Coal mine geologic model dynamic updating method based on drilling data and related equipment

Abstract

The invention relates to the technical field of geological data processing and prediction, and provides a coal mine geological model dynamic updating method based on drilling data and related equipment. The method comprises the following steps: acquiring drilling data generated by an intelligent drilling machine in a drilling process, and carrying out preprocessing and feature extraction to generate a drilling response sequence taking a drilling depth as an index; performing data analysis to generate a geological response feature vector composed of a plurality of statistical features; performing data analysis and sampling processing on the geological response feature vector through a multilayer Fourier neural operator to generate an initial calculation result; according to the method, the continuity and the consistency of results are optimized through a sequence re-calibration technology, a virtual geological section with high credibility is generated, and finally, accurate and incremental model updating is only performed on a local space region influenced by drilling based on the section, so that the updating efficiency is greatly improved while the accuracy is ensured, the geological model can dynamically evolve along with drilling, and the drilling efficiency is improved. And the urgent demand of a production site on real-time geological information is met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological data processing and prediction, in particular to a coal mine geological model dynamic updating method based on drilling data and related equipment. BACKGROUND

[0002] With the continuous advancement of intelligent mine construction, transparent geology gradually becomes an important foundation for ensuring the safe and efficient mining of coal mines. At present, the three-dimensional geological model of a coal mine is mainly constructed based on drilling, geophysical prospecting and other data obtained during the exploration stage. Such data is usually sparse in spatial distribution, which limits the accuracy of the geological model and prolongs the model updating cycle. In actual production, as the roadway is excavated or the working face is advanced, small faults, changes in coal seam thickness or weak parting and other geological structure changes that were not accurately predicted during the exploration stage are often encountered. Due to the lag in updating the existing geological model, the above local geological changes cannot be reflected in a timely manner, which can adversely affect on-site construction decisions and safety production.

[0003] In recent years, intelligent drilling rigs have been widely used in coal mines, and they can collect various drilling data in real time during drilling. However, the utilization of drilling data in existing technologies is mostly focused on data display, record storage or simple threshold alarm, and there is no systematic method that can effectively combine real-time drilling data with three-dimensional geological models. At the same time, traditional three-dimensional geological models are usually large in size, and when new geological information is introduced, the model often needs to be reconstructed or updated on a large scale, which is computationally expensive and inefficient, making it difficult to meet the real-time and local fine-grained updating needs of geological information in the production process. SUMMARY

[0004] The present application provides a coal mine geological model dynamic updating method based on drilling data and related equipment, which can at least partially solve the problem of low updating efficiency of local three-dimensional geological models in coal mines, and meet the real-time and local fine-grained updating needs of geological information in the production process.

[0005] Other characteristics and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the present application.

[0006] According to an aspect of the present application, a coal mine geological model dynamic updating method based on drilling data is provided, comprising: obtaining drilling data generated by an intelligent drilling rig during drilling; pre-processing and feature extraction of the drilling data to generate a drilling response sequence indexed by drilling depth; data analysis of the drilling response sequence to generate a geological response feature vector composed of multiple statistical features; data analysis and sampling processing of the geological response feature vector by a multi-layer Fourier neural operator to generate an initial calculation result; recalibration of the initial calculation result to generate a virtual geological profile corresponding to each drilling depth along the borehole trajectory; updating of a local spatial region affected by the current drilling activity based on the virtual geological profile to generate a coal mine geological model.

[0007] In the present application, based on the foregoing scheme, the drilling data includes drilling pressure, drilling torque, drill pipe rotation speed, pump pressure and drilling depth generated at each sampling time.

[0008] In the present application, based on the foregoing scheme, the pre-processing and feature extraction of the drilling data to generate a drilling response sequence indexed by drilling depth comprises: representing the drilling data as a signal vector of a multi-dimensional drilling response varying with time; smoothing the parameter components in the signal vector to generate a first signal; mapping the first signal to a drilling response sequence indexed by drilling depth based on the mapping relationship between drilling time and drilling depth.

[0009] In the present application, based on the foregoing scheme, the data analysis of the drilling response sequence to generate a geological response feature vector composed of multiple statistical features comprises: combining the drilling data to generate an original feature vector; calculating the statistical features of each parameter in the drilling response sequence under a preset depth window scale; generating drilling energy features and energy change amounts at a preset depth based on each parameter in the drilling response sequence; combining the original feature vector, the statistical features, the drilling energy features and the energy change amounts to generate a geological response feature vector.

[0010] In the present application, based on the foregoing scheme, the data analysis and sampling processing of the geological response feature vector by a multi-layer Fourier neural operator to generate an initial calculation result comprises: layer-by-layer transformation of the geological response feature vector by a multi-layer Fourier neural operator to generate intermediate features; inputting the intermediate features into a pre-trained geological attribute operator inference model to output continuous prediction results representing geological attributes; sampling the continuous prediction results based on a preset drilling depth to generate an initial calculation result.

[0011] In this application, based on the aforementioned scheme, the step of recalibrating the initial estimation results to generate virtual geological profiles corresponding to each drilling depth along the borehole trajectory includes: sorting and combining the initial estimation results according to the increasing drilling depth to generate a depth sequence; encoding and linearly projecting the depth sequence to generate sequence-aware features; and linearly projecting the sequence-aware features to generate recalibrated results corresponding to each drilling depth, which serve as virtual geological profiles along the borehole trajectory.

[0012] In this application, based on the aforementioned scheme, the step of updating the local spatial region affected by the current drilling activity based on the virtual geological profile to generate a coal mine geological model includes: determining the local spatial region affected by the current drilling activity based on the spatial location in the three-dimensional geological model and the sequence of spatial sampling points formed along the drilling trajectory; and incrementally updating the local spatial region based on the virtual geological profile to generate a coal mine geological model.

[0013] In this application, based on the aforementioned scheme, after updating the local spatial area affected by the current drilling activity based on the virtual geological profile to generate a coal mine geological model, the method further includes: using the coal mine geological model as a new prior model, and iteratively updating the prior model based on the newly generated virtual geological profile during subsequent drilling processes.

[0014] According to one aspect of this application, a dynamic updating device for a coal mine geological model based on drilling data is provided, comprising: The acquisition module is used to acquire drilling data generated by the intelligent drilling rig during the drilling process; The extraction module is used to preprocess and extract features from the drilling data to generate a drilling response sequence indexed by the drilling depth. The statistics module is used to perform data analysis on the drilling response sequence and generate a geological response feature vector composed of multiple statistical features; The estimation module is used to perform data analysis and sampling processing on the geological response feature vector through multi-layer Fourier neural operators to generate initial estimation results; The calibration module is used to recalibrate the initial calculation results and generate virtual geological profiles corresponding to each drilling depth along the borehole trajectory. The update module is used to update the local spatial area affected by the current drilling activity based on the virtual geological profile, and generate a coal mine geological model.

