A method and device for correcting a longitudinal wave velocity logging curve and an electronic device

Abstract

The present application relates to oil and gas exploration and geophysical logging technical field, disclose a kind of longitudinal wave velocity logging curve correction method, device and electronic equipment, method includes constructing input sample data and output sample data;According to input sample data and output sample data through preset model training strategy to the depth feedforward neural network model is iteratively trained, obtains longitudinal wave velocity logging curve correction model;The logging curve set of all the diameter expansion section logging curves that meet the preset condition in diameter expansion section is input into longitudinal wave velocity logging curve correction model and carries out longitudinal wave velocity logging curve correction, obtains the diameter expansion section longitudinal wave velocity logging curve after correction.The present application can improve the rationality of longitudinal wave velocity logging curve correction.

Description

Technical Field

[0001] This invention relates to the field of oil and gas exploration and geophysical logging technology, and in particular to a method, apparatus and electronic equipment for correcting longitudinal wave velocity logging curves. Background Technology

[0002] Well logging curves are an important foundation for well seismic analysis and reservoir prediction. However, in mudstone formations, diameter enlargement and collapse often occur due to factors such as changes in drilling rate, resulting in diameter enlargement anomalies in sonic and density curves. This affects synthetic record calibration, rock physical analysis, and subsequent reservoir prediction work. Therefore, it is necessary to correct the abnormal values ​​of the curves affected by diameter enlargement so that they can better conform to geological laws.

[0003] Currently, commonly used methods for correcting P-wave velocity curves include parameter fitting, empirical formulas, and rock physics modeling.

[0004] The parameter fitting method, also known as the standard layer statistical method, generally involves selecting a non-expansion section as the stable section, performing cross-fitting on the target curve of the stable section and other curves to obtain the fitting relationship between parameters, and then applying this relationship to the expansion section to correct the target curve of the expansion section. The drawback of this method is that cross-fitting often only fits simple functional relationships between parameters, while in reality, the curves of each parameter may have more complex nonlinear relationships.

[0005] The most commonly used empirical formula method for calculating P-wave velocity is the Faust formula method, which uses the empirical relationship between P-wave impedance and resistivity in mudstone sections to correct the P-wave velocity curve. The drawback of this method is that it only considers the influence of resistivity on the single factor of P-wave velocity, resulting in low prediction accuracy.

[0006] Therefore, there is an urgent need for a correction method that can reasonably correct the P-wave velocity logging curve in the enlarged diameter section to solve the above-mentioned technical problems. Summary of the Invention

[0007] To address the above problems, this invention provides a method, apparatus, and electronic device for correcting P-wave velocity logging curves, which can improve the rationality of P-wave velocity logging curve correction in the enlarged diameter section, thereby laying a good foundation for subsequent logging response characteristics and rock physics analysis, synthetic record calibration, reservoir prediction, and other work.

[0008] This invention provides a method for correcting P-wave velocity logging curves, the method comprising:

[0009] Construct the input sample data and output sample data;

[0010] Based on the input and output sample data, the depth feedforward neural network model is iteratively trained using a preset model training strategy to obtain a P-wave velocity logging curve correction model.

[0011] All logging curves of the enlarged section that meet the preset conditions are input into the P-wave velocity logging curve correction model to perform P-wave velocity logging curve correction, and the corrected P-wave velocity logging curve of the enlarged section is obtained.

[0012] Furthermore, the input sample data and output sample data are constructed, including:

[0013] Based on the preset construction strategy, the logging curve sets of the stable section and the enlarged section in the target well and the target layer are constructed respectively;

[0014] All stable segment logging curves that meet the preset conditions in the stable segment logging curve set are used as input sample data, and the stable segment P-wave velocity logging curves in the stable segment logging curve set are used as output sample data.

[0015] Furthermore, the preset build strategies include:

[0016] The well section in the target well with a diameter greater than the preset diameter threshold is designated as the stable section, and the well section in the target well with a diameter not greater than the preset diameter threshold is designated as the enlarged section.

[0017] The stable segment logging curves corresponding to the stable segment are extracted from each logging curve of the target layer of the target well to construct a set of stable segment logging curves that includes all stable segment logging curves.

[0018] Extract the enlarged diameter section logging curve corresponding to the enlarged diameter section from each logging curve of the target layer of the target well to construct a logging curve set of the enlarged diameter section that includes all the enlarged diameter section logging curves.

[0019] Further, determine the stable logging curves that meet the preset conditions, including:

[0020] Remove the P-wave velocity logging curves from the stable segment of the logging curve set to obtain the target curve set;

[0021] Correlation analysis was performed on each stable segment logging curve in the target curve set and the stable segment P-wave velocity logging curve to obtain the correlation analysis results.

[0022] Based on the correlation analysis results, the stable section logging curves that meet the preset conditions are determined.

[0023] Furthermore, the preset model training strategy includes the least squares method.

