Deep geothermal target area selection system based on artificial intelligence

Abstract

The invention relates to the technical field of geothermal exploration, in particular to a deep geothermal target area selection system based on artificial intelligence. Obtaining an actual direction vector according to the first principal component vector of the exploration point in the neighborhood of the exploration point and the unit vector of the exploration point in the neighborhood and the centroid of the neighborhood; obtaining a direction consistency index according to the unit vector and the actual direction vector between the exploration point outside the neighborhood and the centroid; constructing a heat source feature sequence from the centroid along the direction of the actual direction vector, and obtaining a change rate; and obtaining a gradient consistency index according to the change rate, the distance characteristics between the exploration points outside the neighborhood and the centroid, the theoretical heat source characteristics and the heat source characteristics of the neighborhood of the exploration points outside the neighborhood. The method comprises the following steps: correcting a clustering measurement distance according to a direction consistency index and gradient consistency, and clustering exploration points to obtain an exploration point cluster; the integrity of heat source area structure analysis and the accuracy of geothermal target area selection are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of geothermal exploration, and particularly relates to a deep geothermal target area selection system based on artificial intelligence. Background Art

[0002] A deep geothermal target area refers to a deep area with geothermal resources, development prospects, and clear goals; by exploring the deep area, different exploration points are obtained, and the geothermal target area suitable for development is analyzed and evaluated according to the heat source characteristics at the exploration points. The prior art can identify candidate areas with similar heat source characteristics in space by clustering the coordinates of different exploration points and multi-dimensional heat source characteristics, and then judge different candidate areas to determine the final geothermal target area. In the clustering task of geothermal exploration point data with complex spatial distribution and unknown number of clusters, the existing DBSCAN clustering algorithm has become the preferred clustering algorithm due to its adaptability to clusters of arbitrary shapes and the characteristic of not needing to determine the number of clusters.

[0003] The DBSCAN clustering algorithm determines core points through the neighborhood radius and the minimum number of neighboring points, and divides data points; in the scenario of this solution, since deep heat flow areas often distribute along deep fault zones, the heat flow migration path migrates along the strike of the fault zone and expands linearly or strip-like, and some of the areas are far from the central area; however, DBSCAN judges core points based on circular neighborhoods and is difficult to perceive the characteristics of geological bodies with ductility, resulting in heat source areas distributed along fault zones being misclassified into multiple clusters, splitting the actual heat storage space, or being misrecognized as isolated points and discarded; ultimately affecting the integrity of the heat source area structure analysis and the accuracy of geothermal target area selection. Summary of the Invention

[0004] In order to solve the above technical problem that due to the possible linear or strip-like expansion of deep heat source areas, DBSCAN may divide the same heat source area into different clusters, affecting the accuracy of geothermal target area selection, the purpose of the present invention is to provide a deep geothermal target area selection system based on artificial intelligence, and the specific technical solution adopted is as follows:

[0005] A data acquisition module, configured to acquire the coordinates and heat source characteristics of exploration points;

[0006] A position analysis module, configured to obtain a first principal component vector according to the distribution characteristics of exploration points within the neighborhood of an exploration point; obtain the actual direction vector of the neighborhood of the exploration point according to the first principal component vector and the unit vector between the exploration points within the neighborhood and the centroid of the neighborhood; obtain a direction consistency index according to the direction difference characteristics between the unit vector between the exploration points outside the neighborhood of the exploration point and the centroid and the actual direction vector.

[0007] A heat source feature analysis module, configured to construct a heat source feature sequence of exploration points along the direction of the actual direction vector starting from the centroid; obtain a change rate according to the change characteristics of the heat source feature sequence; obtain a theoretical heat source feature of the centroid according to the actual direction vector and the exploration points within the neighborhood; obtain a gradual change consistency index according to the change rate, the distance characteristics between the exploration points outside the neighborhood and the centroid, the theoretical heat source feature, and the heat source features of the neighborhoods of the exploration points outside the neighborhood.

[0008] An exploration point clustering module, configured to obtain a trend index according to the direction consistency index and the gradual change consistency index; correct the clustering metric distance between the exploration points outside the neighborhood and the exploration points according to the trend index to obtain a corrected distance; cluster the exploration points according to the corrected distance to obtain exploration point clusters.