[0015] According to one aspect of this application, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method for dynamically updating a coal mine geological model based on drilling data as described in the above embodiments.

[0016] According to an aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method for dynamically updating a coal mine geological model based on drilling data as described in the above embodiments.

[0017] According to an aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, causing the computer device to perform the method for dynamically updating a coal mine geological model based on drilling data provided in the various optional implementation manners described above.

[0018] The difference and technical effect of the technical solution of the present application compared with the prior art are mainly in the following aspects: On the one hand, the real-time drilling data of the intelligent drilling machine is directly inputted, the geological information acquisition process is moved to the drilling process, the traditional static modeling completed after drilling is changed to dynamic perception and updating while drilling based on the industrial Internet of Things, the three-dimensional geological model can continuously follow the mining operation progress, and the timeliness of the geological information is significantly improved. By adaptively determining the drilling influence range, only the local geological area affected by the drilling activity is incrementally updated, and repeated reconstruction of the global geological model is avoided, thereby effectively reducing the computational complexity and resource consumption while ensuring the model accuracy, and meeting the actual needs of fast response and lightweight calculation in the underground production environment.

[0019] On the other hand, by introducing the drilling response-geological attribute modeling method based on artificial intelligence deep learning, the nonlinear correlation between the drilling data and the geological attribute is automatically mined, the intelligent inference and evaluation of the geological attribute are realized, the dependence on artificial experience interpretation is reduced, and the objectivity, consistency and repeatability of the geological prediction result are improved. By taking each local geological model update result as the prior basis for subsequent drilling and model correction, a closed-loop updating process is formed, the three-dimensional geological model can continuously absorb new drilling observation information, gradually approach the real geological structure, and enhance the adaptability of the model in complex geological conditions.

[0020] The technical solution of the present application can provide real-time and fine local geological transparent expression within the scope of the mining working face, intuitively present key geological information such as faults, coal thickness changes and lithology mutations, provide reliable basis for gas extraction hole layout, roadway support design and mining process adjustment, directly serve on-site construction decision-making and safety production management, and help to improve the safety level and comprehensive management efficiency of coal mine production.

[0021] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application, as claimed. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and serve to explain the principles of the application. It is readily apparent to one skilled in the art that the following description of the drawings is merely exemplary and that other drawings can be utilized in conjunction with the description below to further illustrate the principles of the application.

[0023] Figure 1 A flow chart of a method for dynamically updating a coal mine geological model based on drilling data is schematically shown in one embodiment of the application.

[0024] Figure 2 A flow chart of a method for dynamically updating a coal mine geological model based on drilling data is schematically shown in one embodiment of the application.

[0025] Figure 3 A flow chart of a method for dynamically updating a coal mine geological model based on drilling data is schematically shown in one embodiment of the application.

[0026] Figure 4 A flow chart of a method for dynamically updating a coal mine geological model based on drilling data is schematically shown in one embodiment of the application.

[0027] Figure 5 A structural schematic diagram of a computer system of an electronic device suitable for implementing embodiments of the application is shown. DETAILED DESCRIPTION

[0028] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example implementations to those skilled in the art.

[0029] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the

[0030] It should be noted that the data acquisition or information collection in the embodiment is performed after authorization by the user or the collection object, and the process and purpose thereof strictly follow relevant regulations.

[0031] The block diagrams shown in the drawings are merely functional entities, which do not necessarily correspond to physically independent entities. That is, the functional entities can be implemented in the form of software, or in one or more hardware modules composed of intelligent chips, intelligent integrated circuits or application-specific integrated circuits (ASIC), or in different network and / or processor devices and / or microcontroller devices.

[0032] The flowcharts shown in the drawings are merely illustrative, and do not necessarily include all contents and operations / steps, nor are they necessarily executed in the described order. For example, some operations / steps can be further decomposed, and some operations / steps can be combined or partially combined, so that the actual execution order can be changed according to actual conditions.

[0033] The implementation details of the technical solutions of the present application are described in detail as follows: Figure 1 A flowchart of a coal mine geological model dynamic updating method based on drilling data according to an embodiment of the present application is shown. Referring to Figure 1 The coal mine geological model dynamic updating method based on drilling data includes at least steps S110 to S160, which are described in detail as follows: S110, acquiring drilling data generated by the intelligent drilling rig in the drilling process.

[0034] In the embodiment, the intelligent drilling rig system deployed in the underground mining face of the coal mine is used to achieve the above. The intelligent drilling rig system integrates a high-precision sensor array, an edge computing unit and a data communication module, which are used to synchronously and continuously collect multi-dimensional drilling data reflecting the interaction state between the drilling rig and the stratum during the process of breaking the stratum by the drill bit, to form the original data source for the geological model dynamic updating, as the drilling data.

[0035] The technical solutions of the present application can be used in new technical services in the fields of coal mines, petroleum and the like, such as mineral geological exploration services using high technologies, and other natural science research and experimental development.

[0036] Specifically, the drilling data in the embodiment includes but is not limited to drilling pressure, drilling torque, drill pipe rotating speed, pump pressure and drilling depth data generated at each sampling time. The above collected drilling data can be stored as industrial big data to the cloud platform, to realize the storage and management of the industrial big data.

[0037] Specifically, the sensor array equipped on the intelligent drilling rig includes: a bit pressure sensor installed on the feed mechanism for measuring the axial pressure (F) of the drill bit in real time; a torque sensor (T) and a rotation speed encoder (RPM) integrated in the rotary power head for measuring the driving torque and the rotation speed of the drill pipe, respectively; a pump pressure sensor (P_p) arranged on the flushing fluid circulation pipeline for monitoring the pressure in the hole; and a depth measurement unit (D) connected to the feed device for accurately recording the real-time drilling depth of the drill bit from the hole mouth. Preferably, the system can also obtain the rate of penetration (ROP) through the differentiation of the depth signal or direct measurement.

[0038] During the drilling operation, each intelligent sensor synchronously collects analog signals at a preset fixed sampling frequency (for example, 10 Hz to 100 Hz) through the built-in sensor chip. After being amplified and preliminarily filtered by the on-board signal conditioning circuit, the signals are converted into digital signals by an analog-to-digital converter. The edge computing controller built in the intelligent drilling rig receives the data of each channel, aligns and packs them based on a unified time reference, and forms an original drilling data vector x_raw(t) = [F(t), T(t), RPM(t), P_p(t), D(t),...] organized in sequence according to the sampling time (t).