[0024] The present invention also provides a P-wave velocity logging curve correction device, the device comprising:

[0025] The building blocks are used to construct the input and output sample data.

[0026] The training module is used to iteratively train the depth feedforward neural network model based on input sample data and output sample data using a preset model training strategy to obtain a P-wave velocity logging curve correction model.

[0027] The calibration module is used to input the well logging curves of the enlarged section that meet the preset conditions from the set of well logging curves of the enlarged section into the P-wave velocity well logging curve calibration model for P-wave velocity well logging curve calibration, so as to obtain the calibrated P-wave velocity well logging curve of the enlarged section.

[0028] Furthermore, the building blocks include:

[0029] The set of construction units is used to construct sets of logging curves for the stable section and the enlarged section in the target well according to the preset construction strategy;

[0030] The sample data determination unit is used to take all stable segment logging curves that meet the preset conditions in the set of stable segment logging curves as input sample data, and take the stable segment P-wave velocity logging curves in the set of stable segment logging curves as output sample data.

[0031] Furthermore, the building blocks also include:

[0032] The curve determination unit is used to delete the P-wave velocity logging curves of the stable segment from the set of logging curves of the stable segment to obtain the target curve set; and to perform correlation analysis between each logging curve of the stable segment in the target curve set and the P-wave velocity logging curve of the stable segment to obtain the correlation analysis results; and to determine the logging curves of the stable segment that meet the preset conditions based on the correlation analysis results.

[0033] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by one or more processors, implements the steps of the above-described method.

[0034] The present invention also provides an electronic device, including a memory and one or more processors, wherein a computer program is stored in the memory, and when the computer program is executed by one or more processors, the steps of the above method are performed.

[0035] The P-wave velocity logging curve correction method, apparatus, and electronic equipment provided by this invention iteratively trains a depth feedforward neural network model based on input and output sample data using a preset model training strategy to obtain a P-wave velocity logging curve correction model. When correcting the P-wave velocity logging curve in the enlarged diameter section, all logging curves in the enlarged diameter section that meet preset conditions are used as model input to obtain the corrected P-wave velocity logging curve for the enlarged diameter section. This invention, through iterative training of the depth feedforward neural network model, can fully explore the nonlinear relationship between input and output sample data. This relationship is then applied to the enlarged diameter section, and the trained model is used to correct the P-wave velocity logging curve. Compared to conventional parameter fitting methods and empirical formula methods, this invention considers the influence of multiple factors, resulting in higher learning accuracy and more reliable curve correction results. This improves the rationality of curve correction, thus laying a solid foundation for subsequent work such as logging response characteristics and rock physics analysis, synthetic record calibration, and reservoir prediction. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] It should also be noted that, for ease of description, only the parts relevant to the present invention are shown in the accompanying drawings. The accompanying drawings, which constitute a part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions in the invention are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0038] Figure 1 This is a flowchart of the steps of a longitudinal wave velocity logging curve correction method provided in Embodiment 1 of the present invention;

[0039] Figure 2 This is a flowchart of a preset construction strategy step provided in Embodiment 1 of the present invention;

[0040] Figure 3 This is a schematic diagram of a deep feedforward neural network model architecture provided in Embodiment 1 of the present invention;

[0041] Figure 4 This is a schematic diagram of a longitudinal wave velocity logging curve correction device provided in Embodiment 2 of the present invention;

[0042] Figure 5 This is a schematic diagram of the building module structure provided in Embodiment 2 of the present invention;

[0043] Figure 6 This is a schematic diagram of another building module structure provided in Embodiment 2 of the present invention;

[0044] Figure 7 The target well and target layer logging curve in Embodiment 3 of the present invention;

[0045] Figure 8 This is a schematic diagram illustrating the training accuracy of the deep feedforward network model in Embodiment 3 of the present invention;

[0046] Figure 9 This is a schematic diagram of the longitudinal wave velocity curve correction result in Embodiment 3 of the present invention;

[0047] Figure 10 This is a schematic diagram comparing the synthesized records before and after correction in Embodiment 3 of the present invention;

[0048] Figure 11 This is a schematic diagram of the electronic device structure provided in Embodiment Six of the present invention;

[0049] Figure label:

[0050] Figures 4 to 6 In Chinese: 401-Construction Module, 402-Training Module, 403-Correction Module, 4011-Set Construction Unit, 4012-Sample Data Determination Unit, 4013-Curve Determination Unit;

[0051] Figure 11 In Chinese: 1100 - Electronic device, 1101 - Processor, 1102 - Communication bus, 1103 - User interface, 1104 - Communication interface, 1105 - Memory. Detailed Implementation

[0052] The present invention will be further described below with reference to the embodiments shown in the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0053] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0054] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more unless explicitly defined or given contrary instructions in the context.

[0055] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0056] It should also be understood that the description of the various embodiments in this invention emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0057] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0058] The embodiments of the present invention may not discuss in detail the techniques, methods and devices known to those skilled in the art, but where appropriate, such techniques, methods and devices should be considered part of the specification.

