CN116955966B - Method for judging water-rich grade of mine roof - Google Patents
Method for judging water-rich grade of mine roof Download PDFInfo
- Publication number
- CN116955966B CN116955966B CN202311216058.5A CN202311216058A CN116955966B CN 116955966 B CN116955966 B CN 116955966B CN 202311216058 A CN202311216058 A CN 202311216058A CN 116955966 B CN116955966 B CN 116955966B
- Authority
- CN
- China
- Prior art keywords
- water
- rich
- formula
- mine roof
- grade
- 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.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012360 testing method Methods 0.000 claims abstract description 32
- 238000011156 evaluation Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000010606 normalization Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims abstract description 7
- 241000283153 Cetacea Species 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 18
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 239000003245 coal Substances 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 6
- 239000004927 clay Substances 0.000 claims description 4
- 238000005553 drilling Methods 0.000 claims description 4
- 230000035699 permeability Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 239000003795 chemical substances by application Substances 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000005086 pumping Methods 0.000 description 5
- 238000005192 partition Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention discloses a method for judging the water-rich grade of a mine roof, and relates to the technical field of data processing with specific functions. The method comprises the following steps: determining an evaluation index according to the water-rich influence factors, dividing evaluation index data into a training set and a testing set, carrying out normalization pretreatment on sample data of the evaluation index data, constructing a water-rich prediction model, training the water-rich prediction model by using an MATLAB program, testing the accuracy of the model, storing the model after the accuracy of the water-rich prediction model meets the requirement, inputting the water-rich evaluation index data of a top plate to be tested, outputting a prediction result and dividing the water-rich grade. The method for judging the water-rich grade of the mine roof can predict according to various main control factors, and provides technical support for improving the safety of mine exploitation.
Description
Technical Field
The invention relates to the technical field of data processing with specific functions, in particular to a distinguishing method suitable for mine roof water-rich grades.
Background
The coal resource is taken as a main body of China, the position of the main body of China is not changed in a short period, water burst is one of serious mine disasters, mine safety production is seriously threatened, the water-rich property of an aquifer directly determines the occurrence and the occurrence times of water burst, and is influenced by coal seam mining, the water-rich property of the aquifer dynamically changes, and a water pumping test cannot carry out space-time global characterization, so that the water-rich property of the aquifer is necessary to be rapidly and accurately predicted by utilizing multi-factor fusion.
The traditional aquifer water enrichment evaluation is carried out by grading the water enrichment by obtaining unit water inflow through a water pumping test, and the multi-factor fusion evaluation method mainly uses mathematical models such as an analytic hierarchy process, an entropy weight process, a TOPSIS and the like to construct a weight matrix and draw water enrichment subareas. With the development of artificial intelligence, machine learning and a neural network are applied to the prediction of the water-rich property, and a plurality of prediction evaluation methods are proposed by a plurality of students from different angles aiming at the water-rich property of a coal seam roof. The following problems are mainly present: (1) The traditional water pumping test method has the defects of higher field test cost, easy experience influence, difficult data acquisition and small number of water pumping holes, and can not carry out space-time global characterization on the water enrichment. (2) The model prediction accuracy is low due to the defects of strong subjectivity, weak correlation among indexes, strong dependence on weight matrix and the like of the mathematical analysis methods such as an analytic hierarchy process, an entropy weight process, a TOPSIS and the like. (3) Other machine learning and neural networks require a large number of samples, and the prediction accuracy is insufficient, so that the requirement for fast and accurate prediction of the rich water can not be met. It follows that the prior art is still further improved.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a judging method of the water-rich grade of a mine roof, which is used for solving the problem that the judging of the water-rich grade is completely dependent on a water pumping test by constructing a multi-factor composite prediction model to invert the unit water inflow, improving the prediction accuracy and providing technical support for improving the deep mining safety of a mine.
In order to achieve the above object, the present invention adopts the following technical scheme.
