Stratum pore pressure prediction method, device, equipment and medium

Abstract

This invention provides a method, apparatus, device, and medium for predicting formation pore pressure. The method includes: confirming one-dimensional wave impedance data of a single well based on well logging data of a target area; establishing a first relationship model between P-wave velocity and wave impedance based on the one-dimensional wave impedance data of the single well; confirming a first wave impedance data volume using a genetic inversion algorithm based on the one-dimensional wave impedance data of the single well and seismic data; confirming a first wave velocity data volume based on the first wave impedance data volume and the first relationship model; and confirming a formation pore pressure data volume based on the first wave velocity data volume, and predicting formation pore pressure based on the formation pore pressure data volume. This invention predicts formation pore pressure based on the logging characteristics of drilled wells and combined with high-resolution seismic data, taking into account various factors such as regional tectonic background and sedimentary characteristics, thus improving the accuracy of pore pressure prediction for undrilled formations.

Description

Technical Field

[0001] This invention relates to the field of wellbore stability in oil and gas wells, and more specifically, to a method for predicting formation pore pressure, a device for predicting formation pore pressure, and equipment and computer-readable storage medium for implementing the method for predicting formation pore pressure. Background Technology

[0002] As the exploration and development of oil and gas resources increasingly focuses on unconventional resources, pre-drilling abnormal pressure prediction has become a crucial aspect of oil and gas exploration and development. Accurate prediction of abnormal pore pressure is of great significance in oil and gas exploration, oil and gas field development, and reservoir engineering. Pore pressure prediction information is also fundamental to ensuring the safe, efficient, and economical implementation of drilling operations. Pre-drilling pressure prediction data helps in selecting appropriate mud density, preventing safety accidents such as well kicks and blowouts caused by abnormally high pressure, reducing non-operational time, and avoiding problems such as wellbore instability, wellbore erosion, and drilling fluid loss due to excessive drilling fluid density, thus reducing formation damage. Furthermore, predicted pressure also helps in designing reasonable casing procedures, saving engineering costs while ensuring safety.

[0003] Meanwhile, predicted pressure is also crucial data for geomechanical modeling in reservoir engineering. Combined with information such as rock elastic parameters and strength, it can predict and quantify the impact of stress on various operations throughout the reservoir production cycle, thus aiding decision-making, including new well location and drilling / completion design, production enhancement and stabilization, minimizing risks, and making new investments. Furthermore, overpressure contributes to oil and gas production, increasing yields. Studies have shown that increasing the pore pressure gradient by 0.905 kPa can increase oil and gas production by 150% and recovery rate by 73%. Therefore, accurate pore pressure prediction contributes to accurate economic benefit prediction for oil and gas zones.

[0004] Currently, shale gas exploration and development in my country is still in its initial stage, characterized by high risks and costs. The formation pressure systems encountered in shale gas development are becoming increasingly complex, demanding higher accuracy in formation pressure prediction. Most conventional pre-drilling methods for formation pressure prediction are based on velocity spectra or seismic layer velocity data. Their prediction mechanism is based on the constant compaction trend of mudstone, resulting in low resolution. Pore pressure prediction methods are mainly based on empirical relationships between single geophysical parameters and pore pressure (or effective stress). However, anomalous pore pressure is not only complex in its causes (non-equilibrium compaction, fluid expansion, load migration, lateral migration, hydrocarbon generation, etc.), but is also influenced by various factors such as regional tectonic background and sedimentary characteristics. Univariate models often cannot fully describe the complex changes in pore pressure.

