Oil exploration method adopting intelligent oil exploration robot system

Abstract

The invention belongs to the technical field of oil exploration, and discloses an oil exploration method adopting an intelligent oil exploration robot system. The method comprises the steps of collecting geological information data; analyzing the geological information data, and constructing a three-dimensional geological model; planning an exploration path based on the three-dimensional geologic model; according to the exploration path, controlling the exploration robot to perform drilling operation, and collecting drilling data; the drilling data are analyzed, and petroleum resources are evaluated; according to the invention, automation and intelligentization of the oil exploration process can be realized, the efficiency and accuracy of oil exploration are obviously improved, the operation risk and cost are reduced, systematic evaluation of the whole oil resource is realized, and a reliable basis is provided for subsequent development and utilization of oil.

Description

Technical Field

[0001] The present invention relates to the field of oil exploration technology, and more specifically, to an oil exploration method using an intelligent oil exploration robot system. Background Art

[0002] With the continuous growth of global energy demand, oil exploration technology faces unprecedented challenges. Traditional oil exploration methods rely on manual operation and fixed equipment. Although significant progress has been made in the early stages, as oil resources gradually enter complex geological environments and hard-to-reach areas, traditional methods have exposed some shortcomings. For example, the drilling process is high-risk, low-efficiency, and expensive, and manual operation may lead to data errors and unstable operations. In addition, the geological conditions of oil and gas reservoirs are becoming more and more complex, and accurate exploration data and real-time decision support are usually required to ensure the safety and economy of mining.

[0003] In this context, the introduction of intelligent technology has become an important breakthrough in the field of oil exploration; with the development of robotics, artificial intelligence, the Internet of Things, big data analysis and automation technology, intelligent oil exploration methods have begun to receive more and more attention; these methods can effectively optimize decisions in the exploration process and effectively improve exploration efficiency; for example, a patent application with publication number CN115559712A discloses an intelligent oil exploration system and its application method; including: a detection module, an information transmission module, a central processing module and an interaction module; the detection module is used to detect downhole data in real time, and divide the downhole data into important data and secondary data, and store the secondary data; the information transmission module is used to transmit important data to the central processing module; the central processing module is used to analyze important data and correct drilling parameters in real time; the interaction module is used to provide real-time feedback of downhole conditions to the staff and make manual corrections according to the downhole conditions; this invention ensures the accuracy and effectiveness of downhole signal transmission by adding a relay station, and at the same time classifies the data in combination with the actual working conditions, and analyzes important data in real time to correct the drilling parameters.

[0004] However, although the above-mentioned technology can detect downhole data in real time and ensure the accuracy of signal transmission through relay stations, and classify data and correct drilling parameters in real time in combination with actual working conditions; it mainly focuses on the real-time correction of drilling parameters and the guarantee of data transmission, lacks systematic evaluation and optimization planning of overall oil resources, and cannot fully support resource evaluation and long-term planning during the exploration process; thus, it leads to insufficient resource evaluation, unscientific mining planning, and incoordination between technology and cost during the exploration process, which in turn affects exploration efficiency and economic benefits.

[0005] In view of this, the present invention proposes an oil exploration method using an intelligent oil exploration robot system to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purpose, the present invention provides the following technical solution: a petroleum exploration method using an intelligent petroleum exploration robot system, comprising:

[0007] S1: Collect geological information data;

[0008] S2: Analyze geological information data and construct a three-dimensional geological model;

[0009] S3: Plan exploration paths based on 3D geological models;

[0010] S4: According to the exploration path, control the exploration robot to perform drilling operations and collect drilling data;

[0011] S5: Analyze drilling data and evaluate oil resources.

[0012] Furthermore, the geological information data includes seismic data, magnetic field data and gravity field data; the seismic data is the distribution of seismic wave reflection time underground in the area to be explored, and the area to be explored is the area where oil exploration is planned; the magnetic field data is the distribution of magnetic field intensity on the ground in the area to be explored; the gravity field data is the gravity distribution on the ground in the area to be explored;

[0013] The steps of constructing the three-dimensional geological model include:

[0014] S201: preprocessing geological information data;

[0015] S202: Performing time-depth conversion on the preprocessed seismic data to obtain depth data;

[0016] S203: constructing a three-dimensional geological model according to the depth data;

[0017] S204: performing seismic inversion on the preprocessed seismic data to obtain velocity data;

[0018] S205: performing magnetic field inversion on the preprocessed magnetic field data to obtain magnetization data;

[0019] S206: performing gravity inversion on the preprocessed gravity field data to obtain density data;

[0020] S207: Update the three-dimensional geological model according to the velocity data, magnetization data and density data.

[0021] Furthermore, in step S201, the method for preprocessing seismic data includes:

[0022] A rectangular coordinate system is constructed for the area to be explored and marked as a regional coordinate system; a grid area is preset, and the area to be explored is divided into grids according to the grid area; the coordinates of each grid point and seismic point are obtained according to the regional coordinate system, where the grid point is the center point of each grid, and the seismic point is the position point in the area to be explored corresponding to each reflection time in the seismic data; based on the coordinates of each grid point and seismic point, the Euclidean distance between each grid point and each seismic point is calculated and used as the influence distance;

[0023] Preset the influence factor, and calculate the weight coefficient between each grid point and each earthquake point according to the influence factor and influence distance; the expression of the weight coefficient is: Where qz(p,q) is the weight coefficient between the pth grid point and the qth seismic point, yx(p,q) is the influence distance between the pth grid point and the qth seismic point, a is the influence factor, p∈[1,P],q∈[1,Q], P is the number of grid points, and Q is the number of seismic points. According to the weight coefficient between each grid point and each seismic point, the reflection time of each seismic point is weighted and summed, and the reflection time corresponding to each grid point is calculated and marked as weighted time. The expression of weighted time is: In the formula, js p is the weighted time of the pth grid point, fs q is the reflection time of the qth earthquake point;

[0024] Methods for preprocessing magnetic field data include:

[0025] Count the number of magnetic field intensities in the magnetic field data and mark them as the number of samples; add each magnetic field intensity in the magnetic field data in turn, and then divide it by the number of samples to obtain the background intensity; subtract the background intensity from each magnetic field intensity in the magnetic field data to obtain the magnetic anomaly data corresponding to each magnetic field point, where the magnetic field point is the position point in the area to be explored corresponding to each magnetic field intensity in the magnetic field data;

[0026] Methods for preprocessing gravity field data include:

[0027] Obtain the exploration altitude and calculate the terrain influence value; subtract the terrain influence value from each gravity in the gravity field data to obtain the gravity correction value corresponding to each gravity point, where the gravity point is the position point in the area to be explored corresponding to each gravity in the gravity field data; the expression of the terrain influence value is: dy=ρgh; where dy is the terrain influence value, ρ is the crust density, g is the standard gravity, and h is the exploration altitude.