[0039] Subsequently, the edge computing unit sends the packed real-time data stream to the data aggregation node located in the underground centralized control station or the ground server through the mine industrial ring network or the special wireless transmission link. The data transmission process adopts a reliable communication protocol or communication mechanism, such as an Internet of Things security communication protocol or an industrial Internet-based security communication protocol, to ensure the integrity, timing, and low latency of the data.

[0040] Before the data is used by subsequent steps, the system performs preliminary data quality control, including but not limited to: parameter value range verification based on physical mechanism, monotonicity check of drilling depth sequence, and labeling and filtering of instantaneous abnormal values. The data stream that passes the quality control is stored in a time series database and provides a standardized access interface for the subsequent data preprocessing and feature extraction module.

[0041] Through the above implementation, the present application ensures that the multi-dimensional drilling data stream representing the mechanical properties of the formation can be obtained in real time and reliably, providing an accurate and continuous data input basis for subsequent data-driven dynamic inference of geological properties and model updating.

[0042] S120, pre-processing and feature extraction are performed on the drilling data to generate a drilling response sequence indexed by drilling depth.

[0043] In the embodiment, the real-time collected drilling data is preprocessed and feature extracted to construct a standardized drilling response sequence indexed by drilling depth. Specifically, the multi-dimensional drilling response signal varying with time is subjected to smoothing filtering processing to suppress transient noise caused by equipment disturbance or sensor abnormality and retain persistent change trend reflecting formation characteristics; then the processed signal is converted from time domain to depth domain according to the mapping relationship between drilling time and drilling depth, and is aligned to uniform depth interval through resampling, and finally a drilling response sequence continuous, consistent and having clear spatial orientation along the drilling depth direction is formed, providing a structured input data basis for subsequent analysis and extraction of geological response features.

[0044] In an embodiment of the present application, the drilling data is preprocessed and feature extracted to generate a drilling response sequence indexed by drilling depth, comprising: representing the drilling data as a signal vector of multi-dimensional drilling response varying with time; smoothing the parameter components in the signal vector to generate a first signal; mapping the first signal to a drilling response sequence indexed by drilling depth based on the mapping relationship between drilling time and drilling depth.

[0045] In the process of coal mine drilling operation, the intelligent drilling rig deployed in the downhole is used to collect drilling pressure multi-source drilling data in the drilling process. The drilling data reflects the mechanical and motion state in the process of interaction between the drill bit and the formation, which is directly affected by geological factors such as formation lithology, structural integrity and fragmentation degree. Therefore, the drilling data collected in the drilling process is represented as a signal vector of multi-dimensional drilling response varying with time for: wherein, represents the sampling time of the drilling data; represents the drilling pressure at time ; represents the drilling torque at time ; represents the rotation speed of the drill pipe at time ; represents the mechanical drilling speed at time ; represents the pump pressure at time ; represents the drilling depth corresponding to the drill bit at time .

[0046] In actual drilling process, drilling data is not only affected by formation conditions, but also interfered by non-geological factors such as equipment start-stop, operation adjustment and sensor transient abnormality. In order to avoid the interference of the above non-geological disturbance on subsequent geological response analysis, the robust signal modeling algorithm is introduced to preprocess the drilling response signal. In the time window , any drilling data component is smoothed by using the median-mean joint filtering method to obtain the first signal : Wherein, represents the original value of the first drilling data at time ; represents the filtered robust drilling data, i.e. the first signal; represents the time window centered at time ; represents the median value operation in the window; represents the mean value operation in the window; is a weighting coefficient for balancing the influence of median filtering and mean filtering. Through the above processing, the transient abnormal change caused by non-geological factors can be effectively suppressed, while the persistent drilling response characteristics caused by the change of formation properties are retained. Since the drilling process is gradually advanced along the drilling depth direction, and the geological model is usually constructed based on spatial coordinates, it is necessary to map the drilling response signal in the time domain to the depth domain. Based on the drilling depth signal

[0047] , the mapping relationship between drilling time and drilling depth is constructed as follows: Wherein, the mapping function represents the mapping relationship between drilling time and drilling depth, which is determined by the depth data recorded by the drilling machine in real time. Further, the robust drilling response signal is resampled to a uniform depth step , and the drilling response sequence indexed by depth is constructed as follows: Wherein, represents the drilling depth, i.e. the k-th discrete drilling depth position, and k represents the identification of the drilling depth; represents the inverse mapping of the mapping function ; represents the drilling response signal vector corresponding to the depth , i.e. the drilling response sequence. ​​

[0048] Through the above real-time drilling data stream acquisition and signal processing steps, standard drilling timing data with unified structure, time and space alignment are formed, providing a stable data basis for subsequent drilling response feature characterization and geological change perception.

[0049] S130, data analysis is performed on the drilling response sequence to generate a geological response feature vector composed of multiple statistical features.

[0050] In this embodiment, by performing multi-dimensional analysis on the drilling response sequence indexed by drilling depth, a geological response feature vector that can comprehensively reflect the formation characteristics is constructed. First, the drilling parameters are directly combined to form an original feature vector to retain the real-time state information of drilling; then, under multiple preset depth window scales, the mean, variance and other statistical features of each parameter are calculated to depict the sustained change trend of the formation structure at different spatial scales; at the same time, based on the drilling parameters, the drilling energy features per unit depth and their changes along the depth direction are calculated to represent the absolute size and relative mutation of the formation drilling resistance; finally, the original features, multi-scale statistical features, drilling energy features and their changes are fused to form a unified high-dimensional geological response feature vector, thereby providing an intelligent inference model with sensitive geological change and rich information input features.

[0051] In an embodiment of the present application, data analysis is performed on the drilling response sequence to generate a geological response feature vector composed of multiple statistical features, including: combining the drilling data to generate an original feature vector; calculating the statistical features of each parameter in the drilling response sequence under a preset depth window scale; based on each parameter in the drilling response sequence, generating drilling energy features and energy changes at a preset depth; combining the original feature vector, the statistical features, the drilling energy features and the energy changes to generate a geological response feature vector.

[0052] In this embodiment, based on the robust and depth-aligned drilling response sequence obtained by the foregoing steps, drilling response features that can sensitively reflect changes in the physical and mechanical properties of the formation are further constructed to represent the differences in drilling behavior of the drill bit under different geological conditions.

[0053] At drilling depth , the original feature vector generated in the initial drilling process is defined as: wherein, is the original drilling response feature vector at drilling depth , i.e. the original feature vector; respectively represent the robustly filtered WOB, torque, RPM, ROP and pump pressure at depth .

[0054] Considering that different scales of geological structure changes will affect the drilling response at different spatial scales, statistical response features are constructed at multiple depth window scales. In the depth window centered at depth with window length , the statistical features of the th drilling data are calculated as follows: where represents different depth window scales; represents the depth window at the th scale; represents the window length at the corresponding scale; represents the number of sample points in the window; and represent the data before and after processing of the th parameter at depth ; , represent the mean and variance of the th parameter at the scale . By introducing multi-scale statistical features, short-term fluctuations caused by random noise can be effectively distinguished from persistent response changes caused by changes in formation structure.

[0055] To further characterize the relationship between input energy and formation resistance during drilling, the specific energy model in engineering mechanics is introduced to construct the drilling energy feature as follows: where represents the specific energy at depth , i.e., the energy feature; represents the effective cross-sectional area of the drill bit, which is used to normalize the energy to unit area and eliminate the influence of drill bit size; , , , represent the WOB, torque, RPM and ROP at the corresponding depth, respectively.

[0056] Then, the energy change of specific energy at adjacent depths is calculated as: where ​This represents the change in specific energy between adjacent depth locations, reflecting abrupt changes in formation resistance. A significant increase in energy change usually corresponds to a harder formation, while a significant decrease in energy change usually corresponds to a softer formation.

[0057] Subsequently, the original response characteristics, multi-scale statistical characteristics, and drilling energy characteristics are fused to construct a unified geological response feature vector. for: in, It represents the original drilling response characteristics and reflects real-time drilling behavior; It represents multi-scale statistical characteristics, distinguishing noise from persistent changes in the formation; It represents the characteristics of drilling energy, and is expressed as the absolute and relative changes in formation resistance; Indicates depth The geological change-sensitive feature vector is used as input for subsequent dynamic inference of geological attributes and local geological model update algorithms.

[0058] By using the above-mentioned real-time characterization method of geological change sensitive features (geological response feature vector), the original drilling signal is transformed into a multi-level feature representation that is sensitive to geological changes, providing high-quality input features for subsequent preliminary inference models of geological attributes and sequence recalibration inference networks.

[0059] S140, the geological response feature vector is analyzed and sampled using a multi-layer Fourier neural operator to generate initial calculation results.

[0060] In this embodiment, the geological response feature vector is input into an inference model constructed based on multi-layer Fourier neural operators. This model first performs layer-by-layer nonlinear transformation and information fusion on the input features in the frequency and spatial domains through its multi-layered cascaded operator structure, effectively capturing and modeling the complex, particularly spatially correlated, global mapping relationship between drilling response and geological properties. Then, based on this learned relationship, the model outputs a geological property prediction curve continuously distributed along the borehole depth. Finally, this continuous prediction result is discretely sampled according to the actual drilling depth sequence, thereby generating initial inference results corresponding to each depth point, reflecting lithology or other key geological properties, providing basic inference data for subsequent sequence calibration steps.

[0061] In one embodiment of this application, the geological response feature vector is analyzed and sampled using a multi-layer Fourier neural operator to generate an initial estimation result, including: The geological response feature vector is transformed layer by layer using a multi-layer Fourier neural operator to generate intermediate features; The intermediate features are input into a pre-trained geological attribute operator inference model, which outputs continuous prediction results representing geological attributes. The continuous prediction results are sampled based on a preset drilling depth to generate initial calculation results.

[0062] To achieve rapid initial inference of geological attributes in transparent geological modeling of coal mines, a preliminary inference method based on the Fourier Neural Operator (FNO) is designed, and a pre-trained geological attribute operator inference model is generated. The geological change sensitivity features (geological response feature vectors) calculated in the aforementioned steps are used as the basis for this method. As input, the spatial correlation features of geological data are captured through a global mapping from the frequency domain to the spatial domain, and the initial values ​​and confidence levels of coarse-precise geological attributes are output, providing a basis for subsequent sequence optimization.

[0063] The geological change sensitivity features obtained along the borehole trajectory are considered as multi-channel characteristic functions defined over the continuous drilling depth domain, denoted as... , representing the geological response feature vector The continuous feature field is reconstructed along the depth direction. The complex nonlinear relationship between drilling response features and geological properties is addressed by employing a deep learning-based deep neural network model as the geological property inference function. This model models the overall distribution of geological change-sensitive features along the depth direction, and the mapping relationship is expressed as follows: in, This indicates the continuous prediction results of geological properties along the borehole trajectory; The geological attribute operator inference model is represented by the FNO structure, and its parameter set is as follows: .

[0064] Subsequently, the model internally transforms the input feature field layer by layer through multi-layer FNO operator mapping, then the th The intermediate feature function of the layer is represented as: in, ; and These represent the learnable spectral weight matrix and the bias term, respectively. To represent a non-linear activation function, choose Sigmoid or its equivalent variant. This represents the number of layers in the FNO operator network. Its value can be set according to the complexity of the drilling data and the scale of geological structure changes. The initial value is set to 4.

[0065] in, denotes the Fourier integral operator, which is used to capture the global spatial correlation in the frequency domain, specifically by the following process: wherein, and denote the Fourier transform and inverse Fourier transform, respectively, represents element-wise multiplication.

[0066] Finally, the output layer samples the continuous prediction results of the geological attribute to discrete depth points to obtain the initial inference results of the geological attribute as follows: wherein, denotes the geological change sensitive feature vector at depth ; and is the preliminary inference value of the geological attribute at depth ; and denotes the overall mapping relationship of the FNO model.

[0067] Optionally, considering the continuous distribution characteristics of the geological body in space, a depth direction continuity constraint is introduced in the geological attribute inference process to construct a joint optimization target loss function: wherein, is the true geological attribute; is the predicted inferred geological attribute; denotes the prediction error term; is the continuity constraint weight; is the prediction error term, representing the fitting degree of the model prediction value and the true geological attribute; is the continuity constraint term, which controls the change amplitude of the geological attribute at adjacent depths through the weight to make the results more consistent with the actual stratum distribution.

[0068] Optionally, the feature change rate is calculated as: wherein, when greater than a preset threshold, it is determined that the position is a potential geological mutation point, which is used as a reference to perform subsequent local model partition update.

[0069] Finally, the geological attribute set G on the drilling trajectory is obtained as: wherein, is the geological attribute set on the drilling trajectory; This is a preliminary inference of the geological properties at the corresponding depth; This represents the confidence level of the corresponding preliminary inference result. The higher the confidence level, the stronger the reliability of the inference. This set is directly used as the core input for sequence recalibration, providing basic constraints for accurate correction.