[0059] The embodiments of this invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Well-known examples of terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0060] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0061] As the background technology shows, well logging curves are an important foundation for well seismic analysis and reservoir prediction. However, in mudstone formations, due to factors such as changes in drilling rate, enlargement and collapse often occur, resulting in enlargement anomalies in sonic and density curves. This affects synthetic record calibration, rock physical analysis, and subsequent reservoir prediction work. Therefore, it is necessary to correct the abnormal values ​​of the curves affected by enlargement so that they can better conform to geological laws.

[0062] Currently, commonly used methods for correcting P-wave velocity curves include parameter fitting, empirical formulas, and rock physics modeling.

[0063] The parameter fitting method, also known as the standard layer statistical method, generally involves selecting a non-expansion section as the stable section, performing cross-fitting on the target curve of the stable section and other curves to obtain the fitting relationship between parameters, and then applying this relationship to the expansion section to correct the target curve of the expansion section. The drawback of this method is that cross-fitting often only fits simple functional relationships between parameters, while in reality, the curves of each parameter may have more complex nonlinear relationships.

[0064] The most commonly used empirical formula method for calculating P-wave velocity is the Faust formula method, which uses the empirical relationship between P-wave impedance and resistivity in mudstone sections to correct the P-wave velocity curve. The drawback of this method is that it only considers the influence of resistivity on the single factor of P-wave velocity, resulting in low prediction accuracy.

[0065] Therefore, this application provides a correction method for the P-wave velocity logging curve in the enlarged diameter section to solve the above-mentioned technical problems.

[0066] Example 1

[0067] In Embodiment 1 of the present invention, as Figure 1 As shown, a method for correcting P-wave velocity logging curves is provided, which specifically includes the following steps:

[0068] Step S101: Construct input sample data and output sample data.

[0069] Step S102: Based on the input sample data and output sample data, the depth feedforward neural network model is iteratively trained using a preset model training strategy to obtain the P-wave velocity logging curve correction model.

[0070] Step S103: Input all the well logging curves of the enlarged section that meet the preset conditions from the set of well logging curves of the enlarged section into the P-wave velocity well logging curve correction model to perform P-wave velocity well logging curve correction, and obtain the corrected P-wave velocity well logging curve of the enlarged section.

[0071] Deep feedforward neural networks, also known as multilayer perceptrons (MLPs), are typical deep learning models where neurons are arranged in layers. Each neuron is connected only to neurons in the previous layer, receiving the output of the previous layer and outputting it to the next layer; there is no feedback between layers. Deep feedforward neural networks can learn data representations and features through multilayer nonlinear transformations, thereby enabling various machine learning tasks.

[0072] Optionally, in step S101, the input sample data and output sample data are constructed, specifically including the following steps:

[0073] Step S1011: Construct the logging curve sets of the stable section and the enlarged section in the target well according to the preset construction strategy;

[0074] Step S1012: Take all stable segment logging curves that meet the preset conditions in the stable segment logging curve set as input sample data, and take the stable segment P-wave velocity logging curves in the stable segment logging curve set as output sample data.

[0075] Specifically, the selection of the target well and the target layer shall be determined by the technical personnel according to actual needs, and the present invention does not impose any special restrictions on this.

[0076] For example, a typical well in the study area can be selected as the target well.

[0077] Optionally, in step S1011, as follows Figure 2 As shown, the preset build strategy specifically includes the following steps:

[0078] Step S10111: The well section in the target well with a diameter greater than the preset well diameter threshold is designated as the stable section, and the well section in the target well with a diameter not greater than the preset well diameter threshold is designated as the enlarged section.

[0079] It should be noted that the preset well diameter threshold can be determined by technicians according to the actual situation, and the present invention does not impose any special limitation on the preset well diameter threshold.

[0080] Step S10112: Extract the stable segment logging curve corresponding to the stable segment from each logging curve of the target layer of the target well, so as to construct a set of stable segment logging curves including all stable segment logging curves.

[0081] Step S10113: Extract the enlarged section logging curve corresponding to the enlarged section from each logging curve of the target layer of the target well, so as to construct a set of logging curves for the enlarged section that includes all the logging curves for the enlarged section.

[0082] The target well and its target formation include multiple logging curves, such as P-wave velocity (logging symbol VP), density (logging symbol RHO), well diameter (logging symbol CAL), deep lateral resistivity (logging symbol LLD), shallow lateral resistivity (logging symbol LLS), drilling depth (logging symbol MD), and spontaneous potential (logging symbol SP). Each logging curve reflects the variation of its corresponding parameter with depth.

