CN117454256A - Geological survey method and system based on artificial intelligence - Google Patents
Geological survey method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117454256A CN117454256A CN202311802844.3A CN202311802844A CN117454256A CN 117454256 A CN117454256 A CN 117454256A CN 202311802844 A CN202311802844 A CN 202311802844A CN 117454256 A CN117454256 A CN 117454256A
- Authority
- CN
- China
- Prior art keywords
- geological
- model
- data
- individual
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000000605 extraction Methods 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000007405 data analysis Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000012800 visualization Methods 0.000 claims abstract description 7
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 238000005553 drilling Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 239000011435 rock Substances 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 229910052500 inorganic mineral Inorganic materials 0.000 claims description 3
- 239000011707 mineral Substances 0.000 claims description 3
- 230000000704 physical effect Effects 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 239000011148 porous material Substances 0.000 claims description 3
- 239000002689 soil Substances 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims 1
- 238000010845 search algorithm Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V11/00—Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a geological survey method and a geological survey system based on artificial intelligence, wherein the method comprises the following steps: the method comprises the steps of data collection, data preprocessing, feature extraction, data arrangement and segmentation, geological model establishment, geological model training, model parameter optimization, geological model evaluation and optimization and geological survey report generation, and the method adopts the MECOA algorithm to perform parameter optimization on the geological model after training, so that the geological model is more accurate and reliable, and a better solution is provided for a geological survey method; meanwhile, the global loss function based on norm and Huber is used for measuring the difference degree between the output of the geological model and the real label, so that the numerical stability of the model is improved, and the model training is more reliable; the system comprises a data acquisition and preprocessing module, a feature extraction module, a data analysis and modeling module, a model training and optimization module and a result analysis and visualization module.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a geological survey method and system based on artificial intelligence.
Background
Geological survey is a scientific method for systematically observing, researching and analyzing geological structures, geological processes and resource distribution on the surface and underground of the earth, and aims at the problems that the traditional parameter optimization algorithm generally uses local search algorithms such as gradient descent and the like, is easy to sink into local optimal solutions and cannot find global optimal solutions, and meanwhile, has low robustness and low reliability; for the problem that a common loss function cannot handle unbalanced data sets or unbalanced categories, if the number of samples in a certain category is small, the loss function may bias to predict the category with more samples, and ignore the category with fewer samples, resulting in performance degradation of the model.
Disclosure of Invention
Aiming at the problems that the conventional parameter optimization algorithm generally uses a local search algorithm such as gradient descent and the like, so that a local optimal solution is easy to sink and a global optimal solution cannot be found, and meanwhile, the problem of low robustness and low reliability exists; aiming at the problem that an unbalanced data set or an unbalanced class cannot be processed by a common loss function, if the number of samples in a certain class is small, the loss function may be biased to predict the class of more samples, and the class of less samples is ignored, so that the performance of a model is reduced.
The technical scheme adopted by the invention is as follows: the invention provides a geological survey method based on artificial intelligence, which comprises the following steps:
step S1: data collection, namely drilling by using a drilling machine, collecting geological samples, extracting geological data from the geological samples, wherein the geological data comprise a bottom layer sequence, age, physical properties and mineral resources of the geological samples, and collecting geological parameters by adopting sensors;
step S2: preprocessing data, namely preprocessing geological data and geological parameters, and performing data cleaning and normalization processing to obtain preprocessed geological data and geological parameters;
step S3: feature extraction, namely performing feature extraction on the preprocessed geological data and geological parameters to obtain geological samples and geological parameters after feature extraction;
step S4: data sorting and segmentation, namely, a data set is established, geological data and geological parameters after feature extraction are recorded and sorted and then put into the data set, the data set is divided into a training set, a verification set and a test set, 70% of the data set is the training set, 15% of the data set is the verification set, and 15% of the data set is the test set;
step S5: establishing a geological model, selecting a CNN model as an infrastructure of the geological model, wherein the geological model comprises an input layer, a convolution layer, a pooling layer, a full connection layer, a batch normalization layer, a Dropout layer and an output layer, and setting an activation function;
step S6: training a geological model, and training the geological model by using a training set to obtain a trained geological model;
step S7: model parameter optimization, namely performing parameter optimization on the trained geologic model by using a MECOA algorithm to obtain an optimized geologic model;
step S8: evaluating and optimizing the geological model, evaluating the optimized geological model by using a test set, calculating the accuracy, recall and F1 value to obtain a calculation result, and optimizing the geological model according to the calculation result;
step S9: and generating a geological survey report, and analyzing and explaining data of the geological survey.