[0009] Further, the step of obtaining the first principal component vector according to the distribution characteristics of the exploration points within the neighborhood of the exploration points includes:

[0010] Obtain the first principal component vector through principal component analysis according to the coordinates of the exploration points within the neighborhood of the exploration point.

[0011] Further, the step of obtaining the actual direction vector of the neighborhood of the exploration point according to the first principal component vector and the unit vector between the exploration point within the neighborhood and the centroid of the neighborhood includes:

[0012] Calculate the vector angle between the unit vector between the exploration point within the neighborhood and the centroid of the neighborhood and the first principal component vector to obtain a first angle value; calculate the cosine value of the first angle value and perform a positive correlation mapping to obtain an angle weight; calculate the product of the unit vector between the exploration point within the neighborhood and the centroid of the neighborhood and the angle weight to obtain the weighted unit vector of the exploration point within the neighborhood; calculate the sum value of the weighted unit vectors of all the exploration points within the neighborhood of the exploration point to obtain the actual direction vector.

[0013] Further, the step of obtaining the direction consistency index according to the direction difference characteristics between the unit vector between the exploration point outside the neighborhood of the exploration point and the centroid and the actual direction vector includes:

[0014] Calculate the cosine value of the vector angle between the unit vector between the exploration point outside the neighborhood and the centroid and the actual direction vector and normalize it to obtain the direction consistency index between the exploration point outside the neighborhood and the exploration point.

[0015] Further, the step of obtaining the change rate according to the change characteristics of the heat source feature sequence includes:

[0016] Calculate the average value of the ratio of the absolute value of the difference between the heat source characteristics of adjacent exploration points in the heat source characteristic sequence to the corresponding spatial distance to obtain the change rate.

[0017] Further, the step of obtaining the theoretical heat source characteristics of the centroid according to the actual direction vector and the exploration points within the neighborhood includes:

[0018] Calculate the vector angle between the unit vector between the exploration points within the neighborhood and the centroid and the actual direction vector to obtain a second angle value; use the exploration point within the neighborhood corresponding to the minimum value of the second angle value as the reference exploration point; calculate the Euclidean distance between the reference exploration point and the centroid to obtain a reference distance; calculate the product of the reference distance and the change rate to obtain a reference change amount; calculate the sum of the reference change amount and the heat source characteristics of the reference exploration point to obtain the theoretical heat source characteristics of the centroid.

[0019] Further, the step of obtaining the gradual change consistency index according to the change rate, the distance characteristics between the exploration points outside the neighborhood and the centroid, the theoretical heat source characteristics, and the heat source characteristics of the neighborhood of the exploration points outside the neighborhood includes:

[0020] In the formula, V represents the gradual change consistency index between the exploration points outside the neighborhood and the exploration point, exp() represents the exponential function with the natural constant as the base, N represents the number of types of heat source characteristics, D represents the Euclidean distance between the exploration points outside the neighborhood and the exploration point, H n represents the change rate of the nth heat source characteristic, D*H n represents the characteristic change amount of the nth type of heat source characteristic, A n represents the nth heat source characteristic of the exploration points outside the neighborhood, R n represents the nth theoretical heat source characteristic of the centroid, |D*H n +A n -R n | represents the characteristic gradual change difference value; represents the gradual change characteristic value; S n represents the variance of the nth heat source characteristic within the neighborhood of the exploration points outside the neighborhood, represents the stability of the heat source characteristic distribution.

[0021] Further, the step of obtaining the trend index according to the direction consistency index and the gradual change consistency index includes:

[0022] Calculate the average value of the direction consistency index and the gradual change consistency index to obtain the trend index between the exploration points outside the neighborhood and the exploration point.

[0023] Further, the step of correcting the clustering metric distance between the exploration points outside the neighborhood and the exploration point according to the trend index to obtain a corrected distance includes:

[0024] Calculate the difference between the constant 1 and the trend index to obtain an adjustment coefficient; calculate the product of the clustering metric distance between the exploration points outside the neighborhood and the exploration point and the adjustment coefficient to obtain the corrected distance.