[0005] In summary, most current methods for predicting formation pressure before drilling are based on the assumption of constant compaction of mudstone and use low-resolution seismic velocity data to predict formation pressure. Geological bodies have complex spatiotemporal structures, and different understandings of the causes of pressure and its influencing factors can lead to different theoretical models. The data used for prediction (well logging and seismic data) itself contains errors. At the same time, the existing data used for prediction are sparse samples of geological bodies, that is, local prediction of the whole, so there is a lot of uncertainty in pressure prediction. Summary of the Invention

[0006] The purpose of this invention is to address at least one of the aforementioned shortcomings of the prior art. For example, one objective of this invention is to provide a method for predicting formation pore pressure by integrating well logging and seismic data, which combines high-resolution impedance information and employs a genetic inversion algorithm to obtain formation pore pressure prediction results with better resolution.

[0007] To achieve the above objectives, the present invention provides a method for predicting formation pore pressure.

[0008] The formation pore pressure prediction method includes the following steps:

[0009] S1. Confirm the one-dimensional wave impedance data of a single well based on the logging data of the target area, and establish a first relationship model between the longitudinal wave velocity and the wave impedance based on the one-dimensional wave impedance data of the single well.

[0010] S2. Based on the single-well one-dimensional wave impedance data and seismic data, the first wave impedance data volume is confirmed using a genetic inversion algorithm.

[0011] S3. Based on the first wave impedance data volume and the first relationship model, confirm the first wave velocity data volume.

[0012] S4. Confirm the formation pore pressure data volume based on the first wave velocity data volume, and predict the formation pore pressure based on the formation pore pressure data volume.

[0013] In an exemplary embodiment of the formation pore pressure prediction method of the present invention, the first relationship model includes:

[0014]

[0015] Where AI is the wave impedance, kg / (m) 2 ·s); vp is the longitudinal wave velocity, km / s; C and A are fitting coefficients.

[0016] In an exemplary embodiment of the formation pore pressure prediction method of the present invention, step S2 may include:

[0017] S21. Process the earthquake data to obtain earthquake data volume.

[0018] S22. After processing the single-well one-dimensional wave impedance data, use it as a learning object and use the genetic inversion algorithm to obtain a nonlinear multi-channel operator.

[0019] S23. Apply the nonlinear multi-channel operator to the seismic data volume to obtain the first wave impedance data volume.

[0020] In an exemplary embodiment of the formation pore pressure prediction method of the present invention, step S21 may include:

[0021] S211. Perform amplitude and noise reduction processing on the seismic data volume, and confirm the first selected range by selecting the first top structural surface and the first bottom structural surface of the target area.

[0022] In an exemplary embodiment of the formation pore pressure prediction method of the present invention, step S22 may include:

[0023] S221. After processing the abnormal data in the one-dimensional acoustic impedance data of the single well, the acoustic impedance data points on the single well are confirmed.

[0024] S222. The first acoustic impedance data volume is derived from the seismic data volume of the first selected range, and the first acoustic impedance data volume is used as the initial value.

[0025] S223. Confirm the error value of the acoustic impedance data points on the single wells of all well groups in the target area and the first acoustic impedance data volume. Based on the error value, confirm the first well as the learning object to invert and confirm the second acoustic impedance data point. Based on the error value, confirm the second well and update the error value after exchanging and mutating until the error value reaches the global minimum.

[0026] S224. Confirm the second selected range by selecting the second top surface and the second bottom surface of the target area, and replace the first selected range with the second selected range.

[0027] S225. Repeat steps S222 to S224 until the inversion of the target region is completed, and use the second acoustic impedance data point as the first wave impedance data body.

[0028] In an exemplary embodiment of the formation pore pressure prediction method of the present invention, step S4 includes: establishing a formation pore pressure model using the Fillippone method and the Eaton method, and confirming the formation pore pressure data volume based on the formation pore pressure model and the first wave velocity data volume.

[0029] In an exemplary embodiment of the formation pore pressure prediction method of the present invention, the formation pore pressure model may include:

[0030]

[0031] Among them, P p P represents formation pore pressure, in MPa; ov P represents the pressure of the overlying strata, in MPa; w The hydrostatic pressure is MPa; V i V is the layer velocity of the i-th layer, in km / s; max V is the velocity when porosity approaches zero, in km / s; min The velocity is given in km / s when the rock's rigidity approaches zero.

