A smart exploration system for oil exploration

Abstract

This invention belongs to the field of petroleum exploration technology. It discloses an intelligent exploration system for petroleum exploration, comprising: a data acquisition module for acquiring multi-source information data of the exploration area; a data processing module for preprocessing the multi-source information data to obtain a multi-source feature dataset; a full-waveform inversion algorithm to transform the multi-source feature dataset into a three-dimensional geological model, and visualization of the three-dimensional geological model to obtain a three-dimensional geological map; a region prediction module for training an oil and gas reservoir region prediction model based on the three-dimensional geological map, and predicting the distribution area of ​​oil and gas reservoirs based on the oil and gas reservoir region prediction model; a path planning module for formulating a preliminary oil drilling path based on the predicted oil and gas reservoir distribution area; acquiring real-time drilling data, and dynamically adjusting the preliminary oil drilling path based on the real-time drilling data to obtain the final oil drilling path; realizing an intelligent drilling process, reducing human intervention, and improving overall operational efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil exploration, more particularly, the present application relates to an intelligent exploration system for oil exploration. BACKGROUND

[0002] The patent with the patent publication number CN115559712A discloses an intelligent oil exploration system and its application method, wherein the system comprises a detection module, an information transmission module, a central processing module and an interaction module; the detection module is used for real-time detection of downhole data, and the downhole data is divided into important data and secondary data, and the secondary data is stored; the information transmission module is used for transmitting the important data to the central processing module; the central processing module is used for analyzing the important data and real-time correcting the drilling parameters; the interaction module is used for real-time feedback of downhole conditions to the workers and manual correction according to the downhole conditions. The present application ensures the accuracy and effectiveness of downhole signal transmission by adding a relay station, and classifies the data in combination with the actual working conditions, analyzes the important data in real time to correct the drilling parameters. At the same time, the present application considers the error of intelligent operation, and adopts the combination of manual and intelligent to process the field conditions.

[0003] The existing oil exploration system mainly has the following main problems:

[0004] Without using the elastic wave equation, the propagation behavior of seismic waves in complex underground media may not be accurately reflected; ignoring the influence of wave velocity, density and medium heterogeneity, etc., may result in a large difference between the simulation results and the actual observed waveforms; without using gradient descent and other optimization algorithms, the parameters in the three-dimensional geological model cannot be effectively adjusted to make the simulated waveforms gradually approach the actual observed waveforms; without the propagation operator restriction formula, the influence of the source point and the receiving point on the propagation operator cannot be effectively adjusted. The influence of different sources and receiving points may be treated equally, resulting in that some unrelated or noisy receiving points contribute too much to the final model, interfering with the optimization process of the model; without considering the dynamic adjustment of the weight factor of the receiving point, the time offset problem of the received waveform may be ignored; the receiving points with large time offset usually contain more important wave propagation information, but if the weight of these receiving points is not high enough, important information may be lost or error accumulation may occur, affecting the accuracy of the final model; dynamic adjustment of the weight factor of the receiving point may ignore the time offset problem of the received waveform. The receiving points with large time offset usually contain more important wave propagation information, but if the weight of these receiving points is not high enough, important information may be lost or error accumulation may occur, affecting the accuracy of the final model;

[0005] The model can not fully reflect the heterogeneity and complexity of the underground geology without discretizing the oil and gas reservoir distribution area into voxels and providing multi-source information for each voxel; the path cost function is only optimized based on the distance between nodes, ignoring geological factors such as rock hardness and formation pressure, which can lead to the selection of an inappropriate path; without quantifying the actual challenges that can be encountered during drilling through a comprehensive path cost formula, the path planning can not adequately consider these challenges; without reasonably predicting the remaining path cost from the target node to the current node during path search, the path selection can not be forward-looking; simply relying on the cost of the current path can miss the actual optimal path, resulting in ineffective control of drilling costs and time;

[0006] Without real-time acquisition of drilling data using measurement-while-drilling technology, the dynamic changes during drilling cannot be reflected in real time; without optimization based on real-time data, the drilling path can not be adjusted in a timely manner, and the geological conditions during drilling can change; if the path planning is not updated in a timely manner, it can lead to the selection of an inappropriate path during drilling, increasing drilling time and cost, and even possibly resulting in the inability to complete the predetermined target; without using path risk calculation and risk assessment formulas, key factors such as friction coefficient, bit pressure, and drilling speed cannot be considered comprehensively, which can lead to inadequate assessment of the safety of the drilling path; without optimizing the drilling path and parameters through real-time data, the drilling efficiency is greatly reduced.

[0007] In view of this, the present application provides an intelligent exploration system for oil exploration to solve the above problems. SUMMARY

[0008] In order to overcome the above-mentioned defects of the prior art, and to achieve the above-mentioned purposes, the present application provides the following technical scheme: an intelligent exploration system for oil exploration, comprising:

[0009] A data acquisition module for acquiring multi-source information data of the exploration area;

[0010] A data processing module for preprocessing the multi-source information data to obtain a multi-source feature data set; converting the multi-source feature data set into a three-dimensional geological model using a full-waveform inversion algorithm, and visualizing the three-dimensional geological model to obtain a three-dimensional geological map;

[0011] A regional prediction module for training an oil and gas reservoir region prediction model based on the three-dimensional geological map, and predicting the oil and gas reservoir distribution area based on the oil and gas reservoir region prediction model;

[0012] A path planning module for formulating a preliminary oil drilling path based on the predicted oil and gas reservoir distribution area; collecting real-time drilling data and dynamically adjusting the preliminary oil drilling path based on the real-time drilling data to obtain a final oil drilling path;

[0013] The communication transmission module is configured to transmit the final oil drilling path to the intelligent exploration terminal in real time through satellite communication technology; the modules are connected through wired and / or wireless means.

[0014] Further, the multi-source information data includes geophysical data, seismic wave data and geological data; the geophysical data includes gravity, magnetic force, resistivity, electromagnetic method and natural potential; the seismic wave data includes seismic wave reflection data, seismic wave propagation speed, seismic wave amplitude and seismic wave frequency; the geological data includes core samples, surface sediment samples and fluid samples.