[0083] After dividing the target well into a stable segment and an enlarged segment according to step S10111, the stable segment corresponds to a depth range and the enlarged segment corresponds to a depth range. Therefore, in steps S10112 and S10113, logging curves of corresponding depths can be extracted from each logging curve of the target well in the target well according to the depth range of the stable segment and the depth range of the enlarged segment, respectively, so as to obtain a set of logging curves of the stable segment including multiple logging curves of the stable segment and a set of logging curves of the enlarged segment including multiple logging curves of the enlarged segment.

[0084] Optionally, in step S102, the preset model training strategy includes the least squares method.

[0085] The Least Squares Method (LS) is a mathematical tool widely used in various data processing disciplines, including error estimation, uncertainty, system identification and prediction. It finds the optimal function match for data by minimizing the sum of squared errors. The Least Squares Method can be used to easily obtain unknown data while minimizing the sum of squared errors between the obtained data and the actual data.

[0086] For example, in actual training, assuming the target P-wave velocity curve (stable P-wave velocity logging curve) to be corrected is variable y, all stable P-wave velocity logging curves that meet the preset conditions (curves with high correlation to the stable P-wave velocity logging curve and less affected by borehole enlargement) are of two types, x1 and x2. Iterative training of the depth feedforward neural network model using the least squares method includes:

[0087] Using x1 and x2 as input sample data and y as output sample data, a deep feedforward neural network model with two hidden layers and three neurons in each hidden layer is established (see schematic diagram of deep feedforward neural network model architecture as shown). Figure 3 (As shown), conduct learning and training.

[0088] The activation function of the hidden layer neurons is a non-linear sigmoid logic function, i.e.

[0089] In a deep feedforward neural network model, w and b are the weight coefficients and bias terms of the network model, respectively. The neurons in each layer of the network are connected and transmitted to the neurons in the next layer through their respective weight coefficients w and bias terms b. These two parameters need to be initialized before training.

[0090] x1 and x2 are input into the deep feedforward neural network model, and first a weighted calculation is performed as shown in equation (1) to obtain z1, z2, and z3:

[0091]

[0092] z1, z2, and z3 are passed to the neurons in the first hidden layer for nonlinear Sigmoid logic function transformation to obtain f1(z1) and f2(z2).

[0093] The result of the nonlinear transformation is weighted and summed before being passed to the next layer of neurons, and so on, to perform nonlinear operations between parameters.

[0094] During the training process, the objective function (Equation 2) is optimized by using the conjugate gradient method according to the principle that the variance of each layer should be as equal as possible. The calculation is terminated when the output result and the target curve y reach the least squares error. At this time, the obtained w and b are the optimal solutions, and the model corresponding to the optimal solution is the longitudinal wave velocity logging curve correction model obtained by training.

[0095] The objective function of the conjugate gradient method includes:

[0096]

[0097] In equation (2), Let w be the L2 norm, λ be the weighting coefficient of the norm, P be the number of sample points of the logging curve in the input sample data, L be the total number of layers of the deep neural network model, l be the l-th layer, m be the number of neurons in the l-th layer, i be the i-th neuron in the l-th layer, j be the j-th neuron in the (l-1)-th layer, and f() be the nonlinear Sigmoid logic function.

[0098] Furthermore, during model training, the number of hidden layers or different numbers of neurons in the deep feedforward neural network model can be adjusted based on the error variation pattern between the output result and the target curve y.

[0099] Furthermore, in one implementation method, determining the stable logging curve that meets the preset conditions includes the following specific steps:

[0100] Step S10121: Delete the P-wave velocity logging curves of the stable segment from the logging curve set of the stable segment to obtain the target curve set.

[0101] Step S10122: Perform correlation analysis between each stable segment logging curve in the target curve set and the stable segment P-wave velocity logging curve to obtain the correlation analysis results.

[0102] Step S10123: Determine the stable section logging curve that meets the preset conditions based on the correlation analysis results.

[0103] Specifically, in step S10122, the correlation analysis includes:

[0104] The correlation between each stable segment logging curve and the stable segment P-wave velocity logging curve in the target curve set is analyzed, as well as the extent to which each stable segment logging curve in the target curve set is affected by the enlargement.

[0105] In step S10123, the stable logging curves that meet the preset conditions are determined based on the correlation analysis results, including:

[0106] Several types of logging curves that are highly correlated with P-wave velocity and less affected by diameter expansion are identified as stable segment logging curves that meet preset conditions. Then, all stable segment logging curves that meet preset conditions are determined from the set of stable segment logging curves.

[0107] It is understandable that in step S103, the logging curves of all enlarged sections that meet the preset conditions are of the same type as the logging curves of all stable sections that meet the preset conditions. That is, the logging curves of all enlarged sections that meet the preset conditions need to be determined based on the logging curves of all stable sections that meet the preset conditions.

[0108] For example, when all stable-section logging curves that meet the preset conditions include deep lateral resistivity (LLD) logging curves, shallow lateral resistivity (LLS) logging curves, drilling depth (MD) logging curves, spontaneous potential (SP) logging curves, and natural gamma (GR) logging curves, then all enlarged-diameter-section logging curves that meet the preset conditions also include deep lateral resistivity (LLD) logging curves, shallow lateral resistivity (LLS) logging curves, drilling depth (MD) logging curves, spontaneous potential (SP) logging curves, and natural gamma (GR) logging curves.