[0032] In another aspect, the present invention provides a formation pore pressure prediction device. The formation pore pressure prediction device includes a first relational model determination module, a first wave impedance data volume determination module, a first wave velocity data volume determination module, and a formation pore pressure prediction module, which are connected in sequence.

[0033] The first relationship model determination module is configured to confirm the one-dimensional wave impedance data of a single well based on the logging data of the target area, and establish a first relationship model between the longitudinal wave velocity and the wave impedance based on the one-dimensional wave impedance data of the single well.

[0034] The first wave impedance data volume determination module is configured to confirm the first wave impedance data volume based on the single-well one-dimensional wave impedance data and seismic data using a genetic inversion algorithm.

[0035] The first wave velocity data volume determination module is configured to confirm the first wave velocity data volume based on the first wave impedance data volume and the first relationship model.

[0036] The formation pore pressure prediction module is configured to confirm the formation pore pressure data volume based on the first wave velocity data volume, and to predict the formation pore pressure based on the formation pore pressure data volume.

[0037] In another aspect, the present invention provides a computer device, the computer device comprising:

[0038] Processor; memory storing a computer program that, when executed by the processor, implements the formation pore pressure prediction method as described above.

[0039] In another aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the formation pore pressure prediction method as described above.

[0040] Compared with the prior art, the beneficial effects of the present invention include at least one of the following:

[0041] (1) This invention provides a method for predicting formation pore pressure by integrating well logging and seismic data. This method avoids the current practice of relying mainly on empirical relationships between single geophysical parameters and pore pressure for pore pressure prediction. Instead, it adopts a multivariate model, integrates well logging and seismic data, and uses a genetic inversion algorithm to predict pore pressure.

[0042] (2) The formation pore pressure prediction method provided by this invention utilizes well logging data to reflect the formation properties around the wellbore. While well logging data can be used for pore pressure prediction to obtain the pore pressure variation with depth at well points in a region, it is difficult to accurately reflect the changes in pore pressure between wells and in areas without wells. Seismic data, on the other hand, can provide high-resolution information about the inter-well locations. Using seismic data for pre-drilling pore pressure prediction (constructing a pore pressure field) can provide spatial pressure distribution information. This method not only considers pore pressure prediction at a single well but also, based on high-resolution seismic data and taking into account the influence of various factors such as regional tectonic background and sedimentary characteristics, employs a genetic inversion machine learning algorithm to establish a high-resolution acoustic impedance data volume for predicting formation pore pressure in un-drilled areas. Attached Figure Description

[0043] The above and other objects and / or features of the present invention will become clearer from the following description taken in conjunction with the accompanying drawings, in which:

[0044] Figure 1 A schematic diagram of the genetic inversion algorithm flow of an embodiment of the formation pore pressure prediction method of the present invention is shown.

[0045] Figure 2 A schematic diagram illustrating the principle of the genetic inversion algorithm of an embodiment of the formation pore pressure prediction method of the present invention is shown. Detailed Implementation

[0046] In the following sections, the formation pore pressure prediction method, apparatus, device, and medium of the present invention will be described in detail with reference to exemplary embodiments.

[0047] It should be noted that the terms "first," "second," "third," etc., and "S1," "S2," "S3," etc., used in this invention are merely for ease of description and distinction, and should not be construed as indicating or implying relative importance or describing a specific order or sequence. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0048] The purpose of this invention is to solve the problems existing in the prior art. Current pore pressure prediction methods are mainly based on empirical relationships between single parameters (sonic transit time, drilling speed, etc.) and pore pressure. However, abnormal pore pressure is affected by multiple factors such as regional tectonic background and sedimentary characteristics, and univariate models often cannot fully describe the complex changes in pore pressure. Therefore, we provide a formation pore pressure prediction method that integrates well logging and seismic data. By combining high-resolution impedance information and using a genetic inversion algorithm, we can obtain formation pore pressure prediction results with better resolution.

