CN116816340A - Stratum lithology and geological structure while-drilling intelligent identification method and system - Google Patents
Stratum lithology and geological structure while-drilling intelligent identification method and system Download PDFInfo
- Publication number
- CN116816340A CN116816340A CN202310811946.5A CN202310811946A CN116816340A CN 116816340 A CN116816340 A CN 116816340A CN 202310811946 A CN202310811946 A CN 202310811946A CN 116816340 A CN116816340 A CN 116816340A
- Authority
- CN
- China
- Prior art keywords
- drilling
- lithology
- stratum
- geological
- layer
- 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
- 238000005553 drilling Methods 0.000 title claims abstract description 145
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 43
- 238000005755 formation reaction Methods 0.000 claims abstract description 43
- 238000013528 artificial neural network Methods 0.000 claims abstract description 25
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000004140 cleaning Methods 0.000 claims abstract description 11
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 5
- 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
- 210000002445 nipple Anatomy 0.000 claims description 3
- 230000001902 propagating effect Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 13
- 238000010276 construction Methods 0.000 description 7
- 238000005422 blasting Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 230000005641 tunneling Effects 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000011435 rock Substances 0.000 description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Landscapes
- Investigation Of Foundation Soil And Reinforcement Of Foundation Soil By Compacting Or Drainage (AREA)
Abstract
The invention is suitable for the technical field of geotechnical engineering, and relates to an intelligent identification method and system for formation lithology and geological structure while drilling, wherein the intelligent identification method comprises the following steps: collecting drilling parameters of the drilling machine under different formations by the monitoring function of the drilling machine and combining sensors arranged on the short joint of the drill rod; preprocessing and cleaning the parameter data set while drilling; determining main characteristics of different stratum lithology and geological structures, and extracting the main characteristics of the stratum lithology and the geological structures from the parameter data set while drilling; establishing stratum models under different strata based on the existing geological exploration data, and verifying the reliability of the stratum models by comparing the stratum models with the existing geological exploration data; based on the while-drilling parameters and stratum models of different strata, a feature and parameter mapping set of lithology and geological structures of the different strata is established, and the lithology and geological structures of the different strata are intelligently identified by using a feedforward neural network method. The method has the advantages of simple flow and convenient and fast process, and improves the identification precision of stratum lithology and geological structures.
Description
Technical Field
The invention belongs to the technical field of geotechnical engineering, and particularly relates to an intelligent identification method and system for formation lithology and geological structure while drilling.
Background
Along with the continuous development of the economy in China, the geotechnical engineering construction quantity is continuously increased, and as more and more complicated geological conditions are encountered in engineering construction, fine lithology and geological structure identification are reliable bases for defining the spatial distribution and quantity of different lithology of a target area, so that specific geological information is provided for regional geological feature depiction, and important bases are provided for the design and optimization of tunneling parameters, blasting parameters and supporting parameters in actual engineering, so that the identification technology of the lithology and the geological structure plays an immeasurable role in the geotechnical engineering field.
The while-drilling sensing technology is an important technical means in the field of geotechnical engineering, and is a technology for monitoring drilling parameters such as drilling speed, jacking force, rotating speed, torque and the like of a drilling machine in real time in the drilling process of the drilling machine, synchronously uploading data to a terminal for processing and analyzing, and finally identifying stratum lithology and geological structure. The traditional lithology recognition technology often adopts methods such as excavation disclosure, drilling coring, geological radar, experience judgment and the like, so that the cost is high, the construction period is long, the subjectivity is strong, and the traditional lithology recognition method cannot accurately judge the rock type and characteristics for complex geological conditions. The existing intelligent lithology while drilling recognition technology can automatically process a large amount of data, but has a plurality of defects, such as simple algorithm, and cannot comprehensively consider the mapping relation between various parameters while drilling and stratum lithology and geological structure; the identification model cannot accurately represent the lithology and geological structure information of the real stratum, so that the identification is inaccurate; the quality of the obtained parameters while drilling is low, the identification result is affected, and the like.