[0109] The P-wave velocity logging curve correction method provided in this embodiment iteratively trains a depth feedforward neural network model based on input and output sample data using a preset model training strategy to obtain a P-wave velocity logging curve correction model. When correcting the P-wave velocity logging curve in the enlarged diameter section, all logging curves in the enlarged diameter section that meet preset conditions are used as model input to obtain the corrected P-wave velocity logging curve in the enlarged diameter section. By iteratively training the depth feedforward neural network model, the nonlinear relationship between the input and output sample data can be fully explored. This relationship is then applied to the enlarged diameter section, and the trained model is used to correct the P-wave velocity logging curve. Compared with conventional parameter fitting methods and empirical formula methods, this invention considers the influence of multiple factors, has higher learning accuracy, and obtains more reliable curve correction results, improving the rationality of curve correction. This lays a good foundation for subsequent logging response characteristics and rock physics analysis, synthetic record calibration, reservoir prediction, and other work.

[0110] Example 2

[0111] In Embodiment 2 of the present invention, as Figure 4 As shown, a P-wave velocity logging curve correction device is provided, the device specifically includes:

[0112] Module 401 is used to construct input sample data and output sample data;

[0113] Training module 402 is used to iteratively train the depth feedforward neural network model based on input sample data and output sample data using a preset model training strategy to obtain a P-wave velocity logging curve correction model.

[0114] The correction module 403 is used to input all the well logging curves of the enlarged diameter section that meet the preset conditions into the P-wave velocity well logging curve correction model to perform P-wave velocity well logging curve correction, and obtain the corrected P-wave velocity well logging curve of the enlarged diameter section.

[0115] Optionally, such as Figure 5 As shown, the building module 401 includes:

[0116] The set of construction unit 4011 is used to construct the set of logging curves for the stable section and the enlarged section in the target well according to the preset construction strategy.

[0117] The sample data determination unit 4012 is used to take all stable segment logging curves that meet the preset conditions in the set of stable segment logging curves as input sample data, and take the stable segment P-wave velocity logging curves in the set of stable segment logging curves as output sample data.

[0118] Optionally, the preset model training strategy includes the least squares method.

[0119] Optionally, such as Figure 6 As shown, the building module 401 also includes:

[0120] The curve determination unit 4013 is used to delete the stable segment P-wave velocity logging curve from the set of stable segment logging curves to obtain the target curve set; and to perform correlation analysis between each stable segment logging curve in the target curve set and the stable segment P-wave velocity logging curve to obtain the correlation analysis results; and to determine the stable segment logging curve that meets the preset conditions based on the correlation analysis results.

[0121] The P-wave velocity logging curve correction device provided in this embodiment iteratively trains a depth feedforward neural network model based on input and output sample data using a preset model training strategy to obtain a P-wave velocity logging curve correction model. When correcting the P-wave velocity logging curve in the enlarged diameter section, all logging curves in the enlarged diameter section that meet preset conditions are used as model input to obtain the corrected P-wave velocity logging curve in the enlarged diameter section. By iteratively training the depth feedforward neural network model, the nonlinear relationship between the input and output sample data can be fully explored. This relationship is then applied to the enlarged diameter section, and the trained model is used to correct the P-wave velocity logging curve. Compared with conventional parameter fitting methods and empirical formula methods, this invention considers the influence of multiple factors, has higher learning accuracy, and obtains more reliable curve correction results, improving the rationality of curve correction. This lays a good foundation for subsequent logging response characteristics and rock physics analysis, synthetic record calibration, reservoir prediction, and other work.

[0122] Example 3

[0123] In Embodiment 3 of the present invention, a specific example is provided for correcting the P-wave velocity logging curve using the P-wave velocity logging curve correction method in Embodiment 1.

[0124] In this embodiment, well S1, a typical well in a block in the western Ordos Basin, is selected as the target well. Figure 7 As shown, the P-wave velocity of the Permian Shanxi Formation in the target layer exhibits an anomaly of enlargement. The correction method of Embodiment 1 of the present invention is used to correct the P-wave velocity logging curve of the enlarged section.

[0125] Analysis determined that well diameters less than 23 cm in the target layer were stable sections, while well diameters greater than 23 cm were enlargement sections requiring correction. A pseudo-well W1 was constructed by selecting the stable section (the logging curve set of pseudo-well W1 is the logging curve set of the stable section).