[0025] Further, the step of clustering the exploration points according to the corrected distance to obtain exploration point clusters includes:

[0026] Cluster according to the coordinates and heat source characteristics of the exploration points through the DBSCAN clustering algorithm. When other exploration points are not within the neighborhood of the exploration point, use the corrected distance as the clustering metric distance between the other exploration points and the exploration point. After clustering, different exploration point clusters are obtained.

[0027] The present invention has the following beneficial effects:

[0028] In the present invention, obtaining the first principal component vector can analyze the main trend direction and heat flow extension direction of the exploration points within the neighborhood of the exploration point; obtaining the actual direction vector can reduce the error of the first principal component vector and improve the accuracy of determining the heat flow extension direction and exploration point clustering. Since the heat flow has an extension feature on the fault zone within the crust, obtaining the direction consistency index can determine whether the extension change directions of the exploration point and the exploration points outside the neighborhood are consistent, so as to judge whether they are in the same heat source area and improve the accuracy of exploration point clustering. Obtaining the change rate can determine the degree of change of the heat source characteristics that conform to the heat source extension trend, so as to judge whether the exploration points conform to the gradual change of the heat source characteristics corresponding to the heat flow migration in the fault zone. Obtaining the theoretical heat source characteristics can determine the heat source characteristics at the centroid. Obtaining the gradual change consistency index can characterize whether the heat source characteristic change trends of the exploration point and the exploration points outside the neighborhood conform to the heat flow extension characteristics of the same heat source area. Obtaining the trend index can judge the possibility that the exploration point and the exploration points outside the neighborhood are in the same heat source area; clustering according to the corrected distance to obtain exploration point clusters can cluster the exploration points corresponding to the strip-shaped heat source area in the actual underground deep scenario of the heat source distribution into one cluster, thereby improving the integrity of the heat source area structure analysis and the accuracy of geothermal target area selection. Description of the Drawings

[0029] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0030] Figure 1 A block diagram of a deep geothermal target area selection system based on artificial intelligence provided by an embodiment of the present invention. Detailed implementation manners

[0031] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of a deep geothermal target area selection system based on artificial intelligence proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0033] The following specifically describes the specific solution of a deep geothermal target area selection system based on artificial intelligence provided by the present invention in combination with the accompanying drawings.

[0034] Please refer to Figure 1 , which shows a block diagram of a deep geothermal target area selection system based on artificial intelligence provided by an embodiment of the present invention. The system includes the following modules:

[0035] A data acquisition module S1 for acquiring the coordinates and heat source characteristics of exploration points.

[0036] In the implementation of the present invention, the implementation scenario is to select a deep geothermal target area to improve the accuracy of target area selection. Exploration is carried out in the exploration area to obtain the coordinates and heat source characteristics of exploration points at different positions. The coordinates represent the positions of the exploration points in the underground three-dimensional space; the heat source characteristics represent the possibility that the exploration point is a heat storage area. In the embodiments of the present invention, the heat source characteristics include temperature and thermal conductivity, and the heat source characteristics are obtained by in-situ measurement of the exposed rock formations or profiles. For ease of analysis, all heat source characteristics of the exploration points are standardized to eliminate the dimension difference; the implementer can determine the acquisition type of the heat source characteristics of the exploration points according to the implementation scenario.

[0037] A position analysis module S2, configured to obtain a first principal component vector according to the distribution characteristics of exploration points within the neighborhood of an exploration point; obtain an actual direction vector of the neighborhood of the exploration point according to the first principal component vector and the unit vector between the exploration points within the neighborhood and the centroid of the neighborhood; and obtain a direction consistency index according to the direction difference characteristics between the unit vector between the exploration points outside the neighborhood of the exploration point and the centroid and the actual direction vector.