A distinguishing method of the water-rich grade of a mine roof comprises the following steps: a. and determining main control factors influencing the water-rich property of the mine roof, and selecting a plurality of evaluation indexes.
b. And c, dividing all evaluation indexes in the step a into two types, namely a training set and a testing set, and carrying out normalization pretreatment on all data.
c. And constructing a WOA-CNN-SVM rich water prediction model.
d. And training a WOA-CNN-SVM water-rich prediction model by utilizing a MATLAB program, testing the accuracy of the WOA-CNN-SVM water-rich prediction model, and storing the WOA-CNN-SVM water-rich prediction model after the accuracy of the WOA-CNN-SVM water-rich prediction model meets the requirement.
e. And d, inputting the data of the evaluation index selected in the step a into the WOA-CNN-SVM water-rich prediction model of the step d for prediction, and outputting a prediction result.
f. The ArcGis software is utilized to visually display the data, and the mining area water enrichment is divided by a natural breakpoint method or a division standard of reference to the coal control water rule.
In the above method for determining the water-rich level of the mine roof, in the step a, the main control factors affecting the water-rich level of the mine roof are determined from the hydraulic contact characteristics and the aquifer characteristics.
In the above method for determining the water-rich grade of the mine roof, in the step a, the plurality of evaluation indexes mainly comprise the thickness of the aquifer, the influence radius, the water level drop depth, the permeability coefficient, the core drilling rate and the clay thickness ratio.
The method for judging the water-rich grade of the mine roof comprises the following specific construction method in the step c: c1, optimizing a convolutional neural network learning rate eta, a batch size b and a regularization parameter alpha by adopting a whale optimization algorithm, and mapping the 3 parameters into a space vector position of a whale individual, wherein the position of an nth whale is as follows: xn= (η, b, α).
According to the hunting characteristics, 3 behaviors of surrounding the prey, prey and random search are abstracted.
Surrounding the prey, this behavior is represented by the following equation (1).
（1）。
In the formula (1):is the distance of the search agent from the prey;andis a coefficient vector;is a position vector of a globally optimal solution, updated in each iteration;is a position vector;representing the current number of iterations.
Coefficient vectorAndthe calculation formula of (2) is shown in the formula.
（2）。
In the formula (2):is a convergence factor that decreases linearly from 2 to 0 in an iterative process;、is distributed in [0,1]]Random vector between them.
Predatory prey is shown in formula (3).
（3）。
In the formula (3):representing the obtained optimal distance;is a constant defining a logarithmic spiral shape;is [ -1,1]Random numbers in (a);represents [0,1]]Random numbers in the two, and the probabilities of 0 and 1 are the same;is an irrational base.
Random search: when coefficient ofWhen the whale is in the surrounding ring, selecting a spiral surrounding prey; when (when)When the whale is contracted and enclosedOutside the circle, a random search is performed at this time.
The random search update formula is shown in formula (4).
（4）。
In the formula (4):is a randomly selected whale position.
And c2, obtaining the optimal parameters and inputting the optimal parameters into a convolutional neural network model.
The convolution process extraction features are shown in formula (5).
（5）。
In formula (5):representing an output;representing a weight matrix;is convolution operation;representing an input matrix;is a bias term;is a nonlinear activation function.
Using RELU as the activation function, the mathematical expression is shown in equation (6).
； （6）。
In formula (6):is an independent variable;the output interval is set to be 0, ++ infinity A kind of electronic device.
And c3, taking output data of the full connection layer as input of a support vector machine to construct the WOA-CNN-SVM rich water prediction model.
In the above method for judging the water-rich grade of the mine roof, in the step b, 80% of the evaluation index is used as a training set, and the rest is a test set.
According to the method for judging the water-rich grade of the mine roof, regression prediction is carried out by taking the unit water inflow as a target value according to the rule of preventing and controlling water by coal as a division standard of water-rich.
Step c) of the method for judging the water-rich grade of the mine roof 2 The middle convolution neural network model comprises two network substructures, wherein the convolution kernel of the convolution calculation of the first network substructures is 3*1, the number of channels is 16, the convolution kernel of the convolution calculation of the second network substructures is 3*1, and the number of channels is 32.
Step c) of the method for judging the water-rich grade of the mine roof 2 The first and second network substructures in the medium convolutional neural network model each include a convolutional layer-batch normalization layer-RELU activation layer.
