CN117471572A - Coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove wave - Google Patents
Coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove wave Download PDFInfo
- Publication number
- CN117471572A CN117471572A CN202311432946.0A CN202311432946A CN117471572A CN 117471572 A CN117471572 A CN 117471572A CN 202311432946 A CN202311432946 A CN 202311432946A CN 117471572 A CN117471572 A CN 117471572A
- Authority
- CN
- China
- Prior art keywords
- coal
- thickness
- earthquake
- wave
- ground penetrating
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 268
- 230000005540 biological transmission Effects 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000000149 penetrating effect Effects 0.000 title claims abstract description 62
- 238000012545 processing Methods 0.000 claims abstract description 56
- 238000005065 mining Methods 0.000 claims abstract description 38
- 238000003384 imaging method Methods 0.000 claims abstract description 30
- 238000013499 data model Methods 0.000 claims abstract description 29
- 238000012937 correction Methods 0.000 claims abstract description 14
- 230000003068 static effect Effects 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims description 71
- 239000011159 matrix material Substances 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 26
- 238000005259 measurement Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 18
- 230000009466 transformation Effects 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 230000005284 excitation Effects 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000000556 factor analysis Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 17
- 230000010287 polarization Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 239000004484 Briquette Substances 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- 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
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Abstract
The invention belongs to the technical field of coal seam prediction, and discloses a coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove waves. Exciting and receiving a ground penetrating radar and an earthquake transmission groove wave, exciting the earthquake transmission groove wave by adopting the ground penetrating radar, carrying out standardization processing on stored coal thickness earthquake transmission groove wave signals, acquiring an earthquake transmission groove wave map, identifying a plurality of coal sub-layers in a coal bed, and simultaneously carrying out static correction processing on the plurality of coal sub-layers to finally obtain a coal sub-layer which is not lower than two layers; respectively carrying out imaging treatment on each coal sub-layer subjected to static correction treatment, and constructing a coal seam superposition identification data model; and acquiring an image after the total coal seam superposition treatment, and predicting the coal thickness. The coal thickness prediction method based on the ground penetrating radar and the earthquake transmission groove wave is high in accuracy, and provides data basis for acquiring water containing characteristics and water containing and guiding characteristics of a water containing layer in a zone and a roadway and a coal mining face in a future zone.
Description
Technical Field
The invention belongs to the technical field of coal seam prediction, and particularly relates to a coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove waves.
Background
The water enrichment of the goaf of the coal mine can greatly influence the safe production of the coal mine, the area of a certain mining area of a certain coal mine is 7.09 square kilometers, 80% of the mining area is the goaf of the coal mine, the geological structure in the area is relatively clear, and most of accumulated water in the goaf flows away through a drainage roadway, but the possibility of partial accumulated water is not eliminated; the area of the other mining area is 5.01 square kilometers, 30% of the mining area is a coal seam goaf, the geological structure in the area is unknown, and most of accumulated water in the goaf flows away through a drainage roadway, but partial accumulated water is not discharged. The geological hydrologic conditions in the mining area are complex, and the coal mining layer is seriously threatened by rich (water guiding) structures and empty water. Therefore, ground exploration is needed to find out the water-bearing characteristics and water-guiding characteristics of the aquifer in the area, and a basis is provided for planning the roadway and the coal mining face in the future area.
The earthquake transmission wave excited in the coal bed is formed by the fact that part of energy is subjected to multiple total reflections through the top plate and the bottom plate of the coal bed, superimposed and interfered by each other, guided by the coal bed and only spread in two-dimensional space near the coal bed, and the groove wave is the earthquake transmission groove wave only spread in the coal bed, and is also called coal bed wave or guided wave. In a coal-bearing rock system, the density of a coal bed is generally smaller than that of upper and lower surrounding rocks, the propagation speed of a seismic transmission groove wave in the coal bed is low, and the groove wave can be classified into a lux type and a Rayleigh type according to the vibration direction of particles and polarization characteristics of the particles. The lux type groove wave is formed by interference of horizontal polarized transverse waves (SH waves), and particles are parallel to the coal seam layer surface and perpendicular to the wave propagation direction in the coal seam; the most important feature of the channel wave is dispersion, i.e. vibrations of different frequencies propagate at different speeds, so that the channel wave trains disperse with the propagation, while the phase velocity of the channel wave differs significantly from the group velocity. Phase velocity refers to the propagation velocity of single frequency harmonic vibrations. Group velocity refers to the propagation velocity of a wave packet consisting of multiple frequency close harmonics and vibrations. The stronger the dispersion, the greater the phase velocity and group velocity difference.
The slot wave exploration can achieve a certain exploration effect on the coal thickness, but the exploration and research on the aspect of estimating the coal thickness are still needed. The slot wave exploration utilizes the guidance effect of the coal bed on the earthquake transmission slot wave, and can also effectively survey various geological structures in the coal bed.
Ground penetrating radar (Ground Penetrating radar. Gpr) is a geophysical method for detecting the characteristics and distribution of substances inside a medium by transmitting and receiving high-frequency electromagnetic waves through antennas. There are various early names for ground penetrating radar. Such as Ground-sounding Radar (Ground-sounding Radar), subsurface Radar (Sub-surface Radar), geological Radar (Geo Radar), pulse Radar (Impulse Radar), surface penetrating Radar (Surface Penetrating Radar), etc., all refer to an electromagnetic wave method for detecting the internal structure of a geological target by using high-frequency pulse electromagnetic waves, which is oriented to the geological exploration target.
Due to the high precision, high efficiency and nondestructive characteristics of ground penetrating radar detection, the method is mainly used in many fields such as archaeology, mineral exploration, disaster geological investigation, geotechnical engineering investigation, engineering quality detection, building structure detection and military target detection.