[0049] To achieve the above objectives, the present invention provides a method for predicting formation pore pressure.

[0050] In a first exemplary embodiment of the formation pore pressure prediction method of the present invention, the formation pore pressure prediction method includes the following steps:

[0051] S1. Confirm the one-dimensional wave impedance data of a single well based on the logging data of the target area, and establish the first relationship model between P-wave velocity and wave impedance based on the one-dimensional wave impedance data of the single well.

[0052] The first relational model includes:

[0053]

[0054] Where AI is the wave impedance, kg / (m) 2 ·s); vp is the longitudinal wave velocity, km / s; C and A are fitting coefficients.

[0055] S2. Based on single-well one-dimensional wave impedance data and seismic data, the first wave impedance data volume is confirmed using a genetic inversion algorithm.

[0056] S21. Process the seismic data to obtain the seismic data volume.

[0057] S211. Perform amplitude and noise reduction processing on the seismic data volume, and confirm the first selected range by selecting the first top structural surface and the first bottom structural surface of the target area.

[0058] S22. After processing the one-dimensional wave impedance data of a single well, use it as a learning object and use the genetic inversion algorithm to obtain a nonlinear multi-channel operator.

[0059] S221. After processing the abnormal data in the one-dimensional acoustic impedance data of a single well, confirm the acoustic impedance data points on the single well.

[0060] S222. The first acoustic impedance data volume is derived from the seismic data volume of the first selected range, and the first acoustic impedance data volume is used as the initial value.

[0061] S223. Confirm the error values ​​of the acoustic impedance data points on the single wells of all well groups in the target area and the first acoustic impedance data volume. Based on the error values, confirm the first well as the learning object to invert and confirm the second acoustic impedance data points. Also, based on the error values, confirm the second well and update the error values ​​after exchanging and mutating until the error values ​​reach the global minimum.

[0062] S224. Confirm the second selected range by selecting the second top surface and the second bottom surface of the target area, and replace the first selected range with the second selected range.

[0063] S225. Repeat steps S222 to S224 until the inversion of the target region is completed, and use the second acoustic impedance data point as the first wave impedance data volume.

[0064] S3. Based on the first wave impedance data and the first relationship model, confirm the first wave velocity data.

[0065] S4. Confirm the formation pore pressure data volume based on the first wave velocity data volume, and predict the formation pore pressure based on the formation pore pressure data volume.

[0066] Optionally, a formation pore pressure model can be established using the Fillippone method and the Eaton method, and the formation pore pressure data volume can be confirmed based on the formation pore pressure model and the first wave velocity data volume.

[0067] Formation pore pressure models may include:

[0068]

[0069] Among them, P p P represents formation pore pressure, in MPa; ov P represents the pressure of the overlying strata, in MPa; w The hydrostatic pressure is MPa; V i V is the layer velocity of the i-th layer, in km / s; max V is the velocity when porosity approaches zero, in km / s; min The velocity is given in km / s when the rock's rigidity approaches zero.

[0070] In another aspect, the present invention provides a second exemplary embodiment of a formation pore pressure prediction device.

[0071] The formation pore pressure prediction device includes a first relational model determination module, a first wave impedance data volume determination module, a first wave velocity data volume determination module, and a formation pore pressure prediction module connected in sequence.

[0072] The module is configured to: ...

[0073] In another aspect, the present invention provides a third exemplary embodiment of a computer device. The computer device includes a processor and a memory. The memory stores a computer program. The computer program is executed by the processor, causing the processor to execute the computer program for the formation pore pressure prediction method according to the present invention.