Further, in step S1, drilling is performed by using a drilling machine, geological samples are collected, and geological parameters are collected by using sensors, which specifically include the following:
the drilling machine records the depth, diameter and inclination angle of the drilling hole at the same time;
geological samples include subsurface rock and soil that provide information about geologic structures, lithology, and underlying sequences;
the sensor comprises an earthquake sensor, a stress sensor, a pressure sensor and a temperature sensor, wherein the earthquake sensor is buried underground, the earthquake magnitude, the earthquake source position and the propagation speed of earthquake waves are acquired, the stress sensor is arranged on the wall of a borehole, the stress state, the deformation and the stress release of underground rock are acquired, the pressure sensor is arranged in the borehole, the underground water level, the underground gas pressure and the pore water pressure are acquired, the temperature sensor is arranged in the borehole, and the underground heat flow, the rock thermal property and the underground water temperature are acquired.
Further, in step S6, the geological model is trained by using the training set, which specifically includes the following steps:
step S61: defining samples and labels, defining each data in a training set as a sample, and setting a corresponding real label for each sample to represent expected geological model prediction output;
step S62: forward propagation, namely inputting a training set into a geological model, and calculating the output of the geological model through forward propagation;
step S63: loss function calculation, namely measuring the difference degree between the output of the geological model and the real label by using global loss functions based on norm and Huber, wherein the following formula is used:
;
;
step S64: back propagation, by means of a back propagation algorithm, the parameters of the geologic model are updated layer by layer from the input layer to the output layer.
Further, in step S7, parameter optimization is performed on the trained geologic model by using the MECOA algorithm, which specifically includes the following steps:
step S71: initializing parameters, and defining a population, a population size, a maximum iteration number, an initial position and speed range of individuals in the population, and a position and speed of the population;
step S72: calculating fitness values, converting initial positions of individuals into parameter values of a geological model, simulating by using the geological model, and calculating the fitness values of each individual to obtain the fitness values of each individual, wherein the formula is as follows:
;
wherein, fitness is the fitness value,for the number of individuals to be counted,for the predicted output of the geologic model,the actual observation output is obtained;
step S73: determining a leading individual, and selecting the individual with the highest fitness as the leading individual;
step S74: updating the position and speed of the individual, updating the position and speed of each individual by using multiple strategies according to the position and speed of the leading individual, wherein the multiple strategies comprise a random strategy, a following strategy and a exploring strategy, and the updated individual is obtained by using the following formula:
;
;
wherein,for individualsAt the time ofIs provided in the position of (a),for individualsAt the time ofIs used for the speed of the (c) in the (c),is time ofIs to be added to the next time of the (c),for individualsAt the time ofIs used to determine the optimal individual position of the (c),as a global optimum position for the device,in order to lead the location of the individual,as the weight of the inertia is given,、、in order to accelerate the factor of the velocity,、、is a random number;
step S75: calculating the fitness value of the updated individual, converting the updated individual position into a parameter value of a geological model, simulating by using the geological model, and calculating the fitness value of each updated individual to obtain the fitness value of each updated individual;
step S76: updating the leading individual, and if the updated individual fitness value is better than that of the leading individual, updating the leading individual;
step S77: iterating the steps S73 to S76 until the maximum iteration number is reached;
step S78: outputting an optimal solution, wherein the optimal solution is the geological model parameter value corresponding to the leading individual.
The invention provides a geological survey system based on artificial intelligence, which comprises a data acquisition and preprocessing module, a feature extraction module, a data analysis and modeling module, a model training and optimization module and a result analysis and visualization module;
the data acquisition and preprocessing module is used for collecting geological data and geological parameters, carrying out data cleaning and normalization processing, obtaining preprocessed geological data and geological parameters and sending the acquired data to the feature extraction module;
the feature extraction module receives the data sent by the data acquisition and preprocessing module, selects the feature combination with the minimum feature evaluation to determine the finally selected feature, and sends the data to the data analysis and modeling module;
the data analysis and modeling module receives the data sent by the feature extraction module and builds a geological model by taking the CNN model as a basic framework;
the model training and optimizing module trains the geological model, and parameter optimization is carried out on the trained geological model by using the MECOA algorithm;
and the result analysis and visualization module is used for analyzing and visually displaying the geological survey result by using the geological model.