[0028] Furthermore, in step S202, the method for obtaining depth data includes:

[0029] Obtain preliminary velocity data, which is the estimated wave velocity distribution underground in the area to be explored. According to the preliminary velocity data, obtain the estimated wave velocity of each grid point; multiply the estimated wave velocity of each grid point by the corresponding weighted time, and then divide by 2 to obtain the depth value of each grid point, and use the depth value of each grid point as the depth data;

[0030] In step S203, the method for constructing a three-dimensional geological model includes:

[0031] According to the coordinates and depth value of each grid point, the three-dimensional coordinates of each grid point are constructed; according to the three-dimensional coordinates of each grid point, a three-dimensional grid reconstruction algorithm is used to convert it into a three-dimensional geological model;

[0032] In step S207, the method for updating the three-dimensional geological model includes:

[0033] The velocity data, magnetization data and density data are used as analysis data, and the analysis data are input into the trained geological analysis model to predict the corresponding geological labels; the geological labels are digital labels corresponding to the geological data, and the geological labels corresponding to different geological data are different; the geological data include rock formation type, rock formation depth, oil reservoir area and oil reservoir depth; among which, the rock formation type is the type of each rock formation in the area to be explored; the rock formation depth is the vertical distance from the ground of the area to be explored to the top of each rock formation; the oil reservoir area is the grid where oil exists in the area to be explored; the oil reservoir depth is the vertical distance from the ground of the area to be explored to the bottom of each oil-bearing rock formation; according to the geological labels, the corresponding geological data are obtained, and the three-dimensional geological model is updated; the training process of the geological analysis model includes:

[0034] Collect b groups of analysis data in advance, set corresponding geological labels for b groups of analysis data, and convert the analysis data and the corresponding geological labels into a corresponding set of feature vectors; use each set of feature vectors as input of a geological analysis model, the geological analysis model uses a set of predicted geological labels corresponding to each set of analysis data as output, and uses the actual geological labels corresponding to each set of analysis data as prediction targets, where the actual geological labels are pre-set geological labels corresponding to the analysis data; minimize the sum of prediction errors of all analysis data as a training target; train the geological analysis model until the sum of prediction errors reaches convergence and stops training; the geological analysis model is a deep neural network model.

[0035] Furthermore, the step of planning the exploration path includes:

[0036] Step S301: All grids are regarded as nodes, and the oil reservoir area is regarded as the oil node;

[0037] Step S302: randomly select an oil node and mark it as the initial node; starting from the initial node, explore all adjacent nodes of the initial node, select a node from all adjacent nodes as a successor node according to a preset screening rule, and mark the successor node as a screening node;

[0038] Step S303: Explore all adjacent nodes of the successor node, and select a node from all adjacent nodes as an update node according to a preset screening rule, update the successor node to the update node, and mark the update node as a screening node;

[0039] Step S304: loop step S303 until all adjacent nodes corresponding to the successor node are marked as screening nodes, then the loop ends and the initial path is obtained;

[0040] Step S305: determine whether the initial path includes all oil nodes; if so, retain the initial path; if not, delete the initial path;

[0041] Step S306: looping steps S302 to S305, obtaining m1 initial paths, where m1 is an integer greater than 1, and the m1 initial paths are all different;

[0042] Step S307: Calculate the cumulative depth gradient of each initial path, and select m2 initial paths, and mark the m2 initial paths as intermediate paths, 1<m2<m1;

[0043] Step S308: Count the path distance of each intermediate path, select the best path, and use the best path as the exploration path.

[0044] Furthermore, in step S302, the screening rule is: if there is an oil node among the adjacent nodes, one of the oil nodes is randomly selected as the successor node; if there is no oil node among the adjacent nodes, one of the nodes is randomly selected as the successor node;

[0045] In step S307, the expression of the accumulated depth gradient is: In the formula, ls d is the cumulative depth gradient of the dth initial path, d∈[1,m1], sd dk is the oil reservoir depth of the kth oil node in the dth initial path, sd dk+1 is the oil reservoir depth of the k+1th oil node in the dth initial path, k∈[1,K-1], K is the number of oil nodes;

[0046] Methods for selecting m2 initial paths include:

[0047] Sort the cumulative depth gradients of each initial path from small to large, select the first m2 cumulative depth gradients in positive order, and mark them as screening depths; select the initial paths corresponding to m2 screening depths from the m1 initial paths;

[0048] In step S308, the path distance of the intermediate path is the number of all nodes passed by the intermediate path;

[0049] Methods for selecting the best path include:

[0050] Sort the path distance of each intermediate path from small to large, select the first path distance in positive order, and mark it as the shortest distance; select the intermediate path corresponding to the shortest distance from the m2 intermediate paths.

[0051] Furthermore, the method of controlling the exploration robot to perform drilling operations includes:

[0052] The oil reservoir area where drilling operations are carried out is marked as the current area, and the maximum drilling depth of the current area is determined according to the oil reservoir depth of the current area; the current drilling depth is obtained in real time, and the current drilling depth is the vertical distance of the drill bit relative to the ground to be explored; the rock formation depths corresponding to the current area are all marked as comparison depths, and all comparison depths and the current drilling depth are sorted from small to large, and the comparison depth that is ranked before the current drilling depth is obtained in positive order and marked as the determined depth, and the rock formation type corresponding to the determined depth is marked as the determined type; the drilling parameters of the exploration robot are adjusted in real time according to the current drilling depth and the determined type; when the current drilling depth reaches the maximum drilling depth, the exploration robot is controlled to stop drilling operations.