[0015] Further, the method for preprocessing the multi-source information data to obtain the multi-source feature data set comprises:

[0016] The density clustering algorithm is used to identify and eliminate abnormal values in the geophysical data, seismic wave data and geological data included in the multi-source information data, to obtain a geophysical feature data set, a seismic wave feature data set and a geological feature data set;

[0017] The principal component analysis is used to extract features from the geophysical feature data set, the seismic wave feature data set and the geological feature data set, and the geophysical feature data set, the seismic wave feature data set and the geological feature data set after feature extraction are subjected to standard deviation normalization processing to convert them into standard normal distribution with a mean of 0 and a standard deviation of 1, to obtain normalized geophysical feature data set, seismic wave feature data set and geological feature data set; the normalized geophysical feature data set, seismic wave feature data set and geological feature data set are fused through a weighted model to obtain a multi-source feature data set.

[0018] Further, the method for converting the multi-source feature data set into a three-dimensional geological model using a full waveform inversion algorithm comprises:

[0019] S41, the preset three-dimensional geological model is m, the three-dimensional geological model m includes two underground medium physical properties, the two underground medium physical properties are seismic wave speed and density, and the distribution of the preset seismic wave speed and density in the three-dimensional geological model is: m(x,y,z)=(v'(x,y,z),ρ(x,y,z)); wherein v'(x,y,z) is the seismic wave speed at a position (x,y,z) in the three-dimensional geological model; ρ(x,y,z) is the density at a position (x,y,z) in the three-dimensional geological model; (x,y,z) is the position coordinate of the seismic wave propagation in the three-dimensional geological model;

[0020] S42, according to the current three-dimensional geological model, the propagation process of the seismic wave is simulated through the elastic wave equation; the elastic wave equation is: wherein, Let u(x,t) be the second derivative of the seismic wave displacement u(x,t) with respect to time t, i.e., the acceleration of the seismic wave; u(x,t) is the seismic wave displacement at a certain location (x,y,z) in the three-dimensional geological model at time t; c 2 (x,y,z) is the wave velocity function, representing the propagation speed of seismic waves at each point in the three-dimensional geological model; t is the Laplace operator, representing wave propagation in a three-dimensional geological model; t is the time variable, representing the evolution of the wave's propagation over time.

[0021] S43. The simulated waveform of the seismic wave is obtained by solving the elastic wave equation using the finite difference method. The simulated waveform of the seismic wave is: b pe =F[m,(x ce ,y ce ,z ce ),(x a ,y a ,z a )]; where b pe For simulated waveform data of seismic waves; F is the propagation operator of seismic waves; (x ce ,y ce ,z ce (x) represents the coordinates of the seismic wave source location; (x) a ,y a ,z a () represents the coordinates of the receiving point of the seismic wave;

[0022] S44. The propagation operator of seismic waves is constrained using the propagation operator constraint formula, which is as follows: Where F′ is the constrained propagation operator for the seismic wave; N su N represents the number of seismic wave source points. re denoted as the number of receiving points for seismic waves; ∈ is a constant controlling the influence of the source point and receiving points on the propagation operator;

[0023] S45. Construct an L2 norm loss function to quantify the difference between simulated and observed seismic waveform data; the L2 norm loss function is: Where J(m) is the L2 norm loss function; b os ((x a ,y a ,z a ),t a ) represents the actual observed waveform data of the seismic wave at the a-th receiving point; b pe ((x a ,y a ,z a ),t am) is the simulated waveform data of the seismic wave calculated by the three-dimensional geological model m;t a is the time offset of the ath receiving point; ω a is the weight factor of each receiving point; M is the total number of receiving points of the seismic wave; a is the index of the receiving point, a = 1, 2, …, M; the weight factor ω a of each receiving point is dynamically adjusted and designed by the weight factor adaptive formula.

[0024] S46, update the parameters of the three-dimensional geological model by the gradient descent update formula, the gradient descent update formula is: wherein, m k+1 is the three-dimensional geological model of the k+1 iteration; m k is the three-dimensional geological model of the k iteration; γ is the learning rate; is the gradient of the L2 norm loss function J(m) with respect to the three-dimensional geological model m k .

[0025] S47, preset the loss threshold of the L2 norm loss function, and continuously update the three-dimensional geological model by repeated iteration until the L2 norm loss function is less than or equal to the preset loss threshold of the L2 norm loss function, and stop, to obtain the final three-dimensional geological model m * .

[0026] Further, the method of dynamically adjusting and designing the weight factor ω a of each receiving point by the weight factor adaptive formula comprises:

[0027] The weight factor adaptive formula is: wherein, T max is the maximum time of seismic wave propagation; T M is the total time required for receiving the seismic wave.

[0028] Further, the method for obtaining the three-dimensional geological map comprises:

[0029] Different filters in the ParaView software are used to cut the three-dimensional geological model according to any geometric shape, view different parts of the three-dimensional geological model, create a profile, and display the slices passing through the model to view the geological structure at different depths underground; the surface of the three-dimensional geological model is extracted from the three-dimensional grid data to view the external morphology of the underground structure; different colors are set for different regions according to the seismic wave velocity and density to distinguish different underground rock layers; the transparency of different parts is adjusted to view the internal structure of the three-dimensional geological model, and the underground hierarchical structure is presented by adjusting the transparency and color, and finally the three-dimensional geological map is obtained.

[0030] Further, the training method of the oil and gas reservoir area prediction model comprises:

[0031] The dataset is divided into training, validation, and test sets; an oil and gas reservoir region prediction model is constructed, which includes an input layer, a 3D convolutional layer, a 3D pooling layer, a fully connected layer, and an output layer; the input data is a historical 3D geological map, and the output data is the distribution area of ​​oil and gas reservoirs; ReLU is used as the activation function; the oil and gas reservoir region prediction model is a 3D convolutional neural network model.

[0032] Mean squared error is used as the loss function of the model to measure the difference between the model's predicted value and the actual value; the model is trained using the training set, and the loss function is minimized using the Adam optimizer; the performance of the oil and gas reservoir area prediction model is evaluated using the validation set, and the accuracy index is calculated to measure the model's performance; the hyperparameters of the model are tuned, the gradient of each hyperparameter is calculated using the backpropagation algorithm, and the model hyperparameters are optimized using the gradient descent method to improve the model performance.

[0033] The model's performance in the prediction task is evaluated using a test set. The test is stopped when the model's performance in the prediction task reaches a preset performance threshold, thus obtaining the oil and gas reservoir area prediction model. The trained oil and gas reservoir area prediction model is then used to predict the current three-dimensional geological map to obtain the oil and gas reservoir distribution area.