The working frequency range of the ground penetrating radar is between 1M and 1GHz, and the propagation in the underground medium is mainly based on displacement current. Although the physical mechanism of the ground penetrating radar and the seismic method are different from the measured physical quantity (electromagnetic wave and elastic wave), the kinematic characteristics of the two are consistent, and the wave equation with similar form is followed, but the physical meaning of the parameters is different. The similarity of the kinematic features enables the technical achievements of the method for seismic exploration to be borrowed from the data acquisition, the data processing (including processing software) and the data interpretation of the ground penetrating radar method. In recent years, as electromagnetic wave theory research is in progress, some electromagnetic characteristics such as polarization characteristics and the like are being studied more intensively. And is developed and applied in radar equipment, acquisition technology, data processing methods and the like.
Ground penetrating radars (Ground Penetrating Radar, GPR) usually employ antennas to emit high-frequency pulse electromagnetic waves to a detection target for detection. The depth of the detection target is generally satisfied with far field conditions and can be approximately regarded as propagating in the form of plane waves. The polarization of plane waves refers to the characteristic of the change over time of the direction of the field vector at a given point in space. Generally, three types of linear polarization, circular polarization, and elliptical polarization can be distinguished. Polarization of waves is an important characteristic of electromagnetic waves, and waves of different polarization modes have different engineering applications. When the subsurface medium is anisotropic, plane waves incident in linear polarization may transform their reflected echoes into elliptical polarization. Therefore, information on the physical properties of the underground medium can be obtained by studying the change in the polarization of the radar wave.
Through the above analysis, the problems and defects existing in the prior art are as follows: the prior art has poor accuracy in predicting the coal thickness, and can not provide data basis for acquiring the water-containing characteristics and the water-containing and water-guiding characteristics of a water-containing layer in a zone and providing data basis for roadways and coal mining surfaces in future zones.
Disclosure of Invention
In order to overcome the problems in the related art, the disclosed embodiments of the invention provide a coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove waves.
The technical scheme is as follows: the coal thickness prediction method based on the ground penetrating radar and the earthquake transmission groove wave is applied to a ground penetrating radar and earthquake transmission groove wave data processing module, and comprises the following steps:
s1, exciting and receiving a ground penetrating radar and an earthquake transmission groove wave, exciting the earthquake transmission groove wave by adopting the ground penetrating radar, burying a coal thickness photodetector at different positions away from an excitation point, transmitting the earthquake transmission groove wave to a coal thickness detection terminal through a signal wire, amplifying the earthquake transmission groove wave through the coal thickness detection terminal, and storing after analog-to-digital conversion;
s2, carrying out standardized processing on the stored coal thickness seismic transmission channel wave signals, obtaining a seismic transmission channel wave map, identifying a plurality of coal sub-layers in a coal bed, and simultaneously carrying out static correction processing on the plurality of coal sub-layers to finally obtain a coal sub-layer which is not lower than two layers; respectively carrying out imaging treatment on each coal sub-layer subjected to static correction treatment, and constructing a coal seam superposition identification data model;
and S3, acquiring an image after the total coal seam superposition processing based on the constructed coal seam superposition identification data model, and predicting the coal thickness.
In step S2, the normalization process includes: according to the stored coal thickness seismic transmission channel wave signals, a matrix X affecting the detection precision is established, and the expression is:
X＝(x ab ) n×p
wherein X is a matrix affecting the detection precision, n is the number of sample groups for measuring the coal thickness, and p is an external factor affecting the detection precision, and the external factors comprise the coal seam mining depth, the coal seam inclination angle, the mining thickness, the coal seam compressive strength and the coal seam inclined length; x is x ab Representing the signal value of the coal thickness seismic transmission channel wave, wherein a represents the transverse reference quantity of coal, and b represents the longitudinal reference quantity of coal;
eliminating the influence of different dimensions of each coal thickness actual measurement sample and the error caused by the fact that each coal thickness actual measurement sample has a relatively large variation or value difference, wherein a standardized formula is shown as follows:
in the method, in the process of the invention,for the b-th evaluationAverage value of coal briquette thickness real measurement sample S b Standard deviation of the coal thickness test sample was evaluated for the b-th. X is X ab Signal value x representing coal thickness seismic transmission channel wave ab Normalized actual values of the coal thickness seismic transmission channel wave signals.
In step S2, the imaging process includes:
according to the matrix X affecting the detection precision, the external factors p affecting the detection precision are expressed as a combination form of m new variables, m < p, and the combination model is as follows:
expressed in matrix form as:
X＝AF+i∈
wherein f m Is a common sample which is two-by-two orthogonal, beta p Is a special sample; i.e ab A = 1,2, …, n, the load of the common sample; b=1, 2, …, p, a is the load matrix of the common sample, x p In order to influence the detection value under the external factor p of the detection precision, F is the load matrix coefficient of the common sample, i is the load of the sample, and E is the load coefficient of the sample.
In one embodiment, the imaging process steps are as follows:
(1) Calculating variance matrix according to matrix X affecting detection accuracyThe expression is:
wherein r is ab Representing the current coal thickness seismic transmission channel wave signal value, and p multiplied by p represents a matrix of external factors p influencing the detection precision;
(2) Calculating the characteristic root mu according to the variance matrix a And its corresponding feature vector;
(3) Determining the number p of public samples by taking the fact that the variance accumulation percentage of p previous eigenvalues is more than 75% as a judgment principle;
(4) And performing factor rotation and calculating a load matrix A of the common sample to obtain a detection precision value.