[0053] Furthermore, the step of real-time regulating the drilling parameters of the exploration robot includes:

[0054] Step S401: construct N parameter sets, set different digital labels for the N parameter sets, and mark them as parameter labels;

[0055] Step S402: construct a population S, which includes n individuals, generate the position of each individual, the individual position corresponds to the parameter label one by one, and set the number of iterations t to 0;

[0056] Step S403: Determine the attraction function and iteration threshold T;

[0057] Step S404: Calculate the attractiveness of each individual in the population S and update the position of each individual;

[0058] Step S405: determine whether the number of iterations t is less than the iteration threshold T. If so, set t=t+1 and return to step S404. If not, proceed to step S406.

[0059] Step S406: Calculate the attractiveness corresponding to each individual in the population S, obtain the parameter label corresponding to the individual with the maximum attractiveness, obtain the corresponding parameter set according to the obtained parameter label, and adjust the drilling parameters of the exploration robot in real time according to the obtained parameter set.

[0060] Further, in step S401, the method for constructing N parameter sets is: obtaining a parameter range, the parameter range includes the range of each parameter in the drilling parameters; the drilling parameters include drilling speed, drill bit speed, drill bit pressure and drill bit temperature; randomly selecting a value from each range in the parameter range, and constructing a parameter set, constructing a total of N parameter sets, and the N parameter sets are all different;

[0061] In step S402, the expression of each individual position is: In the formula, is the position of the ith individual, C i is the random coefficient of the ith individual, C i ∈[0,1],i∈[1,n];

[0062] In step S403, the expression of the attraction function is: f=tz; wherein f is the attraction, and tz is the drilling quality; the method for obtaining the drilling quality is: setting different digital labels for different rock formation types and marking them as rock formation labels; obtaining the corresponding parameter set according to the parameter label corresponding to the individual position; taking the current drilling depth, the rock formation label corresponding to the determined type, and the parameter set corresponding to the individual position as evaluation data, inputting the evaluation data into the trained quality evaluation model to evaluate the corresponding drilling quality, and the drilling quality is a comprehensive indicator of drilling efficiency, drilling safety, and drilling cost; the training process of the quality evaluation model is consistent with the training process of the geological analysis model, and both are deep neural network models;

[0063] In S404, the method for updating each individual position includes:

[0064]

[0065] In the formula, is the position of the i-th individual after update, v is the maximum attraction, y is the attenuation factor, e is the natural constant, l ib is the distance between the ith individual and the optimal individual, is the position of the optimal individual, is the position of the i-th individual before updating, L is the disturbance factor, R is a random number between [0, 1], and the optimal individual is the individual with the greatest attractiveness in the population S.

[0066] Further, the drilling data includes lithology data, porosity data and permeability data; the lithology data is the actual type of the oil reservoir rock formation; the porosity data is the proportion of the pore volume in the oil reservoir rock formation to the total volume; the permeability data is the ability of the rock in the oil reservoir rock formation to allow fluid to pass through; the oil resources include oil reserves and recoverability;

[0067] Methods for assessing petroleum resources include:

[0068] The three-dimensional geological model is divided into grids according to the grid area, and the divided grids are marked as cells; the drilling data is added to the corresponding cells to obtain a simulated geological model; the simulated geological model is dynamically simulated using numerical simulation calculation methods to obtain oil reserves and exploitability.

[0069] The technical effects and advantages of the oil exploration method using an intelligent oil exploration robot system of the present invention are as follows:

[0070] By integrating multi-source geological information data such as earthquakes, magnetic fields, and gravity, the oil exploration process is automated and intelligent by building a three-dimensional geological model and planning the optimal exploration path. By adjusting drilling parameters in real time and intelligently controlling the exploration robot to perform drilling operations, the efficiency and accuracy of oil exploration are significantly improved, and operational risks and costs are reduced. At the same time, the drilling data collected during the drilling operation is used to use dynamic simulation calculations to accurately evaluate the oil reserves and exploitability of the oil-bearing rock formations, thereby achieving a systematic evaluation of the overall oil resources and providing a reliable basis for the subsequent development and utilization of oil. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a flow chart of a petroleum exploration method using an intelligent petroleum exploration robot system according to Embodiment 1 of the present invention;

[0072] Figure 2 This is a flow chart of the exploration path planning method of Example 1 of the present invention. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] Example 1

[0075] See also Figure 1 As shown, this embodiment provides a petroleum exploration method using an intelligent petroleum exploration robot system, the method comprising:

[0076] S1: Collect geological information data.

[0077] Geological information data includes seismic data, magnetic field data and gravity field data;

[0078] The seismic data is the reflection time distribution of seismic waves underground in the area to be explored, and the area to be explored is the area where oil exploration is planned; the seismic data is obtained by generating seismic waves through a seismic source device (such as a mechanical seismic source, a heavy hammer seismic source, etc.) built into the exploration robot, and then receiving and recording the reflected seismic waves through a seismic detector built into the exploration robot to obtain seismic data, and the exploration robot is an oil exploration robot; it should be understood that obtaining seismic data is helpful to infer the structure and characteristics of underground rock formations, thereby inferring the shape, scale and location of underground oil reservoirs;

[0079] The magnetic field data is the distribution of magnetic field intensity on the ground in the area to be explored; the magnetic field data is obtained through the built-in magnetometer (such as superconducting quantum interferometer, laser magnetometer, electronic magnetometer, etc.) of the exploration robot; it should be understood that the collection of magnetic field data helps to identify underground magnetic minerals, rock formation structures and oil reservoirs, thereby assisting oil exploration;

[0080] Gravity field data refers to the gravity distribution of the ground in the area to be explored. Gravity field data is obtained through the built-in gravimeter of the exploration robot (such as particle gravimeter, gyro gravimeter, etc.). It should be understood that the collection of gravity field data helps to infer the characteristics of underground structures, such as faults, salt domes and other geological structures, thereby revealing the spatial distribution and potential reserves of oil reservoirs, and providing important support for oil exploration.

[0081] S2: Analyze geological information data and construct a three-dimensional geological model.

[0082] The steps to construct a 3D geological model include:

[0083] S201: preprocessing geological information data;

[0084] S202: Performing time-depth conversion on the preprocessed seismic data to obtain depth data;

[0085] S203: constructing a three-dimensional geological model according to the depth data;

[0086] S204: performing seismic inversion on the preprocessed seismic data to obtain velocity data;

[0087] S205: performing magnetic field inversion on the preprocessed magnetic field data to obtain magnetization data;

[0088] S206: performing gravity inversion on the preprocessed gravity field data to obtain density data;

[0089] S207: Update the three-dimensional geological model according to the velocity data, magnetization data and density data.

[0090] In the above step S201, the method for preprocessing seismic data includes:

[0091] A rectangular coordinate system is constructed for the area to be explored and marked as a regional coordinate system. The origin of the regional coordinate system is selected by a person skilled in the art according to actual conditions. A grid area is preset. The grid area is preset by a person skilled in the art according to the area of ​​the area to be explored. The area of ​​the area to be explored is obtained by a person skilled in the art through on-site measurement. The area to be explored is divided into grids according to the grid area. The coordinates of each grid point and seismic point are obtained according to the regional coordinate system. The grid point is the center point of each grid. The seismic point is the position point in the area to be explored corresponding to each reflection time in the seismic data. The Euclidean distance between each grid point and each seismic point is calculated according to the coordinates of each grid point and seismic point, and is used as the influence distance.

[0092] Preset influence factors, which are preset by technicians in this field according to actual conditions; calculate the weight coefficient between each grid point and each seismic point according to the influence factor and the influence distance; the expression of the weight coefficient is: Where qz(p,q) is the weight coefficient between the pth grid point and the qth seismic point, yx(p,q) is the influence distance between the pth grid point and the qth seismic point, a is the influence factor, p∈[1,P],q∈[1,Q], P is the number of grid points, and Q is the number of seismic points. According to the weight coefficient between each grid point and each seismic point, the reflection time of each seismic point is weighted and summed, and the reflection time corresponding to each grid point is calculated and marked as weighted time. The expression of weighted time is: In the formula, js p is the weighted time of the pth grid point, fs q is the reflection time of the qth earthquake point.

[0093] Methods for preprocessing magnetic field data include:

[0094] The number of magnetic field intensities in the magnetic field data is counted and marked as the sampling number; each magnetic field intensity in the magnetic field data is added in turn, and then divided by the sampling number to obtain the background intensity; each magnetic field intensity in the magnetic field data is subtracted from the background intensity to obtain the magnetic anomaly data corresponding to each magnetic field point. The magnetic field point is the position point in the area to be explored corresponding to each magnetic field intensity in the magnetic field data.

[0095] Methods for preprocessing gravity field data include:

[0096] The exploration altitude is obtained and the terrain influence value is calculated. The exploration altitude is obtained through the built-in GPS positioning system of the exploration robot. The terrain influence value is subtracted from each gravity in the gravity field data to obtain the gravity correction value corresponding to each gravity point. The gravity point is the position point in the area to be explored corresponding to each gravity in the gravity field data. The expression of the terrain influence value is: dy = ρgh; where dy is the terrain influence value and ρ is the crust density, which is usually 2.67g / cm 3 , g is standard gravity, usually 9.81m / s 2 , h is the exploration altitude; crust density and standard gravity are obtained by technicians in this field by referring to geological research materials or literature.

[0097] In the above step S202, the method for obtaining depth data includes:

[0098] Obtain preliminary velocity data, which is the estimated wave velocity distribution underground in the area to be explored. The preliminary velocity data is obtained by technical personnel in this field based on geological exploration data of areas adjacent to the area to be explored. Obtain the estimated wave velocity of each grid point based on the preliminary velocity data. Multiply the estimated wave velocity of each grid point by the corresponding weighted time, and then divide the result by 2 to obtain the depth value of each grid point, and use the depth value of each grid point as the depth data.

[0099] In the above step S203, the method for constructing a three-dimensional geological model includes:

[0100] According to the coordinates and depth value of each grid point, the three-dimensional coordinates of each grid point are constructed; according to the three-dimensional coordinates of each grid point, a three-dimensional grid reconstruction algorithm (such as De Launay triangulation algorithm, Marching Cubes algorithm, etc.) is used to convert it into a three-dimensional geological model.

[0101] In the above step S204, the seismic inversion method is, for example, least squares inversion, Ti khonov regularization inversion, etc.; the velocity data is the actual wave velocity distribution underground in the area to be explored.

[0102] In the above step S205, the magnetic field inversion method is, for example, least squares inversion, adaptive filtering inversion, geomagnetic tensor inversion, etc.; the magnetization data is the magnetic susceptibility distribution of the underground in the area to be explored.

[0103] In the above step S206, the gravity inversion method is, for example, the least squares inversion method, the wave inversion method, the boundary element method, etc.; the density data is the density distribution of the underground of the area to be explored.

[0104] In the above step S207, the method for updating the three-dimensional geological model includes:

[0105] The velocity data, magnetization data and density data are used as analysis data, and the analysis data are input into the trained geological analysis model to predict the corresponding geological labels; the geological labels are digital labels corresponding to the geological data, and the geological labels corresponding to different geological data are all different; the geological data include rock formation type, rock formation depth, oil reservoir area and oil reservoir depth; among which, the rock formation type is the type of each rock formation in the area to be explored, such as sandstone, limestone, shale, etc.; the rock formation depth is the vertical distance from the ground of the area to be explored to the top of each rock formation; the oil reservoir area is the grid where oil exists in the area to be explored; the oil reservoir depth is the vertical distance from the ground of the area to be explored to the bottom of each oil-bearing rock formation, and the oil-bearing rock formation is the rock formation that stores oil; according to the geological labels, the corresponding geological data are obtained, and the three-dimensional geological model is updated.

[0106] The training process of the geological analysis model includes:

[0107] b groups of analysis data are collected in advance, corresponding geological labels are set for the b groups of analysis data, b is an integer greater than 1, and the analysis data and the corresponding geological labels are converted into a corresponding set of feature vectors; the geological labels corresponding to the analysis data are collected by a technician in the field during the construction of the historical three-dimensional geological model, b groups of analysis data are collected, and under the conditions of each group of analysis data, the area to be explored corresponding to each group of analysis data is explored to obtain the geological data corresponding to each area to be explored; according to the geological data corresponding to each area to be explored, the corresponding geological labels are sequentially set for the b groups of analysis data;

[0108] Each set of feature vectors is used as the input of the geological analysis model. The geological analysis model takes a set of predicted geological labels corresponding to each set of analysis data as output, and takes the actual geological labels corresponding to each set of analysis data as the prediction target. The actual geological labels are the pre-set geological labels corresponding to the analysis data. The training goal is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is η w =(β w -ε w ) 2 , where η w is the prediction error, w is the group number of the eigenvector corresponding to the analyzed data, β w is the predicted geological label corresponding to the wth group of analysis data, ε w is the actual geological label corresponding to the wth group of analysis data; the geological analysis model is trained until the sum of the prediction errors reaches convergence and the training is stopped.

[0109] The above geological analysis model is specifically a deep neural network model; it includes an input layer, a hidden layer and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, and the activation function introduces nonlinearity, allowing the network to learn more complex patterns and features.

[0110] S3: Plan exploration routes based on 3D geological models.

[0111] like Figure 2 As shown, the steps of planning the exploration path include:

[0112] Step S301: All grids are regarded as nodes, and the oil reservoir area is regarded as the oil node;

[0113] Step S302: randomly select an oil node and mark it as the initial node; starting from the initial node, explore all adjacent nodes of the initial node, select a node from all adjacent nodes as a successor node according to a preset screening rule, and mark the successor node as a screening node;

[0114] Step S303: Explore all adjacent nodes of the successor node, and select a node from all adjacent nodes as an update node according to a preset screening rule, update the successor node to the update node, and mark the update node as a screening node;

[0115] Step S304: loop step S303 until all adjacent nodes corresponding to the successor node are marked as screening nodes, then the loop ends and the initial path is obtained;

[0116] Step S305: determine whether the initial path includes all oil nodes; if so, retain the initial path; if not, delete the initial path;

[0117] Step S306: looping steps S302 to S305, obtaining m1 initial paths, where m1 is an integer greater than 1, and the m1 initial paths are all different;

[0118] Step S307: Calculate the cumulative depth gradient of each initial path, and select m2 initial paths, and mark the m2 initial paths as intermediate paths, 1<m2<m1;

[0119] Step S308: Count the path distance of each intermediate path, select the best path, and use the best path as the exploration path.

[0120] In the above step S302, the screening rule is: if there is an oil node among the adjacent nodes, one of the oil nodes is randomly selected as the successor node; if there is no oil node among the adjacent nodes, one of the nodes is randomly selected as the successor node.

[0121] In the above step S307, the expression of the accumulated depth gradient is: In the formula, ls d is the cumulative depth gradient of the dth initial path, d∈[1,m1], sd dk is the oil reservoir depth of the kth oil node in the dth initial path, sd dk+1 is the oil reservoir depth of the k+1th oil node in the dth initial path, k∈[1,K-1], K is the number of oil nodes;

[0122] Methods for selecting m2 initial paths include:

[0123] Sort the cumulative depth gradients of each initial path from small to large, select the first m2 cumulative depth gradients in positive order, and mark them as screening depths; filter out initial paths corresponding to m2 screening depths from the m1 initial paths.

[0124] In the above step S308, the path distance of the intermediate path is the number of all nodes passed by the intermediate path;

[0125] Methods for selecting the best path include:

[0126] Sort the path distance of each intermediate path from small to large, select the first path distance in positive order, and mark it as the shortest distance; select the intermediate path corresponding to the shortest distance from the m2 intermediate paths.

[0127] S4: According to the exploration path, control the exploration robot to perform drilling operations and collect drilling data.

[0128] The method of controlling the exploration robot to perform drilling operations includes:

[0129] The oil reservoir area where drilling operations are carried out is marked as the current area, and the maximum drilling depth of the current area is determined according to the oil reservoir depth of the current area; the current drilling depth is obtained in real time, and the current drilling depth is the vertical distance of the drill bit relative to the ground to be explored. The drill bit is integrated in the drilling equipment of the exploration robot, and the current drilling depth is obtained by the depth sensor integrated in the drill bit; the rock formation depth corresponding to the current area is marked as the comparison depth, and all the comparison depths and the current drilling depth are sorted from small to large, and the comparison depth that is ranked before the current drilling depth is obtained in positive order and marked as the determined depth, and the rock formation type corresponding to the determined depth is marked as the determined type; according to the current drilling depth and the determined type, the drilling parameters of the exploration robot are adjusted in real time; when the current drilling depth reaches the maximum drilling depth, the exploration robot is controlled to stop drilling operations.

[0130] The steps of real-time control of the drilling parameters of the exploration robot include:

[0131] Step S401: construct N parameter sets, set different digital labels for the N parameter sets, and mark them as parameter labels;

[0132] Step S402: construct a population S, which includes n individuals, generate the position of each individual, the individual position corresponds to the parameter label one by one, and set the number of iterations t to 0;

[0133] Step S403: Determine the attraction function and iteration threshold T;

[0134] Step S404: Calculate the attractiveness of each individual in the population S and update the position of each individual;

[0135] Step S405: determine whether the number of iterations t is less than the iteration threshold T. If so, set t=t+1 and return to step S404. If not, proceed to step S406.

[0136] Step S406: Calculate the attractiveness corresponding to each individual in the population S, obtain the parameter label corresponding to the individual with the maximum attractiveness, obtain the corresponding parameter set according to the obtained parameter label, and adjust the drilling parameters of the exploration robot in real time according to the obtained parameter set.

[0137] In the above step S401, the method for constructing N parameter sets is: obtaining a parameter range, the parameter range includes the range of each parameter in the drilling parameters, and the parameter range is obtained by technical personnel in this field according to the technical parameters of the drilling equipment integrated in the exploration robot; the drilling parameters include drilling speed, drill bit speed, drill bit pressure and drill bit temperature; wherein, the drilling speed is the speed at which the drill bit drills in the rock formation, the drill bit speed is the number of times the drill bit rotates per unit time (such as per second, per minute, etc.), the drill bit pressure is the vertical pressure applied to the drill bit, and the drill bit temperature is the heat generated by the drill bit during the drilling process; a value is randomly selected from each range in the parameter range, and a parameter set is constructed, and a total of N parameter sets are constructed, and the N parameter sets are all different.

[0138] In the above step S402, the expression of each individual position is: In the formula, is the position of the ith individual, C i is the random coefficient of the ith individual, C i ∈[0,1],i∈[1,n].

[0139] In the above step S403, the expression of the attraction function is: f=tz; wherein f is the attraction, and tz is the drilling quality; the method for obtaining the drilling quality is: setting different digital labels for different rock formation types and marking them as rock formation labels; obtaining the corresponding parameter set according to the parameter label corresponding to the individual position; taking the current drilling depth, the rock formation label corresponding to the determined type, and the parameter set corresponding to the individual position as evaluation data, inputting the evaluation data into the trained quality evaluation model to evaluate the corresponding drilling quality, and the drilling quality is a comprehensive indicator of drilling efficiency, drilling safety, and drilling cost; the training process of the quality evaluation model is consistent with the training process of the geological analysis model, and both are deep neural network models; the drilling quality corresponding to the evaluation data is recorded by a technician in this field when the drilling parameters are historically adjusted, and under the conditions of the current drilling depth and the determined type in each set of evaluation data, the exploration robot is controlled to perform drilling operations according to the parameter set, and the drilling operation results are analyzed through the three dimensions of drilling efficiency, drilling safety, and drilling cost, and the corresponding drilling quality is evaluated, and the corresponding drilling quality is set for each set of evaluation data.

[0140] In the above S404, the method for updating the position of each individual includes:

[0141]

[0142] In the formula, is the position of the i-th individual after update, v is the maximum attraction, y is the attenuation factor, e is the natural constant, l ib is the distance between the ith individual and the optimal individual, is the position of the optimal individual, is the position of the i-th individual before updating, L is the disturbance factor, R is a random number between [0, 1], and the optimal individual is the individual with the greatest attractiveness in the population S; the maximum attraction, attenuation factor and disturbance factor are pre-set by technical personnel in this field according to actual conditions.

[0143] Drilling data include lithology data, porosity data and permeability data;

[0144] Lithology data refers to the actual type of oil-bearing rock formations; lithology data is obtained through gamma-ray logging, sonic logging and other methods;

[0145] Porosity data is the ratio of pore volume to total volume in oil reservoir rock formations; porosity data is obtained through neutron porosity logging, density porosity logging and other methods;

[0146] Permeability data refers to the ability of rocks in oil reservoir formations to allow fluid to pass through; permeability data is obtained through the acoustic time difference method and the pressure difference method;

[0147] It should be noted that drilling data is important data for evaluating oil reserves and exploitability. Among them, lithology data determines the type and distribution of oil-bearing rock formations, porosity data determines the oil storage capacity of oil-bearing rock formations, and permeability data determines the fluidity and exploitation efficiency of oil in oil-bearing rock formations. Through comprehensive analysis of drilling data, a comprehensive assessment of oil-bearing rock formations can be achieved, and the oil reserves and exploitability of oil-bearing rock formations can be accurately assessed, which is helpful to formulate the optimal exploitation plan.

[0148] S5: Analyze drilling data and evaluate oil resources.

[0149] Petroleum resources include petroleum reserves and recoverability.

[0150] Methods for assessing petroleum resources include:

[0151] The three-dimensional geological model is gridded according to the grid area, and the grids are marked as cells; the drilling data is added to the corresponding cells to obtain a simulated geological model; numerical simulation calculation methods (such as Eclipse, CMG, Schlumberger and other reservoir simulation software) are used to dynamically simulate the simulated geological model to obtain oil reserves and exploitability.

[0152] This embodiment integrates multi-source geological information data such as earthquakes, magnetic fields, gravity, etc., and realizes the automation and intelligence of the oil exploration process by constructing a three-dimensional geological model and planning the optimal exploration path; and by real-time regulation of drilling parameters, intelligent control of exploration robots to perform drilling operations, thereby significantly improving the efficiency and accuracy of oil exploration and reducing operational risks and costs; at the same time, for the drilling data collected during the drilling operation, dynamic simulation calculations are used to accurately evaluate the oil reserves and exploitability of the oil-bearing rock formations, thereby achieving a systematic evaluation of the overall oil resources and providing a reliable basis for the subsequent development and utilization of oil.

[0153] Example 2

[0154] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, they can execute an oil exploration method using an intelligent oil exploration robot system.

[0155] The method or system according to the implementation mode of the present application can also be implemented with the aid of the architecture of the electronic device shown in the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store a petroleum exploration method using an intelligent petroleum exploration robot system provided in the present application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in the present application is only exemplary. When implementing different devices, one or more components in the electronic device shown in the present application may be omitted according to actual needs.

[0156] Example 3

[0157] As shown, one embodiment of the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, an oil exploration method using an intelligent oil exploration robot system according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0158] In addition, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: an oil exploration method using an intelligent oil exploration robot system. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0159] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0160] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A petroleum exploration method using an intelligent petroleum exploration robot system, characterized in that: include: S1: Collect geological information data; S2: Analyze geological information data and construct a three-dimensional geological model; S3: Plan exploration paths based on 3D geological models; S4: According to the exploration path, control the exploration robot to perform drilling operations and collect drilling data; S5: Analyze drilling data and evaluate oil resources.

2. The oil exploration method using the intelligent oil exploration robot system according to claim 1 is characterized in that: The geological information data includes seismic data, magnetic field data and gravity field data; the seismic data is the distribution of seismic wave reflection time underground in the area to be explored, and the area to be explored is the area where oil exploration is planned; the magnetic field data is the distribution of magnetic field intensity on the ground in the area to be explored; The gravity field data is the gravity distribution of the ground in the area to be explored; The steps of constructing the three-dimensional geological model include: S201: preprocessing geological information data; S202: Performing time-depth conversion on the preprocessed seismic data to obtain depth data; S203: constructing a three-dimensional geological model according to the depth data; S204: performing seismic inversion on the preprocessed seismic data to obtain velocity data; S205: performing magnetic field inversion on the preprocessed magnetic field data to obtain magnetization data; S206: performing gravity inversion on the preprocessed gravity field data to obtain density data; S207: Update the three-dimensional geological model according to the velocity data, magnetization data and density data.

3. The oil exploration method using the intelligent oil exploration robot system according to claim 2 is characterized in that: In step S201, the method for preprocessing seismic data includes: A rectangular coordinate system is constructed for the area to be explored and marked as a regional coordinate system; a grid area is preset, and the area to be explored is divided into grids according to the grid area; the coordinates of each grid point and seismic point are obtained according to the regional coordinate system, where the grid point is the center point of each grid, and the seismic point is the position point in the area to be explored corresponding to each reflection time in the seismic data; based on the coordinates of each grid point and seismic point, the Euclidean distance between each grid point and each seismic point is calculated and used as the influence distance; Preset the influence factor, and calculate the weight coefficient between each grid point and each earthquake point according to the influence factor and influence distance; the expression of the weight coefficient is: Where qz(p,q) is the weight coefficient between the pth grid point and the qth seismic point, yx(p,q) is the influence distance between the pth grid point and the qth seismic point, a is the influence factor, p∈[1,P],q∈[1,Q], P is the number of grid points, and Q is the number of seismic points. According to the weight coefficient between each grid point and each seismic point, the reflection time of each seismic point is weighted and summed, and the reflection time corresponding to each grid point is calculated and marked as weighted time. The expression of weighted time is: In the formula, js p is the weighted time of the pth grid point, fs q is the reflection time of the qth earthquake point; Methods for preprocessing magnetic field data include: Count the number of magnetic field intensities in the magnetic field data and mark them as the number of samples; add each magnetic field intensity in the magnetic field data in turn, and then divide it by the number of samples to obtain the background intensity; subtract the background intensity from each magnetic field intensity in the magnetic field data to obtain the magnetic anomaly data corresponding to each magnetic field point, where the magnetic field point is the position point in the area to be explored corresponding to each magnetic field intensity in the magnetic field data; The methods for preprocessing gravity field data include: Obtain the exploration altitude and calculate the terrain influence value; subtract the terrain influence value from each gravity in the gravity field data to obtain the gravity correction value corresponding to each gravity point, where the gravity point is the position point in the area to be explored corresponding to each gravity in the gravity field data; the expression of the terrain influence value is: dy=ρgh; where dy is the terrain influence value, ρ is the crust density, g is the standard gravity, and h is the exploration altitude.

4. The oil exploration method using the intelligent oil exploration robot system according to claim 3 is characterized in that: In step S202, the method for obtaining depth data includes: Obtain preliminary velocity data, which is the estimated wave velocity distribution underground in the area to be explored. According to the preliminary velocity data, obtain the estimated wave velocity of each grid point; multiply the estimated wave velocity of each grid point by the corresponding weighted time, and then divide by 2 to obtain the depth value of each grid point, and use the depth value of each grid point as the depth data; In step S203, the method for constructing a three-dimensional geological model includes: According to the coordinates and depth value of each grid point, the three-dimensional coordinates of each grid point are constructed; according to the three-dimensional coordinates of each grid point, a three-dimensional grid reconstruction algorithm is used to convert it into a three-dimensional geological model; In step S207, the method for updating the three-dimensional geological model includes: The velocity data, magnetization data and density data are used as analysis data, and the analysis data are input into the trained geological analysis model to predict the corresponding geological labels; the geological labels are digital labels corresponding to the geological data, and the geological labels corresponding to different geological data are different; the geological data include rock formation type, rock formation depth, oil reservoir area and oil reservoir depth; among which, the rock formation type is the type of each rock formation in the area to be explored; the rock formation depth is the vertical distance from the ground of the area to be explored to the top of each rock formation; the oil reservoir area is the grid where oil exists in the area to be explored; the oil reservoir depth is the vertical distance from the ground of the area to be explored to the bottom of each oil-bearing rock formation; according to the geological labels, the corresponding geological data are obtained, and the three-dimensional geological model is updated; the training process of the geological analysis model includes: Collect b groups of analysis data in advance, set corresponding geological labels for b groups of analysis data, and convert the analysis data and the corresponding geological labels into a corresponding set of feature vectors; use each set of feature vectors as input of a geological analysis model, the geological analysis model uses a set of predicted geological labels corresponding to each set of analysis data as output, and uses the actual geological labels corresponding to each set of analysis data as prediction targets, where the actual geological labels are pre-set geological labels corresponding to the analysis data; minimize the sum of prediction errors of all analysis data as a training target; train the geological analysis model until the sum of prediction errors reaches convergence and stops training; the geological analysis model is a deep neural network model.

5. The oil exploration method using the intelligent oil exploration robot system according to claim 4 is characterized in that: The steps of planning the exploration path include: Step S301: All grids are regarded as nodes, and the oil reservoir area is regarded as the oil node; Step S302: randomly select an oil node and mark it as the initial node; starting from the initial node, explore all adjacent nodes of the initial node, select a node from all adjacent nodes as a successor node according to a preset screening rule, and mark the successor node as a screening node; Step S303: Explore all adjacent nodes of the successor node, and select a node from all adjacent nodes as an update node according to a preset screening rule, update the successor node to the update node, and mark the update node as a screening node; Step S304: loop step S303 until all adjacent nodes corresponding to the successor node are marked as screening nodes, then the loop ends and the initial path is obtained; Step S305: determine whether the initial path includes all oil nodes; if so, retain the initial path; if not, delete the initial path; Step S306: looping steps S302 to S305, obtaining m1 initial paths, where m1 is an integer greater than 1, and the m1 initial paths are all different; Step S307: Calculate the cumulative depth gradient of each initial path, and select m2 initial paths, and mark the m2 initial paths as intermediate paths, 1<m2<m1; Step S308: Count the path distance of each intermediate path, select the best path, and use the best path as the exploration path.

6. The oil exploration method using the intelligent oil exploration robot system according to claim 5 is characterized in that: In step S302, the screening rule is: if there is an oil node among the adjacent nodes, one of the oil nodes is randomly selected as the successor node; if there is no oil node among the adjacent nodes, one of the nodes is randomly selected as the successor node; In step S307, the expression of the accumulated depth gradient is: In the formula, ls d is the cumulative depth gradient of the dth initial path, d∈[1,m1], sd dk is the oil reservoir depth of the kth oil node in the dth initial path, sd dk+1 is the oil reservoir depth of the k+1th oil node in the dth initial path, k∈[1,K-1], K is the number of oil nodes; Methods for selecting m2 initial paths include: Sort the cumulative depth gradients of each initial path from small to large, select the first m2 cumulative depth gradients in positive order, and mark them as screening depths; select the initial paths corresponding to m2 screening depths from the m1 initial paths; In step S308, the path distance of the intermediate path is the number of all nodes passed by the intermediate path; Methods for selecting the best path include: Sort the path distance of each intermediate path from small to large, select the first path distance in positive order, and mark it as the shortest distance; select the intermediate path corresponding to the shortest distance from the m2 intermediate paths.

7. The oil exploration method using the intelligent oil exploration robot system according to claim 6 is characterized in that: The method for controlling the exploration robot to perform drilling operations comprises: The oil reservoir area where drilling operations are carried out is marked as the current area, and the maximum drilling depth of the current area is determined according to the oil reservoir depth of the current area; the current drilling depth is obtained in real time, and the current drilling depth is the vertical distance of the drill bit relative to the ground to be explored; the rock formation depths corresponding to the current area are all marked as comparison depths, and all comparison depths and the current drilling depth are sorted from small to large, and the comparison depth that is ranked before the current drilling depth is obtained in positive order and marked as the determined depth, and the rock formation type corresponding to the determined depth is marked as the determined type; the drilling parameters of the exploration robot are adjusted in real time according to the current drilling depth and the determined type; when the current drilling depth reaches the maximum drilling depth, the exploration robot is controlled to stop drilling operations.

8. The oil exploration method using the intelligent oil exploration robot system according to claim 7 is characterized in that: The step of real-time regulating the drilling parameters of the exploration robot comprises: Step S401: construct N parameter sets, set different digital labels for the N parameter sets, and mark them as parameter labels; Step S402: construct a population S, which includes n individuals, generate the position of each individual, the individual position corresponds to the parameter label one by one, and set the number of iterations t to 0; Step S403: Determine the attraction function and iteration threshold T; Step S404: Calculate the attractiveness of each individual in the population S and update the position of each individual; Step S405: determine whether the number of iterations t is less than the iteration threshold T. If so, set t=t+1 and return to step S404. If not, proceed to step S406. Step S406: Calculate the attractiveness corresponding to each individual in the population S, obtain the parameter label corresponding to the individual with the maximum attractiveness, obtain the corresponding parameter set according to the obtained parameter label, and adjust the drilling parameters of the exploration robot in real time according to the obtained parameter set.

9. The oil exploration method using the intelligent oil exploration robot system according to claim 8, characterized in that: In step S401, the method for constructing N parameter sets is: obtaining a parameter range, the parameter range includes the range of each parameter in the drilling parameters; the drilling parameters include drilling speed, drill bit speed, drill bit pressure and drill bit temperature; randomly selecting a value from each range in the parameter range, and constructing a parameter set, constructing a total of N parameter sets, and the N parameter sets are all different; In step S402, the expression of each individual position is: In the formula, is the position of the ith individual, C i is the random coefficient of the ith individual, C i ∈[0,1],i∈[1,n]; In the step S403, the expression of the attractiveness function is: f=tz; Where f is the attractiveness, tz is the drilling quality; the method for obtaining drilling quality is: different digital labels are set for different rock formation types and marked as rock formation labels; according to the parameter labels corresponding to the individual positions, the corresponding parameter set is obtained; the current drilling depth, the rock formation label corresponding to the determined type, and the parameter set corresponding to the individual position are used as evaluation data, and the evaluation data are input into the trained quality evaluation model to evaluate the corresponding drilling quality. The drilling quality is a comprehensive indicator of drilling efficiency, drilling safety and drilling cost; the training process of the quality evaluation model is consistent with the training process of the geological analysis model, and both are deep neural network models; In S404, the method for updating each individual position includes: In the formula, is the position of the i-th individual after update, v is the maximum attraction, y is the attenuation factor, e is the natural constant, l ib is the distance between the ith individual and the optimal individual, is the position of the optimal individual, is the position of the i-th individual before updating, L is the disturbance factor, R is a random number between [0, 1], and the optimal individual is the individual with the greatest attractiveness in the population S.

10. The oil exploration method using the intelligent oil exploration robot system according to claim 9, characterized in that: The drilling data includes lithology data, porosity data and permeability data; the lithology data is the actual type of the oil reservoir rock formation; the porosity data is the proportion of the pore volume in the oil reservoir rock formation to the total volume; the permeability data is the ability of the rock in the oil reservoir rock formation to allow fluid to pass through; the oil resources include oil reserves and recoverability; Methods for assessing petroleum resources include: The three-dimensional geological model is divided into grids according to the grid area, and the divided grids are marked as cells; the drilling data is added to the corresponding cells to obtain a simulated geological model; the simulated geological model is dynamically simulated using numerical simulation calculation methods to obtain oil reserves and exploitability.

Images