Mining area geologic structure intelligent analysis method and system based on three-dimensional visual modeling

Abstract

The invention relates to the technical field of three-dimensional geologic visualization modeling, and discloses a mining area geologic structure intelligent analysis method and system based on three-dimensional visualization modeling, and the method comprises the steps: obtaining continuous drilling process parameters along a drill hole, building a parameter fingerprint database, and carrying out the cause discrimination of the changes of the parameters, according to the method, effective physical beacon points capable of representing real geological discontinuity are identified, a geological authenticity guide field is generated in a three-dimensional space from the effective physical beacon points, and a weight crossing a potential geological boundary is constrained when spatial interpolation is executed. According to the method, drilling process data neglected for a long time is converted into effective geometric constraint on a three-dimensional modeling kernel, so that model construction is changed from pure mathematical filling to form generation which is guided by a physical process and is closer to engineering reality, and the reliability of a constraint information source is ensured through an internal authentication mechanism; therefore, the structural authenticity of the final geologic model is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to a mine area geological structure intelligent analysis method and system based on three-dimensional visualization modeling, and belongs to the technical field of three-dimensional geological visualization modeling. BACKGROUND

[0002] In the field of three-dimensional visualization modeling technology, especially for the analysis and construction of mine area geological structure, the widely followed and generally relied upon technical method in the current industry is to use spatial interpolation algorithm to construct continuous three-dimensional geological entity model based on discrete geological sample point information such as drilling core, tunnel logging and other engineering exposed sample points. This method provides basic technical support for the visualization and reserve estimation of underground resources.

[0003] However, this widely accepted technical method is based on an implicit technical compromise in principle, that is, in order to achieve mathematical continuity, it cognitively regards the area between the wide sample points as a pure information vacuum and completely discards the continuous process data carrying rock mass mechanical response information generated in the physical process of obtaining these sample points, such as drilling rate and torque changes of drilling machine, which directly reflect the real-time interaction between drilling tools and rock. In the existing modeling process, these physical quantities are usually only archived as engineering logs, and the geological information value contained therein is not utilized by the modeling engine.

[0004] The technical evolution in the field has long focused on seeking more optimized spatial interpolation algorithms, from Kriging method to emerging machine learning models, which are essentially seeking a more smooth or accurate filling function in the existing information vacuum framework. However, this does not address the root of the problem, that is, the three-dimensional modeling kernel naturally faces static and discrete geometric and attribute data in design philosophy, lacking an internal mechanism to receive, understand and apply dynamic and continuous process physical data to impose and derive physical reality constraints on the core geometric interpolation process. Specifically, the existing technical method mainly has the following deficiencies: 1. The core driving force of model construction is purely mathematical algorithm, and the form of the result lacks direct internal correlation with the physical genesis of geological structure, especially in areas with complex structural changes, the authenticity of the model depends on the density of sample points, 2. Continuous physical process data obtained at low cost during exploration is systematically ignored, and continuous physical process data is not fully utilized, and the model lacks a physical basis for verifying and constraining its geometric form. Therefore, how to enable the three-dimensional modeling kernel to break through the limitation of only processing discrete static samples, and establish a method to convert continuous physical process data generated during exploration into effective constraints on spatial interpolation algorithm, so that model construction is guided by physical process and generates a more realistic form closer to geological reality, has become a technical problem to be solved by the present application. SUMMARY

[0005] The present application provides a kind of based on three-dimensional visualization modeling mine geological structure intelligent analysis method and system, its main purpose is to solve the continuous physical data in the process of exploration cannot be used in existing three-dimensional modeling mode, leading to model construction only relies on discrete sample and mathematical filling, thus lack of physical reality constraint problem.

[0006] To achieve the above object, the present application provides a kind of based on three-dimensional visualization modeling mine geological structure intelligent analysis method, comprising the following steps:

[0007] Step a, in the sample point position of known geological information, the local feature vector of the drilling process parameter corresponding to each sample point is extracted, and the local feature vector is associated with the geological event type at the position, to build a parameter fingerprint library for identifying signal genesis;

[0008] Step b, the drilling rate and torque along the borehole depth are obtained, the local change rate of drilling rate and torque is calculated in the determined sliding depth window, and the position where the local change rate exceeds the threshold value is marked as potential physical beacon point;

[0009] Step c, the local feature vector of the drilling process parameter at each potential physical beacon point is extracted, and the parameter fingerprint library established in step a is identified, only the potential physical beacon point whose parameter characteristics are associated with the real geological discontinuity event is used as an effective physical beacon point;

[0010] Step d, taking all effective physical beacon points as the source, a scalar geological reality guide field is generated in the three-dimensional modeling space by distance transformation;

[0011] Step e, when using discrete geological sample points for three-dimensional space interpolation, the weight of any sample point acting on the interpolated point is adjusted by penalty according to the field value of the geological reality guide field on the path connecting the sample point and the interpolated point.

[0012] Preferably, the penalty adjustment of weight in step e is: the original weight is multiplied by a penalty factor to obtain the adjusted weight, the penalty factor is uniquely determined by the path integral of the field value of the geological reality guide field on the path connecting the sample point and the interpolated point, and the penalty factor is a monotone decreasing function of the path integral value.

[0013] Preferably, the threshold value used in step b for identifying potential physical beacon points is spatially self-adaptively adjusted; the spatial self-adaptive adjustment comprises: calculating the overall variance of the drilling process parameters in each borehole as an index of regional geological contrast, spatially interpolating the index of regional geological contrast based on all boreholes to generate a threshold modulation field, multiplying a global reference threshold value by the field value at the corresponding position of the threshold modulation field to obtain a dynamic threshold value used for judging at the position.

