A 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, belonging to the technical field of geological exploration data monitoring and processing, comprising a geological exploration data acquisition unit, the geological exploration data acquisition unit comprising a geological exploration data actual acquisition unit and a geological exploration data registration unit; the geological exploration data actual acquisition unit comprises an exploration data receiving board, an analog data conditioning board, an analog-to-digital conversion board, a main control board, a GPS differential positioning unit, a monitoring host and a cloud storage unit, a row of acquisition interfaces is arranged on the exploration data receiving board; a geological parameter collector is connected to the acquisition interface; the analog data conditioning board comprises a plurality of conditioning circuits, the geological exploration data intelligent monitoring system and method based on big data of the invention, the geological data acquired is more accurate, and rich geological exploration data can be acquired, and regional geology can be more comprehensively evaluated.

Description

Technical Field

[0001] The present invention specifically relates to a geological exploration data intelligent monitoring system and method based on big data, and belongs to the technical field of geological exploration data monitoring and processing. Background Art

[0002] Geological exploration is a process of obtaining geological information through various means, with the purpose of understanding the structure, strata, lithology and mineral resources of the earth's crust; that is, geological exploration is a method of obtaining information about the surface and underground structural characteristics of the earth by studying the structure, material composition and geological history of the earth. For example, China Patent Authorization Announcement No.: CN117780257B discloses an intelligent monitoring system and method for geological exploration data based on big data. This method can help adjust the drilling direction in time, ensure that the wellbore passes through the target stratum, reduce the situation of re-drilling or reverse drilling, improve the drilling accuracy and efficiency, and save the time and economic cost of drilling; but this method monitors The measured data is only for monitoring drilling data, the monitoring object is relatively single, and geological exploration data can only be obtained by drilling, so data acquisition is relatively cumbersome; another example is the Chinese patent authorization announcement number: CN106707299B, which discloses a GNSS geological exploration automatic positioning and timing system; it integrates the data acquisition system and the data processing system, and integrates the information collection, transmission, storage and processing and analysis; the system has the ability to realize real-time timing and automatic positioning of feature points under various geological conditions, which greatly increases the efficiency of geological exploration data collection; but the system does not pre-process the collected data, and the accuracy of the collected data is general. Summary of the invention

[0003] To solve the above problems, the present invention proposes a geological exploration data intelligent monitoring system and method based on big data, which can collect geological data with higher accuracy and obtain rich geological exploration data, and can make a more comprehensive assessment of regional geology.

[0004] The intelligent monitoring system for geological exploration data based on big data of the present invention comprises:

[0005] A geological exploration data acquisition unit, the geological exploration data acquisition unit includes a geological exploration data acquisition unit and a geological exploration data registration unit; the geological exploration data acquisition unit includes:

[0006] An exploration data receiving board, on which a row of acquisition interfaces are arranged; a geological parameter collector is connected to the acquisition interface; the geological parameter collector acquires data such as amplitude, phase, apparent resistivity, apparent amplitude frequency, absolute phase, relative phase and apparent polarizability, and sends the data to the analog data conditioning board through the acquisition interface;

[0007] An analog data conditioning board, the analog data conditioning board includes multiple groups of conditioning circuits, the conditioning circuit includes a low-pass filter connected to the acquisition interface, the low-pass filter is connected to an active filter through an operational amplifier circuit, and the active filter is connected to a single-ended to differential circuit;

[0008] The conditioning circuit receives the signal sent by the geological parameter collector and sends the signal to the input end of the low-pass filter. The low-pass filter adopts a first-order RC filter. During the process of the geological parameter collector being transmitted to the low-pass filter, the signal is attenuated or interfered by external factors, causing the signal to be greatly attenuated or a small interference signal with a large amplitude or a high frequency is collected, so that the collected signal is incorrect or the signal is too large, impacting the analog-to-digital conversion board. Therefore, the large abnormal signal at the input end is eliminated by the low-pass filter, and the analog-to-digital conversion board obtains a safe input signal; then the processed signal is sent to the operational amplifier circuit, which adopts a programmable gain amplifier for amplification. After the amplification is completed, it is sent to the active filter for filtering. The active filter is a second-order active low-pass filter. After obtaining the amplified signal, the noise in the signal is processed. During the processing, since the noise is synchronously amplified, it is filtered twice through a second-order active low-pass filter to obtain a stable and accurate input signal. Finally, the data is converted through a single-ended to differential circuit, and the converted data that can be converted and processed by the analog-to-digital conversion board is output;