By adopting the scheme, the beneficial effects obtained by the invention are as follows:
(1) Aiming at the problems that a traditional parameter optimization algorithm generally uses a local search algorithm such as gradient descent and the like, a local optimal solution is easy to sink into and a global optimal solution cannot be found, and meanwhile, the robustness is low and the reliability is low, the MECOA algorithm is adopted to perform parameter optimization on a geological model which is trained, the geological model can be more accurate and reliable through optimizing parameters of the geological model, the geological model can be helped to converge to the optimal solution faster, the geological model can be more robust through parameter optimization, namely the change of input data is more robust, the optimized parameters can enable the geological model to be more robust to noise and abnormal data, and the reliability and stability of the geological model are improved, so that a better solution is provided for a geological survey method.
(2) Aiming at the problem that an unbalanced data set or an unbalanced class cannot be processed by a common loss function, if the number of samples in a certain class is small, the loss function may be biased to predict the class of more samples, and the class of less samples is ignored, so that the performance of a model is reduced.
Drawings
FIG. 1 is a schematic flow chart of an artificial intelligence based geological survey method provided by the invention;
fig. 2 is a flow chart of step S6;
fig. 3 is a flow chart of step S7;
FIG. 4 is a schematic block diagram of an artificial intelligence based geological survey system provided by the present invention.
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention; all other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "top," "bottom," "inner," "outer," and the like indicate orientation or positional relationships based on those shown in the drawings, merely to facilitate description of the invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the invention.
In a first embodiment, referring to fig. 1, the present invention provides an artificial intelligence based geological survey method, which includes the following steps:
step S1: data collection, namely drilling by using a drilling machine, collecting geological samples, extracting geological data from the geological samples, wherein the geological data comprise a bottom layer sequence, age, physical properties and mineral resources of the geological samples, and collecting geological parameters by adopting sensors;
step S2: preprocessing data, namely preprocessing geological data and geological parameters, and performing data cleaning and normalization processing to obtain preprocessed geological data and geological parameters;
step S3: feature extraction, namely performing feature extraction on the preprocessed geological data and geological parameters to obtain geological samples and geological parameters after feature extraction;
step S4: data sorting and segmentation, namely, a data set is established, geological data and geological parameters after feature extraction are recorded and sorted and then put into the data set, the data set is divided into a training set, a verification set and a test set, 70% of the data set is the training set, 15% of the data set is the verification set, and 15% of the data set is the test set;
step S5: establishing a geological model, selecting a CNN model as an infrastructure of the geological model, wherein the geological model comprises an input layer, a convolution layer, a pooling layer, a full connection layer, a batch normalization layer, a Dropout layer and an output layer, and setting an activation function;
step S6: training a geological model, and training the geological model by using a training set to obtain a trained geological model;
step S7: model parameter optimization, namely performing parameter optimization on the trained geologic model by using a MECOA algorithm to obtain an optimized geologic model;
step S8: evaluating and optimizing the geological model, evaluating the optimized geological model by using a test set, calculating the accuracy, recall and F1 value to obtain a calculation result, and optimizing the geological model according to the calculation result;
step S9: and generating a geological survey report, and analyzing and explaining data of the geological survey.
In step S1, drilling is performed by using a drilling machine, geological samples are collected, and geological parameters are collected by using sensors, which specifically include the following:
the drilling machine records the depth, diameter and inclination angle of the drilling hole at the same time;
geological samples include subsurface rock and soil that provide information about geologic structures, lithology, and underlying sequences;
the sensor comprises an earthquake sensor, a stress sensor, a pressure sensor and a temperature sensor, wherein the earthquake sensor is buried underground, the earthquake magnitude, the earthquake source position and the propagation speed of earthquake waves are acquired, the stress sensor is arranged on the wall of a borehole, the stress state, the deformation and the stress release of underground rock are acquired, the pressure sensor is arranged in the borehole, the underground water level, the underground gas pressure and the pore water pressure are acquired, the temperature sensor is arranged in the borehole, and the underground heat flow, the rock thermal property and the underground water temperature are acquired.
In step S6, the geological model is trained by using the training set, referring to fig. 2, which specifically includes the following steps:
step S61: defining samples and labels, defining each data in a training set as a sample, and setting a corresponding real label for each sample to represent expected geological model prediction output;
step S62: forward propagation, namely inputting a training set into a geological model, and calculating the output of the geological model through forward propagation;
step S63: loss function calculation, namely measuring the difference degree between the output of the geological model and the real label by using global loss functions based on norm and Huber, wherein the following formula is used:
;
;
step S64: back propagation, by means of a back propagation algorithm, the parameters of the geologic model are updated layer by layer from the input layer to the output layer.
By executing the above operation, aiming at the problem that an unbalanced data set or an unbalanced class cannot be processed by a common loss function, if the number of samples in a certain class is small, the loss function may be biased to predict the class of more samples, and the class of less samples is ignored, so that the performance of a model is reduced.
Fourth embodiment, referring to fig. 3, based on the above embodiment, in step S7, parameter optimization is performed on the trained geologic model using MECOA algorithm, and specifically includes the following steps:
step S71: initializing parameters, and defining a population, a population size, a maximum iteration number, an initial position and speed range of individuals in the population, and a position and speed of the population;
step S72: calculating fitness values, converting initial positions of individuals into parameter values of a geological model, simulating by using the geological model, and calculating the fitness values of each individual to obtain the fitness values of each individual, wherein the formula is as follows:
;
wherein, fitness is the fitness value,for the number of individuals to be counted,for the predicted output of the geologic model,the actual observation output is obtained;
step S73: determining a leading individual, and selecting the individual with the highest fitness as the leading individual;
step S74: updating the position and speed of the individual, updating the position and speed of each individual by using multiple strategies according to the position and speed of the leading individual, wherein the multiple strategies comprise a random strategy, a following strategy and a exploring strategy, and the updated individual is obtained by using the following formula:
;
;
wherein,for individualsAt the time ofIs provided in the position of (a),for individualsAt the time ofIs used for the speed of the (c) in the (c),is time ofIs to be added to the next time of the (c),for individualsAt the time ofIs used to determine the optimal individual position of the (c),as a global optimum position for the device,in order to lead the location of the individual,as the weight of the inertia is given,、、in order to accelerate the factor of the velocity,、、is a random number;
step S75: calculating the fitness value of the updated individual, converting the updated individual position into a parameter value of a geological model, simulating by using the geological model, and calculating the fitness value of each updated individual to obtain the fitness value of each updated individual;
step S76: updating the leading individual, and if the updated individual fitness value is better than that of the leading individual, updating the leading individual;
step S77: iterating the steps S73 to S76 until the maximum iteration number is reached;
step S78: outputting an optimal solution, wherein the optimal solution is the geological model parameter value corresponding to the leading individual.
By executing the above operations, aiming at the problems that the traditional parameter optimization algorithm generally uses a local search algorithm such as gradient descent and the like, a local optimal solution is easy to sink into and a global optimal solution cannot be found, and meanwhile, the robustness is low and the reliability is low, the MECOA algorithm is adopted to perform parameter optimization on the trained geologic model, the geologic model can be more accurate and reliable by optimizing the parameters of the geologic model, the geologic model can be helped to converge to the optimal solution more quickly, the geologic model can be more robust to the change of input data by parameter optimization, the optimized parameters can enable the geologic model to be more robust to noise and abnormal data, and the reliability and stability of the geologic model are improved, so that a better solution is provided for a geologic survey method.
Fifth embodiment referring to fig. 4, the embodiment is based on the above embodiment, and the artificial intelligence-based geological survey system provided by the present invention includes a data acquisition and preprocessing module, a feature extraction module, a data analysis and modeling module, a model training and optimization module, and a result analysis and visualization module;
the data acquisition and preprocessing module is used for collecting geological data and geological parameters, carrying out data cleaning and normalization processing, obtaining preprocessed geological data and geological parameters and sending the acquired data to the feature extraction module;
the feature extraction module receives the data sent by the data acquisition and preprocessing module, selects the feature combination with the minimum feature evaluation to determine the finally selected feature, and sends the data to the data analysis and modeling module;
the data analysis and modeling module receives the data sent by the feature extraction module and builds a geological model by taking the CNN model as a basic framework;
the model training and optimizing module trains the geological model, and parameter optimization is carried out on the trained geological model by using the MECOA algorithm;
and the result analysis and visualization module is used for analyzing and visually displaying the geological survey result by using the geological model.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
The invention and its embodiments have been described above with no limitation, and the actual construction is not limited to the embodiments of the invention as shown in the drawings. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.