In step S2, constructing a coalbed superposition identification data model includes:
(1) Constructing an unsupervised model;
(2) The non-supervision model carries out simulation training on the sample:
(3) Determining factor analysis and data sources influencing detection precision;
(4) Extracting a main component;
(5) Acquiring a coal seam superposition identification data model;
(6) And (5) checking a model.
In the step (1), the unsupervised model has 3 layers, namely an input layer, an hidden layer and an output layer; nonlinear transformation is arranged between the input layer and the hidden layer, and linear transformation is arranged from the hidden layer to the output layer; in the unsupervised model, the input layer is used only as a channel to transmit signals, the transformation function of neurons in the hidden layer is a radial basis function, signals can be transmitted from the input layer to the hidden layer through nonlinear transformation, and the output layer is a response to the input signals; the training process of the unsupervised model is divided into two steps, unsupervised learning is firstly carried out, the sum between an input layer and an hidden layer is calculated, a common unsupervised function is a Gaussian function, and an output value is obtained by the following activation functions:
in the method, in the process of the invention, ||x p -c a I is the European norm, c a Is the cluster center, sigma a Standard deviation of the basis function; x is x p -c a The distance of the euro type is expressed,representing the sum output value, x, between the input layer and the hidden layer p Representing the sum between an input layer and an hidden layer in the coal thickness of an external factor p affecting the detection precision;
solving weight omega between hidden layer and output layer a Finally, the output of the unsupervised model is obtained:
wherein omega a Connecting weights from the hidden layer to the output layer; y is p The p-th sample corresponds to the output of the model.Representing the sum output value between the input layer and the hidden layer, n representing an integer; a represents the transverse reference quantity of coal;
in the step (5), a coal seam superposition identification data model is obtained by combining imaging processing and an unsupervised model, the imaging processing is adopted to carry out dimension reduction processing on original variables, the correlation between the original variables is eliminated, and a new comprehensive variable with the accumulated contribution rate of more than 75% is extracted to be used as a new input of the unsupervised model; and carrying out simulation training on the sample through an unsupervised model, and finally carrying out prediction results on the sample through a test sample.
In step (3), determining the factor analysis and the data source that affect the detection accuracy includes: selecting 5 coal thickness real measurement samples of coal mining depth, coal seam inclination angle, mining thickness, coal seam compressive strength and coal seam inclined length as main control factors affecting detection accuracy, and respectively representing the 5 coal thickness real measurement samples by M1, M2, M3, M4 and M5, wherein the 5 coal thickness real measurement samples obtain specific data through mine geological data;
imaging processing is carried out through software, variance contribution rate and accumulated contribution rate of each component are calculated, the first 4 components are selected as new predicted coal thickness actual measurement samples, and rotation is carried out by adopting a maximum variance method; calculating factor scores by adopting a regression method, respectively marking the factor scores as N1, N2, N3 and N4, and finally obtaining score models of 4 new components; for the main component F1, the load contribution of the components of the compressive strength of the coal bed and the inclined length of the coal bed is larger, and the factors are summarized as the characteristics of the top layer of the coal bed and the geometric dimension factors of the mining surface, and the factors have a strong positive correlation with the compressive strength of the coal bed and a strong negative correlation with the inclined length of the coal bed; the main component N2 has larger load on the mining depth and mainly represents the mining depth factor; the main component N3 has larger load on the dip angle of the coal seam and mainly represents the development characteristics of the coal seam; the main component N4 has larger load on the mining thickness and mainly represents the factor of the mining thickness of the coal seam;
wherein N is a For component score, M a The processed values are normalized for the raw data.
In the step (5), the score values of the score models N1, N2, N3 and N4 of the new components are used as input factors of the models, the number of input nodes of the models is 4, the standardized value of the detection precision value of the training sample is used as a prediction object, and the number of output nodes of the models is 1; training an unsupervised model through a function newrb provided by software, wherein a command calling format is as follows:
net＝newrb(P,T,goal,spread,mn,df)
wherein net is a radial basis function neural network prediction model to be established, newrb is a call command of the radial basis function neural network model in MATLAB, P is a model input matrix, and scores of four main components, namely N1, N2, N3 and N4, extracted by imaging processing are obtained; t is a target output matrix and is a standardized value of the detection precision value of the training sample; gol is mean square error, set to 0.00001; the spread is an extension function; mn is the maximum neuron number of the hidden layer; df is the display frequency of the iterative process.
Another object of the present invention is to provide a coal thickness prediction system based on ground penetrating radar and earthquake transmission groove wave, which is applied to a ground penetrating radar and earthquake transmission groove wave data processing module, and implements the coal thickness prediction method based on ground penetrating radar and earthquake transmission groove wave, the system includes:
the ground penetrating radar and the earthquake transmission groove wave excitation and receiving module is used for exciting the earthquake transmission groove wave by adopting the ground penetrating radar;
the coal thickness photodetector is buried at different positions from the excitation point, transmits the earthquake transmission groove wave to the coal thickness detection terminal through the signal wire, and stores the earthquake transmission groove wave after amplifying and analog-digital converting through the coal thickness detection terminal;
the method comprises the steps of constructing a coal seam superposition identification data model module, performing standardized processing on stored coal thickness seismic transmission trough wave signals, obtaining a seismic transmission trough wave map, identifying multiple coal sublayers in a coal seam, and performing static correction processing on the multiple coal sublayers to finally obtain a coal sublayer which is not lower than two layers; respectively carrying out imaging treatment on each coal sub-layer subjected to static correction treatment, and constructing a coal seam superposition identification data model;
and the coal thickness prediction module is used for acquiring an image after the total coal seam superposition processing based on the constructed coal seam superposition identification data model and predicting the coal thickness.