[0009] The analog-to-digital conversion board includes a plurality of groups of AD conversion units, and the input end of the AD conversion unit is connected to the single-ended to differential circuit; the converted data is sent to the AD conversion unit, and the AD conversion unit performs analog-to-digital conversion to obtain a high-precision digital signal;

[0010] A main control board, the output end of the single-ended to differential circuit is connected to the main control board; the main control board is connected to a temporary storage unit;

[0011] A GPS differential positioning unit, wherein the GPS differential positioning unit is connected to a main control board;

[0012] A monitoring host, to which the geological exploration data acquisition unit and the main control board are both connected;

[0013] A cloud storage unit, wherein the monitoring host is communicatively connected to the cloud storage unit.

[0014] Furthermore, the monitoring host acquires and packages the seismic exploration data, and sends it to the cloud storage unit for storage; the cloud storage unit includes a positioning storage area, in which N positioning storage blocks are arranged, and when each positioning storage block is stored, the positioning data is used as a label, and all seismic exploration data associated with the positioning data are stored in the positioning storage block.

[0015] Furthermore, the data entered into the geological exploration data registration unit includes location information and measured data, and the measured data is one or more of geological structure data, geological attribute data, geophysical exploration data, drilling data and experimental data; the above-mentioned measured data are interrelated and together constitute the geological exploration data; among them, the geological structure data mainly includes spatial data such as geological layers, structural lines, geological interfaces, etc.; the geological attribute data mainly includes attribute data such as rock type, mineral composition, porosity, permeability, etc.; the geophysical exploration data includes seismic, electromagnetic, gravity, magnetic and other data; the drilling data includes drilling location, depth, core length, core sampling rate and other data; the experimental data includes rock mechanics experiments, geochemical experiments, physical experiments and other data.

[0016] Furthermore, the acquisition object of the geological parameter collector is one or more of amplitude, phase, apparent resistivity, apparent amplitude frequency, absolute phase, relative phase and apparent polarizability.

[0017] A method for intelligent monitoring of geological exploration data based on big data, using an intelligent monitoring system for geological exploration data based on big data, the method is specifically as follows:

[0018] First, the historical data of the cloud storage unit is processed by constructing a processing unit. The structure and processing process of the processing unit are as follows:

[0019] A classification unit, wherein the classification unit is connected to the positioning storage area, obtains all stored data in the positioning storage area, and classifies the seismic exploration data according to all classification items of the geological exploration data to obtain N groups of classified data; for example, the seismic exploration data is classified into geological structure data, geological attribute data, geophysical exploration data, drilling data and experimental data, etc., and the above data can be further grouped, such as dividing the geological attribute data into N groups, such as rock type group, mineral composition group, porosity group, permeability group, etc.;

[0020] Clustering unit: clustering each group of classified data in turn to obtain N clustering blocks, each clustering block includes multiple labels; clustering blocks of the same group of classified data are sent to the same clustering area; when the clustering unit operates, a threshold difference can be set for each group, and the difference of each value in the group can be calculated. When the difference is lower than the threshold difference, it is returned to the same clustering block; or K-MEANS algorithm, K-MEDOIDS algorithm or CLARANS algorithm is directly used for clustering to obtain N clustering blocks;

[0021] The correlation generation unit obtains all clustering areas and calculates the correlation of cluster blocks in different clustering areas, specifically:

[0022] right and Calculate the correlation degree; is a cluster block in a cluster area, is a cluster block in another cluster area, and They are The total number of labels for clustering blocks, for The total number of labels for clustering blocks; for The clustering block tags, for The clustering block labels; when calculating, first compare The numerical size between A and s, if the values ​​are equal, it is determined whether A and B are subsets of each other. If so, a complete association is output; if not, the association score calculation is entered; if the values ​​are not equal, it is then determined whether the cluster block with a smaller value is a true subset of the cluster block with a larger value. If so, a complete association is output; if not, the association score calculation is entered; the association score calculation is specifically as follows:

[0023] (1)

[0024] In the above formula (1), for and The correlation score between for and Next, set a correlation threshold value. When it is greater than the correlation threshold, and Establish associations between them; complete the association calculations between two cluster blocks in turn; obtain cluster association data , is a clustering association set, for Clustering blocks and The cluster blocks after merging the cluster blocks, and is any cluster block in different cluster areas; then, within Perform the association calculation between any two cluster blocks again to generate a secondary cluster association set, and perform the association calculation in sequence to generate N cluster association sets until all cluster blocks in a certain cluster association set are When the value is less than the association threshold, the association calculation is stopped again to obtain a cluster association set group from the first cluster association set to the Nth cluster association set;

[0025] An association fitting unit, wherein the association fitting unit obtains the cluster association set group and performs curve fitting, wherein the fitting process is as follows: obtaining any cluster association data in the cluster set group, and fitting the cluster association data, during the fitting, obtaining the corresponding seismic exploration data through the classification items of the cluster association data and the labels of the cluster blocks, and then taking a certain classification item as the output result and other associated classification items as association factors to obtain a fitting curve;

[0026] A monitoring and inference unit, wherein the monitoring and inference unit obtains one or more classified real-time geological exploration data, and uses one or more unobtained seismic exploration data as inference objects. During inference, the real-time geological exploration data is sent to the classification unit for classification, and after classification, the data is clustered by the clustering unit, the real-time geological exploration data is included in the corresponding clustering block, and the object of the corresponding clustering block is obtained; then, one of the classification items in the inference object is taken as the output result to be obtained, and the object of the clustering block is taken as the correlation factor, and fitting curve matching is performed, a matching fitting curve is retrieved, and the real-time geological exploration data is sent to the fitting curve, and the inference result of the inference object is output through the fitting curve.

[0027] Furthermore, the fitting curve matching process is as follows: first, a classification item in the inferred object is matched with a classification item of the fitting curve as an output result, and then the clustering block corresponding to the real-time geological exploration data and the clustering block with the fitting curve as the correlation factor are completely matched to complete the fitting curve matching.

[0028] Furthermore, the fitting curve fitting process is described by the following formula:

[0029] (2)

[0030] In the above formula (2), is a polynomial function, is the function coefficient, For the The coefficient of the order function, g is the correlation factor, which is the set of corresponding seismic exploration data obtained by the classification items of clustered correlation data and the labels of cluster blocks; is the correlation factor g Step; is the order of the nonlinear function, which can be directly taken as the number of elements in the set; The value of can be determined by adjusting the polynomial function to fit the training data; and measured by minimizing the error function; the error function measures the value of for any given The error between the calculated result and the actual output result of a certain classification item is selected. The value is used as the function coefficient; the specific process is as follows:

[0031] (3)

[0032] In the above formula (3), To minimize the error function, A category item in The output result obtained by calculating the polynomial function; For a certain category The actual output of the order; To minimize the calculation order of the error function, the calculation order is selected according to the amount of calculation and can be set to Same size.

[0033] Compared with the prior art, the intelligent monitoring system and method for geological exploration data based on big data of the present invention can pre-process the geological data collected in real time, remove interference data, make the collected geological data more accurate, and obtain rich geological exploration data, so as to make a more comprehensive assessment of regional geology. For geological exploration data that require high-intensity and cumbersome steps such as drilling and experiments to obtain, it can be obtained through fitting prediction, which reduces the difficulty of regional geological assessment and improves the convenience of regional geological assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the overall structure of the intelligent monitoring system for geological exploration data of the present invention.

[0035] Figure 2 It is a schematic diagram of the storage structure of the cloud storage unit of the present invention.

[0036] Figure 3 It is a schematic diagram of the structure of the processing unit of the present invention.

[0037] Figure 4 It is a schematic diagram of the processing flow of the processing unit of the present invention.

[0038] Figure 5 It is a schematic diagram of the fitting curve matching process of the present invention.

[0039] Figure 6 It is a schematic diagram of the fitting process of the fitting curve of the present invention. DETAILED DESCRIPTION

[0040] Example:

[0041] like Figures 1 to 6 The geological exploration data intelligent monitoring system based on big data shown includes:

[0042] A geological exploration data acquisition unit, the geological exploration data acquisition unit includes a geological exploration data acquisition unit and a geological exploration data registration unit; the geological exploration data acquisition unit includes:

[0043] An exploration data receiving board, on which a row of acquisition interfaces are arranged; a geological parameter collector is connected to the acquisition interface; the geological parameter collector acquires data such as amplitude, phase, apparent resistivity, apparent amplitude frequency, absolute phase, relative phase and apparent polarizability, and sends the data to the analog data conditioning board through the acquisition interface;

[0044] An analog data conditioning board, the analog data conditioning board includes multiple groups of conditioning circuits, the conditioning circuit includes a low-pass filter connected to the acquisition interface, the low-pass filter is connected to an active filter through an operational amplifier circuit, and the active filter is connected to a single-ended to differential circuit;

[0045] The conditioning circuit receives the signal sent by the geological parameter collector and sends the signal to the input end of the low-pass filter. The low-pass filter adopts a first-order RC filter. During the process of the geological parameter collector being transmitted to the low-pass filter, the signal is attenuated or interfered by external factors, causing the signal to be greatly attenuated or a small interference signal with a large amplitude or a high frequency is collected, so that the collected signal is incorrect or the signal is too large, impacting the analog-to-digital conversion board. Therefore, the large abnormal signal at the input end is eliminated by the low-pass filter, and the analog-to-digital conversion board obtains a safe input signal; then the processed signal is sent to the operational amplifier circuit, which adopts a programmable gain amplifier for amplification. After the amplification is completed, it is sent to the active filter for filtering. The active filter is a second-order active low-pass filter. After obtaining the amplified signal, the noise in the signal is processed. During the processing, since the noise is synchronously amplified, it is filtered twice through a second-order active low-pass filter to obtain a stable and accurate input signal. Finally, the data is converted through a single-ended to differential circuit, and the converted data that can be converted and processed by the analog-to-digital conversion board is output;

[0046] The analog-to-digital conversion board includes a plurality of groups of AD conversion units, and the input end of the AD conversion unit is connected to the single-ended to differential circuit; the converted data is sent to the AD conversion unit, and the AD conversion unit performs analog-to-digital conversion to obtain a high-precision digital signal;

[0047] A main control board, the output end of the single-ended to differential circuit is connected to the main control board; the main control board is connected to a temporary storage unit;

[0048] A GPS differential positioning unit, wherein the GPS differential positioning unit is connected to a main control board;

[0049] A monitoring host, to which the geological exploration data acquisition unit and the main control board are both connected;

[0050] A cloud storage unit, wherein the monitoring host is communicatively connected to the cloud storage unit.

[0051] The monitoring host obtains and packages the seismic exploration data, and sends it to the cloud storage unit for storage; the cloud storage unit includes a positioning storage area, in which N positioning storage blocks are arranged. When each positioning storage block is stored, the positioning data is used as a label, and all seismic exploration data associated with the positioning data are stored in the positioning storage block.

[0052] The data entered into the geological exploration data registration unit include location information and measured data, wherein the measured data are one or more of geological structure data, geological attribute data, geophysical exploration data, drilling data and experimental data; the above-mentioned measured data are interrelated and together constitute the geological exploration data; wherein the geological structure data mainly include spatial data such as geological layers, structural lines, geological interfaces, etc.; the geological attribute data mainly include attribute data such as rock type, mineral composition, porosity, permeability, etc.; the geophysical exploration data include seismic, electromagnetic, gravity, magnetic method and other data; the drilling data include drilling location, depth, core length, core sampling rate and other data; the experimental data include rock mechanics experiments, geochemical experiments, physical experiments and other data.

[0053] The acquisition object of the geological parameter collector is one or more of amplitude, phase, apparent resistivity, apparent amplitude frequency, absolute phase, relative phase and apparent polarizability.

[0054] A method for intelligent monitoring of geological exploration data based on big data, using an intelligent monitoring system for geological exploration data based on big data, the method is specifically as follows:

[0055] First, the historical data of the cloud storage unit is processed by constructing a processing unit. The structure and processing process of the processing unit are as follows:

[0056] A classification unit, wherein the classification unit is connected to the positioning storage area, obtains all stored data in the positioning storage area, and classifies the seismic exploration data according to all classification items of the geological exploration data to obtain N groups of classified data; for example, the seismic exploration data is classified into geological structure data, geological attribute data, geophysical exploration data, drilling data and experimental data, etc., and the above data can be further grouped, such as dividing the geological attribute data into N groups, such as rock type group, mineral composition group, porosity group, permeability group, etc.;

[0057] Clustering unit: clustering each group of classified data in turn to obtain N clustering blocks, each clustering block includes multiple labels; clustering blocks of the same group of classified data are sent to the same clustering area; when the clustering unit operates, a threshold difference can be set for each group, and the difference of each value in the group can be calculated. When the difference is lower than the threshold difference, it is returned to the same clustering block; or K-MEANS algorithm, K-MEDOIDS algorithm or CLARANS algorithm is directly used for clustering to obtain N clustering blocks;

[0058] The correlation generation unit obtains all clustering areas and calculates the correlation of cluster blocks in different clustering areas, specifically:

[0059] right and Calculate the correlation degree; is a cluster block in a cluster area, is a cluster block in another cluster area, and They are The total number of labels for clustering blocks, for The total number of labels in the clustering block; for The clustering block tags, for The clustering block labels; when calculating, first compare The numerical size between A and s, if the values ​​are equal, it is determined whether A and B are subsets of each other. If so, a complete association is output; if not, the association score calculation is entered; if the values ​​are not equal, it is then determined whether the cluster block with a smaller value is a true subset of the cluster block with a larger value. If so, a complete association is output; if not, the association score calculation is entered; the association score calculation is specifically as follows:

[0060] (1)

[0061] In the above formula (1), for and The correlation score between for and Next, set a correlation threshold value. When it is greater than the correlation threshold, and Establish associations between them; complete the association calculations between two cluster blocks in turn; obtain cluster association data , is a clustering association set, for Clustering blocks and The cluster blocks after merging the cluster blocks, and is any cluster block in different cluster areas; then, within Perform the association calculation between any two cluster blocks again to generate a secondary cluster association set, and perform the association calculation in sequence to generate N cluster association sets until all cluster blocks in a certain cluster association set are When the value is less than the association threshold, the association calculation is stopped again to obtain a cluster association set group from the first cluster association set to the Nth cluster association set;

[0062] An association fitting unit, wherein the association fitting unit obtains the cluster association set group and performs curve fitting, wherein the fitting process is as follows: obtaining any cluster association data in the cluster set group, and fitting the cluster association data, during the fitting, obtaining the corresponding seismic exploration data through the classification items of the cluster association data and the labels of the cluster blocks, and then taking a certain classification item as the output result and other associated classification items as association factors to obtain a fitting curve;

[0063] A monitoring and inference unit, wherein the monitoring and inference unit obtains one or more classified real-time geological exploration data, and uses one or more unobtained seismic exploration data as inference objects. During inference, the real-time geological exploration data is sent to the classification unit for classification, and after classification, the data is clustered by the clustering unit, the real-time geological exploration data is included in the corresponding clustering block, and the object of the corresponding clustering block is obtained; then, one of the classification items in the inference object is taken as the output result to be obtained, and the object of the clustering block is taken as the correlation factor, and fitting curve matching is performed, a matching fitting curve is retrieved, and the real-time geological exploration data is sent to the fitting curve, and the inference result of the inference object is output through the fitting curve.