Claims (5)
1. The geological survey method based on artificial intelligence is characterized in that: the method comprises the following steps:
step S1: data collection, namely drilling by using a drilling machine, collecting geological samples, extracting geological data from the geological samples, wherein the geological data comprise a bottom layer sequence, age, physical properties and mineral resources of the geological samples, and collecting geological parameters by adopting sensors;
step S2: preprocessing data, namely preprocessing geological data and geological parameters, and performing data cleaning and normalization processing to obtain preprocessed geological data and geological parameters;
step S3: feature extraction, namely performing feature extraction on the preprocessed geological data and geological parameters to obtain geological samples and geological parameters after feature extraction;
step S4: data sorting and segmentation, namely, a data set is established, geological data and geological parameters after feature extraction are recorded and sorted and then put into the data set, the data set is divided into a training set, a verification set and a test set, 70% of the data set is the training set, 15% of the data set is the verification set, and 15% of the data set is the test set;
step S5: establishing a geological model, selecting a CNN model as an infrastructure of the geological model, wherein the geological model comprises an input layer, a convolution layer, a pooling layer, a full connection layer, a batch normalization layer, a Dropout layer and an output layer, and setting an activation function;
step S6: training a geological model, and training the geological model by using a training set to obtain a trained geological model;
step S7: model parameter optimization, namely performing parameter optimization on the trained geologic model by using a MECOA algorithm to obtain an optimized geologic model;
step S8: evaluating and optimizing the geological model, evaluating the optimized geological model by using a test set, calculating the accuracy, recall and F1 value to obtain a calculation result, and optimizing the geological model according to the calculation result;
step S9: and generating a geological survey report, and analyzing and explaining data of the geological survey.
2. The artificial intelligence based geological survey method of claim 1, wherein: in step S1, drilling is performed by using a drilling machine, geological samples are collected, and geological parameters are collected by using sensors, which specifically include the following:
the drilling machine records the depth, diameter and inclination angle of the drilling hole at the same time;
geological samples include subsurface rock and soil that provide information about geologic structures, lithology, and underlying sequences;
the sensor comprises an earthquake sensor, a stress sensor, a pressure sensor and a temperature sensor, wherein the earthquake sensor is buried underground, the earthquake magnitude, the earthquake source position and the propagation speed of earthquake waves are acquired, the stress sensor is arranged on the wall of a borehole, the stress state, the deformation and the stress release of underground rock are acquired, the pressure sensor is arranged in the borehole, the underground water level, the underground gas pressure and the pore water pressure are acquired, the temperature sensor is arranged in the borehole, and the underground heat flow, the rock thermal property and the underground water temperature are acquired.
3. The artificial intelligence based geological survey method of claim 1, wherein: in step S6, the geological model is trained by using the training set, which specifically includes the following steps:
step S61: defining samples and labels, defining each data in a training set as a sample, and setting a corresponding real label for each sample to represent expected geological model prediction output;
step S62: forward propagation, namely inputting a training set into a geological model, and calculating the output of the geological model through forward propagation;
step S63: loss function calculation, namely measuring the difference degree between the output of the geological model and the real label by using global loss functions based on norm and Huber, wherein the following formula is used:
;
;
step S64: back propagation, by means of a back propagation algorithm, the parameters of the geologic model are updated layer by layer from the input layer to the output layer.