[0038] The existing DBSCAN algorithm may not be able to identify exploration points that are far away in the heat source area based on the neighborhood radius, resulting in low accuracy of the clustering division of the heat source area. In order to improve the accuracy of the selection of the heat source area, it is necessary to improve the selection of the neighborhood radius in the clustering process. Deep heat source areas are usually formed near fault zones, and the heat flow often extends along the fault zones. The exploration points arranged artificially will follow the local geological laws, and the distribution of the exploration points can initially reflect the directionality of the local deep heat source; therefore, the extension trend of the exploration points can be judged, and the extension characteristics of the heat source area can be characterized based on the extension area of the exploration points. Therefore, a first principal component vector is obtained according to the distribution characteristics of the exploration points within the neighborhood of the exploration point; preferably, in the embodiment of the present invention, the step of obtaining the first principal component vector includes: obtaining the first principal component vector by principal component analysis according to the coordinates of the exploration points within the neighborhood of the exploration point. It should be noted that the principal component analysis method belongs to the prior art, and this algorithm can select the direction with the largest variance after data projection as the principal component; the direction of the first principal component vector characterizes the distribution extension trend of all exploration points in the neighborhood space of the exploration point. The neighborhood of the exploration point is the range formed by the neighborhood radius in the DBSCAN algorithm. In the implementation of the present invention, taking a common geothermal exploration grid with a side length of 2 km as an example, the neighborhood radius is set to 200 meters and the minimum number of neighborhoods is set to 8; the implementer can determine it according to the implementation scenario.

[0039] Furthermore, since the first principal component vector obtained by the principal component analysis method cannot distinguish whether it is the consistent contribution of most exploration points or the twisting of a few strongly influential points such as isolated points, in order to improve the accuracy of determining the heat flow extension direction, it can be further determined according to the angle relationship between the exploration points in the neighborhood of the exploration point and the first principal component vector, reducing the interference of isolated points on the first principal component vector. Therefore, the actual direction vector of the exploration point neighborhood is obtained according to the first principal component vector and the unit vector between the exploration points in the neighborhood and the centroid of the neighborhood; preferably, in the embodiment of the present invention, the steps of obtaining the actual direction vector include: calculating the vector angle between the unit vector between the exploration points in the neighborhood and the centroid of the neighborhood and the first principal component vector to obtain a first angle value; the centroid reflects the central position of all exploration points in the neighborhood of the exploration point, and the unit vector characterizes the positional relationship of the exploration points in the neighborhood relative to the neighborhood center. The magnitude of the first angle value characterizes the degree of consistency between any exploration point in the neighborhood and the main trend direction. When the first angle value is smaller, it means that the direction is more consistent, and the direction of the exploration points in the neighborhood with the centroid is more consistent with the main trend direction of the neighborhood and more consistent with the overall trend. Calculate the cosine value of the first angle value and perform a positive correlation mapping to obtain an angle weight; when the first angle value is smaller, the cosine value is larger, and the angle weight is larger; furthermore, the exploration points in the neighborhood that are more consistent with the main trend direction are more capable of dominating the determination of the true direction and are given a higher weight. Calculate the product of the unit vector between the exploration points in the neighborhood and the centroid of the neighborhood and the angle weight to obtain the weighted unit vector of the exploration points in the neighborhood; calculate the sum value of the weighted unit vectors of all neighborhoods of the exploration point to obtain the actual direction vector; the actual direction vector reflects the main distribution direction of the exploration points in all neighborhoods of the exploration point and the heat flow extension direction in the fault zone.

[0040] After obtaining the actual direction vector corresponding to the neighborhood of the exploration point, since the deep heat flow region usually forms a relatively long extension zone with the extended region of the fault zone, although the extension zone is relatively far apart in space, if the extension direction has a high consistency with the original heat flow extension direction, then this extension zone may belong to the extended region of the heat flow region. Therefore, the difference characteristics between the direction characteristics from the exploration points outside the neighborhood of the exploration point to the centroid of the neighborhood of the exploration point and the actual direction vector can be analyzed to determine whether they belong to the same heat flow region. Thus, the direction consistency index is obtained based on the direction difference characteristics between the unit vector between the exploration points outside the neighborhood of the exploration point and the centroid and the actual direction vector; preferably, in the embodiment of the present invention, the step of obtaining the direction consistency index includes: calculating the cosine value of the vector angle between the unit vector between the exploration points outside the neighborhood and the centroid and the actual direction vector and normalizing it to obtain the direction consistency index between the exploration points outside the neighborhood and the exploration point; when the vector angle is smaller, it means the direction is more consistent, then the cosine value is larger and the direction consistency index is larger. Since the heat flow region is usually distributed along the fault zone, the heat flow migration direction is consistent with the strike of the fault zone and extends linearly or strip-like. When the vector angle is smaller and the direction consistency index is larger, then the exploration point outside the neighborhood is more likely to belong to the extended region of the exploration point and more likely to belong to the same heat flow region. On the contrary, when the direction consistency index is smaller, the possibility that the exploration point outside the neighborhood and the exploration point belong to the same heat flow region is smaller.

[0041] The heat source feature analysis module S3 is used to construct the heat source feature sequence of the exploration point along the direction of the actual direction vector starting from the centroid; obtain the change rate according to the change characteristics of the heat source feature sequence; obtain the theoretical heat source feature of the centroid according to the actual direction vector and the exploration points within the neighborhood; obtain the gradual change consistency index according to the change rate, the distance feature between the exploration points outside the neighborhood and the centroid, the theoretical heat source feature, and the heat source feature of the neighborhood of the exploration points outside the neighborhood.

[0042] In a deep geothermal system, since the heat conduction and diffusion mechanism in the earth's crust is to diffuse from high-temperature areas to geothermal areas and gradually weaken with distance; especially in the heat flow extension area distributed along the fault zone, the fault zone will serve as a high-speed channel for heat energy transmission, and the energy released by the central heat source will propagate along the fault zone, making the heat source characteristics of different exploration points on the fault zone show a gradual change; at the same time, affected by the same geological structure, the change of heat source characteristics in the same area is stable. Therefore, first construct a heat source characteristic sequence of exploration points along the direction of the actual direction vector starting from the centroid. This heat source characteristic sequence characterizes the change trend of heat source characteristics along the direction of the actual direction vector starting from the centroid. Furthermore, the change rate can be obtained according to the change characteristics of the heat source characteristic sequence, specifically including: calculating the average value of the ratio of the absolute value of the difference between the heat source characteristics of adjacent exploration points in the heat source characteristic sequence to the corresponding spatial distance to obtain the change rate of the heat source characteristics, where the spatial distance is the Euclidean distance between adjacent exploration points in space; this change rate characterizes the normal change degree of the heat source characteristics in the heat flow extension direction. The larger the change rate, the greater the change degree of the heat source characteristics with distance, and the smaller the change rate, the smaller the change degree.

[0043] Furthermore, the change degree of the heat source characteristics from exploration points outside the neighborhood to the exploration points can be analyzed according to the change rate to see if it conforms to the characteristics of the heat source extension trend. First, obtain the theoretical heat source characteristics of the centroid according to the actual direction vector and the exploration points within the neighborhood; since there may be no real exploration points at the centroid and the heat source characteristics at the centroid have not been collected, in order to determine the heat source characteristics at the centroid for evaluating the change trend of the heat source characteristics of exploration points outside the neighborhood, it is necessary to calculate the heat source characteristics according to the existing exploration points within the neighborhood. Preferably, in the embodiment of the present invention, the steps of obtaining the theoretical heat source characteristics include: calculating the vector angle between the unit vector between the exploration points within the neighborhood and the centroid and the actual direction vector to obtain a second angle value; the smaller the second angle value, the closer the position of the exploration point is to the extension direction within the neighborhood, and the more this exploration point within the neighborhood conforms to the gradual change characteristics of the heat source characteristics on the fault zone; then, take the exploration point within the neighborhood corresponding to the minimum value of the second angle value as the reference exploration point; calculate the Euclidean distance between the reference exploration point and the centroid to obtain a reference distance; calculate the product of the reference distance and the change rate to obtain a reference change amount; the reference change amount is the change amount of the heat source characteristics from this reference exploration point to the centroid under normal gradual change characteristics. Calculate the sum value of the reference change amount and the heat source characteristics of the reference exploration point to obtain the theoretical heat source characteristics of the centroid; the theoretical heat source characteristics characterize the normal degree of gradual change of the heat source characteristics at this centroid; it should be noted that if there is a real exploration point at the centroid, then use the real heat source characteristics as the theoretical heat source characteristics.

[0044] Further, after obtaining the theoretical heat source characteristics at the centroid, the gradient consistency index can be obtained based on the change rate, the distance characteristics between the exploration points outside the neighborhood and the centroid, the theoretical heat source characteristics, and the heat source characteristics in the neighborhood of the exploration points outside the neighborhood; preferably, in the embodiments of the present invention, the steps of obtaining the gradient consistency index include:

[0045]

[0046] In the formula, V represents the gradient consistency index between the exploration point outside the neighborhood and the exploration point, exp() represents the exponential function with the natural constant as the base, which is used for negative correlation mapping, N represents the number of types of heat source characteristics, D represents the Euclidean distance between the exploration point outside the neighborhood and the exploration point, H n represents the change rate of the nth heat source characteristic, D*H n represents the characteristic change amount of the nth type of heat source characteristic, that is, the heat source characteristic change amount from the exploration point outside the neighborhood in the extension direction to the centroid in the neighborhood, A n represents the nth heat source characteristic of the exploration point outside the neighborhood, R n represents the nth theoretical heat source characteristic of the centroid. |D*H n +A n -R n | represents the characteristic gradient difference value. If the sum of A n and D*H n is closer to the theoretical heat source characteristic at the centroid, the characteristic gradient difference value is smaller, which means that the heat source characteristic change trend from the centroid to the exploration point outside the neighborhood is more in line with the gradient trend of the heat source characteristic caused by the heat flow extension on the fault zone, and the exploration point outside the neighborhood is more likely to belong to the same heat source area; represents the gradient characteristic value; the larger the gradient characteristic value, the more likely it means that the exploration point in the neighborhood belongs to the same heat source area. S n represents the variance of the nth heat source characteristic in the neighborhood of the exploration point outside the neighborhood. When the variance is smaller, it means that the heat source characteristics near the neighborhood of the exploration point outside the neighborhood are more stable and more likely to be affected by the same geological structure, represents the heat source characteristic distribution stability. When the heat source characteristic distribution stability is larger, it means that the exploration point outside the neighborhood is more likely to be on the heat flow extension direction. Furthermore, when the gradient consistency index is larger, it means that the exploration point outside the neighborhood and the exploration point are more likely to belong to the same heat flow extension direction, and the characterized heat source areas are more similar.

[0047] The exploration point clustering module S4 is used to obtain the trend index according to the direction consistency index and the gradient consistency index; correct the clustering metric distance between the exploration points outside the neighborhood and the exploration point according to the trend index to obtain the corrected distance; cluster the exploration points according to the corrected distance to obtain the exploration point clusters.

[0048] After obtaining the directional consistency index and the gradual change consistency index of all the out-of-neighborhood exploration points of the exploration point, the trend index can be obtained based on the directional consistency index and the gradual change consistency index. Preferably, in the embodiment of the present invention, the steps of obtaining the trend index include: calculating the average value of the directional consistency index and the gradual change consistency index to obtain the trend index between the out-of-neighborhood exploration point and the exploration point. The larger the trend index, the more similar the heat flow extension trend and the heat source change trend between the out-of-neighborhood exploration point and the exploration point, and thus the more likely it is to characterize the characteristics of the same heat source area. Even if the spatial interval is far, they should be clustered into the same cluster.

[0049] Furthermore, the clustering metric distance between the out-of-neighborhood exploration point and the exploration point can be corrected according to the trend index to obtain the corrected distance. Preferably, in the embodiment of the present invention, the steps of obtaining the corrected distance include: calculating the difference between the constant 1 and the trend index to obtain the adjustment coefficient. The smaller the adjustment coefficient, the more similar the heat source area characteristics represented by the out-of-neighborhood exploration point and the exploration point. Calculate the product of the clustering metric distance between the out-of-neighborhood exploration point and the exploration point and the adjustment coefficient to obtain the corrected distance. If the heat source area characteristics represented by the out-of-neighborhood exploration point and the exploration point are more similar, the corrected distance is less than the corresponding clustering metric distance, thereby avoiding splitting the two during the clustering process. It should be noted that the clustering metric distance is obtained by weighted summing the spatial distance between the exploration points and the difference distance of the heat source characteristics, and is used for DBSCAN to cluster the exploration points. The specific steps are not described in detail here. The smaller the clustering metric distance, the more similar the position characteristics and the represented heat source characteristics between the two exploration points.

[0050] After obtaining the corrected distance between each exploration point and the corresponding out-of-neighborhood exploration point, the exploration points can be clustered according to the corrected distance to obtain exploration point clusters. Specifically, it includes: clustering according to the coordinates and heat source characteristics of the exploration points through the DBSCAN clustering algorithm. When other exploration points are not in the neighborhood of the exploration point, the corresponding corrected distance is used as the clustering metric distance between the other exploration point and the exploration point. After clustering, different exploration point clusters are obtained. According to this clustering method, in the actual geothermal exploration scenario, exploration points that are far away but belong to the same heat source area can be clustered into the same cluster, thereby avoiding splitting the same heat source area. Finally, different exploration point clusters can be used to screen the geothermal target area, improving the integrity of the heat source area structure analysis and the accuracy of geothermal target area selection.

[0051] In summary, the embodiment of the present invention provides an artificial intelligence-based deep geothermal target selection system; the actual direction vector is obtained according to the first principal component vector of the exploration points in the neighborhood of the exploration point and the unit vector of the exploration points in the neighborhood and the centroid of the neighborhood; the direction consistency index is obtained according to the unit vector between the exploration points outside the neighborhood and the centroid and the actual direction vector; a heat source feature sequence is constructed along the direction of the actual direction vector starting from the centroid and the change rate is obtained; the gradual change consistency index is obtained according to the change rate, the distance feature between the exploration points outside the neighborhood and the centroid, the theoretical heat source feature, and the heat source feature of the neighborhood of the exploration points outside the neighborhood. The present invention corrects the clustering metric distance according to the direction consistency index and the gradual change consistency and clusters the exploration points to obtain exploration point clusters; improving the integrity of the heat source area structure analysis and the accuracy of the deep geothermal target selection.

[0052] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown or a sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0053] Each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An artificial intelligence-based deep geothermal target selection system, characterized in that, The system includes the following modules: A data acquisition module, which is used to acquire the coordinates and heat source characteristics of exploration points; A location analysis module, which is used to obtain a first principal component vector according to the distribution characteristics of exploration points in the neighborhood of the exploration point; obtain the actual direction vector of the neighborhood of the exploration point according to the first principal component vector and the unit vector between the exploration points in the neighborhood and the centroid of the neighborhood; obtain a direction consistency index according to the direction difference characteristics between the unit vector between the exploration points outside the neighborhood of the exploration point and the centroid and the actual direction vector; A heat source characteristic analysis module, which is used to construct a heat source characteristic sequence of exploration points along the direction of the actual direction vector starting from the centroid; obtain a change rate according to the change characteristics of the heat source characteristic sequence; Obtain the theoretical heat source characteristic of the centroid according to the actual direction vector and the exploration points in the neighborhood; obtain a gradual change consistency index according to the change rate, the distance characteristics between the exploration points outside the neighborhood and the centroid, the theoretical heat source characteristic, and the heat source characteristics of the neighborhoods of the exploration points outside the neighborhood; An exploration point clustering module, which is used to obtain a trend index according to the direction consistency index and the gradual change consistency index; correct the clustering metric distance between the exploration points outside the neighborhood and the exploration point according to the trend index to obtain a corrected distance; cluster the exploration points according to the corrected distance to obtain exploration point clusters.

2. The deep geothermal target area selection system based on artificial intelligence according to claim 1, characterized in that The step of obtaining the first principal component vector according to the distribution characteristics of exploration points in the neighborhood of the exploration point includes: Obtaining the first principal component vector by principal component analysis according to the coordinates of the exploration points in the neighborhood of the exploration point.

3. The deep geothermal target area selection system based on artificial intelligence according to claim 1, characterized in that, The step of obtaining the actual direction vector of the neighborhood of the exploration point according to the first principal component vector and the unit vector between the exploration points in the neighborhood and the centroid of the neighborhood includes: Calculating the vector angle between the unit vector between the exploration points in the neighborhood and the centroid of the neighborhood and the first principal component vector to obtain a first angle value; calculating the cosine value of the first angle value and performing a positive correlation mapping to obtain an angle weight; calculating the product of the unit vector between the exploration points in the neighborhood and the centroid of the neighborhood and the angle weight to obtain the weighted unit vector of the exploration points in the neighborhood; calculating the sum value of the weighted unit vectors of all the neighborhoods of the exploration point to obtain the actual direction vector.