[0064] The fitting curve matching process is as follows: first, a classification item in the inference object is matched with a classification item of the fitting curve as an output result, and then the clustering block corresponding to the real-time geological exploration data and the clustering block with the fitting curve as the correlation factor are completely matched to complete the fitting curve matching.

[0065] The fitting curve fitting process is described by the following formula:

[0066] (2)

[0067] In the above formula (2), is a polynomial function, is the function coefficient, For the The coefficient of the order function, g is the correlation factor, which is the set of corresponding seismic exploration data obtained by the classification items of clustered correlation data and the labels of cluster blocks; is the correlation factor g Step; is the order of the nonlinear function, which can be directly taken as the number of elements in the set; The value of can be determined by adjusting the polynomial function to fit the training data; and measured by minimizing the error function; the error function measures the value of for any given The error between the calculated result and the actual output result of a certain classification item is selected. The value is used as the function coefficient; the specific process is as follows:

[0068] (3)

[0069] In the above formula (3), To minimize the error function, A category item in The output result obtained by calculating the polynomial function; For a certain category The actual output of the order; To minimize the calculation order of the error function, the calculation order is selected according to the amount of calculation and can be set to Same size.

[0070] The above embodiments are only preferred implementations of the present invention, so any equivalent changes or modifications made according to the structures, features and principles described in the scope of application of the present invention are included in the scope of application of the present invention.

Claims

1. A geological exploration data intelligent monitoring system based on big data, characterized by: include A geological exploration data acquisition unit, the geological exploration data acquisition unit includes a geological exploration data acquisition unit and a geological exploration data registration unit; the geological exploration data acquisition unit includes An exploration data receiving board, on which a row of acquisition interfaces are arranged; a geological parameter collector is connected to the acquisition interface; An analog data conditioning board, the analog data conditioning board includes multiple groups of conditioning circuits, the conditioning circuit includes a low-pass filter connected to the acquisition interface, the low-pass filter is connected to an active filter through an operational amplifier circuit, and the active filter is connected to a single-ended to differential circuit; An analog-to-digital conversion board, the analog-to-digital conversion board comprising a plurality of groups of AD conversion units, the input ends of the AD conversion units being connected to a single-ended to differential circuit; A main control board, the output end of the single-ended to differential circuit is connected to the main control board; the main control board is connected to a temporary storage unit; A GPS differential positioning unit, wherein the GPS differential positioning unit is connected to a main control board; A monitoring host, to which the geological exploration data acquisition unit and the main control board are both connected; A cloud storage unit, wherein the monitoring host is in communication connection with the cloud storage unit; The monitoring method of the geological exploration data intelligent monitoring system based on big data is as follows: First, the historical data of the cloud storage unit is processed by constructing a processing unit. The structure and processing process of the processing unit are as follows: A classification unit, wherein the classification unit is connected to the positioning storage area, obtains all stored data in the positioning storage area, and classifies the seismic exploration data according to all classification items of the geological exploration data to obtain N groups of classified data; The clustering unit clusters each set of classified data in turn to obtain N cluster blocks, each of which includes multiple labels; cluster blocks of the same set of classified data are sent to the same clustering area; The correlation generation unit obtains all clustering areas and calculates the correlation of cluster blocks in different clustering areas, specifically: right and Calculate the correlation degree; is a cluster block in a cluster area, is a cluster block in another cluster area, for The total number of labels for clustering blocks, for The total number of labels in the clustering block; for The clustering block tags, for The clustering block labels; when calculating, first compare and If the values ​​are equal, determine whether A and B are subsets of each other. If so, output complete association; if not, enter the association score calculation; if the values ​​are not equal, then determine whether the cluster block with a smaller value is a true subset of the cluster block with a larger value. If so, output complete association; if not, enter the association score calculation; the association score calculation is as follows: （1） In the above formula (1), for and The correlation score between for and The number of identical labels between When it is greater than the association threshold, and Establish associations between them; complete the association calculations between two cluster blocks in turn; obtain cluster association data , is a clustering association set, for Clustering blocks and The cluster blocks after merging the cluster blocks. and is any cluster block in different cluster areas; then, within Perform the association calculation between any two cluster blocks again to generate a secondary cluster association set, and perform the association calculation in sequence to generate N cluster association sets until all cluster blocks in a certain cluster association set are When the value is less than the association threshold, the association calculation is stopped again to obtain a cluster association set group from the first cluster association set to the Nth cluster association set; An association fitting unit, wherein the association fitting unit obtains the cluster association set group and performs curve fitting, wherein the fitting process is as follows: obtaining any cluster association data in the cluster set group, and fitting the cluster association data, during the fitting, obtaining the corresponding seismic exploration data through the classification items of the cluster association data and the labels of the cluster blocks, and then taking a certain classification item as the output result and other associated classification items as association factors to obtain a fitting curve; A monitoring and inference unit, wherein the monitoring and inference unit obtains one or more classified real-time geological exploration data, and uses one or more unobtained seismic exploration data as inference objects. During inference, the real-time geological exploration data is sent to the classification unit for classification, and after classification, the data is clustered by the clustering unit, the real-time geological exploration data is included in the corresponding clustering block, and the object of the corresponding clustering block is obtained; then, one of the classification items in the inference object is taken as the output result to be obtained, and the object of the clustering block is taken as the correlation factor, and fitting curve matching is performed, a matching fitting curve is retrieved, and the real-time geological exploration data is sent to the fitting curve, and the inference result of the inference object is output through the fitting curve.

2. The intelligent monitoring system for geological exploration data based on big data according to claim 1 is characterized in that: The monitoring host obtains and packages the seismic exploration data, and sends it to the cloud storage unit for storage; the cloud storage unit includes a positioning storage area, in which N positioning storage blocks are arranged. When each positioning storage block is stored, the positioning data is used as a label, and all seismic exploration data associated with the positioning data are stored in the positioning storage block.

3. The intelligent monitoring system for geological exploration data based on big data according to claim 1 is characterized in that: The data entered by the geological exploration data registration unit includes location information and measured data.

4. The intelligent monitoring system for geological exploration data based on big data according to claim 1 is characterized in that: The acquisition object of the geological parameter collector is one or more of amplitude, phase, apparent resistivity and apparent polarizability.

5. The intelligent monitoring system for geological exploration data based on big data according to claim 1 is characterized in that: The fitting curve matching process is as follows: first, a classification item in the inference object is matched with a classification item of the fitting curve as an output result, and then the clustering block corresponding to the real-time geological exploration data and the clustering block with the fitting curve as the correlation factor are completely matched to complete the fitting curve matching.

6. The intelligent monitoring system for geological exploration data based on big data according to claim 1 is characterized in that: The fitting curve fitting process is described by the following formula: （2） In the above formula (2), is a polynomial function, is the function coefficient, For the The coefficient of the order function, g, is the correlation factor, which is obtained by the classification items of the clustered correlation data and the labels of the cluster blocks to obtain the corresponding set of seismic exploration data; is the correlation factor g Step; is the order of the nonlinear function, which can be directly taken as the number of elements in the set; The value of can be determined by adjusting the polynomial function to fit the training data; and measured by minimizing the error function; the error function measures the value of for any given The error between the calculated result and the actual output result of a certain classification item is selected. The value is used as the function coefficient; the specific process is as follows: （3） In the above formula (3), To minimize the error function, A category item in The output result obtained by calculating the polynomial function; For a certain category The actual output of the order; To minimize the calculation order of the error function, the calculation order is selected according to the amount of calculation and can be set to Same size.

Images