[0014] Preferably, the local feature vector in step a and step c is a multi-dimensional vector containing the mean, variance and normalized gradient of the drilling process parameters within the depth window at the corresponding position; the identification by the parameter fingerprint library is achieved by calculating the vector distance between the local feature vector to be identified and the local feature vector stored in the library, and classifying it to the geological event type with the smallest distance.

[0015] Preferably, the field value of any point in the geological authenticity guide field in step d is defined as the Euclidean distance from the point to the nearest effective physical beacon point in space.

[0016] Preferably, it further comprises a correction step of borehole trajectory deviation between step c and step d; the correction step comprises: identifying reference beacon points corresponding to one or more laterally stable geological marker layers from all effective physical beacon points according to the parameter fingerprint library, fitting a theoretical reference surface of the geological marker layer based on the design coordinates of the reference beacon points, calculating the deviation of the design depth of each reference beacon point from the corresponding depth of the theoretical reference surface, and interpolating to generate a depth deviation field, and correcting the spatial coordinates of the effective physical beacon points according to the depth deviation field.

[0017] Preferably, it further comprises the following steps: extracting the drilling process parameters in each borehole segment bounded by the adjacent effective physical beacon points identified in step c, calculating the statistical characteristic values of the drilling process parameters in each borehole segment, and performing three-dimensional spatial interpolation based on the statistical characteristic values to additionally generate a continuous attribute field representing the internal physical property differences of the rock mass inside the geological structure model independently of the generation of the geological authenticity guide field.

[0018] Preferably, it further comprises the following steps performed in parallel: calculating an index E representing drilling efficiency in real time based on the rate of penetration and torque, wherein ROP is the rate of penetration and T is the torque; low-pass filtering the time series of the drilling efficiency index E to extract its long-term trend, determining that the drill tool enters a wear state when the negative slope of the long-term trend exceeds a wear determination threshold value determined according to historical data statistics, and compensating and correcting the rate of penetration and torque obtained in step b according to the state.

[0019] Preferably, after step c, a recognition step of constructing hot spot area is performed, the recognition step comprising: based on the set of three-dimensional spatial positions of all valid physical beacon points, generating a beacon point spatial density field in the three-dimensional modeling space by using a kernel density estimation algorithm, and identifying the area in the beacon point spatial density field with a field value higher than a determined density threshold as the constructing hot spot area; in step e, the penalty adjustment is based entirely on the geological authenticity guiding field, and does not depend on the lithology or grade attribute values of the geological sample points themselves.

[0020] A mine geological structure intelligent analysis system based on three-dimensional visual modeling, comprising:

[0021] A parameter fingerprint library construction module is configured to extract a local feature vector of drilling process parameters corresponding to each sample point at a known geological information sample point position, and associate the local feature vector with a geological event type at the position to construct a parameter fingerprint library for signal cause discrimination.

[0022] A potential beacon point recognition module is configured to obtain a drilling rate and torque that continuously change along the drilling depth, calculate a local change rate of the drilling rate and torque in a determined sliding depth window, and mark a position with a local change rate exceeding a threshold as a potential physical beacon point.

[0023] A beacon point discrimination module is configured to extract a local feature vector of drilling process parameters at each potential physical beacon point, and discriminate according to the parameter fingerprint library, and only use potential physical beacon points with parameter features associated with real geological discontinuity events as valid physical beacon points.

[0024] A guiding field generation module is configured to take all valid physical beacon points as sources, and generate a scalar geological authenticity guiding field in a three-dimensional modeling space through distance transformation.

[0025] A weight adjustment module is configured to, when performing three-dimensional spatial interpolation using discrete geological sample points, adjust a weight of a sample point acting on an interpolated point based on a field value of the geological authenticity guiding field on a path connecting the sample point and the interpolated point.

[0026] Compared with the prior art, the present application has the following advantages:

[0027] 1. The present application establishes a new way of geological modeling. It does not directly interpolate the discrete geological sample points in space, but first identifies the physical beacon points representing geological discontinuity using the local variation characteristics of drilling process parameters obtained continuously along the borehole path, and generates a scalar geological reality guide field in three-dimensional space with these beacon points as the source. When any conventional spatial interpolation algorithm is executed subsequently, the guide field serves as a basic spatial constraint, dynamically adjusting the interpolation weight according to the guide field value between the sample points and the points to be interpolated. In this way, the boundary of the geological body model is no longer a purely mathematical fitting result determined by the spatial position of the sample points, but a boundary reflecting the discontinuity of rock mass mechanical properties, which has integrated physical process information during the construction process.

[0028] 2. The present application further establishes an internal verification mechanism for the guide field source. After identifying potential physical beacon points, it does not immediately use them to generate the guide field, but first extracts the corresponding drilling process parameter characteristics at the known geological sample point positions, and associates them with the geological or engineering event type at that position, thereby building a parameter fingerprint library within the modeling system. Only when the parameter characteristics of any identified physical beacon point match the records representing real geological discontinuity events in the fingerprint library, it is accepted as a valid source. This design allows the modeling process to avoid misinterpreting engineering artifacts in the drilling process as geological structures, so that the structural reality of the guide field generated and the geological model under its constraint is supported at the data source level.