[0074] In another aspect, the present invention provides a fourth exemplary embodiment of a computer-readable storage medium storing a computer program. The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to execute the formation pore pressure prediction method according to the present invention. The computer-readable recording medium is any data storage device capable of storing data read from a computer system. Examples of computer-readable recording media include: read-only memory, random access memory, read-only optical disc, magnetic tape, floppy disk, optical data storage device, and carrier waves (such as data transmission via the Internet through wired or wireless transmission paths).

[0075] To better understand the exemplary embodiments of the present invention described above, further descriptions are provided below in conjunction with specific embodiments and accompanying drawings, but the examples given are not intended to limit the present invention.

[0076] Example 1:

[0077] A method for predicting formation pore pressure by integrating well logging and seismic data includes the following steps:

[0078] S1. Obtain the relevant basic parameters for establishing the formation pore pressure model and clarify the correspondence between the parameters.

[0079] S2. A high-precision wave impedance model is established based on the genetic inversion algorithm combined with well logging data and seismic data.

[0080] S3. Establish a formation pore pressure calculation model. Based on the established high-precision wave impedance model and the corresponding calculation formulas between different parameters, calculate the formation pore pressure data volume of the target area.

[0081] The prediction method provided in this embodiment can obtain the formation pore pressure data volume of the target area, clarify the variation characteristics of the well interval and the no-well area, and provide guidance for the prediction of formation pore pressure before or during drilling.

[0082] Example 2

[0083] This embodiment includes steps S1 to S3 as in Embodiment 1. In step S1, the logging data includes sonic logging and density logging. The obtained basic parameters include sonic transit time, P-wave velocity, and density. Based on the obtained logging parameters, wave impedance data on a one-dimensional scale for a single well is established. Wave impedance can be the product of wave velocity and density, and the calculation formula is as follows:

[0084] AI = ρ * vp

[0085] In the above formula: AI is the wave impedance, with units of kg / (m) 2 ·s); ρ is density, in kg / m³ 3 vp represents the longitudinal wave velocity, measured in km / s.

[0086] Density and P-wave velocity data were obtained from well logging data for a single well. The density and P-wave data were then fitted using the Gardner formula, which is:

[0087] ρ=Cvp A

[0088] In the above formula: C and A are the fitting coefficients, respectively.

[0089] Combining the formulas, we obtain the relationship between the longitudinal wave velocity and the wave impedance:

[0090]

[0091] Example 3

[0092] This embodiment includes steps S1 to S3 as in Embodiment 2. In step S2, the one-dimensional wave impedance data of a single well in S1 is used as a learning sample for genetic inversion. The workflow of the genetic inversion algorithm is shown in the attached figure. Figure 1 As shown.

[0093] First, amplitude and noise reduction processing is performed on the seismic data volume, and the top and bottom structural surfaces of the study area are set as part of the study area.

[0094] Then, outliers in the acoustic impedance data are processed to obtain acoustic impedance data points for a single well.

[0095] Based on the selected range of seismic data volume, the acoustic impedance data volume of the target area is inverted and used as the initial value. The acoustic impedance data of the corresponding single well is then sorted in descending order according to the error value.

[0096] Wells with smaller error values ​​are used as learning objects to re-invert the selected range, while wells with larger error values ​​are swapped and mutated. The error values ​​are recalculated and the wells are sorted in descending order. The data of the wells selected as learning objects are updated. After the global error value is minimized within the selected range, the top and bottom surfaces are reselected until the inversion of the entire study area is completed, and the attribute cube is obtained (i.e., the wave impedance data volume of the target area is obtained).

[0097] The initial well group inversion output is a nonlinear multi-channel operator, which will be applied to the entire seismic dataset (obtained from seismic data) and used as the initial training stage of the genetic inversion algorithm, using acoustic impedance logging curves from a single well for learning and cross-validation.

[0098] The genetic inversion algorithm is an inversion method that combines a multi-layer neural network and a genetic algorithm. The neural network used is a typical multi-layer network with only one hidden layer in the genetic inversion process. The characteristics of the neural network workflow in this embodiment are as follows:

[0099] ① Activation function (sigmoid function):

[0100]

[0101] ② Input / Hidden Layer Relationship:

[0102]

[0103] ③ The biases of the input layer and the hidden layer are expressed as follows:

[0104] w 0,n

[0105] w 0,p+1

[0106] As attached Figure 2 As shown, in the neural network workflow, the input values ​​and weights are randomly combined, the error function is calculated, and the output result is compared with the observation dataset (i.e., the one-dimensional wave impedance data of a single well in step S1). The convergence criterion is checked. If the criterion is met, the process stops; otherwise, the process continues.

[0107] ①Choose:

[0108] Similar to Darwin's hypothesis of natural selection, only the most adapted individuals can survive; in this case, the survival criterion is determined by the individual with the smallest error.

[0109] ② Cross-interchange:

[0110] In this step, chromosomes (here, a chromosome refers to a weighted combination) exchange genes (here, a gene refers to a gene in a weighted combination) (the number of genes exchanged can be one or more). This crossover occurs with a certain probability after each iteration and during each iteration.

[0111] ③ Mutation:

[0112] Similar to the theory of natural evolution, genes are randomly replaced within chromosomes. This is to ensure that the process does not converge to a local minimum. The probability of occurrence is also a function of the iterative steps themselves; for example, mutations are more likely to occur when the evolution of the error function reaches a high point. However, in most cases, the probability of mutation is much lower than the probability of crossover.

[0113] Using wave impedance data from a single well as a learning sample, wave impedance data volume for the target region is obtained based on a genetic inversion algorithm. Based on the relationship between P-wave velocity and wave impedance in S1, a high-resolution wave velocity data volume is obtained.

[0114] Example 4

[0115] This embodiment includes steps S1 to S3 as in Embodiment 3. In step S3, the formation pore pressure can be predicted by combining the Fillippone method and the Eaton method. This combined method first uses the Fillippone method to calculate the formation velocity under normal compaction conditions, and then uses the Eaton method to calculate the formation pore pressure.

[0116] The Fillippone method formula is:

[0117] P p =P ov [(V max -V i ) / (V max -V min )]

[0118] The formula for the EatOne method is:

[0119] P p =P ov -(P ov -P w (V) i / V n ) C

[0120] Combining the Fillippone formula with the Eatone formula, we obtain the formula for calculating formation pore pressure:

[0121]

[0122] In the formula: P p P represents formation pore pressure, measured in MPa. ov P represents the pressure of the overlying strata, expressed in MPa. w V is the hydrostatic pressure, measured in MPa. i V represents the layer velocity of the i-th layer, in km / s. max V is the velocity when porosity approaches zero, approximating the upper limit of rock velocity, and is expressed in km / s. min This represents the velocity of rock when its rigidity approaches zero, approximating the lower limit of rock velocity, and is expressed in km / s.

[0123] By inputting the wave velocity data volume into the formation pore pressure calculation formula, the formation pore pressure data volume of the target area is obtained, and the variation characteristics of the inter-well interval and the un-well area are clarified.

[0124] In summary, the beneficial effects include: This invention predicts formation pore pressure based on the logging characteristics of drilled single wells and combined with high-resolution seismic data, taking into account various factors such as regional tectonic background and sedimentary characteristics, thereby improving the accuracy of pore pressure prediction for undrilled formations.

[0125] Although the present invention has been described above in conjunction with exemplary embodiments and accompanying drawings, those skilled in the art should understand that various modifications can be made to the above embodiments without departing from the spirit and scope of the claims.

Claims

1. A method for predicting formation pore pressure, characterized in that, The method includes the following steps: S1. Confirm the one-dimensional wave impedance data of a single well based on the logging data of the target area, and establish a first relationship model between longitudinal wave velocity and wave impedance based on the one-dimensional wave impedance data of the single well. S2. Based on the single-well one-dimensional wave impedance data and seismic data, the first wave impedance data volume is confirmed using a genetic inversion algorithm. S3. Based on the first wave impedance data volume and the first relationship model, confirm the first wave velocity data volume; and S4. Confirm the formation pore pressure data volume based on the first wave velocity data volume, and predict the formation pore pressure based on the formation pore pressure data volume.

2. The formation pore pressure prediction method according to claim 1, characterized in that, The first relational model includes: where AI is the wave impedance, kg / (m 2 ·s); vp is the P-wave velocity, km / s; C, A are fitting coefficients.

3. The formation pore pressure prediction method according to claim 1, characterized in that, Step S2 includes: S21. Process the earthquake data to obtain an earthquake data volume; S22. After processing the single-well one-dimensional wave impedance data, use it as a learning object and apply the genetic inversion algorithm to the seismic data volume to obtain the first wave impedance data volume.

4. The formation pore pressure prediction method according to claim 3, characterized in that, Step S21 includes: S211. Perform amplitude and noise reduction processing on the seismic data volume, and confirm the first selected range by selecting the first top structural surface and the first bottom structural surface of the target area.

5. The formation pore pressure prediction method according to claim 4, characterized in that, Step S22 includes: S221. Process the abnormal data in the one-dimensional acoustic impedance data of the single well to confirm the acoustic impedance data points on the single well. S222. The first acoustic impedance data volume is derived from the seismic data volume of the first selected range, and the first acoustic impedance data volume is used as the initial value. S223. Confirm the error value between the acoustic impedance data points on a single well in all well groups in the target area and the first acoustic impedance data volume. Based on the error value, confirm the first well as the learning object to invert and confirm the second acoustic impedance data point. Based on the error value, confirm the second well and update the error value after exchanging and mutating until the error value reaches the global minimum. S224. Confirm the second selected range by selecting the second top surface and the second bottom surface of the target area, and replace the first selected range with the second selected range. S225. Repeat steps S222 to S224 until the inversion of the target region is completed, and use the second acoustic impedance data point as the first wave impedance data body.

6. The formation pore pressure prediction method according to claim 1, characterized in that, Step S4 includes: establishing a formation pore pressure model using the Fillippone method and the Eaton method, and confirming the formation pore pressure data volume based on the formation pore pressure model and the first wave velocity data volume.

7. The formation pore pressure prediction method according to claim 6, characterized in that, Formation pore pressure models include: where P p is the formation pore pressure, MPa; P ov is the overburden pressure, MPa; P w is the hydrostatic pressure, MPa; V i is the interval velocity of the ith layer, km / s; V max is the velocity when the porosity tends to zero, km / s; V min is the velocity when the rock stiffness tends to zero, km / s.

8. A formation pore pressure prediction device, characterized in that, The formation pore pressure prediction device includes a first relational model determination module, a first wave impedance data volume determination module, a first wave velocity data volume determination module, and a formation pore pressure prediction module connected in sequence. The first relationship model determination module is configured to confirm the one-dimensional wave impedance data of a single well based on the logging data of the target area, and establish a first relationship model between the longitudinal wave velocity and the wave impedance based on the one-dimensional wave impedance data of the single well. The first wave impedance data volume determination module is configured to use a genetic inversion algorithm to confirm the first wave impedance data volume based on the single-well one-dimensional wave impedance data and seismic data. The first wave velocity data volume determination module is configured to determine the first wave velocity data volume based on the first wave impedance data volume and the first relationship model; The formation pore pressure prediction module is configured to confirm the formation pore pressure data volume based on the first wave velocity data volume, and to predict the formation pore pressure based on the formation pore pressure data volume.

9. A computer device, characterized in that, The computer device includes: At least one processor; and A memory storing program instructions configured to be executed by the at least one processor, the program instructions including instructions for performing the formation pore pressure prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the formation pore pressure prediction method according to any one of claims 1 to 7.

Images