By combining all the technical schemes, the invention has the advantages and positive effects that: the coal thickness prediction method based on the ground penetrating radar and the earthquake transmission groove wave is high in accuracy, and provides data basis for acquiring water containing characteristics and water containing and guiding characteristics of a water containing layer in a zone and a roadway and a coal mining face in a future zone.
The invention adopts imaging processing and combines an unsupervised model to improve the detection precision, and further improves the prediction precision of the model and increases the application range of the model, so that the model can be better applied to the detection of the coal seam.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure;
FIG. 1 is a flow chart of a coal thickness prediction method based on ground penetrating radar and earthquake transmission channel waves provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of comparing predicted values with real values of training samples according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a coal thickness prediction system based on ground penetrating radar and seismic transmission channel waves provided by an embodiment of the invention;
in the figure: 1. excitation and receiving modules of ground penetrating radar and earthquake transmission channel wave; 2. a coal thickness photodetector; 3. constructing a coal seam superposition identification data model module; 4. and a coal thickness prediction module.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to the appended drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The invention may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit or scope of the invention, which is therefore not limited to the specific embodiments disclosed below.
Embodiment 1, as shown in fig. 1, the method for predicting the coal thickness based on the ground penetrating radar and the earthquake transmission groove wave provided by the embodiment of the invention is applied to a data processing module of the ground penetrating radar and the earthquake transmission groove wave, and comprises the following steps:
s1, exciting and receiving ground penetrating radar and earthquake transmission groove waves, and exciting the earthquake transmission groove waves by adopting the ground penetrating radar;
meanwhile, embedding coal thickness photo detectors at different positions from the excitation point, transmitting the seismic transmission channel wave to a coal thickness detection terminal through a signal wire, amplifying the seismic transmission channel wave through the coal thickness detection terminal, and storing after analog-digital conversion;
s2, carrying out standardized processing on the stored coal thickness seismic transmission channel wave signals, obtaining a seismic transmission channel wave map, and identifying multiple coal sublayers in the coal bed;
meanwhile, carrying out static correction treatment on the multi-layer coal sub-layer to finally obtain the coal sub-layer which is not lower than two layers; respectively carrying out imaging treatment on each coal sub-layer subjected to static correction treatment, and constructing a coal seam superposition identification data model;
and S3, acquiring an image after the total coal seam superposition processing based on the constructed coal seam superposition identification data model, and predicting the coal thickness.
In the embodiment of the present invention, in step S2, the normalization process includes:
according to the stored coal thickness seismic transmission channel wave signals, a matrix X affecting the detection precision is established, and the expression is:
X＝(x ab ) n×p
wherein X is a matrix affecting the detection precision, n is the number of sample groups for measuring the coal thickness, and p is an external factor affecting the detection precision, and the external factors comprise the coal seam mining depth, the coal seam inclination angle, the mining thickness, the coal seam compressive strength and the coal seam inclined length; x is x ab Representing the signal value of the coal thickness seismic transmission channel wave, wherein a represents the transverse reference quantity of coal, and b represents the longitudinal reference quantity of coal;
eliminating the influence of different dimensions of each coal thickness actual measurement sample and the error caused by the fact that each coal thickness actual measurement sample has a relatively large variation or value difference, wherein a standardized formula is shown as follows:
in the method, in the process of the invention,mean value of the b-th evaluation coal thickness real measurement sample, S b Standard deviation of the coal thickness test sample was evaluated for the b-th. X is X ab Signal value x representing coal thickness seismic transmission channel wave ab Normalized actual values of the coal thickness seismic transmission channel wave signals.
In an embodiment of the present invention, the imaging process in step S2 includes:
according to the correlation matrix of the variable X, the original p variables are expressed as a combined form of m new variables, m is smaller than p, and the combined model is as follows:
expressed in matrix form as:
X＝AF+i∈
wherein f m Is a common sample which is two-by-two orthogonal, beta p Is a special sample; i.e ab A = 1,2, …, n, the load of the common sample; b=1, 2, …, p, a is the load matrix of the common sample, x p In order to influence the detection value under the external factor p of the detection precision, F is the load matrix coefficient of the public sample, i is the load of the sample, E is the load coefficient of the sample, and the coefficients are selected through experiments and actual needs.
In the embodiment of the present invention, the imaging processing step in step S2 is as follows:
(1) Calculating variance matrix according to matrix X affecting detection accuracyThe expression is:
wherein r is ab Representing the current coal thickness seismic transmission channel wave signal value, and p multiplied by p represents a matrix of external factors p influencing the detection precision; a represents the transverse reference quantity of coal, b represents the longitudinal reference quantity of coal;
(2) Calculating the characteristic root mu according to the variance matrix a And its corresponding feature vector;
(3) Determining the number p of public samples by taking the fact that the variance accumulation percentage of p previous eigenvalues is more than 75% as a judgment principle;
(4) And performing factor rotation and calculating a load matrix A of the common sample to obtain a detection precision value.
In the embodiment of the invention, step S2 builds a coal seam superposition identification data model, which comprises the following steps:
(1) An unsupervised model is built, and the unsupervised model comprises 3 layers, namely an input layer, an hidden layer and an output layer; nonlinear transformation is arranged between the input layer and the hidden layer, and linear transformation is arranged from the hidden layer to the output layer; in the unsupervised model, the input layer is used only as a channel to transmit signals, the transformation function of neurons in the hidden layer is a radial basis function, signals can be transmitted from the input layer to the hidden layer through nonlinear transformation, and the output layer is a response to the input signals; the training process of the unsupervised model is divided into two steps, unsupervised learning is firstly carried out, the sum between an input layer and an hidden layer is calculated, a common unsupervised function is a Gaussian function, and an output value is obtained by the following activation functions:
in the method, in the process of the invention, ||x p -c a I is the European norm, c a Is the cluster center, sigma a Standard deviation of the basis function; x is x p -c a The distance of the euro type is expressed,representing the sum output value, x, between the input layer and the hidden layer p Representing the sum between an input layer and an hidden layer in the coal thickness of an external factor o affecting the detection precision;
solving weight omega between hidden layer and output layer a Finally, the output of the unsupervised model is obtained:
wherein omega a Connecting weights from the hidden layer to the output layer; y is p The p-th sample corresponds to the output of the model.Representing the sum output value between the input layer and the hidden layer, n representing an integer; a represents the transverse reference quantity of coal;
(2) The non-supervision model carries out simulation training on the sample: the coal seam superposition identification data model is formed by combining imaging processing and an unsupervised model and is used for collecting respective unique advantages of the two methods, performing dimension reduction processing on original variables by adopting the imaging processing, eliminating correlation among the original variables, and extracting a new comprehensive variable with the accumulated contribution rate of more than 75% as a new input of the unsupervised model; and carrying out simulation training on the sample through an unsupervised model, and finally carrying out prediction results on the sample through a test sample.
(3) Determining analysis and data sources of factors influencing detection precision: selecting 5 coal thickness real measurement samples of coal mining depth, coal seam inclination angle, mining thickness, coal seam compressive strength and coal seam inclined length as main control factors affecting detection accuracy, and respectively representing the 5 coal thickness real measurement samples by M1, M2, M3, M4 and M5, wherein the 5 coal thickness real measurement samples can obtain relevant specific data through mine geological data;
(4) Extracting main components: after standardized processing is carried out on the training sample data, carrying out correlation analysis on 5 main control factors influencing detection precision; certain correlation exists among the factors, wherein the correlation coefficients among the inclined length of the coal seam, the inclination angle of the coal seam, the mining height and the compressive strength of the coal seam are respectively-0.34, 0.32 and-0.34, which shows that the factors have stronger correlation;
imaging processing is carried out through software, variance contribution rate and accumulated contribution rate of each component are calculated, the first 4 components are selected as new predicted coal thickness actual measurement samples, and rotation is carried out by adopting a maximum variance method; calculating factor scores by adopting a regression method, respectively marking the factor scores as N1, N2, N3 and N4, and finally obtaining score models of 4 new components; for the main component F1, the load contribution of the components of the compressive strength of the coal bed and the inclined length of the coal bed is larger, and the factors are summarized as the characteristics of the top layer of the coal bed and the geometric dimension factors of the mining surface, and the factors have a strong positive correlation with the compressive strength of the coal bed and a strong negative correlation with the inclined length of the coal bed; the main component N2 has larger load on the mining depth and mainly represents the mining depth factor; the main component N3 has larger load on the dip angle of the coal seam and mainly represents the development characteristics of the coal seam; the main component N4 has larger load on the mining thickness and mainly represents the factor of the mining thickness of the coal seam;
wherein N is a For component score, M a The processed values are normalized for the raw data.
(5) Acquiring a coal seam superposition identification data model:
the method comprises the steps that score values of four new components N1, N2, N3 and N4 extracted through imaging processing are used as input factors of a model, the number of input nodes of the model is 4, a standardized value of a detection precision value of a training sample is used as a prediction object, and the number of output nodes of the model is 1; training an unsupervised model through a function newrb provided by software, wherein a command calling format is as follows:
net＝newrb(P,T,goal,spread,mn,df)
the net is a radial basis function neural network prediction model to be built, newrg is a call command of the radial basis function neural network model in MATLAB, P is a model input matrix, and scores of four main components, namely N1, N2, N3 and N4, extracted by imaging processing are obtained; t is a target output matrix and is a standardized value of the detection precision value of the training sample; gol is mean square error, set to 0.00001; the spread is an extension function; mn is the maximum neuron number of the hidden layer; df is the display frequency of the iterative process.
When the unsupervised model is trained, gol is set to be 0.000001, mn is set to be 30, df is set to be 5, and when a trial and error method is adopted to determine that the value of the thread is 1 through repeated experiments, the error of the unsupervised network meets the precision requirement, and the approximation effect is best; when the training times reach a plurality of times, the mean square error reaches 6.35279e-30 which is smaller than the set error requirement, and the training is finished; performing inverse standardization processing on the output value of the coal seam superposition identification data model to obtain a detection precision predicted value of a training sample, comparing the detection precision predicted value with a true value, and determining fitting capacity of the model;
(6) And (3) model inspection: performing effect inspection on the model by adopting 3 reserved groups of test samples; after carrying out standardization processing on 3 groups of test sample data according to the standardization processing principle of the training samples, substituting the standardized data into a formula to obtain score values of four new components after imaging processing, substituting the score values into a built coal seam superposition identification data model, and outputting detection precision predicted values of 3 groups of test samples after inverse standardization processing;
mean absolute error MAE, error root mean square RMSE and mean average error are adoptedThe 3 coal thickness real test samples evaluate the effect of the FA-unsupervised model prediction model; establishing an unsupervised model prediction model and a traditional SVM model prediction model which are not subjected to imaging processing based on the same error level, and comparing a prediction result of a test sample with a coal seam superposition identification data model;
the calculation formula is shown as the following formula:
wherein,outputting a value for a node of the model; y is i Is an actual value; n is the number of test samples, n=3; MAE, RMWE, < >>The smaller the value, the smaller the error, indicating that the model's predictive effect is better.