[0034] Furthermore, the method for obtaining the preliminary oil drilling path includes:

[0035] The distribution area of ​​oil and gas reservoirs is discretized into Q voxels; a voxel is a small volume unit in the distribution area of ​​oil and gas reservoirs, containing multi-source information data of the corresponding oil and gas reservoir distribution area; the spatial location of each voxel is used as a node, and the feasible paths between adjacent voxels are used as edges to construct a graph structure; the graph structure is G={V,E}.

[0036] Where V is the set of nodes; E is the set of edges;

[0037] The default initial node is v s The target node is v o ;

[0038] Define a path cost function to represent the cumulative cost from the initial node to the current node; the path cost function is: Among them, v i For the current node; v j For the current node v i The previous adjacent node; g(v j ) represents the distance from the initial node to node v j The cumulative cost; w ij The path cost between adjacent nodes, i.e., the current node v i With the previous adjacent node v jThe path cost between; i and j are the indices of the node numbers; N′ is the current node v. i The set of adjacent nodes;

[0039] The path cost w between adjacent nodes ij The cost is obtained through the comprehensive path cost formula; the comprehensive path cost formula is w. ij =α1·d(v i ,v j )+α2·|H(v i )-H(v j )|+α3·|P(v i )-P(v j )|;wherein, d(v i ,v j ) represents the current node v i With the previous adjacent node v j The distance between them; H(v) i ) represents the current node v i Rock hardness; H(v) j ) represents the previous adjacent node v j Rock hardness; P(v i ) represents the current node v i Formation pressure; P(v j ) represents the previous adjacent node v j The formation pressure; α1 is the weighting coefficient for adjusting the influence of distance on path cost; α2 is the weighting coefficient for adjusting the influence of rock hardness on path cost; α3 is the weighting coefficient for adjusting the influence of formation pressure on path cost;

[0040] Define a heuristic function to estimate the remaining path cost from the current node to the target node; the heuristic function is h(v i )=‖v i -v o ||-δ·S′; where, ||v i -v o || represents the current node v i to target node v o The Euclidean distance of the current node v; S′ is the distance between the current node v and the Euclidean distance of the i The oil and gas reserves; δ is the coefficient of influence of adjusting the oil and gas reserves on the heuristic function;

[0041] By combining the path cost function and the heuristic function, a comprehensive evaluation function is obtained; the comprehensive evaluation function is f(v i )=g(v i )+h(v i ); Using A * The algorithm performs path search, starting from the initial node v sInitially, the node that minimizes the comprehensive evaluation function is selected step by step as the current node, until the target node v is reached. o Stop when selected; collect all selected nodes to obtain an initial oil drilling path.

[0042] Furthermore, the method for obtaining the final oil drilling path includes:

[0043] Actual drilling is conducted based on the preliminary oil drilling path, and real-time drilling data is collected during the actual drilling process using measurement-while-drilling (MWD) technology. The real-time drilling data includes bit pressure, drilling speed, drilling inclination angle, drilling depth, and adjacent formation pressure. Based on the real-time drilling data, a genetic algorithm is used to iteratively optimize the preliminary oil drilling path. A preset oil drilling path risk threshold is established, and iteration stops when the adjusted oil drilling path risk value is less than or equal to the preset oil drilling path risk threshold, thereby obtaining the final oil drilling path.

[0044] The adjusted oil drilling path risk value is obtained using the path risk calculation formula; the path risk calculation formula is: Where, r i′ The adjusted risk value for oil drilling paths; i is the weighting factor for the adjusted oil drilling path risk value; i′ is the index of the oil drilling path type; the adjusted oil drilling path risk value r i′ It is obtained through a risk assessment formula; the risk assessment formula is: Where μ is the coefficient of friction; p bit For drill bit pressure; υ drill Δp is the drilling speed; Δp is the pressure difference between adjacent formations; Δd is the drilling depth difference; n is the total number of adjusted oil drilling path risk values.

[0045] Furthermore, the method for transmitting the final oil drilling path to the intelligent exploration terminal in real time via satellite communication technology includes:

[0046] Satellite communication equipment, including a mobile satellite antenna and a satellite modem, is installed on the drilling platform or drilling equipment. The satellite communication equipment establishes a real-time communication link with the satellite via the mobile satellite antenna. The satellite communication equipment establishes a connection according to the MQTT protocol and uploads the final oil drilling path to the intelligent exploration terminal through the real-time communication link.

[0047] The technical effects and advantages of the intelligent exploration system for oil exploration proposed in this invention are as follows:

[0048] This invention simulates seismic wave propagation using the elastic wave equation, accurately reflecting the behavior of seismic waves in complex underground media, including the influence of factors such as wave velocity, density, and media heterogeneity. This method offers high simulation accuracy. Employing optimization algorithms such as gradient descent, it continuously adjusts parameters in the 3D geological model, gradually approximating the actual observed waveform. By controlling the influence of the source and receiver points, the propagation operator constraint formula allows the model to adapt to different seismic events and sources of varying sizes. For different sources and propagation paths, the propagation constraint operator helps the model better adapt to various data and conditions. Through L2 norm loss function control, the geological model can be automatically optimized through iterative iterations, resulting in a final model with better predictive capabilities in practical applications, particularly suitable for real-time monitoring and seismic wave simulation in dynamic environments. Dynamically adjusting the receiver point weighting factor optimizes the contribution of each point to the final loss function based on the time offset of different receiver points. Receiver points with larger time offsets receive more attention, while points with smaller time offsets receive relatively lower weights, allowing for more accurate capture of wave propagation details.

[0049] By discretizing the distribution area of ​​oil and gas reservoirs into voxels and providing multi-source information for each voxel, the complex geological structure underground can be better reflected. The path cost function not only considers the distance between adjacent nodes, but also incorporates important factors such as rock hardness and formation pressure. By using a comprehensive path cost formula, the actual challenges that may be encountered during drilling can be quantified more accurately, avoiding the selection of paths with unfavorable or unstable geological conditions, thereby optimizing drilling results. By combining the path cost function with a heuristic function to form a comprehensive evaluation function, it can be ensured that the path search process considers both the actual cost of the current path and can reasonably predict the remaining path cost of the target.