4. The deep geothermal target area selection system based on artificial intelligence according to claim 1, wherein The step of obtaining the direction consistency index according to the direction difference characteristics between the unit vector between the exploration points outside the neighborhood of the exploration point and the centroid and the actual direction vector includes: Calculating the cosine value of the vector angle between the unit vector between the exploration points outside the neighborhood and the centroid and the actual direction vector and normalizing it to obtain the direction consistency index between the exploration points outside the neighborhood and the exploration point.

5. The deep geothermal target selection system based on artificial intelligence according to claim 1, wherein The step of obtaining the change rate according to the change characteristics of the heat source characteristic sequence includes: Calculating the average value of the ratio of the absolute value of the difference between the heat source characteristics of adjacent exploration points in the heat source characteristic sequence to the corresponding spatial distance to obtain the change rate.

6. The deep geothermal target area selection system based on artificial intelligence according to claim 1, characterized in that The step of obtaining the theoretical heat source characteristic of the centroid according to the actual direction vector and the exploration points in the neighborhood includes: Calculate the vector angle between the unit vector between the exploration points within the neighborhood and the centroid and the actual direction vector to obtain a second angle value; take the exploration point within the neighborhood corresponding to the minimum value of the second angle value as the reference exploration point; calculate the Euclidean distance between the reference exploration point and the centroid to obtain a reference distance; calculate the product of the reference distance and the change rate to obtain a reference change amount; calculate the sum of the reference change amount and the heat source feature of the reference exploration point to obtain the theoretical heat source feature of the centroid.

7. An artificial intelligence-based deep geothermal target area selection system according to claim 1, characterized in that, The step of obtaining the gradual change consistency index according to the change rate, the distance feature between the exploration points outside the neighborhood and the centroid, the theoretical heat source feature, and the heat source feature of the neighborhood of the exploration points outside the neighborhood includes: In the formula, V represents the gradual change consistency index between the exploration point outside the neighborhood and the exploration point, exp() represents the exponential function with the natural constant as the base, N represents the number of types of heat source characteristics, D represents the Euclidean distance between the exploration point outside the neighborhood and the exploration point, H n represents the change rate of the nth heat source characteristic, D*H n represents the characteristic change amount of the nth type of heat source characteristic, A n represents the nth heat source characteristic of the exploration point outside the neighborhood, R n represents the nth theoretical heat source characteristic of the centroid, |D*H n +A n -R n | represents the characteristic gradual change difference value; represents the gradual change characteristic value; S n represents the variance of the nth heat source characteristic within the neighborhood of the exploration point outside the neighborhood, represents the stability of the heat source characteristic distribution.

8. An artificial intelligence-based deep geothermal target selection system according to claim 1, characterized in that, The step of obtaining the trend index according to the direction consistency index and the gradual change consistency index includes: Calculate the average value of the direction consistency index and the gradual change consistency index to obtain the trend index between the exploration points outside the neighborhood and the exploration point.

9. The deep geothermal target area selection system based on artificial intelligence according to claim 1, characterized in that The step of correcting the clustering metric distance between the exploration points outside the neighborhood and the exploration point according to the trend index to obtain the corrected distance includes: Calculate the difference between the constant 1 and the trend index to obtain an adjustment coefficient; calculate the product of the clustering metric distance between the exploration points outside the neighborhood and the exploration point and the adjustment coefficient to obtain the corrected distance.

10. The system for selecting deep geothermal target areas based on artificial intelligence according to claim 1, wherein, The step of clustering the exploration points according to the corrected distance to obtain exploration point clusters includes: Cluster according to the coordinates and heat source features of the exploration points through the DBSCAN clustering algorithm. When other exploration points are not within the neighborhood of the exploration point, use the corrected distance as the clustering metric distance between the other exploration points and the exploration point. After clustering, different exploration point clusters are obtained.

Images