Compared with the prior art, the invention has the following beneficial technical effects.
The invention provides a judging method of a mine roof water-rich grade, which comprises the steps of determining an evaluation index according to a water-rich influencing factor, dividing evaluation index data into a training set and a testing set, carrying out normalization pretreatment on sample data of the evaluation index data, constructing a WOA-CNN-SVM water-rich prediction model, training the WOA-CNN-SVM water-rich prediction model by utilizing a MATLAB program, testing the accuracy of the model, storing the model after the accuracy of the WOA-CNN-SVM water-rich prediction model meets the requirement, inputting to-be-tested roof water-rich evaluation index data, outputting a prediction result and dividing the water-rich grade. The method can predict according to various main control factors. Technical support is provided for improving the safety of mine exploitation.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method for determining the water-rich grade of a mine roof according to the present invention.
Fig. 2 and 3 are graphs of the predicted results of the training set and the test set samples according to the present invention, fig. 2 is a predicted value and a true value of the training sample, and fig. 3 is a predicted value and a true value of the test sample.
FIG. 4 is a plot of the water-rich grade partition of the present invention.
Detailed Description
The invention provides a method for judging the water-rich grade of a mine roof, which is further described below by combining specific embodiments in order to make the advantages and the technical scheme of the invention clearer and more definite.
The main technical conception of the invention is as follows: determining an evaluation index according to the water-rich influence factors, dividing evaluation index data into a training set and a testing set, carrying out normalization pretreatment on sample data of the evaluation index data, constructing a water-rich prediction model, training the model by using an MATLAB program, testing the accuracy of the model, storing the model after the accuracy of the model meets the requirement, inputting the water-rich evaluation index data of a top plate to be tested, outputting a prediction result, and dividing the water-rich grade.
Example 1: as shown in FIG. 1, the method for judging the water-rich grade of the mine roof comprises the following steps.
Step one, collecting a plurality of main control factor data influencing the water enrichment of a top plate, including the thickness (X) 1 ) Influence radius (X) 2 ) Depth of water level (X) 3 ) Permeability coefficient (X) 4 ) Coring rate of drilling (X) 5 ) The clay thickness is a proportion of the lower group thickness (X 6 ）。
The above-mentioned water-rich evaluation index sample data are shown in table 1.
Table 1 sample data.
And step two, taking 80% of all data as a training set and 20% as a testing set for testing, and disturbing the sequence.
And thirdly, normalizing all the data.
The programming language of the step three MATLAB is as follows.
[p_train, ps_input] = mapminmax(P_train, 0, 1)。
p_test = mapminmax('apply', P_test, ps_input)。
[t_train, ps_output] = mapminmax(T_train, 0, 1)。
t_test = mapminmax('apply', T_test, ps_output)。
And fourthly, in order to enable the data to meet the model requirements, tiling and transpose the data.
The programming language of the fourth MATLAB is as follows.
p_train = double(reshape(p_train, f_, 1, 1, M))。
p_test = double(reshape(p_test, f_, 1, 1, N))。
t_train = double(t_train)'。
t_test = double(t_test )'。
And fifthly, constructing a WOA-CNN-SVM prediction model, wherein the WOA-CNN-SVM prediction model calculation method is as follows.
The first step, optimizing the convolutional neural network learning rate eta, the batch size b and the regularization parameter alpha by adopting a Whale Optimization Algorithm (WOA), and mapping the 3 parameters into the space vector position of whale individuals, wherein the position of the nth whale is Xn= (eta, b, alpha). According to the hunting characteristics, 3 behaviors of surrounding the prey, prey and random search are abstracted.
Surrounding the prey. This behavior is represented by the following equation.
（1）。
Wherein:is the distance of the search agent from the prey;andis a coefficient vector;is a position vector of a globally optimal solution, updated in each iteration;is a position vector;representing the current number of iterations.
Coefficient vectorAndthe formula of (2) is as follows.
（2）。
Wherein:is a convergence factor that decreases linearly from 2 to 0 in an iterative process;、is distributed in [0,1]]Random vector between them.