The results show that: the method has good fitting capacity based on the unsupervised model, and simultaneously has stronger generalization capacity and better prediction performance for new samples, and the average absolute error, the root mean square error and the average relative error of the prediction result of the new samples are 4.4658m, 4.7091m and 7.52 percent respectively, which are superior to the unsupervised model which is not subjected to imaging treatment and the traditional SVM prediction model. The model not only can avoid the defect that the traditional prediction method affects the prediction precision without considering the correlation among all influence factors, but also simplifies the dimension of an input layer, reduces the scale, and solves the defects that the traditional neural network model is complicated in training, is easy to sink into local minimum, and the number of hidden layer nodes is difficult to determine and the like in the aspect of processing a nonlinear system. The invention provides an effective approach and method for accurately predicting the detection precision. FIG. 2 is a schematic diagram of comparing predicted values with real values of training samples according to an embodiment of the present invention.
Embodiment 2, as shown in fig. 3, the coal thickness prediction system based on ground penetrating radar and earthquake transmission groove wave provided by the embodiment of the invention is applied to a ground penetrating radar and earthquake transmission groove wave data processing module, and comprises:
the excitation and receiving module 1 of the ground penetrating radar and the earthquake transmission groove wave is used for exciting the earthquake transmission groove wave by adopting the ground penetrating radar;
the coal thickness photodetector 2 is buried at different positions from the excitation point, transmits the earthquake transmission groove wave to the coal thickness detection terminal through a signal wire, and stores the earthquake transmission groove wave after amplifying and analog-digital conversion by the coal thickness detection terminal;
the method comprises the steps of constructing a coal seam superposition identification data model module 3, performing standardized processing on stored coal thickness seismic transmission trough wave signals, obtaining a seismic transmission trough wave map, identifying multiple coal sublayers in a coal seam, and performing static correction processing on the multiple coal sublayers to finally obtain a coal sublayer which is not lower than two layers; respectively carrying out imaging treatment on each coal sub-layer subjected to static correction treatment, and constructing a coal seam superposition identification data model;
and the coal thickness prediction module 4 is used for acquiring an image after the total coal seam superposition processing based on the constructed coal seam superposition identification data model and predicting the coal thickness.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The content of the information interaction and the execution process between the devices/units and the like is based on the same conception as the method embodiment of the present invention, and specific functions and technical effects brought by the content can be referred to in the method embodiment section, and will not be described herein.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. For specific working processes of the units and modules in the system, reference may be made to corresponding processes in the foregoing method embodiments.
Based on the technical solutions described in the embodiments of the present invention, the following application examples may be further proposed.
According to an embodiment of the present application, the present invention also provides a computer apparatus, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor performs the steps of any of the various method embodiments described above.
Embodiments of the present invention also provide a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of the respective method embodiments described above.
The embodiment of the invention also provides an information data processing terminal, which is used for providing a user input interface to implement the steps in the method embodiments when being implemented on an electronic device, and the information data processing terminal is not limited to a mobile phone, a computer and a switch.
The embodiment of the invention also provides a server, which is used for realizing the steps in the method embodiments when being executed on the electronic device and providing a user input interface.
Embodiments of the present invention also provide a computer program product which, when run on an electronic device, causes the electronic device to perform the steps of the method embodiments described above.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc.
While the invention has been described with respect to what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (10)
1. The coal thickness prediction method based on the ground penetrating radar and the earthquake transmission groove wave is characterized by being applied to a ground penetrating radar and earthquake transmission groove wave data processing module, and comprises the following steps of:
s1, exciting and receiving a ground penetrating radar and an earthquake transmission groove wave, exciting the earthquake transmission groove wave by adopting the ground penetrating radar, burying a coal thickness photodetector at different positions away from an excitation point, transmitting the earthquake transmission groove wave to a coal thickness detection terminal through a signal wire, amplifying the earthquake transmission groove wave through the coal thickness detection terminal, and storing after analog-to-digital conversion;
s2, carrying out standardized processing on the stored coal thickness seismic transmission channel wave signals, obtaining a seismic transmission channel wave map, identifying a plurality of coal sub-layers in a coal bed, and simultaneously carrying out static correction processing on the plurality of coal sub-layers to finally obtain a coal sub-layer which is not lower than two layers; respectively carrying out imaging treatment on each coal sub-layer subjected to static correction treatment, and constructing a coal seam superposition identification data model;
and S3, acquiring an image after the total coal seam superposition processing based on the constructed coal seam superposition identification data model, and predicting the coal thickness.
2. The method for predicting the thickness of coal based on penetrating slot waves of ground penetrating radar and earthquake according to claim 1, wherein in step S2, the normalization process includes:
according to the stored coal thickness seismic transmission channel wave signals, a matrix X affecting the detection precision is established, and the expression is:
X＝(x ab ) n×p
wherein X is a matrix affecting the detection precision, n is the number of sample groups for measuring the coal thickness, and p is an external factor affecting the detection precision, and the external factors comprise the coal seam mining depth, the coal seam inclination angle, the mining thickness, the coal seam compressive strength and the coal seam inclined length; x is x ab Representing the signal value of the coal thickness seismic transmission channel wave, wherein a represents the transverse reference quantity of coal, and b represents the longitudinal reference quantity of coal;
eliminating the influence of different dimensions of each coal thickness actual measurement sample and the error caused by the fact that each coal thickness actual measurement sample has a relatively large variation or value difference, wherein a standardized formula is shown as follows:
in the method, in the process of the invention,mean value of the b-th evaluation coal thickness real measurement sample, S b Standard deviation, X, of the b-th evaluation coal thickness real measurement sample ab Signal value x representing coal thickness seismic transmission channel wave ab Normalized actual values of the coal thickness seismic transmission channel wave signals.
3. The method for predicting the thickness of coal based on penetrating slot waves of ground penetrating radar and earthquake according to claim 1, wherein in step S2, the imaging process includes:
according to the matrix X affecting the detection precision, the external factors p affecting the detection precision are expressed as a combination form of m new variables, m < p, and the combination model is as follows:
expressed in matrix form as:
X＝AF+i∈
wherein f m Is a common sample which is two-by-two orthogonal, beta p Is a special sample; i.e ab A = 1,2, …, n, the load of the common sample; b=1, 2, …, p, a is the load matrix of the common sample, x p In order to influence the detection value under the external factor p of the detection precision, F is the load matrix coefficient of the common sample, i is the load of the sample, and E is the load coefficient of the sample.
4. A method for predicting coal thickness based on penetrating slot waves of ground penetrating radar and earthquake according to claim 3, wherein the imaging processing steps are as follows:
(1) Calculating variance matrix according to matrix X affecting detection accuracyThe expression is:
wherein r is ab Representing the current coal thickness seismic transmission channel wave signal value, and p multiplied by p represents a matrix of external factors p influencing the detection precision;
(2) Calculating the characteristic root mu according to the variance matrix a And its corresponding feature vector;
(3) Determining the number p of public samples by taking the fact that the variance accumulation percentage of p previous eigenvalues is more than 75% as a judgment principle;
(4) And performing factor rotation and calculating a load matrix A of the common sample to obtain a detection precision value.
5. The method for predicting the thickness of coal based on penetrating slot waves of ground penetrating radar and earthquake according to claim 1, wherein in step S2, constructing a coal seam superposition identification data model includes:
(1) Constructing an unsupervised model;
(2) The non-supervision model carries out simulation training on the sample:
(3) Determining factor analysis and data sources influencing detection precision;
(4) Extracting a main component;
(5) Acquiring a coal seam superposition identification data model;
(6) And (5) checking a model.
6. The method for predicting the coal thickness based on the penetrating slot waves of the ground penetrating radar and the earthquake according to claim 5, wherein in the step (1), the unsupervised model has 3 layers, namely an input layer, an hidden layer and an output layer; nonlinear transformation is arranged between the input layer and the hidden layer, and linear transformation is arranged from the hidden layer to the output layer; in the unsupervised model, the input layer is used only as a channel to transmit signals, the transformation function of neurons in the hidden layer is a radial basis function, signals can be transmitted from the input layer to the hidden layer through nonlinear transformation, and the output layer is a response to the input signals; the training process of the unsupervised model is divided into two steps, unsupervised learning is firstly carried out, the sum between an input layer and an hidden layer is calculated, a common unsupervised function is a Gaussian function, and an output value is obtained by the following activation functions:
in the method, in the process of the invention, ||x p -c a I is the European norm, c a Is the cluster center, sigma a Standard deviation of the basis function; x is x p -c a The distance of the euro type is expressed,representing the sum output value, x, between the input layer and the hidden layer p Representing the sum between an input layer and an hidden layer in the coal thickness of an external factor p affecting the detection precision;
solving weight omega between hidden layer and output layer a Finally, the output of the unsupervised model is obtained:
wherein omega a Connecting weights from the hidden layer to the output layer; y is p For the output of the model corresponding to the p-th sample,representing the sum output value between the input layer and the hidden layer, n representing an integer; a representsCross reference number of coals.
7. The coal thickness prediction method based on ground penetrating radar and earthquake transmission groove waves according to claim 5, wherein in the step (5), the coal seam superposition identification data model is obtained by combining imaging processing and an unsupervised model, the imaging processing is adopted to perform dimension reduction processing on original variables, correlation among the original variables is eliminated, and a new comprehensive variable with a cumulative contribution rate of more than 75% is extracted as a new input of the unsupervised model; and carrying out simulation training on the sample through an unsupervised model, and finally carrying out prediction results on the sample through a test sample.
8. The method for predicting the thickness of coal based on penetrating slot waves of ground penetrating radar and earthquake of claim 5, wherein in step (3), determining factors analysis and data sources affecting detection accuracy comprises: selecting 5 coal thickness real measurement samples of coal mining depth, coal seam inclination angle, mining thickness, coal seam compressive strength and coal seam inclined length as main control factors affecting detection accuracy, and respectively representing the 5 coal thickness real measurement samples by M1, M2, M3, M4 and M5, wherein the 5 coal thickness real measurement samples obtain specific data through mine geological data;
imaging processing is carried out through software, variance contribution rate and accumulated contribution rate of each component are calculated, the first 4 components are selected as new predicted coal thickness actual measurement samples, and rotation is carried out by adopting a maximum variance method; calculating factor scores by adopting a regression method, respectively marking the factor scores as N1, N2, N3 and N4, and finally obtaining score models of 4 new components; for the main component F1, the load contribution of the components of the compressive strength of the coal bed and the inclined length of the coal bed is larger, and the factors are summarized as the characteristics of the top layer of the coal bed and the geometric dimension factors of the mining surface, and the factors have a strong positive correlation with the compressive strength of the coal bed and a strong negative correlation with the inclined length of the coal bed; the main component N2 has larger load on the mining depth and mainly represents the mining depth factor; the main component N3 has larger load on the dip angle of the coal seam and mainly represents the development characteristics of the coal seam; the main component N4 has larger load on the mining thickness and mainly represents the factor of the mining thickness of the coal seam;
wherein N is a For component score, M a The processed values are normalized for the raw data.
9. The method for predicting the coal thickness based on the ground penetrating radar and the earthquake transmission channel wave according to claim 8, wherein in the step (5), the score values of the score models N1, N2, N3 and N4 of the new components are used as input factors of the models, the number of input nodes of the models is 4, the standardized value of the detection precision value of the training sample is used as a prediction object, and the number of output nodes of the models is 1; training an unsupervised model through a function newrb provided by software, wherein a command calling format is as follows:
net＝newrb(P,T,goal,spread,mn,df)
wherein net is a radial basis function neural network prediction model to be established, newrb is a call command of the radial basis function neural network model in MATLAB, P is a model input matrix, and scores of four main components, namely N1, N2, N3 and N4, extracted by imaging processing are obtained; t is a target output matrix and is a standardized value of the detection precision value of the training sample; gol is mean square error, set to 0.00001; the spread is an extension function; mn is the maximum neuron number of the hidden layer; df is the display frequency of the iterative process.
10. A coal thickness prediction system based on ground penetrating radar and earthquake transmission groove wave, which is characterized in that the system is applied to a ground penetrating radar and earthquake transmission groove wave data processing module and implements the coal thickness prediction method based on ground penetrating radar and earthquake transmission groove wave as set forth in any one of claims 1-9, and the system comprises:
the excitation and receiving module (1) is used for exciting the earthquake transmission groove wave by adopting the ground penetrating radar;
the coal thickness photodetector (2) is buried at different positions from the excitation point, transmits the seismic transmission groove wave to the coal thickness detection terminal through a signal wire, amplifies the seismic transmission groove wave through the coal thickness detection terminal, and stores the amplified seismic transmission groove wave after analog-to-digital conversion;
a coal seam superposition identification data model module (3) is constructed and used for carrying out standardized processing on stored coal thickness seismic transmission trough wave signals, obtaining a seismic transmission trough wave map, identifying a plurality of coal sub-layers in a coal seam, and carrying out static correction processing on the plurality of coal sub-layers to finally obtain a coal sub-layer which is not lower than two layers; respectively carrying out imaging treatment on each coal sub-layer subjected to static correction treatment, and constructing a coal seam superposition identification data model;
and the coal thickness prediction module (4) is used for acquiring an image after the total coal seam superposition processing based on the constructed coal seam superposition identification data model and predicting the coal thickness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311432946.0A CN117471572A (en) | 2023-11-01 | 2023-11-01 | Coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove wave |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311432946.0A CN117471572A (en) | 2023-11-01 | 2023-11-01 | Coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove wave |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117471572A true CN117471572A (en) | 2024-01-30 |
Family
ID=89635920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311432946.0A Pending CN117471572A (en) | 2023-11-01 | 2023-11-01 | Coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove wave |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117471572A (en) |
-
2023
- 2023-11-01 CN CN202311432946.0A patent/CN117471572A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Stork et al. | Application of machine learning to microseismic event detection in distributed acoustic sensing data | |
| CN102227650B (en) | Continuous adaptive surface wave analysis for three-dimensional seismic data | |
| Zhu et al. | An end‐to‐end earthquake detection method for joint phase picking and association using deep learning | |
| US7969152B2 (en) | Systems and methods for measuring sea-bed resistivity | |
| CN103250072A (en) | Fracture characterization by interferometric drillbit imaging, time reversal imaging of fractures using drill bit seismics, and monitoring of fracture generation via time reversed acoustics and electroseismics | |
| CN100429527C (en) | Three-dimensional seismic data processing quality monitoring technology | |
| CN107219553B (en) | Underground river based on GR weighted band_wise fills prediction technique | |
| Hallal et al. | An H/V geostatistical approach for building pseudo-3D Vs models to account for spatial variability in ground response analyses Part I: Model development | |
| Hsu et al. | Onsite early prediction of PGA using CNN with multi-scale and multi-domain P-waves as input | |
| Xie et al. | Ü-Net: Deep-learning schemes for ground penetrating radar data inversion | |
| Liu et al. | Inversion of vehicle-induced signals based on seismic interferometry and recurrent neural networks | |
| Mola-Abasi et al. | Shear wave velocity by polynomial neural networks and genetic algorithms based on geotechnical soil properties | |
| Cho et al. | A Bayesian approach to microtremor array methods for estimating shallow S wave velocity structures: identifying structural singularities | |
| Abbas et al. | A frequency-velocity CNN for developing near-surface 2D vs images from linear-array, active-source wavefield measurements | |
| Shen et al. | Data-driven interpretation of ultradeep azimuthal propagation resistivity measurements: Transdimensional stochastic inversion and uncertainty quantification | |
| Naprstek et al. | Convolutional neural networks applied to the interpretation of lineaments in aeromagnetic data | |
| Berg et al. | Inversion of infrasound time series for seismoacoustic source parameters produced by a buried chemical explosion at the source physics experiment phase II: Dry alluvium geology | |
| CN117471572A (en) | Coal thickness prediction method and system based on ground penetrating radar and earthquake transmission groove wave | |
| Angelis et al. | The effects of receiver arrangement on velocity analysis with multi‐concurrent receiver GPR data | |
| CN115469376A (en) | Tunnel advanced geological forecast comprehensive detection method and system based on non-homologous data | |
| Patsia et al. | A deep learning framework for ground penetrating radar | |
| Zhu et al. | Identifying the potash reservoirs from seismic data by using convolution neural network, constrained by the waveform characteristics of potash reservoirs | |
| RU2300126C1 (en) | Mode of geophysical exploration for exposure of small amplitude tectonic abnormalities of oil-gas productive rocks in three-dimensional space | |
| Chen et al. | Seismic ahead-prospecting based on deep learning of retrieving seismic wavefield | |
| Anbazhagan et al. | A Study on the Effectiveness of Various Geophysical Methods in Detecting Naturally Formed Cavities in Lateritic Deposit |
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 |