4. The artificial intelligence based geological survey method of claim 1, wherein: in step S7, parameter optimization is performed on the trained geologic model by using MECOA algorithm, which specifically includes the following steps:
step S71: initializing parameters, and defining a population, a population size, a maximum iteration number, an initial position and speed range of individuals in the population, and a position and speed of the population;
step S72: calculating fitness values, converting initial positions of individuals into parameter values of a geological model, simulating by using the geological model, and calculating the fitness values of each individual to obtain the fitness values of each individual, wherein the formula is as follows:
;
wherein, fitness is the fitness value,for the number of individuals->For predictive output of geologic model, +.>The actual observation output is obtained;
step S73: determining a leading individual, and selecting the individual with the highest fitness as the leading individual;
step S74: updating the position and speed of the individual, updating the position and speed of each individual by using multiple strategies according to the position and speed of the leading individual, wherein the multiple strategies comprise a random strategy, a following strategy and a exploring strategy, and the updated individual is obtained by using the following formula:
;
;
wherein,for individuals->At time->Is (are) located>For individuals->At time->Speed of->For time->Is the next moment of->For individuals->At time->Is the optimal individual position of->Is the global optimum position->For guiding the individual position->Is inertial weight, ++>、/>、/>For acceleration factor, ++>、/>、/>Is a random number;
step S75: calculating the fitness value of the updated individual, converting the updated individual position into a parameter value of a geological model, simulating by using the geological model, and calculating the fitness value of each updated individual to obtain the fitness value of each updated individual;
step S76: updating the leading individual, and if the updated individual fitness value is better than that of the leading individual, updating the leading individual;
step S77: iterating the steps S73 to S76 until the maximum iteration number is reached;
step S78: outputting an optimal solution, wherein the optimal solution is the geological model parameter value corresponding to the leading individual.
5. An artificial intelligence based geological survey system for implementing an artificial intelligence based geological survey method according to any of claims 1-4, wherein: the system comprises a data acquisition and preprocessing module, a feature extraction module, a data analysis and modeling module, a model training and optimizing module and a result analysis and visualization module;
the data acquisition and preprocessing module is used for collecting geological data and geological parameters, carrying out data cleaning and normalization processing, obtaining preprocessed geological data and geological parameters and sending the acquired data to the feature extraction module;
the feature extraction module receives the data sent by the data acquisition and preprocessing module, selects the feature combination with the minimum feature evaluation to determine the finally selected feature, and sends the data to the data analysis and modeling module;
the data analysis and modeling module receives the data sent by the feature extraction module and builds a geological model by taking the CNN model as a basic framework;
the model training and optimizing module trains the geological model, and parameter optimization is carried out on the trained geological model by using the MECOA algorithm;
and the result analysis and visualization module is used for analyzing and visually displaying the geological survey result by using the geological model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311802844.3A CN117454256A (en) | 2023-12-26 | 2023-12-26 | Geological survey method and system based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311802844.3A CN117454256A (en) | 2023-12-26 | 2023-12-26 | Geological survey method and system based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117454256A true CN117454256A (en) | 2024-01-26 |
Family
ID=89589647
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311802844.3A Pending CN117454256A (en) | 2023-12-26 | 2023-12-26 | Geological survey method and system based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117454256A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109615118A (en) * | 2018-11-23 | 2019-04-12 | 泉州装备制造研究所 | Based on big data hazards control Informatization Service integrated control system and method |
CN109948825A (en) * | 2018-11-12 | 2019-06-28 | 中国石油大学(华东) | Favorable Reservoir development area prediction technique based on improvement PSO in conjunction with Adaboost |
CN112614060A (en) * | 2020-12-09 | 2021-04-06 | 深圳数联天下智能科技有限公司 | Method and device for rendering human face image hair, electronic equipment and medium |
CN113011523A (en) * | 2021-04-14 | 2021-06-22 | 中国矿业大学 | Unsupervised depth field adaptation method based on distributed countermeasure |