[0050] By acquiring drilling data in real time (such as bit pressure, drilling speed, and drilling inclination angle) through measurement-while-drilling (MWD) technology, various dynamic changes encountered during drilling can be reflected in real time. This optimization based on real-time data allows for timely adjustments to the drilling path, ensuring a smoother and more efficient drilling process. The path risk calculation and risk assessment formulas can comprehensively consider key factors such as friction coefficient, bit pressure, and drilling speed. By setting risk thresholds, the safety of the drilling path can be ensured, and by continuously optimizing the drilling path, the efficiency of the drilling process can be improved. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the structure of an intelligent exploration system for oil exploration according to the present invention;

[0052] Figure 2 This is a schematic diagram of a smart exploration method for oil exploration according to the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Example 1

[0055] Please see Figure 1 As shown in the figure, this embodiment of an intelligent exploration system for oil exploration includes:

[0056] The data acquisition module is used to collect multi-source information data from the exploration area;

[0057] The data processing module is used to preprocess multi-source information data to obtain a multi-source feature dataset; the multi-source feature dataset is then transformed into a three-dimensional geological model using a full waveform inversion algorithm, and the three-dimensional geological model is visualized to obtain a three-dimensional geological map;

[0058] The regional prediction module is used to train and obtain a regional prediction model for oil and gas reservoirs based on a 3D geological map, and to predict the distribution area of ​​oil and gas reservoirs based on the regional prediction model.

[0059] The path planning module is used to formulate a preliminary oil drilling path based on the predicted oil and gas reservoir distribution area; collect real-time drilling data, and dynamically adjust the preliminary oil drilling path based on the real-time drilling data to obtain the final oil drilling path.

[0060] The communication transmission module is used to transmit the final oil drilling path to the intelligent exploration terminal in real time via satellite communication technology; the modules are connected to each other via wired and / or wireless means.

[0061] Multi-source information data includes geophysical data, seismic wave data, and geological data; geophysical data includes gravity, magnetic, resistivity, electromagnetic methods, and spontaneous potential; seismic wave data includes seismic wave reflection data, seismic wave propagation velocity, seismic wave amplitude, and seismic wave frequency; geological data includes core samples, surface sediment samples, and fluid samples.

[0062] Analyzing magnetic properties helps detect the distribution and structural characteristics of underground magnetic minerals, and in complex tectonic regions, it can effectively assist in identifying the geological background of oil and gas reservoirs. Resistivity helps determine the porosity and permeability of oil and gas reservoirs and is often used to identify oil and gas reserves. Underground rock strata with low resistivity usually indicate high porosity or high water content, while strata with high resistivity indicate dry rock strata or oil and gas content. Electromagnetic methods can penetrate deep underground rock strata and are used to reveal underground oil and gas reservoirs and aquifers, making them suitable for detecting deeply buried oil and gas resources. Spontaneous potential refers to the potential difference generated by underground rock strata under natural conditions, usually caused by natural phenomena such as groundwater flow and electrochemical reactions of minerals, and is used to detect the distribution of groundwater and oil and gas reservoirs.

[0063] Seismic waves reflect at the interfaces of strata with different densities and elastic moduli. Detecting the time difference between the reflected seismic waves (reflection time difference) can construct an image of underground rock strata. Seismic wave reflection data can reveal the depth, morphology, and structure of underground rock strata, helping to identify geological structures such as oil and gas reservoirs and faults. Seismic waves propagate at different speeds in different geological layers. Seismic waves travel faster in harder, denser underground rock strata and slower in softer or aquifers. Seismic wave amplitude reflects the characteristics of underground rock strata interfaces. Stronger seismic wave amplitudes indicate harder, denser underground rock interfaces, while weaker seismic wave amplitudes indicate softer, more porous underground rock interfaces. Seismic wave frequency helps distinguish different types of underground rock strata. High-frequency seismic waves can detect shallow underground rock strata, while low-frequency seismic waves are suitable for penetrating deeper underground rock strata.

[0064] Core samples are columnar rock samples extracted from underground wells to provide detailed data on rock composition; surface sediment samples help to understand sedimentary environments and geological history, thereby inferring the formation background of underground oil and gas resources; fluid samples refer to natural gas, crude oil, groundwater, etc. extracted from oil and gas reservoirs. By analyzing fluid samples, we can understand the properties, reserves, and liquidity of oil and gas reservoirs, providing an important basis for the formulation of development plans.

[0065] Methods for preprocessing multi-source information data to obtain multi-source feature datasets include:

[0066] Density clustering algorithm is used to identify and remove outliers in multi-source information data, including geophysical data, seismic wave data, and geological data, to obtain geophysical feature datasets, seismic wave feature datasets, and geological feature datasets.

[0067] Principal component analysis was used to extract features from the geophysical feature dataset, seismic wave feature dataset, and geological feature dataset. The extracted geophysical feature dataset, seismic wave feature dataset, and geological feature dataset were then normalized to standard deviation, transforming them into a standard normal distribution with a mean of 0 and a standard deviation of 1, resulting in normalized geophysical feature dataset, seismic wave feature dataset, and geological feature dataset. The normalized geophysical feature dataset, seismic wave feature dataset, and geological feature dataset were then fused using a weighted model to obtain a multi-source feature dataset.

[0068] The method for converting multi-source feature datasets into three-dimensional geological models using the full waveform inversion algorithm includes: S41, a preset three-dimensional geological model m, which includes two physical properties of the subsurface medium: seismic wave velocity and density. The preset distribution of seismic wave velocity and density in the three-dimensional geological model is: m(x,y,z)=(v′(x,y,z),ρ(x,y,z)); where v′(x,y,z) is the seismic wave velocity at a certain location (x,y,z) in the three-dimensional geological model; ρ(x,y,z) is the density at a certain location (x,y,z) in the three-dimensional geological model; and (x,y,z) is the coordinate of the location where the seismic wave propagation occurs in the three-dimensional geological model.

[0069] S42. Based on the current three-dimensional geological model, simulate the propagation process of seismic waves using the elastic wave equation; the elastic wave equation is: in, Let u(x,t) be the second derivative of the seismic wave displacement u(x,t) with respect to time t, i.e., the acceleration of the seismic wave; u(x,t) is the seismic wave displacement at a certain location (x,y,z) in the three-dimensional geological model at time t, representing the change in the wave field;

[0070] c 2 (x, y, z) is the wave velocity function, representing the propagation speed of seismic waves at various points in a three-dimensional geological model. Wave velocity is part of the physical properties of the medium and usually varies with the subsurface medium. For example, different rock strata, minerals, or liquids have different wave velocities, therefore c 2 (x,y,z) may be a function of a location (x,y,z) in a three-dimensional geological model; Let be the Laplace operator, representing wave propagation in a three-dimensional geological model; t is the time variable, representing the evolution of the wave's propagation over time. Both the right and left sides of the wave equation involve time evolution, reflecting the propagation and change of the wave over time.