Predatory prey formulas are.
（3）。
In the formula (3): wherein the method comprises the steps ofRepresenting the obtained optimal distance;is a constant defining a logarithmic spiral shape;is [ -1,1]Random numbers in (a);represents [0,1]]Random numbers in the two, and the probabilities of 0 and 1 are the same;is an irrational base.
And (5) random searching. When coefficient ofIn this case, the whale is within a surrounding collar, optionally a spiral surrounding the prey. When (when)When the whale is outside the contracted surrounding ring, random searching is performed at the moment; the random search update formula is as follows.
（4）。
In the formula (4):is a randomly selected whale position.
And secondly, obtaining optimal parameters, and inputting the optimal parameters into a Convolutional Neural Network (CNN) model.
The convolution process extraction features are shown in formula (5).
（5）。
In formula (5):representing an output;representing a weight matrix;is convolution operation;representing an input matrix;is a bias term;is a nonlinear activation function.
Using RELU as the activation function, the mathematical expression is.
（6）。
In formula (6):is an independent variable;the output interval is set to be 0, ++ infinity A kind of electronic device.
And thirdly, taking output data of the full-connection layer as input of the SVM to construct a prediction model.
And step six, training data is carried out by using training set data, and the testing set data is used for testing the accuracy of the model. The training set and test set prediction results are shown in fig. 2 and 3. And storing the model after the accuracy of the model meets the requirement.
Inputting the water-rich evaluation index of the top plate to be tested into the model, and obtaining a final prediction result after inverse normalization.
The data results of the samples to be tested are shown in table 2.
Table 2 test sample data results.
And step eight, visually displaying the result by using ArcGis. And the water enrichment of the mining area is divided by using a natural breakpoint method. The rich water level partition map is shown in fig. 4, and an example given in this embodiment is that level partition is performed according to the natural breakpoint method.
Example 2: the difference from example 1 is that in the eighth step, the mining area water-rich property can be divided by referring to the division standard of the rule of water control for coal.
The multiple evaluation indexes listed in the present invention are not limited to the aquifer thickness, the influence radius, the water level drop depth, the permeability coefficient, the core drilling rate, and the ratio of the clay thickness to the following group thickness, and those skilled in the art can obtain other multiple evaluation indexes in the light of the technical teaching of the present invention.
The foregoing is merely a preferred embodiment of the present invention, and any equivalent or obvious modification thereof by those skilled in the art with the benefit of this disclosure shall fall within the scope of the invention.
Claims (6)
1. The method for distinguishing the water-rich grade of the mine roof is characterized by comprising the following steps of:
a. determining main control factors influencing the water-rich property of a mine roof, and selecting a plurality of evaluation indexes; the multiple evaluation indexes comprise aquifer thickness, influence radius, water level depth, permeability coefficient, core drilling rate and clay thickness accounting for the thickness proportion of the lower group;
b. dividing samples containing all evaluation indexes in the step a into two types, namely a training set and a testing set, and carrying out normalization pretreatment on all sample data;
c. constructing a WOA-CNN-SVM rich water prediction model;
d. training a WOA-CNN-SVM water-rich prediction model by utilizing a MATLAB program, testing the accuracy of the WOA-CNN-SVM water-rich prediction model, and storing the WOA-CNN-SVM water-rich prediction model after the accuracy of the WOA-CNN-SVM water-rich prediction model meets the requirement;
e. inputting the data of the evaluation index selected in the step a into the WOA-CNN-SVM water-rich prediction model of the step d for prediction, and outputting a prediction result;
f. the data are visually displayed by ArcGis software, and the water enrichment of the mining area is divided by a natural breakpoint method or a division standard of reference to the coal control water rule;
the specific construction method in the step c is as follows:
c1, optimizing a convolutional neural network learning rate eta, a batch size b and a regularization parameter alpha by adopting a whale optimization algorithm, and mapping the 3 parameters into a space vector position of a whale individual, wherein the position of an nth whale is as follows: xn= (η, b, α);
according to the hunting characteristics, the hunting method abstracts 3 behaviors of surrounding the hunting object, predating the hunting object and randomly searching:
surrounding the prey, this behavior is represented by the following equation (1):
in the formula (1): d is the distance of the search agent from the prey; a and C are coefficient vectors; x is X * Is a position vector of a globally optimal solution, updated in each iteration; x is a position vector; t represents the current iteration number;
the calculation formula of the coefficient vectors A and C is shown in the formula (2):
in the formula (2): a is a convergence factor that decreases linearly from 2 to 0 during the iteration; r is (r) 1 、r 2 Is distributed in [0,1]]Random vectors between;
predatory prey is shown in formula (3):
in the formula (3): d' represents the optimal distance obtained; b is a constant defining a logarithmic spiral shape; l is a random number in [ -1,1 ]; p represents a random number between [0,1], and the probabilities of 0 and 1 are the same; e is irrational number base number;
random search:
when the coefficient |A| < 1, the whale is in the surrounding circle, and a spiral surrounding prey is selected;
when the A is more than or equal to 1, the whale is outside the contracted surrounding ring, and random search is performed at the moment;
the random search update formula is shown in formula (4):
X(t+1)＝X rand (t)-A·|C·X rand (t)-X(t)| (4)
in the formula (4): x is X rand A whale position selected at random;
c2, obtaining optimal parameters and inputting the optimal parameters into a convolutional neural network model;
the convolution process extraction features are shown in formula (5):
Y＝f(W*X+b) (5)
in formula (5): y represents output; w represents a weight matrix; * Is convolution operation; x represents an input matrix; b is a bias term;
using RELU as an activation function, the mathematical expression is as shown in equation (6):
g(x)＝max(0,x) (6)
in formula (6): x is an independent variable; the g (x) output interval is 0, ++ infinity a) is provided;
and c3, taking output data of the full connection layer as input of a support vector machine to construct the WOA-CNN-SVM rich water prediction model.
2. The method for distinguishing the water-rich grade of the mine roof according to claim 1, wherein the method comprises the following steps of: in step a, the main control factors affecting the water enrichment of the mine roof are determined from the hydraulic connection characteristics and the aquifer characteristics.
3. The method for distinguishing the water-rich grade of the mine roof according to claim 1, wherein the method comprises the following steps of: in step b, 80% of the samples are used as training sets, and the rest are test sets.
4. The method for distinguishing the water-rich grade of the mine roof according to claim 1, wherein the method comprises the following steps of: according to
The rule of water control by coal is used as a division standard of rich water, and regression prediction is carried out by taking the unit water inflow as a target value.
5. The method for distinguishing the water-rich grade of the mine roof according to claim 1, wherein the method comprises the following steps of: the convolutional neural network model in step c2 comprises two network substructures, wherein the convolution kernel of the convolution calculation of the first network substructures is 3*1, the number of channels is 16, the convolution kernel of the convolution calculation of the second network substructures is 3*1, and the number of channels is 32.
6. The method for distinguishing the water-rich grade of the mine roof according to claim 1, wherein the method comprises the following steps of: the first and second network substructures in the convolutional neural network model in step c2 each include a convolutional layer-batch normalization layer-RELU activation layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311216058.5A CN116955966B (en) | 2023-09-20 | 2023-09-20 | Method for judging water-rich grade of mine roof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311216058.5A CN116955966B (en) | 2023-09-20 | 2023-09-20 | Method for judging water-rich grade of mine roof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116955966A CN116955966A (en) | 2023-10-27 |
| CN116955966B true CN116955966B (en) | 2023-12-19 |
Family
ID=88442899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311216058.5A Active CN116955966B (en) | 2023-09-20 | 2023-09-20 | Method for judging water-rich grade of mine roof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116955966B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107942383A (en) * | 2017-11-13 | 2018-04-20 | 山东科技大学 | Roof sandstone watery grade prediction technique |
| CN115935811A (en) * | 2022-11-28 | 2023-04-07 | 贵州电网有限责任公司 | Distributed wind turbine generator power prediction method based on mathematical model |
| CN116050877A (en) * | 2022-11-21 | 2023-05-02 | 彝良驰宏矿业有限公司 | Metal mine aquifer water enrichment evaluation method and evaluation system |
| CN116611002A (en) * | 2023-04-26 | 2023-08-18 | 昆明理工大学 | Slope safety coefficient prediction method based on whale algorithm optimization support vector machine |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112653142B (en) * | 2020-12-18 | 2022-09-02 | 武汉大学 | Wind power prediction method and system for optimizing depth transform network |
-
2023
- 2023-09-20 CN CN202311216058.5A patent/CN116955966B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107942383A (en) * | 2017-11-13 | 2018-04-20 | 山东科技大学 | Roof sandstone watery grade prediction technique |
| CN116050877A (en) * | 2022-11-21 | 2023-05-02 | 彝良驰宏矿业有限公司 | Metal mine aquifer water enrichment evaluation method and evaluation system |
| CN115935811A (en) * | 2022-11-28 | 2023-04-07 | 贵州电网有限责任公司 | Distributed wind turbine generator power prediction method based on mathematical model |
| CN116611002A (en) * | 2023-04-26 | 2023-08-18 | 昆明理工大学 | Slope safety coefficient prediction method based on whale algorithm optimization support vector machine |
Non-Patent Citations (3)
| Title |
|---|
| A novel hybrid optimization enabled robust CNN algorithm for an IoT network intrusion detection approach;Ahmed Bahaa etal.;《PLoS ONE》;第17卷(第12期);全文 * |
| 基于 WOA 优化卷积神经网络的齿轮箱故障诊断研究;刘 奇等;《数字制造科学》;第19卷(第2期);全文 * |
| 基于岩性及结构特征的砂岩含水层富水性评价;魏久传;赵智超;谢道雷;俞功一山;吴霞;;山东科技大学学报(自然科学版)(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116955966A (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110442666B (en) | Mineral resource prediction method and system based on neural network model | |
| CN104866578B (en) | A kind of imperfect Internet of Things data mixing fill method | |
| CN109799533A (en) | A kind of method for predicting reservoir based on bidirectional circulating neural network | |
| CN114492211B (en) | Residual oil distribution prediction method based on autoregressive network model | |
| CN103268607B (en) | A kind of common object detection method under weak supervision condition | |
| CN115906675B (en) | Well position and injection and production parameter joint optimization method based on time sequence multi-target prediction model | |
| CN111667050A (en) | Metric learning method, device, equipment and storage medium | |
| CN106991509A (en) | Log Forecasting Methodology based on radial basis function neural network model | |
| Song et al. | Potential for vertical heterogeneity prediction in reservoir basing on machine learning methods | |
| CN111414951B (en) | Fine classification method and device for images | |
| CN110717270B (en) | Oil and gas reservoir simulation method based on data | |
| CN108241625A (en) | Predict the method and system of student performance variation tendency | |
| CN116129219A (en) | SAR target class increment recognition method based on knowledge robust-rebalancing network | |
| CN115481565A (en) | Earth pressure balance shield tunneling parameter prediction method based on LSTM and ant colony algorithm | |
| CN112949944B (en) | Intelligent groundwater level prediction method and system based on space-time characteristics | |
| CN116955966B (en) | Method for judging water-rich grade of mine roof | |
| CN113378473A (en) | Underground water arsenic risk prediction method based on machine learning model | |
| CN105787045A (en) | Precision enhancing method for visual media semantic indexing | |
| CN110263125B (en) | Service discovery method based on extreme learning machine | |
| CN115203970B (en) | Diagenetic parameter prediction model training method and prediction method based on artificial intelligence algorithm | |
| CN111506855A (en) | Application of T L BO algorithm optimized deep confidence network model in ocean data prediction | |
| CN116720098A (en) | Abnormal behavior sensitive student behavior time sequence modeling and academic early warning method | |
| CN115620068A (en) | Rock lithology automatic identification and classification method under deep learning mode | |
| CN104834934A (en) | Nuclear body capturing method used for identifying reservoir fluid | |
| CN110991641B (en) | Oil reservoir type analysis method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |