Geological exploration data intelligent monitoring system and method based on big data

Abstract

The invention discloses a geological exploration data intelligent monitoring system and method based on big data, and belongs to the technical field of geological exploration. The data acquisition module is used for performing data acquisition on drilling equipment and specifically comprises a rock stratum sensing module and a rock core acquisition module; the data processing module is used for preprocessing and fusing the data acquired by the data acquisition module and specifically comprises a preprocessing module and a fusing module; the three-dimensional modeling module is used for establishing a geological exploration model of a three-dimensional space according to the data output by the fusion module; and the model updating module is used for updating the address exploration model by adopting a dynamic updating mechanism along with continuous data acquisition for the geological exploration model. By adopting the system and the method, the seismic wave velocity field and the electromagnetic wave resistivity field are combined for analysis and processing, the lithology difference of the same position can be verified, the detection precision is further improved, and a geological exploration model can be better evolved in combination with actual core data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological exploration, and in particular to a geological exploration data intelligent monitoring system and method based on big data. BACKGROUND

[0002] Traditional geological exploration mainly relies on manual data collection and processing, and has three technical bottlenecks: data island phenomenon: seismic wave, electromagnetic method, drilling data are scattered in different departments, format is heterogeneous (such as SEGY, LAS, CSV), cross-platform sharing efficiency is low; real-time performance is insufficient: TB-level data generated by field exploration equipment needs to be manually returned, and the response delay of abnormal events is more than 24 hours; single analysis dimension: relying on expert experience to interpret two-dimensional sections, lacking multi-parameter fusion analysis capability, for example, velocity field-resistivity field joint analysis. SUMMARY

[0003] The purpose of the present application is to provide a geological exploration data intelligent monitoring system and method based on big data, to realize the joint analysis effect of seismic wave velocity field and electromagnetic wave resistivity field, and to obtain a geological exploration model with higher precision by combining the actual core data.

[0004] To achieve the above purpose, the present application provides a geological exploration data intelligent monitoring system based on big data, The data acquisition module acquires data from the drilling equipment, specifically including a rock layer perception module and a core collection module; The data processing module pre-processes and fuses the data obtained by the data acquisition module, specifically including a pre-processing module and a fusion module; The three-dimensional modeling module establishes a three-dimensional geological exploration model according to the data output by the fusion module; The model updating module updates the geological exploration model dynamically as more data is collected.

[0005] Preferably, the specific implementation of the data acquisition module is as follows: The rock layer perception module collects seismic wave and electromagnetic wave data; The core collection module collects cores and records data, including collection coordinates, lithology and porosity.

[0006] Preferably, the specific implementation process of the data processing module is as follows: The pre-processing module pre-processes the data collected by the data acquisition module; The fusion module fuses the pre-processed data; The three-dimensional modeling module performs three-dimensional modeling on the output data of the fusion module to obtain a geological exploration model; The model updating module specifically adopts the method of the edge computing node to continuously update and calculate the geological exploration model.

[0007] A geological exploration data intelligent monitoring method based on big data, comprising the following steps: Step one: collect data using the data collection module, for seismic waves and electromagnetic waves, use a seismograph and an electromagnetic detector to construct an array, and arrange a 50m grid around the borehole to collect seismic wave velocity fields and electromagnetic wave resistivity fields, and perform data aggregation through wireless networking, analyze the obtained core during the exploration process, and obtain the collection coordinates, lithology and porosity; Step two: use the data processing module to process the data obtained in step one, for seismic wave velocity fields and electromagnetic wave resistivity fields, perform preprocessing, which includes noise elimination and data alignment, noise elimination uses wavelet transform and outlier detection for processing, and data alignment aligns the data according to time; Use the fusion module to fuse the data and obtain fused data, and the specific fusion method uses a weighted fusion method; Step three: use the three-dimensional modeling module to process the fused data and convert the corresponding data into a geological exploration model; Step four: use the model updating module to update the geological exploration model by using the data of the core collected in step one as the marker point of the geological exploration model, and form a more refined geological exploration model.

[0008] Preferably, the specific process in step two is as follows: The preprocessing process is as follows: discrete wavelet transform is performed on the signal convolution of seismic waves and electromagnetic waves, and the formula is as follows: ; In the formula, denotes a scale parameter, denotes a translation parameter, denotes a signal of a seismic wave or an electromagnetic wave, denotes a wavelet function, and the formula for setting a threshold value is as follows: ; ; In the formula, denotes a threshold value parameter, denotes a noise standard deviation, denotes the number of data points, and the threshold value is used as a reference for noise elimination; The specific formula for outlier detection is as follows: ; In the formula, denotes the value of the i th data point, represents the mean value, represents the standard deviation of the sliding window; After the above processing of the seismic wave velocity field and the electromagnetic wave resistivity field, data alignment is performed, and then the seismic wave and electromagnetic wave data are fused in a weighted fusion manner. First, data normalization is performed. The normalization formula of the seismic wave velocity field is as follows: ; The normalization formula of the electromagnetic wave resistivity field is as follows: ; In the above formula, is the normalized value of the seismic wave velocity field at time t, represents the velocity value of the seismic wave velocity field at time t, is the normalized value of the electromagnetic wave resistivity field at time t, represents the resistance value of the electromagnetic wave resistivity field at time t; the weighted fusion formula is as follows: ; The result of the above formula is the fusion result, is the weight parameter of the seismic wave velocity field, represents the weight parameter of the electromagnetic wave resistivity field.

[0009] Preferably, in step three, the specific process is as follows: The fusion result is imported into the modeling software, and the processing process is as follows: determine the drilling coordinates: extract the XYZ coordinates and lithology attributes, and construct a three-dimensional scattered point set; DEM data: convert to a regular grid point set, fill the holes through Kriging interpolation, and generate a continuous ground surface; merge the drilling points and the DEM grid points into a unified point set, mark the drilling points as hard constraint points, and force to retain in the final grid vertex; Set the constraint conditions: drilling constraints: through the Lawson local optimization algorithm, force to retain the edge where the drilling point is located; DEM constraints: project and match the ground triangular edge with the DEM grid points, and trigger grid reconstruction when the deviation is >0.5m; Generate the model: generate super triangles to wrap all the point sets by using the divide-and-conquer algorithm, insert points one by one, and insert points in the area where the triangular edge length is >10m until the resolution threshold is met; based on Kriging interpolation, fill the fusion result to the grid nodes in time sequence to obtain the geological exploration model.

[0010] Preferably, in step four, the specific process is as follows: According to the coordinates collected by the core, the core is positioned to the corresponding position in the geological exploration model, the measured porosity of the core is taken as a control point, the local attribute of the inverse distance weighted correction model is corrected, cross validation is carried out, the predicted value of the model is compared with the core data, and iteration optimization is carried out until the error is less than 5%.

[0011] Therefore, the geological exploration data intelligent monitoring system and method based on big data have the following advantages: (1) In the present application, the joint analysis and processing of the seismic wave velocity field and the electromagnetic wave resistivity field can verify the lithology difference of the same position, such as the wave impedance difference of limestone and shale reaching 2000 m / s.g / cm 3 , which improves the single parameter detection accuracy by more than 40%; (2) In the present application, by generating a geological exploration model and combining the actually obtained core data, the accuracy of the model can be improved.

[0012] The technical solutions of the present application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 Flowchart of a geological exploration data intelligent monitoring method based on big data DETAILED DESCRIPTION

[0014] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be described clearly and completely below with the help of the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. The specific specifications need to be selected and determined according to the actual specifications of the device. The specific selection calculation method adopts the existing technology in the art, so it will not be described in detail.

[0015] EMBODIMENT As Figure 1 shown, the present application provides a geological exploration data intelligent monitoring system based on big data, which comprises: a data acquisition module: acquiring data of drilling equipment, specifically including a rock stratum perception module and a core acquisition module; The rock stratum perception module acquires seismic wave velocity field and electromagnetic wave resistivity field data. The core acquisition module acquires cores and records data, including acquisition coordinates, lithology and porosity.

[0016] The data processing module: pre-processes and fuses the data obtained by the data acquisition module, specifically including a pre-processing module and a fusion module; The preprocessing module preprocesses the data collected by the data acquisition module; The fusion module performs fusion processing on the pre-processed data; The 3D modeling module performs 3D modeling using the output data from the fusion module to obtain a geological exploration model; The model update module specifically uses the edge computing node method to continuously update the geological exploration model.

[0017] 3D Modeling Module: Based on the data output by the fusion module, a 3D geological exploration model is established. Model update module: For geological exploration models, a dynamic update mechanism is adopted to update the geological exploration models as data is continuously collected.

[0018] A smart monitoring method for geological exploration data based on big data, using the aforementioned system, with the following specific steps: Step 1: Collect data using the data acquisition module. For seismic waves and electromagnetic waves, construct an array using seismographs and electromagnetic detectors, and deploy them in a 50m grid around the borehole to create a range detection effect, which facilitates the generation of geological exploration models later. Collect the seismic wave velocity field and electromagnetic wave resistivity field, and summarize the data through wireless networking. For the rock cores obtained during the exploration process, perform physical and chemical analysis, and record the collection coordinates, lithology, and porosity. Step 2: Use the data processing module to process the data obtained in Step 1. For the seismic wave velocity field and electromagnetic wave resistivity field, preprocessing is performed. Preprocessing includes noise removal and data alignment. Noise removal is performed using wavelet transform and outlier detection. Data alignment is performed by aligning the data according to time. The preprocessing process is as follows: Discrete wavelet transform is performed on the convolution of the seismic wave and electromagnetic wave signals, as shown in the following formula: ; In the above formula, Indicates the scale parameter. Indicates the translation parameter. Signals representing seismic waves or electromagnetic waves, The formula for setting the threshold for the wavelet function is as follows: ; ; In the above formula, Indicates the threshold parameter. Indicates the standard deviation of noise. This represents the number of data points, with a threshold used as the benchmark for noise elimination. The specific formula for outlier detection is as follows: ; In the above formula, This represents the value of the i-th data point. This represents the mean. This represents the standard deviation of the sliding window; The seismic wave velocity field and electromagnetic wave resistivity field are processed as described above, followed by data alignment, and then the seismic wave and electromagnetic wave data are fused using a weighted fusion method. First, the data is normalized; the normalization formula for the seismic wave velocity field is as follows: ; The normalized formula for the electromagnetic wave resistivity field is as follows: ; In the above formula, Let be the normalized value of the seismic wave velocity field at time t. This represents the velocity value of the seismic wave velocity field at time t. Let be the normalized value of the electromagnetic wave resistivity field at time t. The value of the electromagnetic wave resistivity field at time t is represented; the weighted fusion formula is as follows: ; In the above formula, Indicates the fusion result. The weighting parameters representing the seismic wave velocity field. In this embodiment, the weighting parameter representing the electromagnetic wave resistivity field is... , ; The data is processed using a fusion module to obtain fused data. The specific fusion method adopted is a weighted fusion method. Step 3: Use the 3D modeling module to process the fused data and transform it into a geological exploration model; details are as follows: The fusion result Importing the data into the modeling software, the specific processing steps are as follows: Determine the borehole coordinates, extract the borehole coordinates and lithological properties, and construct a three-dimensional scattered point set; convert the DEM data into a regular grid point set, fill the voids through Kriging interpolation, and generate a continuous surface; merge the borehole points and DEM grid points into a unified point set, mark the borehole points as hard constraint points, and force them to remain at the vertices of the final mesh; Set constraints: Drilling constraint: Force the preservation of the edges where the drill points are located using the Lawson local optimization algorithm; DEM constraint: Project the edges of the surface triangles to the DEM grid points, and trigger mesh reconstruction when the deviation is >0.5m. The generative model employs a divide-and-conquer algorithm to generate a super triangle encompassing all points. Points are inserted point by point, with extra points inserted in regions where the triangle's side length is greater than 10m, until a resolution threshold is met. The fused results are then fused in chronological order using Kriging interpolation. Fill the grid nodes to obtain the geological exploration model.

[0019] Step 4: Using the model update module, the core data collected in Step 1 is used as marker points to update the geological exploration model, forming a more refined geological exploration model. The specific process is as follows: Based on the coordinates obtained from the core samples, the cores are located at their corresponding positions in the geological exploration model. The measured porosity of the cores is used as a control point. Local properties of the model are corrected through inverse distance weighting, and cross-validation is performed. The model's predicted values ​​are compared with the core data, and the process is iteratively optimized until the error is less than 5%, resulting in a continuously updated model. Therefore, this invention employs an intelligent monitoring system and method for geological exploration data based on big data. It uses a combined analysis of seismic wave velocity field and electromagnetic wave resistivity field to verify that lithological differences at the same location, such as the impedance difference between limestone and shale, can reach 2000 m / s·g / cm². 3 It improves the accuracy of detection by more than 40% compared to single-parameter detection; by generating a geological exploration model and combining it with the actual core data obtained to form model generation constraints, the accuracy of the model can be improved.

[0020] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A big data-based geological exploration data intelligent monitoring system, characterized in that: Comprise: Data acquisition module: data acquisition of drilling equipment, specifically including rock perception module and core collection module; Data processing module: pre-processing and fusion of data obtained by data acquisition module, specifically including preprocessing module and fusion module; Three-dimensional modeling module: according to the data output by the fusion module, a three-dimensional geological exploration model is established; Model updating module: for the geological exploration model, with continuous data collection, a dynamic updating mechanism is adopted to update the address exploration model. 2.The big data based geological exploration data intelligent monitoring system according to claim 1, characterized in that: The specific implementation of the data acquisition module is as follows: Rock perception module, collecting seismic wave and electromagnetic wave data; Rock core collection module, collecting rock cores and recording data, including collection coordinates, lithology and porosity.

3. The geological exploration data intelligent monitoring system based on big data according to claim 2, characterized in that: The specific implementation process of the data processing module is as follows: The preprocessing module pre-processes the contents collected by the data acquisition module; The fusion module fuses the pre-processed data; The three-dimensional modeling module performs three-dimensional modeling on the output data of the fusion module to obtain a geological exploration model; The model updating module specifically adopts the method of edge computing node to continuously update the calculation of the geological exploration model.

4. A geological exploration data intelligent monitoring method based on big data, using the geological exploration data intelligent monitoring system based on big data according to any one of claims 1-3, comprising the following steps: Step one: use the data acquisition module to collect data, for seismic wave and electromagnetic wave, use the seismograph and electromagnetic detector to build an array, arrange 50m grid around the borehole, collect seismic wave velocity field and electromagnetic wave resistivity field, and perform data aggregation through wireless networking, analyze the obtained core during exploration, and obtain collection coordinates, lithology and porosity; Step two: use the data processing module to process the data obtained in step one, for seismic wave velocity field and electromagnetic wave resistivity field, pre-processing includes noise elimination and data alignment, noise elimination uses wavelet transform and outlier detection for processing, and data alignment aligns data according to time; Use the fusion module to fuse the data to obtain fused data, and the specific fusion method uses weighted fusion method; Step three: use the three-dimensional modeling module to process the fused data, and convert the corresponding data into a geological exploration model; Step four: use the model updating module to update the geological exploration model by using the data of the core collected in step one as the marker point of the geological exploration model, and form a more refined geological exploration model.

5. The big data-based geological exploration data intelligent monitoring method according to claim 4, characterized in that: The specific process in step two is as follows: The pre-processing process is as follows: discrete wavelet transform is performed on the convolution of seismic wave and electromagnetic wave signals, and the formula is as follows: ； In the above formula, denotes a scale parameter, denotes a translation parameter, denotes a signal of a seismic wave or an electromagnetic wave, denotes a wavelet function, and the formula for setting a threshold is as follows: ； ； In the above formula, denotes a threshold parameter, denotes a noise standard deviation, denotes the number of data points, and the threshold is used as a reference for noise elimination; The specific formula of outlier detection is as follows: ； In the above formulae, denotes the value of the i-th data point, denotes the mean value, denotes the standard deviation of the sliding window; After the above processing of seismic wave velocity field and electromagnetic wave resistivity field, data alignment is performed, and then the data of seismic wave and electromagnetic wave are fused, and the fusion method is weighted fusion, first data normalization, the normalization formula of seismic wave velocity field is as follows: ； The normalization formula of electromagnetic wave resistivity field is as follows: ； In the above formula, is the normalized value of the seismic wave velocity field at time t, represents the velocity value of the seismic wave velocity field at time t, is the normalized value of the electromagnetic wave resistivity field at time t, represents the resistance value of the electromagnetic wave resistivity field at time t; the weighted fusion formula is as follows: ； The above formula results in The fusion result, is a weight parameter of a seismic wave velocity field, is a weight parameter representing an electromagnetic wave resistivity field. 6.The big data based geological exploration data intelligent monitoring method according to claim 5, characterized in that: The specific process in the third step is as follows: The fusion result is imported into the modeling software, and the processing process is specifically as follows: determining the drilling coordinates: extracting XYZ coordinates and lithological properties to construct a three-dimensional scattered point set; DEM data: converting into a regular grid point set, filling in the holes through Kriging interpolation to generate a continuous ground surface; merging the drilling points and the DEM grid points into a unified point set, marking the drilling points as hard constraint points and forcing to be retained in the final grid vertices; Set constraint conditions, drill hole constraint: through the Lawson local optimization algorithm, force to keep the edge where the drill hole point is; DEM constraint: project and match the surface triangular edge with the DEM grid point, and when the deviation is greater than 0.5 m, trigger the grid reconstruction; The generating model generates a super triangle to wrap all the point sets by using a divide-and-conquer algorithm, inserts points one by one, and inserts points in a region with a triangle side length greater than 10 m until a resolution threshold is met, and based on Kriging interpolation, the fusion result is arranged in time sequence The grid nodes are filled to obtain a geological exploration model. 7.The big data based geological exploration data intelligent monitoring method according to claim 6, characterized in that: The specific process in the fourth step is as follows: According to the coordinates collected by the core, the core is positioned to the corresponding position in the geological exploration model, the measured porosity of the core is taken as a control point, the local attribute is corrected through the inverse distance weighted correction model, cross validation is carried out, the predicted value of the model is compared with the core data, and iteration optimization is carried out until the error is less than 5%.

Images