[0126] The correlation between the P-wave velocity logging curve of well W1 and other parameter logging curves was analyzed. It was found that there is a good correlation between P-wave velocity and five parameters: deep lateral resistivity (LLD), shallow lateral resistivity (LLS), drilling depth (MD), spontaneous potential (SP), and natural gamma (GR). Moreover, these five parameters are basically unaffected by borehole enlargement. Therefore, the deep lateral resistivity (LLD), shallow lateral resistivity (LLS), drilling depth (MD), spontaneous potential (SP), and natural gamma (GR) logging curves of pseudo-well W1 were used as input data for the depth feedforward neural network model, and the P-wave velocity logging curve of pseudo-well W1 was used as output data to construct a sample set.

[0127] Through model parameter testing, a deep feedforward neural network model with 3 hidden layers, 50 neurons per layer, and 500 iterations was finally established, achieving a training accuracy of 0.926 (e.g., ...). Figure 8 This demonstrates the effectiveness and rationality of the model.

[0128] The logging curves of five parameters—deep lateral resistivity (LLD), shallow lateral resistivity (LLS), drilling depth (MD), spontaneous potential (SP), and natural gamma (GR)—of the enlarged section of the target formation in well S1 were input into the constructed model to obtain the corrected P-wave velocity logging curve, as shown below. Figure 9 As shown, the corrected P-wave velocity logging curves are used to regenerate new synthetic records and calibrate the wellbore sidetracks of seismic data. Figure 10 As shown, a comparison of the synthetic records before and after calibration reveals that the wave group relationship of the synthetic records after calibration is more reasonable, laying a good foundation for subsequent rock physics analysis and reservoir prediction.

[0129] Example 4

[0130] In Embodiment 4 of the present invention, a computer program product is also provided, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, they implement all or part of the steps of the longitudinal wave velocity logging curve correction method described in the above embodiments.

[0131] The methods for correcting P-wave velocity logging curves include:

[0132] Construct the input sample data and output sample data;

[0133] Based on the input and output sample data, the depth feedforward neural network model is iteratively trained using a preset model training strategy to obtain a P-wave velocity logging curve correction model.

[0134] All logging curves of the enlarged section that meet the preset conditions are input into the P-wave velocity logging curve correction model to perform P-wave velocity logging curve correction, and the corrected P-wave velocity logging curve of the enlarged section is obtained.

[0135] Optionally, the input sample data and output sample data are constructed, including:

[0136] Based on the preset construction strategy, the logging curve sets of the stable section and the enlarged section in the target well and the target layer are constructed respectively;

[0137] All stable segment logging curves that meet the preset conditions in the stable segment logging curve set are used as input sample data, and the stable segment P-wave velocity logging curves in the stable segment logging curve set are used as output sample data.

[0138] Optionally, the default build strategy includes:

[0139] The well section in the target well with a diameter greater than the preset diameter threshold is designated as the stable section, and the well section in the target well with a diameter not greater than the preset diameter threshold is designated as the enlarged section.

[0140] The stable segment logging curves corresponding to the stable segment are extracted from each logging curve of the target layer of the target well to construct a logging curve set of the stable segment that includes all the stable segment logging curves;

[0141] Extract the enlarged diameter section logging curve corresponding to the enlarged diameter section from each logging curve of the target layer of the target well to construct a logging curve set of the enlarged diameter section that includes all the enlarged diameter section logging curves.

[0142] Optionally, the stable logging curve that meets preset conditions is determined, including:

[0143] Remove the P-wave velocity logging curves from the stable segment of the logging curve set to obtain the target curve set;

[0144] Correlation analysis was performed on each stable segment logging curve in the target curve set and the stable segment P-wave velocity logging curve to obtain the correlation analysis results.

[0145] Based on the correlation analysis results, the stable section logging curves that meet the preset conditions are determined.

[0146] Optionally, the preset model training strategy includes the least squares method.

[0147] Furthermore, the computer program product may include one or more computer-executable components configured to perform embodiments when the program is run; the computer program product may also include a computer program tangibly contained on a readable medium thereof, the computer program containing program code for performing any of the methods in the embodiments of the present invention. In such embodiments, the computer program may be downloaded and installed from a network via a communication component, and / or installed from a removable medium.

[0148] Example 5

[0149] In Embodiment 5 of the present invention, a computer-readable storage medium is also provided, wherein a computer program stored in the computer-readable storage medium, when executed by one or more processors, implements all or part of the steps of the P-wave velocity logging curve correction method described in the above embodiments.

[0150] The methods for correcting P-wave velocity logging curves include:

[0151] Construct the input sample data and output sample data;

[0152] Based on the input and output sample data, the depth feedforward neural network model is iteratively trained using a preset model training strategy to obtain a P-wave velocity logging curve correction model.

[0153] All logging curves of the enlarged section that meet the preset conditions are input into the P-wave velocity logging curve correction model to perform P-wave velocity logging curve correction, and the corrected P-wave velocity logging curve of the enlarged section is obtained.

[0154] Optionally, the input sample data and output sample data are constructed, including:

[0155] Based on the preset construction strategy, the logging curve sets of the stable section and the enlarged section in the target well and the target layer are constructed respectively;

[0156] All stable segment logging curves that meet the preset conditions in the stable segment logging curve set are used as input sample data, and the stable segment P-wave velocity logging curves in the stable segment logging curve set are used as output sample data.

[0157] Optionally, the default build strategy includes:

[0158] The well section in the target well with a diameter greater than the preset diameter threshold is designated as the stable section, and the well section in the target well with a diameter not greater than the preset diameter threshold is designated as the enlarged section.

[0159] The stable segment logging curves corresponding to the stable segment are extracted from each logging curve of the target layer of the target well to construct a logging curve set of the stable segment that includes all the stable segment logging curves;

[0160] Extract the enlarged diameter section logging curve corresponding to the enlarged diameter section from each logging curve of the target layer of the target well to construct a logging curve set of the enlarged diameter section that includes all the enlarged diameter section logging curves.

[0161] Optionally, the stable logging curve that meets preset conditions is determined, including:

[0162] Remove the P-wave velocity logging curves from the stable segment of the logging curve set to obtain the target curve set;

[0163] Correlation analysis was performed on each stable segment logging curve in the target curve set and the stable segment P-wave velocity logging curve to obtain the correlation analysis results.

[0164] Based on the correlation analysis results, the stable section logging curves that meet the preset conditions are determined.

[0165] Optionally, the preset model training strategy includes the least squares method.

[0166] In the various embodiments of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0167] Computer-readable storage media may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires; portable disks; hard disks; random access memory (RAM); read-only memory (ROM); electrically erasable programmable read-only memory (EPROM); optical fibers; compact disc read-only memory (CD-ROM); optical storage devices; magnetic storage devices; or any suitable combination thereof.

[0168] Example 6

[0169] In Embodiment Six of the present invention, an electronic device 1100 is also provided, which may be a mobile phone, a computer, or a tablet computer, etc. Figure 11 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention, such as... Figure 11 As shown, the electronic device 1100 includes: at least one processor 1101, at least one communication bus 1102, a user interface 1103, at least one external communication interface 1104, and a memory 1105. The communication bus 1102 is configured to enable communication between these components. The user interface 1103 may include a display screen, and the external communication interface 1104 may include standard wired and wireless interfaces. The memory 1105 stores a computer program, and the memory 1105 and one or more processors 1101 are communicatively connected. When the computer program is executed by one or more processors, the processor 1101 is configured to execute the computer program stored in the memory to implement all or part of the steps of the P-wave velocity logging curve correction method in the above embodiments.

[0170] The methods for correcting P-wave velocity logging curves include:

[0171] Construct the input sample data and output sample data;

[0172] Based on the input and output sample data, the depth feedforward neural network model is iteratively trained using a preset model training strategy to obtain a P-wave velocity logging curve correction model.

[0173] All logging curves of the enlarged section that meet the preset conditions are input into the P-wave velocity logging curve correction model to perform P-wave velocity logging curve correction, and the corrected P-wave velocity logging curve of the enlarged section is obtained.

[0174] Optionally, the input sample data and output sample data are constructed, including:

[0175] Based on the preset construction strategy, the logging curve sets of the stable section and the enlarged section in the target well and the target layer are constructed respectively;

[0176] All stable segment logging curves that meet the preset conditions in the stable segment logging curve set are used as input sample data, and the stable segment P-wave velocity logging curves in the stable segment logging curve set are used as output sample data.

[0177] Optionally, the default build strategy includes:

[0178] The well section in the target well with a diameter greater than the preset diameter threshold is designated as the stable section, and the well section in the target well with a diameter not greater than the preset diameter threshold is designated as the enlarged section.

[0179] The stable segment logging curves corresponding to the stable segment are extracted from each logging curve of the target layer of the target well to construct a logging curve set of the stable segment that includes all the stable segment logging curves;

[0180] Extract the enlarged diameter section logging curve corresponding to the enlarged diameter section from each logging curve of the target layer of the target well to construct a logging curve set of the enlarged diameter section that includes all the enlarged diameter section logging curves.

[0181] Optionally, the stable logging curve that meets preset conditions is determined, including:

[0182] Remove the P-wave velocity logging curves from the stable segment of the logging curve set to obtain the target curve set;

[0183] Correlation analysis was performed on each stable segment logging curve in the target curve set and the stable segment P-wave velocity logging curve to obtain the correlation analysis results.

[0184] Based on the correlation analysis results, the stable section logging curves that meet the preset conditions are determined.

[0185] Optionally, the preset model training strategy includes the least squares method.

[0186] The processor can be implemented as an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field-programmable gate array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is used to execute all or part of the steps of the P-wave velocity logging curve correction method described in the above embodiments. This embodiment will not repeat the details here.

[0187] Memory can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0188] The P-wave velocity logging curve correction method, apparatus, and electronic equipment provided by this invention iteratively trains a depth feedforward neural network model based on input and output sample data using a preset model training strategy to obtain a P-wave velocity logging curve correction model. When correcting the P-wave velocity logging curve in the enlarged diameter section, all logging curves in the enlarged diameter section that meet preset conditions are used as model input to obtain the corrected P-wave velocity logging curve in the enlarged diameter section. By iteratively training the depth feedforward neural network model, the nonlinear relationship between the input and output sample data can be fully explored. This relationship is then applied to the enlarged diameter section, and the trained model is used to correct the P-wave velocity logging curve. Compared with conventional parameter fitting methods and empirical formula methods, this invention considers the influence of multiple factors, resulting in higher learning accuracy and more reliable curve correction results. This improves the rationality of curve correction and lays a good foundation for subsequent logging response characteristics, rock physics analysis, synthetic record calibration, reservoir prediction, and other work.

[0189] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of the various embodiments of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the specific details described above.

[0190] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," and "having" are open-ended terms meaning "including but not limited to" and are used interchangeably.

[0191] It should also be noted that in the apparatus, devices, and methods disclosed herein, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered equivalent solutions of the present invention.

[0192] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0193] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for correcting longitudinal wave velocity logging curves, characterized in that, The method includes: Construct the input sample data and output sample data; Based on the input sample data and the output sample data, the depth feedforward neural network model is iteratively trained using a preset model training strategy to obtain a P-wave velocity logging curve correction model. All logging curves of the enlarged section that meet the preset conditions are input into the P-wave velocity logging curve correction model to perform P-wave velocity logging curve correction, and the corrected P-wave velocity logging curve of the enlarged section is obtained. The construction of input sample data and output sample data includes: Based on the preset construction strategy, the logging curve sets of the stable section and the enlarged section in the target well and the target layer are constructed respectively; All stable segment logging curves that meet the preset conditions in the set of stable segment logging curves are used as input sample data, and the stable segment P-wave velocity logging curves in the set of stable segment logging curves are used as output sample data. The preset construction strategy includes: The well section in the target well whose diameter is greater than the preset well diameter threshold is designated as the stable section, and the well section in the target well whose diameter is not greater than the preset well diameter threshold is designated as the enlarged section. The stable segment logging curve corresponding to the stable segment is extracted from each logging curve of the target layer of the target well to construct a logging curve set of the stable segment that includes all stable segment logging curves; Extract the enlarged diameter section logging curve corresponding to the enlarged diameter section from each logging curve of the target layer of the target well, so as to construct a logging curve set of the enlarged diameter section including all the enlarged diameter section logging curves.

2. The P-wave velocity logging curve correction method according to claim 1, characterized in that, Determining the stable logging curve that meets the preset conditions includes: Remove the P-wave velocity logging curves of the stable segment from the set of logging curves of the stable segment to obtain the target curve set; Correlation analysis was performed between each stable segment logging curve in the target curve set and the stable segment P-wave velocity logging curve to obtain the correlation analysis results. Based on the correlation analysis results, the stable section logging curves that meet the preset conditions are determined.

3. A P-wave velocity logging curve correction device for implementing the P-wave velocity logging curve correction method according to any one of claims 1-2, characterized in that, The device includes: The building blocks are used to construct the input and output sample data. The training module is used to iteratively train the depth feedforward neural network model based on the input sample data and the output sample data using a preset model training strategy to obtain a P-wave velocity logging curve correction model. The calibration module is used to input all the well logging curves of the enlarged section that meet the preset conditions from the set of well logging curves of the enlarged section into the P-wave velocity well logging curve calibration model for P-wave velocity well logging curve calibration, so as to obtain the calibrated P-wave velocity well logging curve of the enlarged section.

4. The P-wave velocity logging curve correction device according to claim 3, characterized in that, The building module includes: The set of construction units is used to construct sets of logging curves for the stable section and the enlarged section in the target well according to the preset construction strategy; The sample data determination unit is used to take all stable segment logging curves that meet preset conditions in the set of stable segment logging curves as input sample data, and take the stable segment P-wave velocity logging curves in the set of stable segment logging curves as output sample data.

5. The P-wave velocity logging curve correction device according to claim 4, characterized in that, The building module also includes: The curve determination unit is used to delete the P-wave velocity logging curve of the stable segment from the set of logging curves of the stable segment to obtain a target curve set; and to perform correlation analysis between each stable segment logging curve in the target curve set and the P-wave velocity logging curve of the stable segment to obtain the correlation analysis result; and to determine the stable segment logging curve that meets the preset condition based on the correlation analysis result.

6. A computer-readable storage medium, characterized in that, The computer program stored in the computer-readable storage medium, when executed by one or more processors, implements the steps of the method as described in any one of claims 1 to 2.

7. An electronic device, characterized in that, It includes a memory and one or more processors, wherein a computer program is stored in the memory, and when the computer program is executed by the one or more processors, it performs the steps of the method as described in any one of claims 1 to 2.

Images