Therefore, how to ensure the accuracy of intelligently identifying the formation lithology and the geological structure is a problem to be solved urgently by the person skilled in the art.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide an intelligent identification method for formation lithology and geological structure while drilling, so as to solve the problem of low identification accuracy of the formation lithology and geological structure in the prior art; in addition, the invention also provides an intelligent identification system for formation lithology and geological structure while drilling.
In order to solve the technical problems, the invention adopts the following technical scheme:
s10, collecting while-drilling parameters of the drilling machine under different formations by the monitoring function of the drilling machine and combining sensors arranged on the short joint of the drill rod;
s20, preprocessing and cleaning the collected parameter data set while drilling;
s30, determining main characteristics of different stratum lithology and geologic structures, and extracting the main characteristics of the stratum lithology and geologic structures from the preprocessed and cleaned parameter data set while drilling;
s40, building stratum models under different strata based on the existing geological exploration data, and verifying the reliability of the stratum models by comparing the stratum models with the existing geological exploration data;
s50, based on the while-drilling parameters and stratum models of different strata, establishing characteristic and parameter mapping sets of lithology and geological structures of different strata, and intelligently identifying the lithology and geological structures of different strata by using a feedforward neural network method.
Further, the specific steps of the step S20 are as follows:
s201, carrying out wavelet decomposition on the collected parameter data while drilling to realize denoising treatment;
s202, setting a threshold value by using a soft threshold value method after wavelet decomposition to remove burrs and peaks of parameter data while drilling;
s203, performing wavelet reconstruction on the processed decomposition coefficient to restore the original signal.
Further, in the step S10, the while-drilling parameters include drilling speed, jacking force, drill rod rotation speed, drill rod torque and temperature and humidity.
Further, in step S30, main characteristics of lithology and geological structure of different strata are determined according to the indoor model test and the field data, and a relation curve of drilling speed, jacking force, drill rod rotating speed, drill rod torque and temperature and humidity is established, so as to provide automatic and fine lithology recognition criteria under specific conditions.
Further, the specific steps of the step S50 are as follows:
s501, based on the parameter data sets while drilling after preprocessing and cleaning in the step S20, a training set and a testing set are established, a feedforward neural network technology is used for establishing a drilling speed, a jacking force, a rotating speed, a torque and a temperature and humidity and identification models of different stratum lithologies and geological structures, training set data are defined as input layers, the drilling speed, the jacking force, the rotating speed of a drill rod, the torque and the temperature and humidity of the drill rod are defined as output layers, and the identification models are expressed as follows:
input layer to hidden layer:
the inputs to each hidden layer neuron are:
wherein ,output of the ith node representing layer l-1,/th node>Weight value representing j nodes from i-th node of l-1 layer to l-th layer,/-, and>representing the bias value of the j-th layer;
hidden layer:
the output of each hidden layer neuron is:
wherein f (·) is a nonlinear activation function;
hidden layer to output layer:
the output of the output layer is:
wherein ,nl-1 Representing the number of neurons in the penultimate layer,weight value representing from the jth node of the penultimate layer to the kth node of the output layer,/->A bias value representing a kth node of the output layer;
s502, after forward propagation is completed, the difference between the output predicted by the model and the actual label is measured by using a loss function, and the loss function is expressed as follows:
wherein ,represents mean square error, Y represents true value, < ->Representing a predicted value, K representing the number of samples;
s503, training the neural network by using the training set based on the difference measured by the loss function, back propagating the error to the network to calculate the gradient of each node, and updating the weight and bias connected with each node by using the calculated gradient;
s504, evaluating the accuracy and reliability of the neural network by using the test set, and if the accuracy and reliability of the neural network do not meet the requirements, readjusting the network structure or the optimization algorithm, and repeating the steps S501 to S503 until the loss function is not changed obviously or reduced;
s505, identifying the lithology and the geological structure under different strata by using the trained neural network, and inputting the newly acquired parameter data set while drilling into the trained neural network to output the corresponding stratum lithology and geological structure.