[0071] S43. The simulated waveform of the seismic wave is obtained by solving the elastic wave equation using the finite difference method. The simulated waveform of the seismic wave is: b pe =F[m,(x ce ,yce ,z ce ),(x a ,y a ,z a )]; where b pe For simulated waveform data of seismic waves; F is the propagation operator of seismic waves; (x ce ,y ce ,z ce (x) represents the coordinates of the seismic wave source location; (x) a ,y a ,z a () represents the coordinates of the receiving point of the seismic wave;

[0072] S44. The propagation operator of seismic waves is constrained using the propagation operator constraint formula, which is as follows: Where F′ is the constrained propagation operator for the seismic wave; N su N represents the number of seismic wave source points. re denoted as the number of receiving points for seismic waves; ∈ is a constant controlling the influence of the source point and receiving points on the propagation operator;

[0073] For example, the propagation operator F of seismic waves is 0.8, and the number of seismic wave source points N... su The number of seismic wave receiving points N is 10. re Given a constant ∈ 0.1 controlling the influence of the source and receiver points on the propagation operator, and a value of 20, then the propagation operator of the constrained seismic wave...

[0074] S45. Construct an L2 norm loss function to quantify the difference between simulated and observed seismic waveform data; the L2 norm loss function is: Where J(m) is the L2 norm loss function; b os ((x a ,y a ,z a ),t a ) represents the actual observed waveform data of the seismic wave at the a-th receiving point; b pe ((x a ,y a ,z a ),t a (m) represents the simulated waveform data of the seismic wave calculated using the three-dimensional geological model m; t a ω represents the time offset of the a-th receiving point; a The weighting factor for each receiving point; M is the total number of seismic wave receiving points; a is the index of the receiving point, a = 1, 2, ..., M; the weighting factor ω for each receiving point is adjusted using an adaptive formula. a Dynamically adjust the design;

[0075] S46. Update the parameters of the 3D geological model using the gradient descent update formula, which is: Where, m k+1 This is the three-dimensional geological model for the (k+1)th iteration; m k γ represents the 3D geological model for the k-th iteration; γ is the learning rate, which controls the step size for each update. The L2 norm loss function J(m) is given by the three-dimensional geological model m. k The gradient;

[0076] S47. A preset L2 norm loss function threshold is used to iteratively update the 3D geological model until the L2 norm loss function is less than or equal to the preset L2 norm loss function threshold, at which point the process stops, yielding the final 3D geological model m. * .

[0077] The weighting factor ω for each receiving point is determined using an adaptive formula for the weighting factor. a Methods for dynamically adjusting designs include:

[0078] The adaptive formula for the weighting factor is: Among them, T max T represents the maximum time required for a seismic wave to travel through space; M The total time required to receive seismic waves represents the transmission time from the epicenter to all receiving points.

[0079] In seismic wave propagation, the attenuation of seismic waves occurs as propagation time increases. The longer the propagation time, the weaker the signal received at the receiving point will be, because seismic waves typically encounter absorption and reflection effects during propagation in the medium. Therefore, the weight of receiving points with longer reception times should be smaller to avoid excessive influence of excessively distant receiving points on the model.

[0080] For example, assuming the maximum propagation time of seismic waves is 50 seconds, and the total number of receiving points M is 10, the total time T required to receive the seismic waves... M The transmission time is 100 seconds. The transmission time from the epicenter to the first receiving point is 10 seconds, from the epicenter to the second receiving point is 20 seconds, from the epicenter to the third receiving point is 15 seconds, from the epicenter to the fourth receiving point is 30 seconds, and from the epicenter to the fifth receiving point is 25 seconds. Calculate the weighting factor for each receiving point:

[0081] Weighting factor for the first receiving point: Weighting factor for the second receiving point: Weighting factor for the third receiving point: Weighting factor for the 4th receiving point: Weighting factor for the 5th receiving point:

[0082] Methods for obtaining three-dimensional geological maps include:

[0083] Using different filters in ParaView software, the 3D geological model is cut into arbitrary geometric shapes to view different parts of the model. A cross-section is created and slices passing through the model are displayed to view the geological structure at different depths. The surface of the 3D geological model is extracted from the 3D mesh data to view the external morphology of the underground structure. Different colors are set for different areas based on seismic wave velocity and density to distinguish different underground rock layers. The transparency of different parts is adjusted to view the internal structure of the 3D geological model. By adjusting the transparency and color, the underground hierarchical structure is presented, and finally, a 3D geological map is obtained.

[0084] Training methods for oil and gas reservoir regional prediction models include:

[0085] The dataset was divided into training, validation, and test sets. An oil and gas reservoir region prediction model was constructed, which includes an input layer, a 3D convolutional layer, a 3D pooling layer, a fully connected layer, and an output layer. The input data is a historical 3D geological map, and the output data is the distribution area of ​​oil and gas reservoirs. ReLU was used as the activation function. The oil and gas reservoir region prediction model is a 3D convolutional neural network model.

[0086] Mean squared error is used as the loss function of the model to measure the difference between the model's predicted value and the actual value; the model is trained using the training set, and the loss function is minimized using the Adam optimizer; the performance of the oil and gas reservoir area prediction model is evaluated using the validation set, and the accuracy index is calculated to measure the model's performance; the hyperparameters of the model are tuned, the gradient of each hyperparameter is calculated using the backpropagation algorithm, and the model hyperparameters are optimized using the gradient descent method to improve the model performance.

[0087] The model's performance in the prediction task is evaluated using a test set. The test is stopped when the model's performance in the prediction task reaches a preset performance threshold, thus obtaining the oil and gas reservoir area prediction model. The trained oil and gas reservoir area prediction model is then used to predict the current three-dimensional geological map to obtain the oil and gas reservoir distribution area.

[0088] Methods for obtaining preliminary oil drilling paths include:

[0089] The distribution area of ​​oil and gas reservoirs is discretized into Q voxels; a voxel is a small volume unit in the distribution area of ​​oil and gas reservoirs, containing multi-source information data of the corresponding oil and gas reservoir distribution area; the spatial location of each voxel is used as a node, and the feasible paths between adjacent voxels are used as edges to construct a graph structure; the graph structure is G={V,E}.

[0090] Where V is the set of nodes, representing all possible drilling locations in the oil and gas reservoir distribution area; E is the set of edges, representing the connection relationships between adjacent nodes;

[0091] The default initial node is v s This refers to a point on the Earth's surface or an drilling platform; the target node is v. o This refers to the central point or high-probability area of ​​the oil and gas reservoir distribution area;

[0092] Define a path cost function to represent the cumulative cost from the initial node to the current node; the path cost function is: Among them, v i For the current node; v j For the current node v i The previous adjacent node; g(v j ) represents the distance from the initial node to node v j The cumulative cost; w ij The path cost between adjacent nodes, i.e., the current node v i With the previous adjacent node v j The path cost between; i and j are the indices of the node numbers; N′ is the current node v. i The set of adjacent nodes;

[0093] Path cost w between adjacent nodes ij The cost is obtained through the comprehensive path cost formula; the comprehensive path cost formula is w. ij =α1·d(v i ,v j )+α2·|H(v i )-H(v j )|+α3·|P(v i )-P(v j )|;wherein, d(v i ,v j ) represents the current node v i With the previous adjacent node v j The distance between them; H(v) i ) represents the current node v i Rock hardness; H(v) j ) represents the previous adjacent node v j Rock hardness; P(v i ) represents the current node v i Formation pressure; P(v j ) represents the previous adjacent node v j The formation pressure; α1 is the weighting coefficient for adjusting the influence of distance on path cost; α2 is the weighting coefficient for adjusting the influence of rock hardness on path cost; α3 is the weighting coefficient for adjusting the influence of formation pressure on path cost;

[0094] Define a heuristic function to estimate the remaining path cost from the current node to the target node; the heuristic function is h(v i )=‖v i -v o ||-δ·S′; where, ||v i -v o || represents the current node v i to target node v o The Euclidean distance of the current node v; S′ is the distance between the current node v and the Euclidean distance of the i The oil and gas reserves; δ is the coefficient of influence of adjusting the oil and gas reserves on the heuristic function;

[0095] By combining the path cost function and the heuristic function, a comprehensive evaluation function is obtained; the comprehensive evaluation function is f(v i )=g(v i )+h(v i ); Using A * The algorithm performs path search, starting from the initial node v s Initially, the node that minimizes the comprehensive evaluation function is selected step by step as the current node, until the target node v is reached. o Stop when selected; collect all selected nodes to obtain an initial oil drilling path.

[0096] Methods for obtaining the final oil drilling path include:

[0097] Actual drilling is conducted based on the preliminary oil drilling path, and real-time drilling data is collected during the actual drilling process using measurement-while-drilling (MWD) technology. The real-time drilling data includes bit pressure, drilling speed, drilling inclination angle, drilling depth, and adjacent formation pressure. Based on the real-time drilling data, a genetic algorithm is used to iteratively optimize the preliminary oil drilling path. A preset oil drilling path risk threshold is established, and iteration stops when the adjusted oil drilling path risk value is less than or equal to the preset oil drilling path risk threshold, thereby obtaining the final oil drilling path.

[0098] The adjusted oil drilling path risk value is obtained using the path risk calculation formula; the path risk calculation formula is: Where, r i′ The adjusted risk value for oil drilling paths; i is the weighting factor for the adjusted oil drilling path risk value; i′ is the index of the oil drilling path type; the adjusted oil drilling path risk value r i′ It is obtained through a risk assessment formula; the risk assessment formula is: Where μ is the coefficient of friction; p bit For drill bit pressure; υ drillΔp is the drilling speed; Δp is the pressure difference between adjacent formations; Δd is the drilling depth difference; n is the total number of adjusted oil drilling path risk values.

[0099] Methods for transmitting the final oil drilling path to a smart exploration terminal in real time via satellite communication technology include:

[0100] Satellite communication equipment, including a mobile satellite antenna and a satellite modem, is installed on the drilling platform or drilling equipment. The satellite communication equipment establishes a real-time communication link with the satellite via the mobile satellite antenna. The satellite communication equipment establishes a connection according to the MQTT protocol and uploads the final oil drilling path to the intelligent exploration terminal through the real-time communication link.

[0101] The preset risk threshold for oil drilling paths is set by staff. Risk values ​​for different oil drilling paths are collected through intelligent exploration terminals, and the average of multiple oil drilling path risk values ​​is taken as the preset oil drilling path risk threshold.

[0102] In this embodiment, the propagation of seismic waves is simulated using the elastic wave equation, which can accurately reflect the behavior of seismic waves in complex underground media, including the influence of factors such as wave velocity, density, and media heterogeneity. This method provides high simulation accuracy. Optimization algorithms such as gradient descent are employed to continuously adjust the parameters in the three-dimensional geological model, allowing the simulated waveform to gradually approximate the actual observed waveform. By controlling the influence of the source and receiver points, the propagation operator constraint formula enables the model to adapt to different seismic events and sources of varying sizes. For different sources and propagation paths, the propagation constraint operator helps the model better adapt to various data and conditions. Through the control of the L2 norm loss function, the geological model can be automatically optimized through repeated iterations, resulting in a final model with better predictive capabilities in practical applications, especially suitable for real-time monitoring and seismic wave simulation in dynamic environments. Dynamically adjusting the weight factors of receiver points optimizes the contribution of each point to the final loss function based on the time offset of different receiver points. Receiver points with larger time offsets receive more attention, while points with smaller time offsets receive relatively lower weights, allowing for more accurate capture of wave propagation details.

[0103] By discretizing the distribution area of ​​oil and gas reservoirs into voxels and providing multi-source information for each voxel, the complex geological structure underground can be better reflected. The path cost function not only considers the distance between adjacent nodes, but also incorporates important factors such as rock hardness and formation pressure. By using a comprehensive path cost formula, the actual challenges that may be encountered during drilling can be quantified more accurately, avoiding the selection of paths with unfavorable or unstable geological conditions, thereby optimizing drilling results. By combining the path cost function with a heuristic function to form a comprehensive evaluation function, it can be ensured that the path search process considers both the actual cost of the current path and can reasonably predict the remaining path cost of the target.

[0104] By acquiring drilling data in real time (such as bit pressure, drilling speed, and drilling inclination angle) through measurement-while-drilling (MWD) technology, various dynamic changes encountered during drilling can be reflected in real time. This optimization based on real-time data allows for timely adjustments to the drilling path, ensuring a smoother and more efficient drilling process. The path risk calculation and risk assessment formulas can comprehensively consider key factors such as friction coefficient, bit pressure, and drilling speed. By setting risk thresholds, the safety of the drilling path can be ensured, and by continuously optimizing the drilling path, the efficiency of the drilling process can be improved.

[0105] Example 2

[0106] Please see Figure 2 As shown, parts not described in detail in this embodiment are described in Embodiment 1. A smart exploration method for oil exploration is provided, including:

[0107] S1. Collect multi-source information data of the exploration area;

[0108] S2. Preprocess the multi-source information data to obtain a multi-source feature dataset; use the full waveform inversion algorithm to transform the multi-source feature dataset into a three-dimensional geological model, and visualize the three-dimensional geological model to obtain a three-dimensional geological map;

[0109] S3. Obtain an oil and gas reservoir regional prediction model based on the 3D geological map, and predict the distribution area of ​​oil and gas reservoirs based on the oil and gas reservoir regional prediction model.

[0110] S4. Based on the predicted distribution area of ​​oil and gas reservoirs, formulate a preliminary oil drilling path; collect real-time drilling data, and dynamically adjust the preliminary oil drilling path according to the real-time drilling data to obtain the final oil drilling path.

[0111] S5. The final oil drilling path is transmitted to the intelligent exploration terminal in real time via satellite communication technology.

[0112] Since the electronic device described in this embodiment is the electronic device used in implementing an intelligent exploration system for oil exploration as described in this application, those skilled in the art can understand the specific implementation methods and various variations of the electronic device in this embodiment based on the intelligent exploration system for oil exploration described in this application. Therefore, how the electronic device implements the method in this application will not be described in detail here. Any electronic device used by those skilled in the art in implementing an intelligent exploration system for oil exploration as described in this application falls within the scope of protection of this application.

[0113] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0114] The above description is merely a preferred embodiment of the present invention, and the scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for users of ordinary technical skills, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent exploration system for oil exploration, characterized by, The application relates to an intelligent oil exploration system and method. The data acquisition module is used for acquiring multi-source information data of an exploration area. The data processing module is used for preprocessing the multi-source information data to obtain a multi-source feature data set. The multi-source feature data set is converted into a three-dimensional geological model by using a full waveform inversion algorithm, and the three-dimensional geological model is visualized to obtain a three-dimensional geological map. The method for converting the multi-source feature data set into the three-dimensional geological model by using the full waveform inversion algorithm comprises the following steps: S41, the preset three-dimensional geological model is , the three-dimensional geological model includes two kinds of underground medium physical properties, the two kinds of underground medium physical properties are seismic wave velocity and density, and the distribution of the preset seismic wave velocity and density in the three-dimensional geological model is: ; wherein, is the seismic wave velocity at a position in the three-dimensional geological model; is the density at a position in the three-dimensional geological model; is the position coordinate where the seismic wave propagation occurs in the three-dimensional geological model; S42, according to the current three-dimensional geological model, the propagation process of the seismic wave is simulated by the elastic wave equation; the elastic wave equation is: ; wherein, is the second derivative of the seismic wave displacement with respect to time , that is, the acceleration of the seismic wave; is the seismic wave displacement at a certain position and time moment in the three-dimensional geological model; is the wave velocity function, indicating the propagation speed of the seismic wave at each point in the three-dimensional geological model; is the Laplace operator, indicating the wave propagation in the three-dimensional geological model; is the time variable, indicating the evolution of the change of the wave in the propagation process with time; S43, the simulation waveform of the seismic wave is obtained by solving the elastic wave equation through the finite difference method, and the simulation waveform of the seismic wave is: ; wherein, is simulation waveform data of the seismic wave; is a propagation operator of the seismic wave; is a source position coordinate of the seismic wave; is a receiver position coordinate of the seismic wave; S44, limiting the propagation operator of the seismic wave by a propagation operator limiting formula, the propagation operator limiting formula is: ; wherein, is the propagation operator of the seismic wave after limiting; is the number of source points of the seismic wave; is the number of receiving points of the seismic wave; is a constant for controlling the influence of the source points and the receiving points on the propagation operator; S45. Construct an L2 norm loss function to quantify the difference between simulated and actual observed seismic waveform data; the L2 norm loss function is: ;in, The loss function is the L2 norm. For the first Actual observed waveform data of seismic waves at each receiving point; To use a three-dimensional geological model The calculated simulated waveform data of the seismic waves; For the first The time of each receiving point; Weighting factors for each receiving point; This represents the total number of seismic wave receiving points. For the index of the receiving point, The weighting factor for each receiving point is adjusted using an adaptive formula. Dynamically adjust the design; S46. Update the parameters of the 3D geological model using the gradient descent update formula, which is: ;in, For the first The three-dimensional geological model of the next iteration; For the first The three-dimensional geological model of the next iteration; The learning rate; L2 norm loss function Regarding three-dimensional geological models The gradient; S47, preset the loss threshold of the L2 norm loss function, continuously update the three-dimensional geological model through repeated iterations until the L2 norm loss function is less than or equal to the loss threshold of the preset L2 norm loss function, and stop, to obtain the final three-dimensional geological model ; The weight factor of each receiving point is adaptively calculated by the weight factor adaptive formula The method for dynamically adjusting the design comprises: The weight factor adaptive formula is: ; wherein, is the maximum time of seismic wave propagation; is the total time required for receiving seismic waves; The regional prediction module is used for training an oil and gas reservoir regional prediction model according to the three-dimensional geological map, and the oil and gas reservoir distribution region is predicted based on the oil and gas reservoir regional prediction model. The path planning module is used for formulating a preliminary oil drilling path according to the predicted oil and gas reservoir distribution region, collecting real-time drilling data, dynamically adjusting the preliminary oil drilling path according to the real-time drilling data, and obtaining a final oil drilling path. The communication transmission module is used for transmitting the final oil drilling path to an intelligent exploration terminal in real time through satellite communication technology.

2. The intelligent exploration system for petroleum exploration as claimed in claim 1 wherein, The multi-source information data comprises geophysical prospecting data, seismic wave data and geological data; the geophysical prospecting data comprises gravity, electromagnetic method and natural potential; the seismic wave data comprises seismic wave reflection data, seismic wave propagation velocity, seismic wave amplitude and seismic wave frequency; and the geological data comprises core samples, surface sediment samples and fluid samples.

3. The intelligent exploration system for petroleum exploration as claimed in claim 2 wherein, The method for preprocessing the multi-source information data to obtain the multi-source feature data set comprises the following steps: Abnormal values existing in the geophysical prospecting data, the seismic wave data and the geological data included in the multi-source information data are identified and removed by using a density clustering algorithm to obtain geophysical prospecting feature data set, seismic wave feature data set and geological feature data set; The geophysical prospecting feature data set, the seismic wave feature data set and the geological feature data set are subjected to feature extraction by using principal component analysis, and the geophysical prospecting feature data set, the seismic wave feature data set and the geological feature data set after feature extraction are subjected to standard deviation normalization processing to convert into standard normal distribution with a mean value of 0 and a standard deviation of 1 to obtain normalized geophysical prospecting feature data set, normalized seismic wave feature data set and normalized geological feature data set; and the normalized geophysical prospecting feature data set, the normalized seismic wave feature data set and the normalized geological feature data set are fused by using a weighted model to obtain the multi-source feature data set.

4. The intelligent exploration system for petroleum exploration as claimed in claim 3 wherein, The method for obtaining the three-dimensional geological map comprises the following steps: Different filters in the ParaView software are used to cut the three-dimensional geological model according to any geometric shape, different parts of the three-dimensional geological model are viewed, a profile is created, and a slice thereof is displayed to pass through the model to view the geological structure at different depths underground; the surface of the three-dimensional geological model is extracted from the three-dimensional grid data to view the external morphology of the underground structure; different colors are set for different regions according to seismic wave velocity and density to distinguish different underground rock layers; the transparency of different parts is adjusted to view the internal structure of the three-dimensional geological model, the underground hierarchical structure is presented by adjusting the transparency and the color, and finally the three-dimensional geological map is obtained.

5. The intelligent exploration system for petroleum exploration as claimed in claim 4 wherein, The training method of the oil and gas reservoir regional prediction model comprises the following steps: The data set is divided into a training set, a validation set and a test set; an oil and gas reservoir area prediction model is constructed, the oil and gas reservoir area prediction model comprising an input layer, a 3D convolution layer, a 3D pooling layer, a full connection layer and an output layer; the input data is a historical three-dimensional geological map, and the output data is an oil and gas reservoir distribution area; ReLU is used as an activation function; the oil and gas reservoir area prediction model is a 3D convolutional neural network model; The mean square error is used as the loss function of the model to measure the difference between the predicted value and the actual value of the model; the training set is used for model training, and the Adam optimizer is used to minimize the loss function; the validation set is used to evaluate the performance of the oil and gas reservoir area prediction model, and the accuracy index is calculated to measure the performance of the model; the hyperparameters of the model are optimized, the gradient of each hyperparameter is calculated by the back propagation algorithm, and the model hyperparameters are optimized by the gradient descent method to improve the performance of the model; The performance of the model in the prediction task is evaluated by the test set, and the test is stopped when the performance of the model in the prediction task reaches the preset performance threshold, and the oil and gas reservoir area prediction model is obtained; the trained oil and gas reservoir area prediction model is used to predict the current three-dimensional geological map to obtain the oil and gas reservoir distribution area.

6. The intelligent exploration system for petroleum exploration as claimed in claim 5 wherein, The method for obtaining the preliminary oil drilling path comprises: discretize the oil and gas reservoir distribution region into Q voxels; the voxel is a small volume unit in the oil and gas reservoir distribution region, and contains multi-source information data corresponding to the oil and gas reservoir distribution region; a graph structure is constructed by taking the spatial position of each voxel as a node and the feasible path between adjacent voxels as an edge; the graph structure is ; wherein, is a node set; is an edge set; The preset initial node is , and the target node is ; Define a path cost function to represent the cumulative cost from the initial node to the current node; the path cost function is: ;in, For the current node; For the current node The previous adjacent node; From the initial node to the node The cumulative cost; The path cost between adjacent nodes, i.e., the current node. With the previous adjacent node Path cost between; and The index is the node sequence number; For the current node The set of adjacent nodes; a path cost between the adjacent nodes is obtained by synthesizing a path cost formula; the path cost formula is ; wherein, is a distance between a current node and a previous adjacent node ; is a rock hardness of the current node ; is a rock hardness of the previous adjacent node ; is a formation pressure of the current node ; is a formation pressure of the previous adjacent node ; is a weight coefficient for adjusting an influence of the distance on the path cost; is a weight coefficient for adjusting an influence of the rock hardness on the path cost; is a weight coefficient for adjusting an influence of the formation pressure on the path cost; a heuristic function is defined for estimating the remaining path cost from the current node to the target node; the heuristic function is ; wherein, is the Euclidean distance from the current node to the target node ; is the oil and gas reserves of the current node ; is the adjustment coefficient of the oil and gas reserves on the heuristic function; By combining the path cost function and the heuristic function, a comprehensive evaluation function is obtained; the comprehensive evaluation function is: + ;use The algorithm performs pathfinding, starting from the initial node. Initially, the node that minimizes the comprehensive evaluation function is selected step by step as the current node, until the target node is reached. Stop when selected; collect all selected nodes to obtain an initial oil drilling path.

7. The intelligent exploration system for petroleum exploration as claimed in claim 6 wherein, The method for obtaining the final oil drilling path comprises: According to the preliminary oil drilling path, real-time drilling data is collected in the actual drilling process by using the measurement while drilling technology; the real-time drilling data includes bit pressure, drilling speed, drilling inclination angle, drilling depth and adjacent stratum pressure; based on the real-time drilling data, the genetic algorithm is used to iteratively optimize the preliminary oil drilling path; a preset oil drilling path risk threshold is set, and the iteration is stopped when the risk value of the adjusted oil drilling path is less than or equal to the preset oil drilling path risk threshold, and then the final oil drilling path is obtained; The adjusted oil drilling path risk value is obtained through a path risk calculation formula; the path risk calculation formula is: ; wherein, is the adjusted oil drilling path risk value; is a weight factor of the adjusted oil drilling path risk value; is an index of the oil drilling path type; the adjusted oil drilling path risk value is obtained through a risk assessment formula; the risk assessment formula is ; wherein, is a friction coefficient; is a bit pressure; is a drilling speed; is a difference in adjacent formation pressure; is a difference in drilling depth; is a total number of the adjusted oil drilling path risk values.

8. The intelligent exploration system for petroleum exploration as claimed in claim 7 wherein, The method for transmitting the final oil drilling path to the intelligent exploration terminal in real time through satellite communication technology comprises: The satellite communication equipment is installed on the drilling platform or drilling equipment, and the satellite communication equipment comprises a mobile satellite antenna and a satellite modem; the satellite communication equipment establishes a real-time communication link with the satellite through the mobile satellite antenna, and the satellite communication equipment establishes a connection according to the MQTT protocol and uploads the final oil drilling path to the intelligent exploration terminal through the real-time communication link.

Images