CN113361090A (en) * | 2021-06-01 | 2021-09-07 | 辽宁工程技术大学 | Method for establishing strip mine slope displacement prediction model |
CN113514877A (en) * | 2021-07-07 | 2021-10-19 | 浙江大学 | Self-adaptive quick earthquake magnitude estimation method |
CN113627606A (en) * | 2020-05-06 | 2021-11-09 | 江苏科技大学 | RBF neural network optimization method based on improved particle swarm optimization |
CN116629712A (en) * | 2023-07-21 | 2023-08-22 | 武汉理工大学三亚科教创新园 | Submarine shield tunnel construction quality risk assessment method based on PSO-BP neural network |
CN116816340A (en) * | 2023-07-04 | 2023-09-29 | 长沙理工大学 | Stratum lithology and geological structure while-drilling intelligent identification method and system |
CN117216676A (en) * | 2023-06-30 | 2023-12-12 | 成都理工大学 | Method and system for predicting lithology in real time based on acoustic vibration signal characteristics in drilling and rock breaking process |
-
2023
- 2023-12-26 CN CN202311802844.3A patent/CN117454256A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109948825A (en) * | 2018-11-12 | 2019-06-28 | 中国石油大学(华东) | Favorable Reservoir development area prediction technique based on improvement PSO in conjunction with Adaboost |
CN109615118A (en) * | 2018-11-23 | 2019-04-12 | 泉州装备制造研究所 | Based on big data hazards control Informatization Service integrated control system and method |
CN113627606A (en) * | 2020-05-06 | 2021-11-09 | 江苏科技大学 | RBF neural network optimization method based on improved particle swarm optimization |
CN112614060A (en) * | 2020-12-09 | 2021-04-06 | 深圳数联天下智能科技有限公司 | Method and device for rendering human face image hair, electronic equipment and medium |
CN113011523A (en) * | 2021-04-14 | 2021-06-22 | 中国矿业大学 | Unsupervised depth field adaptation method based on distributed countermeasure |
CN113361090A (en) * | 2021-06-01 | 2021-09-07 | 辽宁工程技术大学 | Method for establishing strip mine slope displacement prediction model |
CN113514877A (en) * | 2021-07-07 | 2021-10-19 | 浙江大学 | Self-adaptive quick earthquake magnitude estimation method |
CN117216676A (en) * | 2023-06-30 | 2023-12-12 | 成都理工大学 | Method and system for predicting lithology in real time based on acoustic vibration signal characteristics in drilling and rock breaking process |
CN116816340A (en) * | 2023-07-04 | 2023-09-29 | 长沙理工大学 | Stratum lithology and geological structure while-drilling intelligent identification method and system |
CN116629712A (en) * | 2023-07-21 | 2023-08-22 | 武汉理工大学三亚科教创新园 | Submarine shield tunnel construction quality risk assessment method based on PSO-BP neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Witter et al. | Uncertainty and risk evaluation during the exploration stage of geothermal development: A review | |
WO2007092596A2 (en) | Methods and apparatus for predicting the hydrocarbon production of a well location | |
CN108717201B (en) | A kind of tunnel surrounding microquake sources localization method | |
US20210381362A1 (en) | Method and apparatus for estimating lithofacies by learning well logs | |
CN115291281B (en) | Real-time micro-earthquake magnitude calculation method and device based on deep learning | |
CN117386350A (en) | Intelligent monitoring method for perforation of oil and gas well | |
CN117454256A (en) | Geological survey method and system based on artificial intelligence | |
CN115046516A (en) | Sliding surface position accurate determination method based on single-sliding-surface r-type deep hole inclination measuring curve | |
CN111751878A (en) | Method and device for predicting transverse wave velocity | |
Entezari et al. | A data-driven approach to predict shear wave velocity from CPTu measurements | |
Khalili et al. | Reservoir modeling & simulation: Advancements, challenges, and future perspectives | |
CN109886420B (en) | Self-adaptive intelligent prediction system for cutting height of coal mining machine | |
Castellini et al. | History matching and uncertainty quantification assisted by global optimization techniques | |
CN109326004B (en) | Automatic arrangement method for water system sediment sampling points | |
CN101609050A (en) | A kind of intelligence system according to core cake identification terrestrial stress | |
CN116911216B (en) | Reservoir oil well productivity factor assessment and prediction method | |
CN117174203B (en) | Logging curve response analysis method for sandstone uranium ores | |
Wang et al. | Grouped machine learning methods for predicting rock mass parameters in a tunnel boring machine‐driven tunnel based on fuzzy C‐means clustering | |
CN116047598B (en) | Oil exploration method and system based on artificial intelligence | |
CN117852416B (en) | Multimode grouting precontrolled analysis method and system based on digital geological model | |
RU2782505C2 (en) | Method and computer system for processing borehole data | |
CN117250658B (en) | Method for creating seismic dataset of investigation region | |
JP2000258551A (en) | Device and method for analyzing underground resources and computer-readable storage medium storing underground resource analysis program | |
CN115688005A (en) | Tunnel rock mass quality identification method and system based on multi-scale drilling model fusion | |
CN108875109B (en) | Method and system for predicting abnormal formation pressure |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |