter prediction model and its loss function.

[0101] In an embodiment of the present invention, the downhole parameter prediction model may adopt but is not limited to any one of the following: a machine learning model, a deep learning model, a plurality of deep learning integrated models, etc.

[0102] Furthermore, a candidate downhole parameter prediction model can be first trained based on the above-mentioned downhole key parameter feature set, and then the candidate downhole parameter model can be subjected to a model parameter optimization test using a corresponding test set to determine the final downhole parameter prediction model.

[0103] In specific applications, you can select but not limited to any one or more of the following: root mean square error RMSE, average relative error δ, maximum relative error δ max , training time, etc., as evaluation indicators of the model prediction effect, so as to determine the final downhole parameter prediction model based on the corresponding evaluation indicators.

[0104] The calculation formulas for the root mean square error RMSE, the average relative error δ, and the maximum relative error δmax are as follows:

[0105]

[0106]

[0107] δ max=max{δ1,δ2,δ3,……δ N}

[0108] Among them, y itrue is the target true value of the i-th data; y ipre is the target prediction value of the i-th data; N is the total number of samples; δ i is the relative error of the i-th value.

[0109] For example, in one specific application, data from 74 wells in a specific block were used to compare and analyze three models: a BP (Back Propagation) neural network, an LSTM (Long Short-Term Memory) network, and a BP-LSTM network. The optimization focused on the number of neural layers, number of neurons, dropout rate, and activation function. Experimental parameters were designed using an orthogonal experiment. The network models were trained using a training set of 52 wells and tested using a test set of 22 wells, with each model trained 120 times. After model training and testing, each neural network generated nine models for predicting bottomhole weight on bit (WOB) and nine models for predicting bottomhole torque, respectively. The bottomhole WOB and bottomhole torque calculation models were optimized using a comprehensive analysis of relative error, root mean square error, and model complexity. The orthogonal experiment scheme is shown in Table 2. The BP-LSTM network was ultimately selected as the final intelligent prediction foundation model.

[0110] Figure 3 A schematic structural diagram of a downhole parameter prediction model in an embodiment of the present invention is shown.

[0111] The downhole parameter prediction model uses a BP-LSTM network. The BP neural network is used to input non-time-series data. For example, three non-time-series variables: drilling tool assembly, drilling fluid type, and drill bit type are encoded into eight types after one-hot encoding. An input sample of the BP network is a one-dimensional vector, which can be expressed as:

[0112]

[0113] The LSTM network is used to input time series data. The historical time step is selected as 5. For example, a data sample input to the LSTM network is a 5×14 matrix, which can be expressed as:

[0114]

[0115] in, represents the i-th sample at the j-th time, and t is the current time.

[0116] The downhole parameter prediction method provided in an embodiment of the present invention uses the above-mentioned downhole parameter prediction model to predict downhole parameters, and deeply integrates data and mechanism by adding mechanism constraints and other methods, trains the downhole parameter intelligent prediction model of mechanism data fusion, and realizes downhole parameter prediction under mechanism constraints, which can effectively improve the accuracy, stability and generalization of the model.

[0117] like Figure 4 FIG. 1 is a flow chart of a downhole parameter prediction method provided by an embodiment of the present invention, comprising the following steps:

[0118] Step 401: Obtain a downhole parameter prediction model and its loss function for predicting downhole parameters that are constructed using multi-source data.

[0119] Step 402: construct a mechanism model for the downhole parameters, embed the mechanism model into the loss function of the downhole parameter prediction model, and obtain a loss function based on physical constraints.

[0120] The mechanism model acts as a physical constraint, ensuring that the prediction results conform to physical laws, preventing them from violating actual engineering conditions and ensuring that the predicted downhole parameters are closer to the actual downhole engineering parameters. For example, physical knowledge constraints such as hydraulics and tubing mechanics can be embedded. The established mechanism models include, but are not limited to, direct and inverse proportional response models, tubing force balance models, and multiphase flow models. These models can be used for the mechanistic calculation of downhole parameters such as bottomhole torque, weight on bit, and equivalent density.

[0121] The input parameters of the mechanism model are expressed as physical functions of the downhole parameters to obtain a loss function based on physical constraints.

[0122] The physical constraints and their neural networks can be expressed as:

[0123]

[0124] Among them, w [n] represents the model weight matrix of the nth layer; b represents the model bias value; x represents the constrained function variable, such as well depth, drilling fluid density, bottom hole torque, etc.; T represents the downhole parameters to be predicted, such as bottom hole drilling pressure, torque, etc.

[0125] Furthermore, given the complexity of constrained neural network objective functions, a penalty function approach can be used to construct the objective function and constraints as auxiliary functions, thereby transforming the constrained nonlinear programming problem into an unconstrained one. At the same time, by properly weighting the physical constraints in the loss function, a balance can be achieved between prediction accuracy and the fit of the physical constraints. For example, by setting and solving for different penalty factors λ, the model can have different responsiveness when faced with different levels of constraints.

[0126]

[0127] Among them, F is the objective function to be optimized, T pre is the model prediction value, T true is the true value of the parameter, and variables such as x1 and x2 represent the network input parameters, such as well depth, drilling fluid density, bottom hole torque, etc.

[0128] Step 403 : Back propagation updates the model parameters through optimization training to obtain a downhole parameter intelligent prediction model fused with mechanism data.

[0129] In this embodiment of the present invention, the model parameters can be back-propagated and updated using an optimizer (i.e., a correction coefficient that balances the error). Specifically, the predicted downhole parameters are compared with the actual measured downhole parameters to analyze the prediction error. Based on the error, the prediction results are corrected using the correction coefficient to further improve the accuracy and reliability of the prediction. Through multiple corrections and adjustments, the prediction results are continuously optimized. When the set error threshold is met, training is terminated, resulting in an intelligent prediction model for downhole engineering parameters that integrates mechanism data.

[0130] Figure 5 It is a schematic diagram of the training process of the intelligent prediction model of downhole engineering parameters based on the above-mentioned mechanism data fusion.

[0131] Step 404: Use the downhole parameter intelligent prediction model to predict downhole engineering parameters to obtain prediction results.

[0132] Accordingly, the present invention also provides a downhole parameter prediction device, such as Figure 6 FIG. 1 is a schematic diagram of the structure of a downhole parameter prediction device provided by an embodiment of the present invention.

[0133] The downhole parameter prediction device of this embodiment includes the following modules:

[0134] The model determination module 601 is used to obtain a downhole parameter prediction model and its loss function for predicting downhole parameters constructed using multi-source data;

[0135] A correction module 602 is configured to construct a mechanism model for the downhole parameters, embed the mechanism model into the loss function of the downhole parameter prediction model, and obtain a loss function based on physical constraints;

[0136] The model optimization module 603 is used to perform back propagation updates on the model parameters through optimization training to obtain a downhole parameter intelligent prediction model fused with mechanism data;

[0137] The prediction module 604 is used to predict the downhole parameters using the downhole parameter intelligent prediction model to obtain prediction results.

[0138] It should be noted that the downhole parameter prediction model may be an existing model or a model constructed by collecting corresponding data.

[0139] Accordingly, the downhole parameter prediction model can be constructed by the model construction module using a data-driven modeling method.

[0140] The model building module may be a part of the downhole parameter prediction device of the present invention, or may be independent of the device, which is not limited in this embodiment of the present invention.

[0141] like Figure 7 FIG. 1 is a structural diagram of a model building module in an embodiment of the present invention.

[0142] The model building module includes the following units:

[0143] The data acquisition unit 701 is used to acquire multi-source data and generate a multi-source data set; the multi-source data includes any one or more of the following data: well logging data, well logging data, and drilling data;

[0144] The data processing unit 702 is used to pre-process the data in the multi-source data set to obtain a downhole key parameter feature set;

[0145] The training unit 703 is used to train the downhole key parameter feature set to obtain a downhole parameter prediction model and its loss function.

[0146] The structure of the above-mentioned downhole parameter prediction model, as well as more functions and implementation methods of each module and unit in the downhole parameter prediction device of the present invention can be referred to the description in the previous embodiment of the method of the present invention, and will not be repeated here.

[0147] The downhole parameter prediction method and device provided by the present invention pre-construct a downhole parameter prediction model to predict downhole parameters, and by adding mechanism constraints, deeply fuse data and mechanism, train a downhole parameter intelligent prediction model that fuses mechanism data, and use this model to realize downhole parameter prediction under mechanism constraints, thereby effectively improving the accuracy, stability and generalization of the model, and improving the stability and accuracy of the prediction results.

[0148] The solution of the present invention can effectively solve the problems existing in the existing downhole drilling parameter prediction, is applicable to different types of drilling operations and geological conditions, has a certain degree of portability, and provides the drilling industry with a reliable and intelligent downhole engineering parameter prediction technology with high practical value and broad application prospects.

[0149] The term “plurality” used in the embodiments of the present invention refers to two or more than two.

[0150] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or apparatuses.

[0151] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Moreover, the system embodiments described above are merely schematic, in which the modules and units described as separate components may or may not be physically separated, that is, they may be located on one network unit, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. A person of ordinary skill in the art can understand and implement it without making any creative effort.

[0152] In specific implementations, the modules / units included in the various devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units.

[0153] For example, for each device or product applied to or integrated into a chip, each module / unit contained therein may be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for each device or product applied to or integrated into a chip module, each module / unit contained therein may be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as a chip, circuit module, etc.) or different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. The element can be implemented in the form of a software program, which runs on the processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal, the various modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal, or, at least some modules / units can be implemented in the form of a software program, which runs on the processor integrated inside the terminal, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0154] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may be physically arranged separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0155] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to perform some steps of the method described in each embodiment of the present application.

[0156] The embodiments of the present invention are described in detail above. Specific implementation methods are used herein to illustrate the present invention. The description of the above embodiments is only used to help understand the method and system of the present invention. They are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention, and the content of this specification should not be understood as limiting the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A downhole parameter prediction method, characterized in that: The method comprises: Obtaining a downhole parameter prediction model and its loss function constructed using multi-source data for predicting downhole parameters; Constructing a mechanism model for the downhole parameters, and embedding the mechanism model into the loss function of the downhole parameter prediction model to obtain a loss function based on physical constraints; The model parameters of the downhole parameter prediction model are back-propagated and updated through optimization training to obtain a downhole parameter intelligent prediction model fused with mechanism data; Using the downhole parameter intelligent prediction model to predict downhole parameters to obtain prediction results; The method further includes constructing the downhole parameter prediction model in the following manner: Acquire multi-source data and generate a multi-source data set; the multi-source data includes any one or more of the following data: well logging data, well logging data, and drilling data; Preprocessing the data in the multi-source data set to obtain a downhole key parameter feature set; Using the downhole key parameter feature set to train, a downhole parameter prediction model and its loss function are obtained; The preprocessing of the data in the multi-source data set to obtain the downhole key parameter feature set includes: Use any one or more methods including outlier removal, linear regression interpolation, and sliding average filtering to screen out abnormal and noisy data in the well; Use variance selection method to select feature parameters; Calculating correlation coefficients between different feature parameters, and determining candidate feature parameters based on the correlation coefficients; Determining effective feature parameters among the candidate feature parameters using a non-parametric method in statistics; Perform one-hot encoding on the non-time series feature parameters to obtain the encoded non-time series feature parameters; The encoded non-time-series characteristic parameters are fused with the effective characteristic parameters to generate a downhole key parameter feature set.

2. The downhole parameter prediction method according to claim 1, characterized in that: The logging data includes any one or more of the following data: well depth, bit pressure, rotary table torque, rotation speed, mechanical penetration rate, pump pressure, total pool volume, inlet density, outlet density, hook load, pump stroke, equivalent density; The logging data includes any one or more of the following data: natural gamma, spontaneous potential, acoustic transit time, deep lateral resistivity curve, shallow lateral resistivity, density or neutron; The drilling data includes any one or more of the following data: natural gamma, natural potential, well diameter, apparent resistivity, deep lateral resistivity curve, shallow lateral resistivity curve, acoustic wave, density, neutron, etc.

3. The downhole parameter prediction method according to claim 1, characterized in that: The downhole parameter prediction model obtained by training the downhole key parameter feature set includes: Using the downhole key parameter feature set to train a candidate downhole parameter prediction model; A model parameter optimization test is performed on the candidate downhole parameter prediction model to determine the downhole parameter prediction model.

4. The downhole parameter prediction method according to claim 3, characterized in that: The performing of a model parameter optimization test on the candidate downhole parameter prediction model includes: Select any one or more of the following as evaluation indicators of model prediction effect: root mean square error RMSE , mean relative error , maximum relative error , training time.

5. The downhole parameter prediction method according to claim 1, characterized in that: The mechanism model includes any one or more of the following: a direct and inverse proportional response relationship model, a string force balance model, and a multiphase flow model.

6. The downhole parameter prediction method according to claim 1, characterized in that: The step of embedding the mechanism model into the loss function of the downhole parameter prediction model to obtain a loss function based on physical constraints includes: The input parameters of the mechanism model are expressed as physical functions of downhole parameters to obtain a loss function based on physical constraints.

7. The downhole parameter prediction method according to any one of claims 1 to 6, characterized in that: The downhole parameters include any one or more of the following: bottom hole torque, weight on bit, and equivalent density.

8. A downhole parameter prediction device, characterized in that: The device comprises: A model determination module is used to obtain a downhole parameter prediction model and its loss function for predicting downhole parameters constructed using multi-source data; A correction module, configured to construct a mechanism model for the downhole parameters, and embed the mechanism model into the loss function of the downhole parameter prediction model to obtain a loss function based on physical constraints; The model optimization module is used to perform back-propagation updates on the model parameters of the downhole parameter prediction model through optimization training to obtain a downhole parameter intelligent prediction model fused with mechanism data; A prediction module, configured to predict downhole parameters using the downhole parameter intelligent prediction model to obtain prediction results; The method further includes constructing the downhole parameter prediction model in the following manner: Acquire multi-source data and generate a multi-source data set; the multi-source data includes any one or more of the following data: well logging data, well logging data, and drilling data; Preprocessing the data in the multi-source data set to obtain a downhole key parameter feature set; Using the downhole key parameter feature set to train, a downhole parameter prediction model and its loss function are obtained; The preprocessing of the data in the multi-source data set to obtain the downhole key parameter feature set includes: Use any one or more methods including outlier removal, linear regression interpolation, and sliding average filtering to screen out abnormal and noisy data in the well; Use variance selection method to select feature parameters; Calculating correlation coefficients between different feature parameters, and determining candidate feature parameters based on the correlation coefficients; Determining effective feature parameters among the candidate feature parameters using a non-parametric method in statistics; Perform one-hot encoding on the non-time series feature parameters to obtain the encoded non-time series feature parameters; The encoded non-time-series characteristic parameters are fused with the effective characteristic parameters to generate a downhole key parameter feature set.

9. The downhole parameter prediction device according to claim 8, characterized in that: The device further includes: a model building module for building the downhole parameter prediction model; the model building module includes: A data acquisition unit is used to acquire multi-source data and generate a multi-source data set; the multi-source data includes any one or more of the following data: well logging data, well logging data, and drilling data; A data processing unit, configured to pre-process the data in the multi-source data set to obtain a downhole key parameter feature set; A training unit is used to train the downhole key parameter feature set to obtain a downhole parameter prediction model and its loss function.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the downhole parameter prediction method according to any one of claims 1 to 7 are executed.

Images