[0029] 3. The present application also utilizes the drilling process parameters within each borehole segment defined by the physical beacon points, calculates their statistical characteristic values, and performs independent three-dimensional spatial interpolation based on these statistical characteristic values, to generate a new continuous attribute field representing the internal physical property differences of the rock mass within the geological structure model. This process operates in parallel with the process of constructing the geological structure boundary based on the guide field, so that the same drilling process data source is used to constrain the macro-structure boundary of the model, and the relatively stable part is used to depict the micro-physical property texture within the model. The final result is no longer a static lithology model with only geometric shape, but an engineering geological object with richer information dimension, which carries both the structure boundary and the internal physical property distribution. BRIEF DESCRIPTION OF DRAWINGS

[0030] Fig. 1 Flow chart of the present application based on physical beacon and guide field three-dimensional geological modeling method;

[0031] Fig. 2 Overall flowchart of the present application from field drilling to engineering application;

[0032] Fig. 3 The figure is a framework diagram of a multi-end cooperative geological structure intelligent analysis system of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical scheme and advantages of the present application more clear, the technical scheme of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0034] The present application provides a mine area geological structure intelligent analysis method and system based on three-dimensional visualization modeling, the overall operation process of which is designed as a set of sequentially executed and logically coupled data processing pipelines. The pipeline starts from the collection and characterization of original data of the drilling process, then through signal discrimination and space field construction, finally converts the physical process information into geometric constraints on the three-dimensional space interpolation algorithm. Specifically, the method includes a parameter fingerprint library construction step, a potential signal point identification step, a signal point discrimination step, a guide field generation step and an interpolation weight adjustment step. The output of the parameter fingerprint library construction step provides a decision basis for the signal point discrimination step. The effective physical signal point set purified by the signal point discrimination step is input as the only signal source of the guide field generation step. Finally, the geological reality guide field constructed by the guide field generation step imposes a decisive constraint on the standard space interpolation process in the interpolation weight adjustment step.

[0035] In a typical application scenario, for example, in the geological modeling task for the deep ore body exploration stage, the general technical challenge is that it is difficult to accurately depict the geological discontinuities such as faults and dikes with significant differences in mechanical properties by relying only on discrete borehole core sample points for spatial interpolation, because the interpolation algorithm regards the area between sample points as a mathematical space with continuous physical properties. To address this challenge, the first step of the present scheme is to extract the local feature vector of the drilling process parameters at the sample point position with known geological information, such as the borehole depth point where the core logging has been completed, and associate the vector with the geological event type at this position to build a parameter fingerprint library for signal origin discrimination. Specifically, the local feature vector is a multidimensional vector containing the mean, variance and normalized gradient of the drilling process parameters within a predetermined depth window at the corresponding position. For example, within a depth window of 0.5 meters centered on the core sample point, the corresponding drilling rate and torque sequences are collected, and their mean, variance and normalized gradient are calculated to form a six-dimensional feature vector. This vector is then bound and stored with the real geological discontinuity event label determined by the granite and surrounding rock contact surface identified by core logging. Conversely, if the engineering log records that a paste drill occurred within the depth window, the corresponding feature vector calculated will be bound with the engineering artifact label. By performing this operation on all known information sample points, the system internally establishes a query database that can map specific parameter signal patterns to their physical origins, i.e., the parameter fingerprint library. The parameter fingerprint library constructed by this procedure provides a basis for subsequent identification of the real geological significance of parameter changes at any position.

[0036] In extracting local feature vectors, the size of the sliding depth window is determined by performing a window size optimization procedure on the calibration drilling data, which iterates through a pre-defined size range, for example 0.2m to 2.0m with a step of 0.1m, and calculates the Davies-Bouldin index of each cluster of feature vectors of geological event types in the parameter fingerprint library for each size value, which is a statistical measure of the ratio of the separation between clusters and the compactness within clusters, and finally selects the window size that results in the minimum index value as the operating parameter for subsequent analysis; while performing beacon point discrimination, the system calculates the minimum Euclidean distance between the vector to be discriminated and all vectors in the library, and compares it with a maximum classification distance threshold, which is obtained by multiplying the maximum intrinsic radius of all known event feature vector clusters in the library by a coefficient of 3, if the minimum distance is greater than the threshold, the potential beacon point is marked as pending and stored in a separate database for manual review, rather than being classified into any existing geological event type; when the modeling data comes from multiple drilling equipment, a cross-equipment data scale normalization calibration procedure is performed before identifying potential physical beacon points, which first specifies one or more lithologically homogeneous and laterally stable strata as standard strata in the regional geological data, then extracts the statistical mean of the torque and drilling rate parameter sequences of each device when it passes through the standard strata, and specifies one of the devices as the reference device, and then calculates the ratio of the parameter mean of each device in the standard strata to the parameter mean of the reference device to obtain the exclusive correction factor C i In subsequent data processing, all original drilling process parameters P raw from device i will be converted by the operation P calibrated = P raw ·C i , so that all multi-source heterogeneous data are unified to the same response benchmark.

[0037] Further in the three-dimensional modeling process, the system first acquires the original time series data of the drilling rate and torque which continuously changes along the depth of all the simulated drilling holes, and in a sliding depth window of a certain size, the local change rate of the drilling rate and torque is calculated, when the local change rate of any parameter exceeds the preset threshold, the depth position is marked as a potential physical beacon point. Given the spatial heterogeneity of the contrast of the mechanical properties of rock mass in different geological regions, a globally fixed threshold may be too sensitive in strong contrast areas, and too slow in weak contrast areas. Therefore, the threshold used to identify potential physical beacon points is configured to adapt to the space, and the adjustment procedure is as follows: first, calculate the overall variance of the torque parameter in each independent drilling hole, for example, in the entire drilling depth range, and take the variance value as an index of regional geological contrast representing the overall mechanical property difference of the stratum passed through by the drilling hole. Then, taking the index values of all drilling holes as discrete samples, a continuous threshold modulation field is generated in the entire three-dimensional modeling space through standard spatial interpolation algorithms, such as inverse distance weighted interpolation. Finally, when judging whether the local change rate at any position exceeds the limit, the dynamic threshold it depends on is obtained by multiplying a global reference threshold by the field value of the position in the threshold modulation field. For example, if the global reference threshold is set to 1.0, and the modulation field value of a position is 1.5 in a strong contrast area, the judgment threshold is automatically raised to 1.5, and vice versa, if the field value of another position is 0.7 in a weak contrast area, the judgment threshold is automatically reduced to 0.7. In this way, the system can automatically adjust the sensitivity of identifying geological discontinuity according to the difference of local geological environment, so as to obtain a set of potential physical beacon points. However, the signal origin of the set of potential physical beacon points obtained in this stage is still uncertain, and may contain engineering artifacts caused by drill tool wear or improper operation, etc. In order to ensure the reliability of the signal source used for geometric constraint, the system starts the beacon point discrimination step, extracts the local feature vector of the drilling process parameter at each potential physical beacon point, and performs origin discrimination according to the parameter fingerprint library established in the above steps. The discrimination process is realized by calculating the vector distance, such as Euclidean distance, between the local feature vector to be discriminated and each feature vector stored in the library, and classifying it to the geological event type with the smallest distance according to the nearest neighbor principle. Only those potential physical beacon points whose parameter features are associated with real geological discontinuity events in the parameter fingerprint library are adopted as effective physical beacon points, the rest are filtered out. Through this inherent anti-fraud mechanism, the modeling process avoids misinterpreting engineering artifacts in the drilling process as geological structures, so that the structural authenticity of the guide field and the geological model constrained by it is supported at the data source level.

[0038] After obtaining the set of all valid physical signal points with high reliability in spatial position and geological significance, the guide field generation module takes this set as the source, generates a scalar geological reality guide field in the three-dimensional modeling space through distance transformation. Specifically, the field value of any point in the guide field is uniquely defined as the Euclidean distance from the point to the nearest valid physical signal point in space. This is a standard distance field that can be efficiently calculated by mature algorithms such as the fast marching method. The guide field describes the possibility of the existence of geological discontinuity in the entire three-dimensional space in the form of a continuous scalar function. The lower the field value, the closer the point is to a verified real geological boundary, and vice versa. This geological reality guide field provides a basic spatial constraint field derived from physical processes for the weight function of the subsequent spatial interpolation algorithm. Finally, when using discrete geological sample points, such as lithology or grade data of drill cores, to perform three-dimensional spatial interpolation to construct the final geological entity model, the weight adjustment module adjusts the original weight of each sample point acting on the interpolated point based on the above-mentioned geological reality guide field. The basis for this punitive adjustment comes entirely from the field value of the geological reality guide field along the path connecting the sample point and the interpolated point, and does not depend on the lithology or grade attribute value of the geological sample point itself. The specific adjustment procedure is as follows: multiply the original weight by a penalty factor to obtain the adjusted weight. The penalty factor is uniquely determined by the path integral of the field value of the geological reality guide field along the path connecting the sample point and the interpolated point, and the penalty factor is a monotonic decreasing function of the path integral value. For example, the adjustment can be performed in the form of where W adj is the adjusted weight, W orig is the original weight, k is the penalty coefficient, and ∫ path (x)dx is the line integral of the guide field value G(x) along the connecting path of the sample point and the interpolated point. When the connecting path passes through an area with low field value, i.e., a potential geological boundary, the integral value increases, and the penalty factor decreases, thereby weakening the cross-border influence of the sample point. In this way, the boundary of the geological body model is no longer a purely mathematical fitting result determined by the spatial position of the sample points, but a physical process information integrated model that reflects the objective expression of the discontinuity of rock mass mechanical properties.

[0039] It should be noted that the present application can also perform a procedure for diagnosing the health status of the data acquisition drilling tool in parallel to further improve the reliability of the input data, which is based on the obtained drilling rate ROP and torque T, and calculates an index E representing the drilling efficiency in real time, wherein E = ROP / T, and the long-term trend of the drilling efficiency index E is extracted by low-pass filtering the time series of the drilling efficiency index E, and when the negative slope of the long-term trend exceeds a wear determination threshold determined according to historical data statistics, the system determines that the drilling tool enters a wear state, and compensates and corrects the currently obtained drilling rate and torque according to the state to eliminate the interference of the systematic drift of the parameters caused by the wear of the drilling tool on the identification of geological discontinuity; further, after obtaining the effective physical beacon point set, the present application can also perform the identification step of constructing the hot spot area, which is based on the three-dimensional spatial position set of all effective physical beacon points, uses the kernel density estimation algorithm to generate a beacon point spatial density field in the three-dimensional modeling space, and identifies the area in the density field where the field value is higher than a preset density threshold as the tectonic hot spot area, which represents the area where the geological structure is most developed and complex, and can provide high-priority decision guidance for subsequent infill exploration or engineering design.

[0040] In addition, the present application can also use the drilling process parameters in each drilling segment defined by the effective physical beacon points, calculate the statistical characteristic values of the parameters in each segment, such as the variance or coefficient of variation of torque, and perform independent three-dimensional spatial interpolation based on these statistical characteristic values, to additionally generate a continuous attribute field representing the difference in physical properties inside the rock mass inside the geological structure model, which operates in parallel with the process of constructing the geological structure boundary based on the guide field, so that the same drilling process data source is used to constrain the geometric boundary of the model, and the relatively stable part is used to depict the physical property texture inside the model, and finally an engineering geological object with richer information dimension is obtained, which carries both the structural boundary and the internal physical property distribution; at the same time, to deal with the problem of drilling trajectory deviation commonly existing in actual engineering, the present application can also include a correction step for drilling trajectory deviation, which first identifies the reference beacon points corresponding to one or more laterally stable geological marker layers among all effective physical beacon points according to the parameter fingerprint library, then fits the theoretical reference surface of the geological marker layer based on the design coordinates of these reference beacon points, and calculates the deviation between the design depth of each reference beacon point and the corresponding depth of the theoretical reference surface, and further generates a three-dimensional depth deviation field, and finally, according to the depth deviation field, the spatial coordinates of the effective physical beacon points are corrected to eliminate the spatial positioning error of the beacon points caused by the bending of the drilling hole, and to ensure the geometric accuracy of the guide field and the final model.

[0041] In a task of building a three-dimensional geological model for slope stability analysis and deep resource exploration in an open-pit to underground mining area, engineers constructed a rock mass model using the standard inverse distance weighted interpolation method based on the data of core samples obtained from more than one hundred drill holes. The visualization result of the model showed that the contact boundary between the hard granite mass and the weak altered zone, which is a key factor affecting the slope stability, appeared as a smooth mathematical fitting surface. However, during the subsequent infrastructure tunneling process, small-scale landslides and water inrush occurred near the smooth boundary indicated by the model. The actual geological conditions revealed that there was a broken structure transition zone with a width of several meters near the boundary, which was not expressed in the model.

[0042] To address the engineering risks caused by the limitations of the modeling method, the project team applied the technical solution of the present application. First, the system obtained the drilling rate and torque parameters that continuously change along the depth during the drilling process of the above-mentioned drill holes. On these continuous data streams, the system calculated the local change rate of the parameters through a sliding depth window, identified a plurality of potential physical beacon points with local change rates exceeding the dynamic threshold, which were densely distributed in the contact area between the hard granite mass and the weak altered zone in space, and also sporadically distributed at other depths in some drill holes. Some of them were caused by the occurrence of a stuck drill in the soft stratum. At this time, the parameter fingerprint library construction and beacon point discrimination mechanism of the system began to operate. The parameter fingerprint library had been previously established by extracting the local feature vectors of the corresponding drilling process parameters at a small number of known geological and engineering event points. The system then extracted the local feature vectors at each potential physical beacon point and compared them with the parameter fingerprint library. Those potential physical beacon points matching the fingerprints of engineering artifacts such as stuck drill were filtered out, while those matching the fingerprints of lithological interfaces were confirmed as valid physical beacon points. The cooperative operation of this process yielded a set of valid physical beacon points that had filtered out engineering artifact signals and outlined the profile of the broken structure transition zone in space.

[0043] Further, the system generated a geological reality guide field in the entire three-dimensional modeling space using the set of valid physical beacon points as the source through distance transformation. When subsequently performing spatial interpolation using the original discrete core sample points, the guide field made a punitive adjustment to the interpolation weights. For any interpolation point located inside the hard granite mass, when the interpolation algorithm tried to reference a sample point located inside the weak altered zone, the path connecting the two points would inevitably pass through the area with low field values in the geological reality guide field, i.e., the location of the broken structure transition zone. According to the weight adjustment rules, the interpolation weight of the sample point located inside the weak altered zone would be significantly reduced, and the interpolation weight of the sample point located inside the hard granite mass would be significantly increased. As a result, the interpolation result of the interpolation point would be closer to the sample point located inside the hard granite mass, and further away from the sample point located inside the weak altered zone. The guiding field path integral value of the path is increased, thereby causing the penalty factor to decrease, and the weight of the altered zone sample point is greatly reduced. This mechanism resolves the contradiction between the requirement for global smoothness and the requirement for boundary sharpening of geological structures in spatial interpolation. It does not change the mathematical kernel of the interpolation algorithm, but changes the way the algorithm acts in space by guiding external physical information, so that the algorithm maintains continuity within the lithology unit, and exhibits discontinuity when crossing the boundary defined by the guiding field. In the final output three-dimensional geological model, the originally smooth mathematical fitting surface is replaced by a separate broken structure transition zone geological entity with a clear spatial range and geometric shape. The spatial position of this entity is consistent with the actual collapse and water gushing areas in subsequent tunnel excavation, thereby providing a decision basis consistent with the engineering reality for slope stability analysis and support design scheme formulation.

[0044] Furthermore, after the geometric boundary of the broken structure transition zone geological entity is determined, the system further performs analysis of the physical property differences within the rock mass. Specifically, the system extracts the parameter segments of all drill holes that pass through the broken structure transition zone entity, and calculates the variance of the drill tool torque in each segment. These variance values distributed along the drill hole path are taken as new discrete sample points, and a continuous torque variance attribute field is independently generated within the geometric model of the entity through three-dimensional spatial interpolation. In the final visualization model, this attribute field is used to control the color rendering inside the model, where the areas with high torque variance values are rendered in red, and the areas with low torque variance values are rendered in blue. This visualization result enables engineers not only to identify the spatial range of the transition zone, but also to intuitively identify the core section with the highest degree of fragmentation within the transition zone, thereby providing more refined partitioning basis for the design of key parameters such as anchor rod density and depth in subsequent rock anchor support.

[0045] Example 2: To objectively verify the effectiveness of the technical scheme of the present application in improving the geometric accuracy of the geological model, the following numerical simulation test was designed and performed. The purpose of the test is to quantitatively compare the spatial position error of the model constructed by the method of the present application and the model constructed by the traditional method in restoring the known geological discontinuous interface. The test platform is based on a three-dimensional numerical calculation environment, in which a digital geological reference model with a size of 500m x 500m x 500m is constructed. The model contains two lithologies: one is the background country rock, and the other is a tilted plate-shaped hard rock intrusion defined by the plane equation z = 0.5x + 100, which penetrates the entire model. The upper and lower interfaces of the intrusion are the true geological boundaries that need to be accurately reconstructed in this test. In the geological reference model, 20 virtual drill holes with random spatial positions but uniform overall distribution are arranged. The system performs data simulation sampling along each virtual drill hole path to generate two data sets: the first set is discrete geological sample point data, i.e., lithology information recorded every 1.0m along the drill hole path, and the second set is continuous drilling process parameter data. The generation rule is that in the background country rock, the reference values of the drilling rate ROP and torque T are set to 15m / h and 2000Nm respectively, and in the hard rock intrusion, they are set to 5m / h and 6000Nm respectively. Gaussian noise with a mean of zero and a standard deviation of 5% of the reference value is superimposed on the two reference value sequences to simulate data fluctuations in real working conditions. Based on the two data sets, two test groups are set up, namely the control group and the test group. The control group only uses discrete geological sample point data and uses the standard inverse distance weighted method for three-dimensional spatial interpolation to construct a geological model. The test group first generates a geological reality guide field according to the specific embodiment procedure using continuous drilling process parameter data, and then applies the guide field for weight penalty adjustment when interpolating the same discrete geological sample points using the same inverse distance weighted method.

[0046] After the two test groups generate corresponding three-dimensional geological models respectively, 10 spatially fixed detection points are preset on the real geological boundary plane, the normal position error of the corresponding boundary constructed by the two models at these detection points is calculated, that is, the shortest distance from the model boundary point to the real boundary plane, the test results show that the average boundary position error of the model constructed by the control group is 7.93 m, and the error of individual detection points reaches 11.2 m, and the boundary shape generated by the control group appears obvious deformation and deviation in the area far away from the constraint of the drilling data, compared with the control group, the average boundary position error of the model constructed by the test group is 0.39 m, and the error of all detection points does not exceed 0.6 m, and the boundary shape generated by the test group shows consistent and clear linear characteristics with the real boundary plane, the internal mechanism of such data difference lies in that the interpolation process of the control group only depends on the spatial distance of the sample points, which leads to the mathematical fitting of the sparse sample area to be oversmoothed, so as to deviate from the real boundary, while in the test group, the low-field value guided field area generated by the dramatic change of the drilling process parameters provides a spatial constraint for the interpolation algorithm, the weight adjustment mechanism weakens the influence of the sample points across the area, so that the interpolation result changes in high gradient at the boundary, thereby keeping consistent with the position of the real geological boundary; the results of the numerical simulation test this time confirm that under the same discrete sample data conditions, by applying the method of the present application, the geological reality guided field generated by the drilling process data is used to constrain the spatial interpolation, the geometric precision of the geological model constructed in restoring the geological discontinuous interface is significantly improved compared with the traditional interpolation method.

[0047] Embodiment 3: This embodiment combines the method and system for intelligent analysis of geological structure in mining area based on three-dimensional visual modeling Figs. 1 to 3 , and the method and system for intelligent analysis of geological structure in mining area based on three-dimensional visual modeling are described, like Fig. 1As shown, the figure starts with the raw data input, i.e. acquiring the drilling rate and torque along the borehole, which is continuously changing, the data stream is used for two purposes, on one hand, it is used for the online diagnosis of the health status of the drilling tools and the correction of the parameters to compensate for the systematic drift of the parameters caused by the wear of the drilling tools, on the other hand, it enters the potential physical beacon point identification module, which completes the identification by calculating the local rate of change of the drilling parameters and marking the positions exceeding the threshold, at the same time, an independent parameter fingerprint library construction process is carried out, which associates known geological events with the local feature vectors of the drilling parameters, the fingerprint library provides the basis for the subsequent beacon point identification step, i.e. identifying false signals based on the fingerprint library and only retaining real geological discontinuous beacons, these identified effective physical beacon points are further differentiated in their use: first, they are used as sources to generate a geological reality guiding field through spatial distance transformation, second, they are used to construct a hotspot area identification, which uses a kernel density estimation algorithm to identify the dense area of beacon points and outputs a tectonic hotspot area map to provide decision guidance for intensive exploration or engineering design, finally, the geological reality guiding field and discrete geological sample points, such as borehole cores, tunnel logs and other static geometric and attribute data, enter the interpolation weight adjustment step together, according to the guiding field, the weight across the geological boundary is adjusted with a punitive adjustment, thus generating a high-fidelity three-dimensional geological model that integrates the structural morphology and internal attributes of the physical process constraints.

[0048] As shown in Fig. 2 The horizontal axis of the figure is the depth of the borehole, with the unit of m, and the vertical axis is the parameter value, in the figure, the drilling rate ROP is indicated by a solid line, with the unit of m / h, and the torque T is indicated by a dashed line, with the unit of T(×100Nm), as can be seen from the figure, the drilling rate ROP and the torque T remain relatively stable in most of the depth interval, but near the depths of about 30m and 66m, the drilling rate ROP decreases significantly, and at the same time, the torque T rises sharply, this dramatic change in parameters indicates that the drilling tools have encountered a geological body with significantly different properties from the surrounding rock, and these dramatic change points are the objects to be captured and marked by the potential physical beacon point identification step.

[0049] As shown in Fig. 3As shown, the system architecture is composed of four parts, the drilling process data acquisition unit inside the field drilling equipment, which sends real-time data stream to the edge computing node, which contains the drilling tool health state diagnosis module and the data real-time preprocessing module, and uploads the preprocessed data to the cloud data and model server, which is the core of the system, which deploys intelligent analysis computing engine and unified data storage inside, where the intelligent analysis computing engine includes parameter fingerprint library construction module, potential / effective beacon point identification and discrimination module, guide field generation and weight adjustment module, and hot spot area identification module, while the unified data storage manages the original drilling database, parameter fingerprint library and three-dimensional geological model library, finally, the engineer workstation interacts with the server through the model request and task issuing mode through the three-dimensional visualization and analysis software and task management and calibration interface carried by it, to execute specific analysis tasks and obtain model results.

[0050] Before applying the method of the present application to a new mine area geological modeling project, a set of systematic calibration and verification procedures need to be performed to match the core algorithm parameters with the specific geological and engineering conditions of the target mine area. The procedure aims to quantitatively set the global reference threshold for identifying potential physical beacon points and the penalty factor k for adjusting interpolation weights, while verifying the parameter fingerprint library's ability to distinguish between common drilling process artifacts and real geological discontinuity signals in the mine area. To do this, the engineer first selects 3 to 5 drill holes in the mine area that have completed drilling and have complete core geological logging and drilling engineering logs. The selection criteria for these drill holes require that they must pass through the main lithological units and their contact zones in the mine area, and the engineering logs must record two or more typical drilling process artifact events such as stuck drill or parameter abnormalities caused by drill tool wear. After the initial state definition is complete, the calibration procedure is started. The system first collects all continuous drilling process parameters for these calibration drill holes and aligns them with the core geological logging and engineering logs. In this way, the system obtains a set of hundreds of parameter signal samples with clear event labels, where each sample is labeled as a real geological discontinuity or a specific engineering artifact type.

[0051] Based on the sample set, the system performs the construction and verification of the parameter fingerprint library, that is, the local feature vector of each event label is extracted at the position, and the distribution and class separability of the vectors in the multi-dimensional feature space are analyzed to confirm that the selected features can effectively separate signals of different causes. In other words, in order to determine the global reference threshold, the system calculates the local variation rate of all sample points labeled as real geological discontinuity to form a distribution, and also calculates the local variation rate of all other sample points, including background noise and engineering artifacts, to form another distribution. The global reference threshold is set at a value point in the overlapping region of the two distributions that can make the recognition rate of real discontinuity greater than 95% and the misjudgment rate of engineering artifacts less than 5%; for the penalty factor k in the weight adjustment procedure, the calibration process is to use the determined effective physical beacon points to generate a geological reality guide field in a local three-dimensional space containing a known complex boundary, and repeatedly perform spatial interpolation modeling under a series of increasing k values covering the range of 0.1 to 10.0. By geometrically comparing the model boundary generated by each k value with the real boundary of the calibration sample, the k value that minimizes the average geometric deviation between the model boundary and the real boundary is finally selected as the working parameter of the mine area; after completing the above series of calibration steps, the newly built parameter fingerprint library dedicated to the mine area, as well as the quantitatively determined global reference threshold and penalty factor k, are solidified as system configuration files, providing a set of verified and locally adapted algorithm operation basis for all subsequent intelligent analysis tasks of geological structures in the mine area.

[0052] In another implementation scenario of the method of the present application, for the problem of drilling trajectory deflection commonly existing in deep hole drilling, in order to eliminate its influence on the geometric accuracy of the final model, the system performs a spatial position correction procedure based on the geological marker layer before generating the geological reality guide field. The procedure first presets one or more parameter fingerprints of the geological marker layer that is stable in lateral distribution in the mine area in the system according to regional geological data, then the system uses the parameter fingerprint library that has been constructed to automatically identify the reference beacon points that match the fingerprint of the geological marker layer among all the identified effective physical beacon points, and based on the design three-dimensional coordinates of these reference beacon points, generates the theoretical reference surface of the geological marker layer through surface fitting algorithm. Subsequently, the system calculates the deviation between the design depth of each reference beacon point and the depth of the theoretical reference surface at the corresponding plane position, and constructs a three-dimensional depth deviation field through spatial interpolation of all deviation values. Finally, the system compensates and corrects the spatial coordinates of all effective physical beacon points, especially the depth coordinates, according to the depth deviation field, thereby obtaining a set of beacon points that have been spatially position corrected for subsequent guide field generation.

[0053] After obtaining the above-mentioned set of effective physical beacon points which have been corrected in spatial position, the system can also perform a task of identifying and dividing complex structures in parallel; the task takes the three-dimensional spatial positions of all the corrected effective physical beacon points as input data, uses a kernel density estimation algorithm to generate a beacon point spatial density field in the entire three-dimensional modeling space, the field value of any point in the density field represents the density of effective physical beacon points in a unit volume around the point, and then by setting a density threshold, the regions in the density field whose field values are higher than the threshold are identified as structure hotspot regions, which intuitively reflect the spatial range where geological structures are most developed and lithology changes most frequently, and the identification results can be used as an independent data layer and superimposed on the final three-dimensional geological structure model to provide decision support for subsequent exploration engineering deployment or mining design.

[0054] In a continuously running deep drilling operation scenario, when the drill tool is passing through a thick layer of homogeneous granite, the drill bit wear state gradually changes due to long-term continuous cutting, which in turn causes the collected drilling rate and torque parameters to slowly drift regardless of lithology changes. To deal with this potential artifact caused by changes in the data acquisition tool state, the method of the present application starts a set of online drill tool health diagnosis and parameter correction procedures in parallel before performing potential physical beacon point identification.

[0055] The procedure first continuously calculates an index E representing drilling efficiency according to the real-time acquired drilling rate ROP and torque T, where E = ROP / T. The time series of the index is sent to a low-pass filter to filter out short-term fluctuations caused by small internal structural differences in the rock, thereby extracting the long-term trend reflecting drill tool wear. The system monitors the negative slope of the long-term trend, and when the absolute value of the negative slope continuously exceeds a wear judgment threshold set according to historical drill tool replacement data statistics, the system determines that the drill tool is in a worn state. Once the drill tool is in a worn state, a correction module is activated, which calculates a dynamic compensation coefficient according to the decline of the current drilling efficiency index E relative to the initial healthy state reference value, and uses the coefficient to amplify or reduce the correction of the subsequent incoming original drilling rate and torque data. Through this online correction mechanism, the systematic bias introduced by drill tool wear is eliminated from the source data stream, so that the subsequent physical beacon point identification step can be based on a calibrated data basis, avoiding the misinterpretation of the device wear process as a gradual change in geological structure.

[0056] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0057] Finally, it should be noted that the above examples are merely intended to illustrate the technical solutions of the present application and not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for intelligent analysis of geological structures of a mining area based on three-dimensional visualization modeling, characterized in that, The method comprises the following steps: Step a: extracting local feature vectors of drilling process parameters corresponding to each sample point at a sample point position with known geological information, and associating the local feature vectors with the type of geological event at the position to construct a parameter fingerprint library for identifying signal causes; Step b: obtaining drilling rates and torques that vary continuously along the depth of the borehole, calculating the local change rates of the drilling rates and torques within a determined sliding depth window, and marking a position as a potential physical beacon point if the local change rate exceeds a threshold value; Step c: extracting local feature vectors of drilling process parameters at each potential physical beacon point, and identifying them according to the parameter fingerprint library established in step a, and only using potential physical beacon points whose parameter features are associated with true geological discontinuity events as effective physical beacon points; Step d: taking all effective physical beacon points as sources, generating a scalar geological reality guide field in a three-dimensional modeling space through distance transformation; Step e: when interpolating in a three-dimensional space using discrete geological sample points, the weight acting on the interpolated point for each sample point is adjusted in a punitive manner according to the field value of the geological reality guide field on the path connecting the sample point and the interpolated point.

2. The method according to claim 1, wherein, The punitive adjustment of the weight in step e is specifically: multiplying the original weight by a penalty factor to obtain the adjusted weight, the penalty factor is uniquely determined by the path integral of the field value of the geological reality guide field on the path connecting the sample point and the interpolated point, and the penalty factor is a monotonically decreasing function of the path integral value. 3.The mine geological structure intelligent analysis method based on three-dimensional visualization modeling of claim 1, wherein, The threshold value for identifying potential physical beacon points in step b is adaptively adjusted in space; the spatial adaptive adjustment includes: calculating the overall variance of drilling process parameters in each borehole as a regional geological contrast index, generating a threshold modulation field based on the regional geological contrast index of all boreholes, multiplying a global reference threshold value by the field value at the corresponding position of the threshold modulation field to obtain a dynamic threshold value for judgment at the position.

4. The method according to claim 1, wherein, The local feature vectors in steps a and c are a multi-dimensional vector containing the mean, variance and normalized gradient of drilling process parameters within a depth window at the corresponding position, and the identification of the parameter fingerprint library is achieved by calculating the vector distance between the local feature vector to be identified and the local feature vectors stored in the library, and classifying it to the geological event type with the smallest distance.

5. The method according to claim 1, wherein, The field value of any point in the geological reality guide field in step d is defined as the Euclidean distance from the point to the nearest effective physical beacon point in space.

6. The method according to claim 1, wherein, Further comprising a correction step of borehole trajectory deviation between steps c and d, the correction step includes: identifying reference beacon points corresponding to one or more laterally stable geological marker layers from all effective physical beacon points according to the parameter fingerprint library, fitting a theoretical reference surface of the geological marker layer based on the design coordinates of the reference beacon points, calculating the deviation between the design depth of each reference beacon point and the corresponding depth of the theoretical reference surface, and interpolating to generate a depth deviation field, and correcting the spatial coordinates of the effective physical beacon points according to the depth deviation field.

7. The method according to claim 1, wherein, Further comprising the following steps: Extracting drilling process parameters within each borehole segment defined by the adjacent valid physical beacon points identified in step c, calculating statistical characteristic values of drilling process parameters within each borehole segment, and performing three-dimensional spatial interpolation based on the statistical characteristic values, an additional continuous attribute field representing the difference in physical properties within the rock mass is generated inside the geological structure model independently of the generation of the geological reality guide field.

8. The method according to claim 1, wherein, Also included is the step of performing in parallel the following steps: calculating in real time an indicator E representing drilling efficiency based on the rate of penetration and the torque, wherein ROP is the rate of penetration, T is the torque; low-pass filtering the time series of the drilling efficiency indicator E to extract its long-term trend, and determining that the drilling tool is in a worn state when the negative slope of the long-term trend exceeds a wear determination threshold determined based on historical data, and compensating the rate of penetration and the torque obtained in step b according to this state.

9. The method according to claim 1, wherein, Further comprising a step of identifying a hot spot area after step c, the identifying step comprising: based on the three-dimensional spatial position set of all valid physical beacon points, generating a beacon point spatial density field in the three-dimensional modeling space using a kernel density estimation algorithm, and identifying the area in the beacon point spatial density field where the field value is higher than a determined density threshold as the hot spot area.

10. A three-dimensional visualization modeling-based intelligent analysis system for geological structures of a mining area, characterized in that, Comprise: A parameter fingerprint library construction module for extracting local feature vectors of drilling process parameters corresponding to each sample point at a known geological information sample point position, and associating the local feature vectors with the geological event type at the position to construct a parameter fingerprint library for signal origin discrimination; A potential beacon point identification module for obtaining continuously varying drilling rate and torque along the borehole depth, calculating the local variation rate of drilling rate and torque within a determined sliding depth window, and marking the position where the local variation rate exceeds the threshold as a potential physical beacon point; A beacon point discrimination module for extracting local feature vectors of drilling process parameters at each potential physical beacon point, and discriminating according to the parameter fingerprint library, only using potential physical beacon points whose parameter characteristics are associated with real geological discontinuity events as valid physical beacon points; A guide field generation module for taking all valid physical beacon points as sources to generate a scalar geological reality guide field in the three-dimensional modeling space through distance transformation; A weight adjustment module for adjusting the weight of each sample point acting on the interpolated point when performing three-dimensional spatial interpolation using discrete geological sample points, according to the field value of the geological reality guide field on the path connecting the sample point and the interpolated point.

Images