[0070] S150, the initial calculation results are recalibrated to generate virtual geological profiles corresponding to each drilling depth along the borehole trajectory.

[0071] In this embodiment, the initial inference results generated in the aforementioned steps, distributed along the depth, are organized into a complete sequence according to their corresponding drilling depths in ascending order. This sequence simultaneously includes the attribute inference values ​​and their confidence information for each depth point. Subsequently, a recalibrated inference network based on an advanced sequence modeling architecture is used to encode and perform depth analysis on this sequence. This network can efficiently model and utilize the long-range dependencies and spatial continuity of geological attributes along the borehole trajectory to globally optimize and context-awarely correct the initial inference results. The network progressively extracts and fuses the correlation features between different depth points through its core sequence processing layer, generating an enhanced sequence-aware representation. Finally, this representation is linearly projected, directly outputting the precisely corrected geological attribute values ​​at each drilling depth, thereby forming a set of spatially continuous, logically consistent, and highly reliable virtual geological profiles, serving as the core constraint data driving the incremental updates of the local geological model.

[0072] In one embodiment of this application, the initial calculation results are recalibrated to generate virtual geological profiles corresponding to each drilling depth along the borehole trajectory, including: The initial calculation results are sorted and combined according to the increasing drilling depth to generate a depth sequence; The depth sequence is encoded and linearly projected to generate sequence-aware features; Linear projection is performed on the sequence sensing features to generate recalibration results corresponding to each drilling depth, which serve as virtual geological profiles along the borehole trajectory.

[0073] To correct potential local abrupt changes and sequence inconsistencies in preliminary inference results, and to fully utilize the long-range dependence and evolutionary continuity of geological attributes along the borehole depth direction, a recalibrated inference network based on the Mamba state-space structure, GeoMamba, is proposed. This network accurately calibrates the preliminary inference sequence, achieves global context modeling of long sequences with linear computational complexity, and outputs geological attribute results with high consistency and high reliability.

[0074] First, the preliminary inference set of geological attributes calculated and output in the above steps is as follows: According to drilling depth Organized in ascending order, the resulting multivariable depth sequence S is: wherein, denote the preliminary inferred value and its confidence at the th depth position, respectively; and K denote the identity and total number of depth sampling points, respectively. The depth sequence generated by the above process directly reflects the evolution trend of geological properties with depth and the reliability of the inference.

[0075] After that, the whole encoding is carried out through the attribute embedding encoder (AEE), and the sequence feature of the single branch is: wherein, denotes the attribute encoding, which is used to map the two-dimensional to high-dimensional features; is used for dimension splitting of the high-dimensional features; is used for long-range dependency modeling of the split features; denotes linear projection, which is used to map the output data block of back to a unified dimension; denotes the output feature.

[0076] Secondly, the data blocks are stacked to obtain the final sequence-aware feature is: wherein, the superscripts (1) (2) (3) denote the 1st / 2nd / 3rd layer stacking. For each data block, the core is the Mamba layer, and combined with the residual connection, the long-range dependency of is captured based on the state space model (SSM), while the local enhanced feature is outputted. wherein, and are the current input feature and the state at the previous time , respectively.

[0077] Finally, based on the sequence-aware feature , the re-calibration result of the geological property at the depth is generated through linear projection. is: wherein, The virtual geological profile is a high-credibility geological constraint information, which contains accurate geological attribute data and quantifies the reliability of the data. The virtual geological profile is directly input into the local implicit representation and incremental updating step of the three-dimensional geological model to drive the dynamic correction of the subsequent local transparent geological model.

[0078] Optionally, in order to support adaptive judgment of subsequent local model updating area, the difference between the preliminary inference and the final calibration result is quantified . Among them, The L2 norm difference between the preliminary inference value and the re-calibration inference value is represented, and the greater the value, the more significant the geological attribute correction at the depth.

[0079] Finally, the calibration result and the calibration difference of each depth are mapped to the three-dimensional spatial coordinates of the borehole to form a virtual geological profile along the borehole trajectory, which is a high-credibility constraint for local geological model updating. Among them, The virtual geological profile is a high-credibility geological constraint information, which contains accurate geological attribute data and quantifies the reliability of the data. The virtual geological profile is directly input into the local implicit representation and incremental updating step of the three-dimensional geological model to drive the dynamic correction of the subsequent local transparent geological model.

[0080] S160, based on the virtual geological profile, updating a local spatial area affected by the current drilling activity to generate a coal mine geological model.

[0081] In this embodiment, first, according to the three-dimensional spatial coordinates of each sampling point in the virtual geological profile, a local spatial area affected by the current drilling activity is adaptively determined along the borehole trajectory. The range of the area is dynamically adjusted according to the significant degree of the change of the geological attribute; then, within the local spatial area, the high-credibility geological attribute observation data provided by the virtual geological profile is fused with the prior information of the existing global three-dimensional geological model in the area, and through the introduction of adaptive weights related to spatial distance and observation credibility, the original model is finely and incrementally corrected and updated, while the spatial continuity constraint is applied to ensure the rationality of the updated geological structure; finally, a coal mine geological model reflecting the latest geological cognition is generated, which is only updated in the local spatial area and remains unchanged in the remaining part. The updated model will serve as new prior knowledge for the continuous iterative updating in the subsequent drilling process, thereby forming a dynamic evolution closed loop.

[0082] As Figure 2 shown, in this embodiment, after obtaining the virtual geological profile along the borehole trajectory Afterwards, based on the existing three-dimensional geological model, the virtual geological profile generated in real time during drilling is taken as a new high-confidence geological constraint to construct a local observation correction term, and only the local incremental update is performed on the local update area affected by the current drilling activity. By introducing the locality, incrementality and closed-loop feedback mechanism in the model updating process, the three-dimensional geological model can evolve with the advancement of drilling operation, and finally realize the dynamic transparent expression of the local geological structure of the coal mine. The update result is taken as the prior input in the next round of drilling work.

[0083] In an embodiment of the present application, based on the virtual geological profile, the local spatial area affected by the current drilling activity is updated to generate a coal mine geological model, comprising: determining the local spatial area affected by the current drilling activity based on the spatial position in the three-dimensional geological model and the spatial sampling point sequence formed along the drilling trajectory; incrementally updating the local spatial area based on the virtual geological profile to generate a coal mine geological model.

[0084] The influence of drilling operation on the formation structure has a significant spatial locality feature. First, based on the virtual geological profile the local model area that needs to be updated is adaptively determined, and the spatial sampling point sequence formed along the drilling trajectory is represented as . Among them, is the three-dimensional space position mapped by the drilling geometry information (spatial coordinates and depth , is the plane coordinate, is the depth. Based on the spatial sampling point sequence, the local model update area is defined as the point set satisfying the spatial proximity relationship, and the local spatial area affected by the drilling data is generated : Among them, represents the entire three-dimensional space position set, represents any spatial position in the three-dimensional geological model; is the influence radius corresponding to the depth point , and its size is adaptively set according to the geological attribute change amplitude in the virtual geological profile, the larger the influence radius, the larger the value range is 5~20m, which ensures that the model update coverage range of the geological mutation area is reasonable.

[0085] After determining the local update area, the geological attribute information in the virtual geological profile is mapped to the local three-dimensional space, and the original three-dimensional geological model in the corresponding spatial position the predicted result of the geological attribute of the original three-dimensional geological model at the spatial position is obtained by constructing a difference value On this basis, the geological model in the local spatial region is incrementally updated: wherein, is a three-dimensional spatial coordinate; is an adaptive update weight, the value of which is related to the spatial position distance to the drilling trajectory and the corresponding virtual geological attribute, the closer the distance, the higher the reliability, the greater the weight, which is used to balance the influence of the prior information of the original model and the new observation information; represents the observation correction item provided by the virtual geological profile ; is the predicted result of the geological attribute of the original three-dimensional geological model at the spatial position ; is the result of the geological attribute of the updated three-dimensional geological model in the local spatial region at the spatial position .

[0086] The update process only acts on the local spatial region, while the original model remains unchanged in other regions, thereby realizing local incremental updating. To ensure the rationality and continuity of the updated local geological model in the spatial structure, a spatial consistency constraint is introduced in the local spatial region. Based on the K-nearest neighbor relationship of three-dimensional grids, a spatial adjacency relationship set is constructed in the local spatial region , and a spatial consistency constraint term is defined as: wherein, is the spatial adjacency relationship set constructed based on the K-nearest neighbor relationship of three-dimensional grids in the local spatial region , i.e., a pair of adjacent spatial points in the three-dimensional model; represents the geological attribute of the adjacent spatial points after updating; this spatial consistency constraint term ensures the spatial continuity of the geological attribute in the local spatial region by minimizing the difference between the attributes of adjacent points.

[0087] This constraint is used to suppress non-physical mutations caused by the introduction of local observations, while maintaining the expression ability of real geological structures such as faults and coal thickness changes, and is incorporated into the update objective function as a regularization term to participate in the local model updating process. The updated local geological model is integrated with the original global model in a transparent manner, and the regions with significant changes (above the threshold value) are highlighted, thereby realizing intuitive and visual expression of the local geological structure of the coal mine.

[0088] In addition, in one embodiment of the present application, based on the virtual geological profile, the local spatial area affected by the current drilling activity is updated, and after generating the coal mine geological model, the coal mine geological model is used as a new prior model, and in the subsequent drilling process, the prior model is iteratively updated based on the newly generated virtual geological profile.

[0089] After completing a local geological model update, the updated model results are input into the subsequent drilling process as a new prior model, continuously receiving newly generated virtual geological profile constraint information, and the closed-loop recursive update relationship is represented as: wherein, is the model after the nth update, which is used as prior information; represents the virtual geological profile generated in the new round of drilling process, which is new observation information; represents the updated model by , The update mode composed of the prior model and the new observation information is responsible for fusing the prior model and the new observation information. Through this closed-loop update mechanism, the three-dimensional geological model can continuously absorb new observation information with the advancement of drilling operations, and realize the dynamic evolution process of continuous updating and gradual approximation of the true geological structure.

[0090] The updated local model and the original global geological model are fused and displayed in a unified spatial coordinate system, and the areas with significant changes are highlighted, so that the geological changes revealed during drilling can be intuitively perceived. When key geological conditions such as faults, sudden changes in coal thickness, or significant changes in lithology are detected, corresponding change prompt information is generated to remind relevant personnel to pay attention to potential geological risks. And the update results and change feedback are used as a reference for subsequent drilling operations and continuous updating of the geological model, so that the three-dimensional geological model can be continuously corrected and improved during drilling, thereby forming a dynamic updating closed loop of the local transparent geological model driven by real-time drilling data.

[0091] As Figure 3 shown, taking the roof gas extraction hole of an intelligent drilling rig in a certain coal mine as an example, before online real-time inference is carried out in actual application, a training sample set is constructed through historical drilling data of the mine area and measured geological attribute labels of the core, the historical data is processed according to the signal processing method of subsequent S1 drilling response characteristics, the feature representation method of S2 geological change sensitive features is generated, the historical feature vectors are paired with the corresponding geological attribute labels, and the geological attribute inference model of S3 and the recalibration inference network of S4 are trained respectively; After training, the model is deployed to the downhole edge node to perform S5 local transparent geological model updating. The specific steps are as follows: (1) Drilling data collection: During the drilling operation, the intelligent drilling rig collects drilling data such as drilling pressure, torque, rotation speed, mechanical drilling speed, pump pressure and drilling depth in real time, and forms a continuous drilling data stream.

[0092] (2) Drilling data processing and feature construction: The collected drilling data is filtered, aligned and feature extracted to construct a drilling response feature sequence indexed by drilling depth.

[0093] (3) Dynamic inference of drilling geological properties: Based on the drilling response feature sequence, the geological property inference model is used to dynamically predict the geological properties at different depths along the drilling trajectory, forming a virtual geological profile along the drilling hole.

[0094] (4) Incremental updating of local geological model: The virtual geological profile is introduced as new geological constraint information into the original three-dimensional geological model, and the local updating area is adaptively determined according to the spatial position of the drilling hole. Only the affected local geological model is incrementally updated.

[0095] (5) Local model display and feedback: The updated local geological model is displayed in a lightweight manner, allowing field operators to intuitively obtain the latest geological information and use it as a reference for adjusting subsequent drilling parameters and extraction schemes.

[0096] (6) Model closed-loop iterative updating: The updated geological model is used as a new prior basis to continuously participate in the geological property inference and model updating during subsequent drilling, achieving dynamic closed-loop updating of the three-dimensional geological model as the drilling progresses.

[0097] The technical scheme of the present application obtains drilling data generated by an intelligent drilling rig during drilling; pre-processes and extracts features from the drilling data to generate a drilling response sequence indexed by drilling depth; analyzes the drilling response sequence to generate a geological response feature vector composed of multiple statistical features; analyzes and samples the geological response feature vector using a multi-layer Fourier neural operator to generate an initial calculation result; recalibrates the initial calculation result to generate a virtual geological profile corresponding to each drilling depth along the drilling trajectory; and updates the local spatial area affected by the current drilling activity based on the virtual geological profile to generate a coal mine geological model. By using a neural network operator to mine the complex mapping relationship between data and geological properties, preliminary intelligent inference is achieved, and the continuity and consistency of the results are optimized through sequence recalibration technology to generate a high-credibility virtual geological profile. Finally, based on this profile, only the local spatial area affected by the drilling hole is accurately and incrementally updated, thereby significantly improving the updating efficiency while ensuring accuracy, allowing the geological model to evolve dynamically with drilling, and meeting the urgent need for real-time geological information in the production field.

[0098] The following introduces an embodiment of a coal mine geological model dynamic updating device based on drilling data of the present application, which can be used to execute the coal mine geological model dynamic updating method based on drilling data in the above embodiments of the present application. It can be understood that the coal mine geological model dynamic updating device based on drilling data can be a computer program (including program code) running in a computer device, for example, the coal mine geological model dynamic updating device based on drilling data can install an industrial application software or an industrial control management software to realize industrial cloud computing of industrial big data generated in the drilling exploration production process through the industrial cloud platform thereof; the coal mine geological model dynamic updating device based on drilling data can be used to execute the corresponding steps in the method provided in the embodiments of the present application. For details not disclosed in the embodiment of the coal mine geological model dynamic updating device based on drilling data of the present application, please refer to the above embodiments of the coal mine geological model dynamic updating method based on drilling data of the present application.

[0099] Figure 4 A block diagram of a coal mine geological model dynamic updating device based on drilling data according to an embodiment of the present application is shown.

[0100] Referring to Figure 4 According to an embodiment of the present application, the coal mine geological model dynamic updating device based on drilling data includes: The acquisition module 310 is configured to acquire drilling data generated by the intelligent drilling rig in the drilling process. The extraction module 320 is configured to pre-process and extract features of the drilling data to generate a drilling response sequence indexed by drilling depth. The statistical module 330 is configured to analyze the drilling response sequence to generate a geological response feature vector composed of multiple statistical features. The calculation module 340 is configured to analyze and sample the geological response feature vector by a multi-layer Fourier neural operator to generate an initial calculation result. The calibration module 350 is configured to recalibrate the initial calculation result to generate a virtual geological profile corresponding to each drilling depth along the borehole trajectory. The updating module 360 is configured to update a local spatial region affected by the current drilling activity based on the virtual geological profile to generate a coal mine geological model.

[0101] In the present application, based on the foregoing scheme, the drilling data includes drilling pressure, drilling torque, drill pipe rotating speed, pump pressure and drilling depth generated at each sampling time.

[0102] In the present application, based on the foregoing scheme, the preprocessing and feature extraction of the drilling data generate a drilling response sequence indexed by drilling depth, including: representing the drilling data as a signal vector of a multi-dimensional drilling response varying with time; smoothing the parameter components in the signal vector to generate a first signal; mapping the first signal to a drilling response sequence indexed by drilling depth based on the mapping relationship between drilling time and drilling depth.

[0103] In the present application, based on the foregoing scheme, the data analysis of the drilling response sequence generates a geological response feature vector composed of multiple statistical features, including: combining the drilling data to generate an original feature vector; calculating the statistical features of each parameter in the drilling response sequence under a preset depth window scale; generating drilling energy features and energy change amounts at a preset depth based on each parameter in the drilling response sequence; combining the original feature vector, the statistical features, the drilling energy features, and the energy change amounts to generate a geological response feature vector.

[0104] In the present application, based on the foregoing scheme, the data analysis and sampling processing of the geological response feature vector by the multi-layer Fourier neural operator generates an initial calculation result, including: performing layer-by-layer transformation on the geological response feature vector by the multi-layer Fourier neural operator to generate intermediate features; inputting the intermediate features into a pre-trained geological attribute operator inference model to output continuous prediction results representing geological attributes; sampling the continuous prediction results based on a preset drilling depth to generate an initial calculation result.

[0105] In the present application, based on the foregoing scheme, the recalibration of the initial calculation result generates a virtual geological profile along the borehole trajectory corresponding to each drilling depth, including: sorting and combining the initial calculation result based on the order of increasing drilling depth to generate a depth sequence; encoding and linearly projecting the depth sequence to generate sequence-aware features; linearly projecting the sequence-aware features to generate recalibration results corresponding to each drilling depth as a virtual geological profile along the borehole trajectory.

[0106] In the present application, based on the foregoing scheme, the coal mine geological model is generated by updating the local spatial region affected by the current drilling activity based on the virtual geological profile, including: determining the local spatial region affected by the current drilling activity based on the spatial position in the three-dimensional geological model and the spatial sampling point sequence formed along the drilling trajectory; incrementally updating the local spatial region based on the virtual geological profile to generate a coal mine geological model.

[0107] In the present application, based on the foregoing scheme, after the coal mine geological model is generated by updating the local spatial region affected by the current drilling activity based on the virtual geological profile, the method further comprises: taking the coal mine geological model as a new prior model, and iteratively updating the prior model based on the newly generated virtual geological profile in the subsequent drilling process.

[0108] The technical scheme of the present application comprises the following steps: obtaining drilling data generated by the intelligent drilling rig in the drilling process; preprocessing and feature extraction are performed on the drilling data to generate a drilling response sequence indexed by drilling depth; data analysis is performed on the drilling response sequence to generate a geological response feature vector composed of multiple statistical features; data analysis and sampling processing are performed on the geological response feature vector by a multi-layer Fourier neural operator to generate an initial calculation result; the initial calculation result is recalibrated to generate a virtual geological profile corresponding to each drilling depth along the drilling trajectory; and based on the virtual geological profile, a local spatial region affected by the current drilling activity is updated to generate a coal mine geological model. By using a neural network operator to mine the complex mapping relationship between data and geological properties, preliminary intelligent inference is realized, and the continuity and consistency of the result are optimized by sequence recalibration technology to generate a high-credibility virtual geological profile. Finally, based on the profile, only the local spatial region affected by the drilling is accurately and incrementally updated, thereby greatly improving the updating efficiency while ensuring the accuracy, enabling the geological model to evolve dynamically with the drilling, and meeting the urgent demand for real-time geological information in the production site.

[0109] Figure 5 A structural schematic diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown.

[0110] It should be noted that the computer system of the electronic device in the present embodiment is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0111] The computer system in the present embodiment comprises a central processing unit 401 which can perform various appropriate actions and processes according to programs stored in a read-only memory 402 or loaded into a random access memory 403 from a storage part 408, such as the coal mine geological model dynamic updating method based on drilling data described in the above embodiments. In the random access memory 403, various programs and data required for system operation are also stored to realize big data storage and big data management. The central processing unit 401, the read-only memory 402 and the random access memory 403 are connected to each other through a bus 404. An input / output interface 405 is also connected to the bus 404.

[0112] The following components are connected to the input / output interface 405: an input portion 406 including input devices such as a keyboard and a mouse; an output portion 407 including output devices such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage portion 408 including a hard disk; and a communication portion 409 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication portion 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as necessary. A removable media 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 410 as necessary, so that a computer program read therefrom is installed in the storage portion 408 as necessary.

[0113] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing computer programs for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication portion 409, and / or installed from the removable media 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are executed.

[0114] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer-readable signal medium can include a data signal carrying computer-readable computer programs in a baseband or as a part of a carrier wave. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit programs for use by or in conjunction with an instruction execution system, device or apparatus. The computer programs contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, or the like, or any suitable combination thereof.

[0115] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In the flowcharts or block diagrams, each block can represent a module, a program segment or a part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than that shown in the drawings. For example, two blocks represented in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0116] The units described in the embodiments of the present application can be implemented by software, or can be implemented by hardware, and the units described can also be arranged in a processor. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0117] According to an aspect of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in the various optional implementation manners described above.

[0118] As another aspect, the present application also provides a computer readable medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs, which, when executed by the electronic device, enable the electronic device to implement the coal mine geological model dynamic updating method based on drilling data described in the above embodiments.

[0119] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into several modules or units.

[0120] From the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or network, and includes several instructions to enable a computing device (which can be a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of the present application.

[0121] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the application following the general principles thereof and including such departures from the present disclosure as come within known use or custom in the art.

[0122] It is to be understood that the application is not limited to the precise construction already described above and shown in the drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application should only be limited by the claims appended hereto.

Claims

1. A method for dynamically updating a coal mine geological model based on drilling data, characterized in that, include: Acquire drilling data generated by the intelligent drilling rig during the drilling process; The drilling data is preprocessed and features are extracted to generate a drilling response sequence indexed by drilling depth; Data analysis is performed on the drilling response sequence to generate a geological response feature vector composed of multiple statistical features; The geological response feature vector is analyzed and sampled using a multi-layer Fourier neural operator to generate initial estimation results; The initial calculation results are recalibrated to generate virtual geological profiles at each drilling depth along the borehole trajectory; Based on the virtual geological profile, the local spatial areas affected by the current drilling activities are updated to generate a coal mine geological model.

2. The method for dynamically updating a coal mine geological model based on drilling data according to claim 1, characterized in that, The drilling data includes drilling pressure, drilling torque, drill rod speed, pump pressure, and drilling depth generated at each sampling time. The drilling data is preprocessed and feature extracted to generate a drilling response sequence indexed by drilling depth, including: The drilling data is represented as a signal vector of a multidimensional drilling response that varies over time. The parameter components in the signal vector are smoothed to generate a first signal; Based on the mapping relationship between drilling time and drilling depth, the first signal is mapped into a drilling response sequence indexed by drilling depth.

3. The method for dynamically updating a coal mine geological model based on drilling data according to claim 1, characterized in that, Data analysis is performed on the drilling response sequence to generate a geological response feature vector composed of multiple statistical features, including: The drilling data is combined to generate an original feature vector; Calculate the statistical characteristics of each parameter in the drilling response sequence under a preset depth window scale; Based on the parameters in the drilling response sequence, the drilling energy characteristics and energy change at the preset depth are generated. The original feature vector, the statistical features, the drilling energy features, and the energy change are combined to generate a geological response feature vector.

4. The method for dynamically updating a coal mine geological model based on drilling data according to claim 1, characterized in that, The geological response feature vector is analyzed and sampled using a multi-layer Fourier neural operator to generate initial estimation results, including: The geological response feature vector is transformed layer by layer using a multi-layer Fourier neural operator to generate intermediate features; The intermediate features are input into a pre-trained geological attribute operator inference model, which outputs continuous prediction results representing geological attributes. The continuous prediction results are sampled based on a preset drilling depth to generate initial calculation results.

5. The method for dynamically updating a coal mine geological model based on drilling data according to claim 1, characterized in that, The initial calculation results are recalibrated to generate virtual geological profiles along the borehole trajectory at each drilling depth, including: The initial calculation results are sorted and combined according to the increasing drilling depth to generate a depth sequence; The depth sequence is encoded and linearly projected to generate sequence-aware features; Linear projection is performed on the sequence sensing features to generate recalibration results corresponding to each drilling depth, which serve as virtual geological profiles along the borehole trajectory.

6. The method for dynamically updating a coal mine geological model based on drilling data according to claim 1, characterized in that, Based on the virtual geological profile, the local spatial areas affected by the current drilling activity are updated to generate a coal mine geological model, including: Based on the spatial location in the three-dimensional geological model and the sequence of spatial sampling points formed along the drilling trajectory, the local spatial area affected by the current drilling activity is determined. Based on the virtual geological profile, incremental updates are performed on the local spatial region to generate a coal mine geological model.

7. The method for dynamically updating a coal mine geological model based on drilling data according to claim 6, characterized in that, Based on the virtual geological profile, after updating the local spatial areas affected by the current drilling activity and generating the coal mine geological model, the process further includes: The coal mine geological model is used as a new prior model. During subsequent drilling, the prior model is iteratively updated based on the newly generated virtual geological profile.

8. A dynamic updating device for a coal mine geological model based on drilling data, characterized in that, include: The acquisition module is used to acquire drilling data generated by the intelligent drilling rig during the drilling process; The extraction module is used to preprocess and extract features from the drilling data to generate a drilling response sequence indexed by the drilling depth. The statistics module is used to perform data analysis on the drilling response sequence and generate a geological response feature vector composed of multiple statistical features; The estimation module is used to perform data analysis and sampling processing on the geological response feature vector through multi-layer Fourier neural operators to generate initial estimation results; The calibration module is used to recalibrate the initial calculation results and generate virtual geological profiles corresponding to each drilling depth along the borehole trajectory. The update module is used to update the local spatial area affected by the current drilling activity based on the virtual geological profile, and generate a coal mine geological model.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for dynamically updating a coal mine geological model based on drilling data as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method for dynamically updating a coal mine geological model based on drilling data as described in any one of claims 1 to 7.

Images