Further, in step S40, according to the geological data of different regions, the lithology and the geological structure of the stratum under different strata are determined, finite element software is adopted to build stratum models under different geology, the reliability of the models is verified by comparing the matching degree of the stratum models and the known geological conditions, and the model parameters are adjusted to optimize the stratum models based on the verification result until an ideal stratum model is obtained.
Further, the method further comprises step S60: and displaying the identification results of different stratum lithology and geological structures to a user in a visual mode.
Further, in the step S60, the visualization manner includes a three-dimensional modeling map of the stratum model, a lithology section map, a fault feature analysis map, and a mineral composition analysis result.
In a second aspect, the present invention also provides a system adopting the above method, including:
the data acquisition module is arranged on a drill pipe nipple of the drilling machine and comprises a plurality of sensors for collecting drilling parameters of the drilling machine when the drilling machine drills different strata;
the data preprocessing module is used for preprocessing and cleaning the acquired parameter data set while drilling;
the feature extraction module is used for extracting main features of stratum lithology and geological structures from the preprocessed and cleaned parameter data set while drilling;
and the intelligent identification module is used for intelligently identifying stratum lithology and geological structures.
Further, the system also comprises a result display module for visually displaying the identification result to the user.
Compared with the prior art, the stratum lithology and geological structure while-drilling intelligent identification method and system provided by the invention have at least the following beneficial effects:
in the prior art, methods such as excavation disclosure, drilling coring, geological radar, experience judgment and the like are often adopted, so that the cost is high, the construction period is long, the subjectivity is strong, the rock type and the characteristics cannot be accurately judged by the traditional lithology recognition method for complex geological conditions, and the existing intelligent lithology while drilling recognition technology can automatically process a large amount of data, but still has a plurality of defects to cause inaccurate recognition; the quality of the obtained parameters while drilling is low, the identification result is affected, and the like. The invention has simple flow and convenient operation, and the data acquisition system respectively monitors and stores the while-drilling parameters under different stratums, including drilling speed, jacking force, drill rod rotating speed, drill rod torque and temperature and humidity by arranging the sensor on the guiding drilling device; the preprocessing system preprocesses and cleans the acquired original data through a wavelet denoising method to obtain a data set with higher quality; the intelligent recognition system establishes feature and parameter mapping sets of different stratum lithology and geological structures based on a feedforward neural network method, and achieves the effect of accurately recognizing the different stratum lithology and geological structures; according to the identification results of stratum lithology and geological structure, references can be provided for the design and optimization of tunneling parameters, blasting parameters and supporting parameters, compared with the traditional lithology while drilling identification, the method and system can reflect the lithology and geological structure information of the current stratum more accurately, more conveniently and more quickly, can timely adjust drilling machine parameters according to the identification results of the stratum lithology and geological structure of a drilling area, can improve drilling speed, and adopts reasonable deviation correction measures to avoid engineering accidents such as drilling stuck holes and collapsing holes.
Drawings
In order to more clearly illustrate the solution of the invention, a brief description will be given below of the drawings required for the description of the embodiments, it being apparent that the drawings in the following description are some embodiments of the invention and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intelligent identification method while drilling of stratum lithology and geological structure provided by the embodiment of the invention;
FIG. 2 is a schematic diagram of the operation of a data acquisition module of an intelligent identification system while drilling for formation lithology and geological structure according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a data preprocessing module of an intelligent identification system while drilling for formation lithology and geological structure according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an identification model of an intelligent identification method while drilling for formation lithology and geological structure provided by the embodiment of the invention;
FIG. 5 is a schematic diagram of a system for intelligent identification while drilling of formation lithology and geological structure according to an embodiment of the present invention;
reference numerals: 10-a data acquisition module; 20-a data preprocessing module; 30-a feature extraction module; 40-an intelligent recognition module; 50-results display module.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
The invention provides an intelligent identification method of stratum lithology and geological structure while drilling, which is applied to the exploration identification process of stratum lithology and geological structure in geotechnical engineering, and comprises the following steps:
s10, collecting while-drilling parameters of the drilling machine under different formations by the monitoring function of the drilling machine and combining sensors arranged on the short joint of the drill rod;
s20, preprocessing and cleaning the collected parameter data set while drilling;
s30, determining main characteristics of different stratum lithology and geologic structures, and extracting the main characteristics of the stratum lithology and geologic structures from the preprocessed and cleaned parameter data set while drilling;
s40, building stratum models under different strata based on the existing geological exploration data, and verifying the reliability of the stratum models by comparing the stratum models with the existing geological exploration data;
s50, based on the while-drilling parameters and stratum models of different strata, establishing characteristic and parameter mapping sets of lithology and geological structures of different strata, and intelligently identifying the lithology and geological structures of different strata by using a feedforward neural network method.
The method has the advantages of simple flow and convenient and fast process, and greatly improves the identification accuracy of stratum lithology and geological structures.
In order to make the person skilled in the art better understand the solution of the present invention, the technical solution of the embodiment of the present invention will be clearly and completely described below with reference to the accompanying drawings.
The invention provides an intelligent identification method of formation lithology and geological structure while drilling, which is applied to the exploration identification process of formation lithology and geological structure in geotechnical engineering, and is characterized in that drilling parameters are monitored, transmitted, analyzed and recorded in real time in the drilling process by a drilling machine, and the change and the characteristics of each drilling parameter are synchronously analyzed during drilling, so that the formation lithology and geological structure information of a drilling area can be automatically identified, and specifically, in combination with fig. 1 to 4, the intelligent identification method of formation lithology and geological structure while drilling comprises the following steps:
s10, collecting while-drilling parameters of the drilling machine under different formations by the monitoring function of the drilling machine and combining sensors arranged on the short joint of the drill rod;
specifically, the sensor comprises a displacement sensor, a pressure sensor, a rotation speed sensor, a torque sensor and a temperature and humidity sensor, and is respectively used for monitoring and acquiring drilling parameters under different strata, including drilling speed, jacking force, drill rod rotation speed, drill rod torque, temperature and humidity and the like.
S20, preprocessing and cleaning the collected parameter data set while drilling, and establishing a training set and a testing set so as to ensure the quality of data processed subsequently;
specifically, step S20 includes the steps of:
s201, wavelet decomposition is carried out on the original data (collected parameter data while drilling), so that not only can local information of the original data be extracted, but also different sub-signals can be selected for denoising, and further, a more accurate denoising effect is achieved;
s202, after wavelet decomposition, setting a threshold value by using a soft threshold value method to remove burrs and peaks in original data so as to improve the data quality;
s203, performing wavelet reconstruction on the processed decomposition coefficients to restore original signals, wherein at the moment, the original data are preprocessed and cleaned, so that the data quality of subsequent operations is ensured.
S30, determining main characteristics of different stratum lithology and geological structures based on an indoor model test and field data, and extracting the main characteristics of the stratum lithology and the geological structures from the pre-processed and cleaned parameter data set while drilling;
specifically, in step S30, main characteristics of different lithology and geological structures are determined according to the indoor model test and the field data, a drilling speed, a jacking force, a drill rod rotating speed, a drill rod torque and a temperature and humidity relation curve are established, and automatic fine lithology recognition criteria under specific conditions, such as abrupt increase and decrease of drilling parameters, correlation coefficients of the drilling parameters, distribution and change trend of the drilling parameters, and the like, are given, so that the characteristic extraction system can accurately extract main characteristics of stratum lithology and geological structures from the preprocessed data set.
S40, building stratum models under different strata based on the existing geological exploration data, and verifying the reliability of the stratum models by comparing the stratum models with the existing geological exploration data;
specifically, in step S40, according to geological data of different regions, formation lithology and geological structure under different strata are determined, finite element software is adopted to build formation models under different geology, reliability of the models is verified by comparing the matching degree of the formation models and known geological conditions, and model parameters are continuously adjusted to optimize the formation models based on verification results until ideal formation models are obtained for accurately identifying formation lithology and geological structure.
S50, based on the while-drilling parameters and stratum models of different strata, establishing characteristic and parameter mapping sets of lithology and geological structures of different strata, and intelligently identifying the lithology and geological structures of different strata by using a feedforward neural network method.
Specifically, the step of step S50 is as follows:
s501, based on the parameter data set while drilling after preprocessing and cleaning in the step S20, a training set and a testing set are established, a feedforward neural network technology is used for establishing a drilling speed, a jacking force, a drill rod rotating speed, a drill rod torque and a temperature and humidity and identification models of different stratum lithologies and geological structures, the training set data are defined as an input layer, the drilling speed, the jacking force, the drill rod rotating speed, the drill rod torque and the temperature and humidity are included, the stratum lithologies and the geological structures are defined as an output layer, and the identification models have the following formulas:
input layer to hidden layer:
the inputs to each hidden layer neuron are:
wherein ,output of the ith node representing layer l-1,/th node>Weight value representing j nodes from i-th node of l-1 layer to l-th layer,/-, and>representing the bias value of the j-th layer;
hidden layer:
the output of each hidden layer neuron is:
wherein f (·) is a nonlinear activation function;
hidden layer to output layer:
the output of the output layer is:
wherein ,nl-1 Representing the number of neurons in the penultimate layer,weight value representing from the jth node of the penultimate layer to the kth node of the output layer,/->A bias value representing a kth node of the output layer;
s502, after forward propagation is completed, the difference between the output predicted by the model and the actual label is measured by using a loss function, and the loss function is expressed as follows:
wherein ,represents mean square error, Y represents true value, < ->Representing a predicted value, K representing the number of samples;
s503, training a neural network by using a training set based on the difference measured by the loss function, and back propagating errors to the network to calculate the gradient of each node, wherein the process calculates the partial derivatives of each node on each sample by layer based on a chain rule, and updates the weight and bias connected with each node by using the calculated gradient;
s504, evaluating the accuracy and reliability of the neural network by using the test set, and if the result does not meet the requirement, readjusting the network structure or the optimization algorithm, and repeating the steps S501 to S503 until the loss function is not changed obviously or reduced;
s505, identifying lithology and geological structures under different strata by using the trained neural network, and inputting a newly acquired parameter data set while drilling (drilling speed, thrust force, drill rod rotating speed, drill rod torque and temperature and humidity) into the trained neural network so as to output corresponding stratum lithology and geological structures.
And S60, displaying the identification result to a user in a visual way.
Specifically, in step S60, the method of visualization includes a three-dimensional modeling map of a formation model, a lithology section map, a fault signature analysis map, and a mineral composition analysis result.
Further, in this embodiment, parameters in the drilling process, such as the vibration frequency, the drilling speed, the drilling pressure, the current, etc., of the drill bit can be adjusted through the recognition results of different geology, so as to improve the drilling efficiency and the service life of the drill bit; in the specific construction process, references can be provided for the design and optimization of tunneling parameters, blasting parameters and supporting parameters, and the quality and safety in the construction process are improved.
The embodiment of the invention also provides an intelligent identifying system for formation lithology and geological structure while drilling by adopting the method in the embodiment, as shown in fig. 5, in the embodiment, the intelligent identifying system for formation lithology and geological structure while drilling comprises: the data acquisition module 10 is arranged on a drill pipe nipple of the drilling machine and comprises a plurality of sensors, wherein the sensors are used for collecting drilling parameters of the drilling machine under different formations, including drilling speed, jacking force, drill pipe rotating speed, drill pipe torque and temperature and humidity; the data preprocessing module 20 is used for preprocessing and cleaning the acquired parameter data set while drilling by a wavelet denoising method to obtain a data set with higher quality; a feature extraction module 30 for extracting main features of formation lithology and geologic structure from the preprocessed and cleaned parameter data set while drilling; the intelligent recognition module 40 establishes feature and parameter mapping sets of different stratum lithology and geological structures based on a feedforward neural network method, achieves the effect of accurately recognizing the different stratum lithology and geological structures, is used for intelligently recognizing the stratum lithology and geological structures, and can provide references for tunneling parameters, blasting parameters and support parameter design and optimization.
Further, in this embodiment, as shown in fig. 5, the device further includes a result display module 50 for visually displaying the identification result to the user.
Compared with the prior art, the intelligent identifying method and system for the formation lithology and the geological structure while drilling, which are disclosed by the embodiment, are often adopted in the prior art, and are high in cost, long in construction period, strong in subjectivity and the like, and for complex geological conditions, the rock type and characteristics cannot be accurately judged by the traditional lithology identifying method, and the existing intelligent lithology while drilling identifying technology can automatically process a large amount of data, but still has a plurality of defects to cause inaccurate identification; the quality of the obtained parameters while drilling is low, the identification result is affected, and the like. The invention has simple flow and convenient operation, and the data acquisition system respectively monitors and stores the while-drilling parameters under different stratums, including drilling speed, jacking force, drill rod rotating speed, drill rod torque and temperature and humidity by arranging the sensor on the guiding drilling device; the preprocessing system preprocesses and cleans the acquired original data through a wavelet denoising method to obtain a data set with higher quality; the intelligent recognition system establishes feature and parameter mapping sets of different stratum lithology and geological structures based on a feedforward neural network method, and achieves the effect of accurately recognizing the different stratum lithology and geological structures; according to the identification results of stratum lithology and geological structure, references can be provided for the design and optimization of tunneling parameters, blasting parameters and supporting parameters, compared with the traditional lithology while drilling identification, the method and system can reflect the lithology and geological structure information of the current stratum more accurately, more conveniently and more quickly, can timely adjust drilling machine parameters according to the identification results of the stratum lithology and geological structure of a drilling area, can improve drilling speed, and adopts reasonable deviation correction measures to avoid engineering accidents such as drilling stuck holes and collapsing holes.
It is apparent that the above-described embodiments are merely preferred embodiments of the present invention, not all of which are shown in the drawings, which do not limit the scope of the invention. This invention may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the invention are directly or indirectly applied to other related technical fields, and are also within the scope of the invention.
Claims (10)
1. The intelligent identification method for the formation lithology and the geological structure while drilling is characterized by comprising the following steps of:
s10, collecting while-drilling parameters of the drilling machine under different formations by the monitoring function of the drilling machine and combining sensors arranged on the short joint of the drill rod;
s20, preprocessing and cleaning the collected parameter data set while drilling;
s30, determining main characteristics of different stratum lithology and geologic structures, and extracting the main characteristics of the stratum lithology and geologic structures from the preprocessed and cleaned parameter data set while drilling;
s40, building stratum models under different strata based on the existing geological exploration data, and verifying the reliability of the stratum models by comparing the stratum models with the existing geological exploration data;
s50, based on the while-drilling parameters and stratum models of different strata, establishing characteristic and parameter mapping sets of lithology and geological structures of different strata, and intelligently identifying the lithology and geological structures of different strata by using a feedforward neural network method.
2. The method for intelligent identification while drilling of stratum lithology and geologic structure according to claim 1, wherein the specific steps of step S20 are as follows:
s201, carrying out wavelet decomposition on the collected parameter data while drilling to realize denoising treatment;
s202, setting a threshold value by using a soft threshold value method after wavelet decomposition to remove burrs and peaks of parameter data while drilling;
s203, performing wavelet reconstruction on the processed decomposition coefficient to restore the original signal.
3. The method for intelligent identification while drilling of stratum lithology and geologic structure according to claim 1, wherein in step S10, the while drilling parameters include drilling speed, jacking force, drill rod rotation speed, drill rod torque and temperature and humidity.
4. The intelligent identification method for formation lithology and geological structure while drilling according to claim 3, wherein in the step S30, main characteristics of different formation lithology and geological structure are determined according to indoor model test and field data, drilling speed, jacking force, rotating speed, torque and temperature and humidity relation curves are established, and automatic fine identification criteria of lithology under specific conditions are given.
5. The method for intelligent identification while drilling of stratum lithology and geologic structure according to claim 4, wherein the specific steps of step S50 are as follows:
s501, based on the parameter data sets while drilling after preprocessing and cleaning in the step S20, a training set and a testing set are established, a feedforward neural network technology is used for establishing a drilling speed, a jacking force, a drill rod rotating speed, drill rod torque and temperature and humidity and identification models of different stratum lithologies and geological structures, the training set data are defined as input layers, the drilling speed, the jacking force, the drill rod rotating speed, the drill rod torque and temperature and humidity are included, the stratum lithologies and the geological structures are defined as output layers, and the identification models are expressed as follows:
input layer to hidden layer:
the inputs to each hidden layer neuron are:
wherein ,output of the ith node representing layer l-1,/th node>Weight value representing j nodes from i-th node of l-1 layer to l-th layer,/-, and>representing the bias value of the j-th layer;
hidden layer:
the output of each hidden layer neuron is:
wherein f (·) is a nonlinear activation function;
hidden layer to output layer:
the output of the output layer is:
wherein ,nl-1 Representing the number of neurons in the penultimate layer,weight value representing from the jth node of the penultimate layer to the kth node of the output layer,/->A bias value representing a kth node of the output layer;
s502, after forward propagation is completed, the difference between the output predicted by the model and the actual label is measured by using a loss function, and the loss function is expressed as follows:
wherein ,represents mean square error, Y represents true value, < ->Representing a predicted value, K representing the number of samples;
s503, training the neural network by using the training set based on the difference measured by the loss function, back propagating the error to the network to calculate the gradient of each node, and updating the weight and bias connected with each node by using the calculated gradient;
s504, evaluating the accuracy and reliability of the neural network by using the test set, and if the accuracy and reliability of the neural network do not meet the requirements, readjusting the network structure or the optimization algorithm, and repeating the steps S501 to S503 until the loss function is not changed obviously or reduced;
s505, identifying the lithology and the geological structure under different strata by using the trained neural network, and inputting the newly acquired parameter data set while drilling into the trained neural network to output the corresponding stratum lithology and geological structure.
6. The intelligent identification method while drilling of the formation lithology and the geological structure according to claim 1, wherein in the step S40, the formation lithology and the geological structure under different formations are determined according to geological data of different areas, the formation model under different geology is built by adopting finite element software, the reliability of the model is verified by comparing the matching degree of the formation model and the known geological condition, and the model parameters are adjusted to optimize the formation model until an ideal formation model is obtained based on the verification result.
7. The method for intelligent identification while drilling of stratum lithology and geologic structure according to claim 1, further comprising step S60: and displaying the identification results of different stratum lithology and geological structures to a user in a visual mode.
8. The method for intelligent identification while drilling of formation lithology and geologic structure according to claim 7, wherein in step S60, the visualization means comprises three-dimensional modeling map of formation model, lithology section map, fault feature analysis map and mineral composition analysis result.
9. A system employing the method of any one of claims 1 to 8, comprising:
the data acquisition module is arranged on a drill pipe nipple of the drilling machine and comprises a plurality of sensors for collecting drilling parameters of the drilling machine when the drilling machine drills different strata;
the data preprocessing module is used for preprocessing and cleaning the acquired parameter data set while drilling;
the feature extraction module is used for extracting main features of stratum lithology and geological structures from the preprocessed and cleaned parameter data set while drilling;
and the intelligent identification module is used for intelligently identifying stratum lithology and geological structures.
10. The system of claim 9, further comprising a result presentation module for visually presenting the identification result to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310811946.5A CN116816340A (en) | 2023-07-04 | 2023-07-04 | Stratum lithology and geological structure while-drilling intelligent identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310811946.5A CN116816340A (en) | 2023-07-04 | 2023-07-04 | Stratum lithology and geological structure while-drilling intelligent identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116816340A true CN116816340A (en) | 2023-09-29 |
Family
ID=88118222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310811946.5A Pending CN116816340A (en) | 2023-07-04 | 2023-07-04 | Stratum lithology and geological structure while-drilling intelligent identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116816340A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454256A (en) * | 2023-12-26 | 2024-01-26 | 长春工程学院 | Geological survey method and system based on artificial intelligence |
-
2023
- 2023-07-04 CN CN202310811946.5A patent/CN116816340A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454256A (en) * | 2023-12-26 | 2024-01-26 | 长春工程学院 | Geological survey method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2321064C2 (en) | Method for building a reversible three-dimensional hydrodynamic model of earth, calibrated in real time during drilling | |
| RU2723805C9 (en) | Method and computer system for control of drilling of the wells | |
| US11899154B2 (en) | DAS same-well monitoring real-time microseismic effective event identification method based on deep learning | |
| CN105277982B (en) | A kind of mud shale total content of organic carbon earthquake prediction method | |
| US10145985B2 (en) | Static earth model calibration methods and systems using permeability testing | |
| WO2009129461A2 (en) | System and method for improved depth measurement correction | |
| CN111254912B (en) | Anchoring and grouting engineering management system based on geological logging big data | |
| CN116816340A (en) | Stratum lithology and geological structure while-drilling intelligent identification method and system | |
| US11789173B1 (en) | Real-time microseismic magnitude calculation method and device based on deep learning | |
| CN109543915B (en) | Method for identifying total organic carbon content of hydrocarbon source rock in whole well section based on logging information | |
| CN104153768B (en) | A kind of method evaluating Granite Reservoir storage and collection performance | |
| CN112100930B (en) | Formation pore pressure calculation method based on convolutional neural network and Eaton formula | |
| CN114066084A (en) | Method and system for predicting phase permeation curve based on machine learning | |
| CN110118994B (en) | Continental facies hydrocarbon source rock quantitative prediction method based on seismic inversion and machine learning | |
| CN116677367A (en) | Intelligent real-time rock stratum inversion identification method based on while-drilling parameter characteristics | |
| CN116203631A (en) | Method for predicting lithology based on seismic data | |
| CN215256164U (en) | Device for monitoring formation change of drilling machine in drilling process | |
| CN112064617B (en) | Soil-stone mixture foundation quality detection method | |
| CN115238564A (en) | Method for automatically matching and optimizing blasting parameters based on drilling parameters and overbreak and undermining results | |
| US11693141B2 (en) | Methods and systems for processing borehole dispersive waves with a physics-based machine learning analysis | |
| CN112282730A (en) | Real-time monitoring and evaluating method for deformation of underground casing induced by reservoir fracturing modification | |
| CN113189672A (en) | Tunnel advanced geological prediction method based on multi-attribute inversion | |
| CN112859172A (en) | Longitudinal and transverse wave micro-logging data processing method and device | |
| CN113464126A (en) | Device and method for monitoring stratum change of drilling machine in drilling process | |
| RU2782505C2 (en) | Method and computer system for processing borehole data |
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 |