CN115358454A - Coal and gas outburst prediction method based on extension-fuzzy hierarchical analysis theory - Google Patents
Coal and gas outburst prediction method based on extension-fuzzy hierarchical analysis theory Download PDFInfo
- Publication number
- CN115358454A CN115358454A CN202210921699.XA CN202210921699A CN115358454A CN 115358454 A CN115358454 A CN 115358454A CN 202210921699 A CN202210921699 A CN 202210921699A CN 115358454 A CN115358454 A CN 115358454A
- Authority
- CN
- China
- Prior art keywords
- prediction
- coal
- gas
- outburst
- risk
- 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
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of coal and gas outburst disaster prediction, in particular to a coal and gas outburst prediction method based on an extension-fuzzy hierarchical analysis theory, which comprises the steps of constructing an outburst risk prediction system; constructing a material element extension prediction framework; determining the weight of the prediction index; calculating the degree of correlation and the bias of the risk level; according to the method, coal and gas outburst key indexes such as the coal seam burial depth, the coal seam firmness coefficient, the coal seam gas content, the coal seam damage type, the gas pressure, the gas diffusion initial speed and the like are comprehensively considered, objective weights and subjective weights of various prediction indexes can be calculated and obtained through a definite mathematical method, and the problem of non-convergence does not exist.
Description
Technical Field
The invention relates to the technical field of coal and gas outburst disaster prediction, in particular to a coal and gas outburst prediction method based on an extension-fuzzy hierarchical analysis theory.
Background
At present, the coal mining depth is gradually increased, the ground stress, the gas pressure and the gas content are also continuously increased, and the frequency and the intensity of outburst disasters of coal and gas are continuously increased. And a large amount of coal, rock mass and gas are violently sprayed out in the coal and gas outburst process, so that the damage is huge. Meanwhile, the main component of the coal bed gas is methane, and the greenhouse effect is aggravated by a large amount of methane discharged in the outburst process. Because the coal and gas outburst relates to the processes of multi-field and multi-phase occurrence, gas adsorption and desorption, multi-physical-field spatial and temporal evolution and the like, the action mechanism is very complex, and the prediction of the coal and gas outburst becomes a worldwide difficult problem for ensuring the safe production of coal mines and protecting the ecological environment.
In recent years, a large amount of research is carried out by domestic and foreign scholars aiming at prediction of coal and gas outburst, and various prediction methods and technologies are proposed, for example:
the Chinese patent with the publication number of CN111079978A discloses a coal and gas outburst prediction method based on logistic regression and reinforcement learning, the method integrates LR and ADABOOST reinforcement learning to design a coal and gas outburst prediction model, collects data samples of various influence factors of coal and gas outburst, and trains and corrects errors of the outburst prediction model based on the data samples.
The Chinese patent with publication number CN107194524B discloses a coal and gas outburst prediction method based on an RBF neural network, and the prediction steps are as follows in sequence: performing dimensionality reduction and normalization processing on the salient feature data, calculating the center of a radial basis function, introducing a self-adaptive differential evolution algorithm to determine the optimal expansion factor and the optimal weight when the number of neurons in a hidden layer is determined, determining a prediction model of the RBF neural network, and testing data to predict.
The Chinese patent with publication number CN109492816B discloses a dynamic prediction method of coal and gas outburst based on mixed intelligence, which comprises the following steps: data detection, data processing by adopting a mean value batch estimation fusion method, forming a new problem for developing prediction, and verifying and correcting a prediction model.
The Chinese patent with publication number CN112183901A discloses a coal and gas outburst strength prediction method based on deep learning, and the prediction steps are as follows in sequence: data preparation, feature extraction, configuration learning process, model training and model verification.
In summary, although the existing coal and gas outburst prediction methods and technologies have various characteristics, the coal and gas outburst prediction models based on artificial intelligence and computer methods have the problems that the index membership degree and the index weight are difficult to determine, and the calculation process is difficult to converge.
Disclosure of Invention
The invention aims to provide a coal and gas outburst prediction method based on an extension-fuzzy hierarchical analysis theory, and aims to solve the problems that index membership and index weight are difficult to determine and a calculation process is difficult to converge in a coal and gas outburst prediction model based on an artificial intelligence and computer method. In order to achieve the above object, the present invention is achieved by the following technical solutions:
the invention provides a coal and gas outburst prediction method based on an extension-fuzzy hierarchical analysis theory, which comprises the following steps:
step 1: constructing an outstanding risk prediction system; firstly, determining the coal seam burial depth, the coal seam firmness coefficient, the coal seam gas content, the coal seam damage type, the gas pressure and the initial gas diffusion speed as coal and gas outburst prediction indexes; then, the outstanding risk level is divided;
and 2, step: constructing a matter element extension prediction framework, and establishing a dimensionless matter element extension prediction model based on an extension theory;
and step 3: determining the weight of the prediction index; firstly, determining objective weight through correlation analysis, then determining subjective weight through a fuzzy hierarchy analysis theory, and finally determining index comprehensive weight through a comprehensive weight distribution method;
and 4, step 4: calculating the risk level correlation degree and the bias thereof; and calculating the correlation between the prediction index and the outstanding risk level through a correlation function, and identifying the final outstanding risk level by adopting a maximum correlation criterion.
As a further technical solution, in the step 1, the prominent risk levels are divided into four levels of no risk, low risk, medium risk, and high risk, and each prominent prediction index is divided into four risk levels according to the magnitude of the measured value.
As a further technical solution, in step 3, firstly, a fuzzy consistency judgment matrix is constructed through expert subjective analysis, and the judgment matrix is adjusted until differences between the first row of elements and corresponding elements of the remaining rows are all constants.
As a further technical scheme, if the judgment matrix with consistency after adjustment is greatly different from the subjective analysis, the judgment matrix without consistency is finally established by taking the subjective analysis as a reference.
As a further technical scheme, the problem of constraint planning is solved through a least square method, and the subjective weight of the prediction index is obtained.
As a further technical scheme, the constrained planning problem and the unconstrained planning problem are equivalently processed by a Lagrange multiplier method.
As a further technical solution, in the step 1, the higher the coal seam firmness coefficient is, the lower the outburst risk is, and the larger the remaining five outburst prediction indexes are, the higher the outburst risk is.
As a further technical solution, in the step 2, when the dimensionless physical element extension prediction model is established based on the extension theory, firstly, dimensionless processing is performed on the prediction index value.
As a further technical solution, in the step 2, the dimensionless material element extension prediction model established based on the extension theory is as follows:
all predictors have the same cross-sectional area (v) iP ＝(<0,1>) Classical field v of the index ij ＝<a ij ,b ij >(1≤i≤6,1J ≦ 4) a range corresponding to each prediction level in the equation; wherein, C i (1. Ltoreq. I. Ltoreq.6) represents a prominent prediction index, N i (1. Ltoreq. I.ltoreq.4) represents the outstanding risk class.
As a further technical scheme, when the objective weight of the prediction index is calculated, a certain outstanding prediction index value a i In the interval v ij ＝<a ij ,b ij >Internal time, a i And v ij The correlation between them can be obtained by a simple correlation function.
The beneficial effects of the invention are as follows:
(1) According to the method, coal and gas outburst key indexes such as coal seam burial depth, coal seam firmness coefficient, coal seam gas content, coal seam damage type, gas pressure and gas diffusion initial speed are comprehensively considered, and the accuracy of a prediction result is high.
(2) According to the method, the objective weight is determined through correlation analysis, the subjective weight is determined through a fuzzy hierarchy analysis theory, and the index comprehensive weight is determined through a comprehensive weight distribution method, so that the objective weight and the subjective weight of various prediction indexes can be calculated and obtained through a clear mathematical method.
(3) The prediction process of the invention does not depend on machine learning, has higher calculation speed and no non-convergence problem, and is suitable for various complex geological conditions.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the invention and not to limit the invention. It will be further appreciated that the figures are for simplicity and clarity and have not necessarily been drawn to scale. The invention will now be described and explained with additional specificity and detail through the use of the accompanying drawings in which:
FIG. 1 shows a flow chart of coal and gas outburst prediction in an embodiment of the invention;
FIG. 2 shows the change rule of the correlation value between the mass of the highlighted coal rock and the maximum value;
FIG. 3 shows the effect of gas content reduction on the overall weight in an embodiment of the invention;
FIG. 4 illustrates the effect of gas pressure reduction on the composite weight in an embodiment of the present invention;
FIG. 5 illustrates the simultaneous reduction of gas content and pressure on the composite weight in an embodiment of the present invention;
FIG. 6 shows the influence of gas drainage on the outburst risk level in the embodiment of the invention.
Detailed Description
The technical solutions in the exemplary embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Examples
As shown in fig. 1 to 6, the embodiment provides a coal and gas outburst prediction method based on the extension-fuzzy hierarchy analysis theory, which includes the following steps:
step 1: construction of highlighted risk prediction system
Step 1.1: selection of an index system
According to the implementation rules of coal and gas outburst prevention and control, and according to the principles of principle, simplicity and quantification, the following 6 evaluation indexes are determined: the coal seam burial depth, the coal seam firmness coefficient, the coal seam gas content, the coal seam damage type, the gas pressure and the initial gas diffusion speed are respectively represented by symbols H, f, Q, Z, p and delta p. The coal seam buried depth H refers to the depth of the coal seam from the earth surface; the coal seam firmness coefficient f is a parameter representing the mechanical strength of the coal seam, and the smaller the mechanical strength of the coal seam is, the smaller the coal seam firmness coefficient is; the coal seam gas content Q refers to the gas quantity contained in a unit mass of coal under the atmospheric conditions of a mine (the ambient temperature is 20 ℃ and the ambient atmospheric pressure is 0.1 MPa); the coal seam failure type Z is a type divided according to the broken degree of the coal and represents the degree of coal seam breakage and crumpling under the action of constructional stress; the gas pressure p refers to the gas pressure in the coal bed; the initial gas diffusion speed delta p refers to the coal bed gas emission speed during initial exposure of coal, and not only reflects the gas diffusion capacity of the coal, but also reflects the gas permeation and flow rule. The coal seam damage types are divided into 5 grades of simple and normal structure, a small amount of fault flexure, fault flexure relatively development and fault flexure development, and the values are respectively assigned to 1-5. The higher the coal seam firmness coefficient is, the lower the outburst risk is; the larger the remaining 5 indices, the higher the highlighted risk.
Step 1.2: risk rating classification
Partitioning prominent risk classes into Risk-free N 1 Low risk N 2 Risk of stroke N 3 High risk N 4 And four levels are waited. And dividing the 6 outburst prediction indexes into 4 risk levels according to the size of the measured value, thereby constructing a hierarchical structure for evaluating the coal and gas outburst risk levels, which meets the data requirements of an extension theory and a fuzzy hierarchical analysis theory. The prediction index ranking criteria are shown in table 1.
TABLE 1 quantitative grading Standard of coal and gas outburst prediction indexes
And 2, step: construction of a material element extension prediction framework
In order to carry out coupling analysis on different prediction indexes, dimensionless processing is carried out on the prediction index values. The coal bed firmness factor is processed according to the formula (1), and the other indexes are processed according to the formula (2).
Wherein a is the actual value of the prediction index, a max And a min ā is a dimensionless index value and a prediction index C 1 ～C 6 The upper limits of (2) are 1500, 2, 25, 5, 3, 35, respectively, and the lower limits are all 0.
The matter element theory and the extended set theory are two theoretical foundations of the extension theory. The former constructs material elements and their transformation, while the latter quantifies the results of the theory of extensibility. The theory of extension regards the objective world as the physical world, and the contradiction problem can be converted into a material factor. The extension theory has very important guiding significance for predicting the coal and gas outburst risk, and the extension theory is introduced into the coal and gas outburst prediction, so that a new thought and direction can be developed for the coal and gas outburst prevention and control work. An ordered triad R = (N, c, v) is used as a basic element (called a material element) describing an object, where N represents a material, c is a feature, v is a measure of the material N on the feature c, and the expression v = c (N) describes the relationship between qualitative and quantitative features of a material. A substance having a plurality of characteristic elements can be described by an n-dimensional substance element, see formula (3).
The theory of extendibility has been used to solve the evaluation problem. The work of the extension evaluation method mainly comprises three parts: constructing an evaluation system, analyzing the correlation between the evaluation object and the evaluation grade, and identifying the evaluation grade of the evaluation object.
(1) Cross-sectional, classical and identical feature elements
Suppose passing the index c 1 ，c 2 ，...，c n And evaluating an object P, wherein P is a general name of all problems to be evaluated in the extension theory. c. C i (1. Ltoreq. I. Ltoreq. N) is at v iP ＝<a iP ，b iP >In the presence of a surfactant. R P Is a matter element of the evaluation target P and can be represented by equation (4).
In the formula, the value range v iP ＝<a iP ，b iP >Referred to as cross-sectional domains. V is ij ＝<a ij ，b ij >Referred to as the classical domain. According to the above definition, the classical domain is contained in the cross-sectional domain, i.e.
A dimensionless matter element extension prediction model established based on an extension theory is shown in formulas (5) to (6).
According to formula (5) R P The evaluation target and the coal and gas outburst prediction index shown in Table 1 are shown in the following table P Dimensionless physical element extension-free prediction model R for specifically characterizing coal and gas outburst risks F As shown in equation 6.
All the above predictors have the same cross-sectional area (v) iP ＝(<0,1>) Classical field v of the index ij ＝<a ij ,b ij >(1. Ltoreq. I.ltoreq. 6,1. Ltoreq. J.ltoreq.4) corresponds to the range of each prediction level in equation (6).
And step 3: determination of predictor weights
And (4) determining the weight of the coal and gas outburst prediction index by using a comprehensive weight distribution method shown in the formula (7).
w i ＝ψ o w io +ψ s w is ψ o +ψ s ＝1 (7)
In the formula, w i Is a prediction index C i Integrated weight of w is And w io Subjective weight and objective weight, respectively; Ψ s And Ψ o The ratio of the subjective weight to the objective weight is 0.5.
Step 3.1: objective weight determination
The objective weights are determined by correlation analysis. The prediction index values between different risk levels in the established outstanding risk prediction system are not overlapped, so that when a certain outstanding prediction index value a is used i In the interval v ij ＝<a ij ,b ij >Internal time, a i And v ij The correlation between them can be obtained by a simple correlation function expression shown in the formula (8).
In the formula, K ij (a i ，v ij ) I is more than or equal to 1 and less than or equal to 6 and j is more than or equal to 1 and less than or equal to 4.
Then, the prediction index a is obtained by the expressions (9) to (10) i Objective weight of (2).
In the formula, w io Is the objective weight of the ith predictor.
Step 3.2: subjective weight determination
Subjective weights are determined by fuzzy hierarchy analysis theory. Firstly, a fuzzy consistency judgment matrix R is constructed through expert subjective analysis and used for representing the relative importance of different prominent prediction indexes, and the matrix R can be represented as an expression (11).
In the formula, r ij Representing element a i And element a j The degree of membership of fuzzy relationship between them is quantitatively expressed by using a scale of 0.1-0.9, and the specific meanings are shown in Table 2.
TABLE 2 quantitative Scale
The fuzzy consistency judgment matrix R should satisfy equation (12).
In the actual decision analysis, due to the complexity of the coal and gas outburst problem and the one-sidedness of subjective recognition, the constructed judgment matrix R often does not meet the above properties, and needs to be adjusted according to the following steps:
1) Selecting the most holding element C 1 Performing analysis to determine r 11 ，r 12 ，...，r 16 A value of (d);
2) If the difference value between the first row element and the second row element of the matrix is not a constant, adjusting the second row element until the difference values are all constants;
3) If the difference value between the first row element and the third row element of the matrix is not a constant, adjusting the third row element until the difference values are all constants;
4) And sequentially adjusting until the difference values between the first row element and the corresponding elements of the rest rows are constant.
When the matrix R is judged to have consistency, the subjective weight values w of the 6 prediction indexes 1s ，w 2s ，…，w 6s There is a relationship shown by the formula (13).
r ij ＝0.5+x(w is -w js )+0.5 i,j＝1,2,...,6 (13)
In the formula, x is the measure of the difference degree of the prediction indexes and is related to the quantity and the difference degree of the indexes, the value is 0<x which is less than or equal to 0.5, and the larger the quantity or the difference degree of the elements is, the larger the value of x is.
And if the judgment matrix with consistency after adjustment is greatly different from the subjective analysis, finally establishing the judgment matrix without consistency by taking the subjective analysis as the standard. At this time, equation (13) is no longer applied, and the problem of constraint programming needs to be solved by the least square method shown in equation (14) to obtain the subjective weight of the prediction index.
From lagrange multiplier method, the constrained planning problem and the unconstrained planning problem can be treated equivalently by equation (15).
In the formula, λ is a lagrange multiplier.
By relating L (w, λ) to w is And making it zero, a system of equations as shown in equations (16) to (17) can be obtained.
The formulae (16) to (17) and w 1s +w 2s +…+w 6s The final equation set is established by simultaneous establishment of the =1, and the subjective weight vector W = [ W ] can be obtained 1s ,w 2s ,…,w 6s ] T The value of each element.
And 4, step 4: calculation of risk level relevance and its bias
If a value a of a certain outstanding predictor i In the interval v ij ＝<a ij ,b ij >Inner, the correlation degree K between the prediction index and the four outstanding risk levels j The (X) can be calculated by the correlation functions expressed by the equations (18) to (22).
∣ν ij ∣＝∣b ij -a ij ∣ (21)
In the formula, w i Is the weight of the predictor.
The maximum correlation criterion shown in equation (23) is used to identify the final outstanding risk level, i.e., maximum K j And (X) the corresponding risk grade is the final prediction risk grade highlighted under the geological parameter.
Final predicted risk level bias j * Calculated by the equations (24) to (25).
Wherein
And
maximum and minimum correlation respectively.
Test examples
In the test example, the coal and gas outburst prediction method based on the extension-fuzzy hierarchical analysis theory is used for predicting the coal and gas outburst of 12 groups of high-gas mines.
According to the outburst prediction model established above, actual prediction index measured values of 8 groups of coal and gas outburst occurring mines and 4 groups of non-outburst occurring high gas mines are obtained through extensive research and study, as shown in table 3.
TABLE 3 actual values of coal and gas outburst prediction model indexes
First, dimensionless processing is performed on the prediction index values of 12 groups of mines by the equations (1) to (2), and the processing results are shown in table 4.
TABLE 4 dimensionless values of coal and gas outburst prediction model indexes
The objective weights of the prominent predictive indicators shown in table 5 are obtained by equations (8) to (10), and the objective weights of the gas pressure, the initial gas diffusion rate, and the coal solidity factor are relatively large, and thus the objective weights of the different mine predictive indicators fluctuate widely.
TABLE 5 Objective weight of coal and gas outburst prediction model index
And acquiring a fuzzy consistency judgment matrix shown in a formula (26) through expert subjective evaluation and consistency adjustment.
Equation (26) satisfies the consistency requirement, the metric a of the degree of difference between the perception objects is taken as 0.5, and equations (13) and w are taken 1s +w 2s +…+w 6s =1, a system of equations is established simultaneously, and the subjective weight of the predictor shown in table 6 is finally obtained.
TABLE 6 subjective weighting of coal and gas outburst prediction index
The overall weight of the prediction index shown in table 7 is obtained by equation (7), and the importance of the prediction index is ranked as follows from the average value of the overall weights: p > Δ p > Z > f > Q > H.
TABLE 7 comprehensive weights of coal and gas outburst prediction model indexes
The correlation K between the prediction index and the risk level shown in table 8 was obtained by equations (18) to (25) j (X) and the final predicted risk level and its bias. 8 groups of mines with coal and gas outburst accidents can be obtained, the risk of the Yangquan five mines is N3, and the risk of the rest 7 groups is N4; among 4 groups of mines in which no outburst occurs, 3 groups are at low risk of N2, and 1 group is at risk of N3. The outburst risk level prediction result is better consistent with the actual outburst disaster occurrence condition, and the feasibility of the coal and gas outburst prediction model based on the extension-fuzzy hierarchical analysis theory is verified.
TABLE 8 coal and gas outburst prediction results
And further analyzing the relationship between the quality of the outburst coal rock mass and the maximum risk grade correlation value in 12 groups of mines, wherein the quality of the outburst coal rock mass without outburst mines is 0. From fig. 2, it can be seen that the change rule of the coal-rock mass quality and the degree of correlation of the maximum risk level is basically consistent.
At present, the main outburst control measure adopted by a high-gas mine is gas extraction. The gas extraction mainly reduces the gas pressure and the gas content of the coal seam. In order to analyze the outburst prevention and control effect of gas extraction, an outburst prediction model is applied to quantitatively research the influence rule of the gas pressure and the gas content change process on the outburst risk level in the gas extraction process of the outburst coal seam of the expected peak sentry.
In the analysis process, the reduction rate of the gas pressure and the gas content in the gas extraction process is set to be 10 percent, and the reduction rate of the gas content in the gas extraction process is set to be 20 grades in total by … … percent. From fig. 3, it can be seen that the reduction of the gas pressure and the gas content has a smaller influence on the comprehensive weight of the prediction index, and the influence effect of the gas pressure is greater than the gas content. The comprehensive weight is obtained by jointly calculating the objective weight and the subjective weight, so that the reduction of the gas pressure and the gas content only changes the objective weight of the prediction index, and the influence on the final result of the comprehensive weight is small.
As can be seen from fig. 4, if the gas extraction only reduces the gas content of the coal seam, even if the gas content is reduced by 90%, the outburst risk level is still N4 high risk. If the gas pressure of the coal seam is only reduced in the gas extraction process, when the gas pressure is reduced by 50%, namely the gas pressure is 1.25MPa, the outburst risk level is reduced to N3; when the gas pressure is reduced by 70 percent, namely the gas pressure is 0.75MPa, the outburst risk grade is reduced to N2 low risk; when the gas pressure is reduced by 90 percent, namely the gas pressure is 0.25MPa, the outburst risk grade is reduced to N1 without risk. When the gas content and the gas pressure are reduced simultaneously, the change rule of the coal seam risk grade is basically consistent with the change rule when the gas pressure is only reduced, and the only difference is that when the gas content and the gas pressure are reduced by 60 percent simultaneously, the outburst risk grade is changed into N2 low risk. Therefore, the main reason that the outburst risk level of gas extraction is reduced is that the gas pressure of the coal bed is reduced.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to limit the present invention, and those skilled in the art can make possible variations and modifications of the present invention using the method and the technical contents disclosed above without departing from the spirit and scope of the present invention, and therefore, any simple modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention are all within the scope of the present invention.
Claims (10)
1. The coal and gas outburst prediction method based on the extension-fuzzy analytic theory is characterized by comprising the following steps of:
constructing an outstanding risk prediction system; firstly, determining the coal seam burial depth, the coal seam firmness coefficient, the coal seam gas content, the coal seam damage type, the gas pressure and the initial gas diffusion speed as coal and gas outburst prediction indexes; then, the outstanding risk level is divided;
constructing a material element extension prediction framework; establishing a dimensionless matter element extension prediction model based on an extension theory;
determining the weight of a prediction index; firstly, determining objective weight through correlation analysis, then determining subjective weight through a fuzzy hierarchy analysis theory, and finally determining index comprehensive weight through a comprehensive weight distribution method;
calculating the risk level correlation degree and the bias thereof; and calculating the correlation between the prediction index and the outstanding risk level through a correlation function, and identifying the final outstanding risk level by adopting a maximum correlation criterion.
2. The coal and gas outburst prediction method based on the prolongation-fuzzy hierarchy analysis theory as claimed in claim 1, characterized in that the outburst risk level is divided into four levels of no risk, low risk, medium risk and high risk, and each outburst prediction index is divided into four risk levels according to the magnitude of the measured value.
3. The extension-fuzzy hierarchy analysis theory-based coal and gas outburst prediction method of claim 1, wherein a fuzzy consistency judgment matrix is firstly constructed, and the judgment matrix is adjusted until the difference values between the first row of elements and the corresponding elements of the other rows are all constant.
4. The method of claim 3, wherein if the adjusted decision matrix with consistency is different from the subjective analysis, the decision matrix without consistency is finally established based on the subjective analysis.
5. The method of claim 4, wherein the constraint programming problem is solved by a least square method to obtain the subjective weight of the prediction index.
6. The extension-fuzzy analytic hierarchy process based coal and gas outburst prediction method of claim 5, wherein the constrained programming problem and the unconstrained programming problem are treated equivalently by a Lagrangian multiplier method.
7. The method of claim 1, wherein the greater the robustness factor of the coal seam, the lower the risk of outburst, and the greater the five remaining outburst predictors, the higher the risk of outburst.
8. The extension-fuzzy hierarchical analysis theory-based coal and gas outburst prediction method according to claim 1, wherein when a dimensionless matter element extension prediction model is established based on the extension theory, dimensionless processing is firstly carried out on the prediction index value.
9. The extension-fuzzy hierarchical analysis theory-based coal and gas outburst prediction method according to claim 2, wherein a dimensionless matter element extension prediction model established based on the extension theory is as follows:
all the above predictors have the same cross-sectional area (v) iP ＝<0,1>) Classical field v of the index ij ＝<a ij ,b ij >(1 ≦ i ≦ 6,1 ≦ j ≦ 4) for each prediction level range in the formula; wherein, C i (1. Ltoreq. I. Ltoreq.6) represents a prominent prediction index, N i (1. Ltoreq. I.ltoreq.4) represents the outstanding risk class.
10. The method of claim 9, wherein when calculating the objective weight of the prediction index, a certain prediction index value is a i In the interval v ij ＝<a ij ,b ij >Internal time, a i And v ij The correlation between them can be obtained by a simple correlation function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210921699.XA CN115358454A (en) | 2022-08-02 | 2022-08-02 | Coal and gas outburst prediction method based on extension-fuzzy hierarchical analysis theory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210921699.XA CN115358454A (en) | 2022-08-02 | 2022-08-02 | Coal and gas outburst prediction method based on extension-fuzzy hierarchical analysis theory |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115358454A true CN115358454A (en) | 2022-11-18 |
Family
ID=84031659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210921699.XA Pending CN115358454A (en) | 2022-08-02 | 2022-08-02 | Coal and gas outburst prediction method based on extension-fuzzy hierarchical analysis theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115358454A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116312929A (en) * | 2023-05-25 | 2023-06-23 | 四川互慧软件有限公司 | OKR-based pressure sore management method, system, equipment and medium |
-
2022
- 2022-08-02 CN CN202210921699.XA patent/CN115358454A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116312929A (en) * | 2023-05-25 | 2023-06-23 | 四川互慧软件有限公司 | OKR-based pressure sore management method, system, equipment and medium |
| CN116312929B (en) * | 2023-05-25 | 2023-07-28 | 四川互慧软件有限公司 | OKR-based pressure sore management method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hosseinali et al. | Weighting spatial information in GIS for copper mining exploration | |
| CN111737642A (en) | Comprehensive evaluation method for failure risk of submarine pipeline based on fuzzy network analysis method | |
| Zhao et al. | CPT-based fully probabilistic seismic liquefaction potential assessment to reduce uncertainty: Integrating XGBoost algorithm with Bayesian theorem | |
| CN111859288A (en) | Method for predicting spontaneous combustion risk of goaf | |
| Bashari et al. | Estimation of deformation modulus of rock masses by using fuzzy clustering-based modeling | |
| CN110889440A (en) | Rockburst grade prediction method and system based on principal component analysis and BP neural network | |
| KR102379472B1 (en) | Multimodal data integration method considering spatiotemporal characteristics of disaster damage | |
| CN116108758A (en) | Landslide susceptibility evaluation method | |
| Zhang et al. | A comprehensive risk assessment method for coal and gas outburst in underground coal mines based on variable weight theory and uncertainty analysis | |
| CN115130375A (en) | Rock burst intensity prediction method | |
| CN115358454A (en) | Coal and gas outburst prediction method based on extension-fuzzy hierarchical analysis theory | |
| CN115049124A (en) | Deep and long tunnel water inrush prediction method based on Bayesian network | |
| CN115270266A (en) | Slope monitoring state risk judgment method based on improved analytic hierarchy process | |
| Rayjada et al. | Machine learning-based RC beam-column model parameter estimation and uncertainty quantification for seismic fragility assessment | |
| Safaeian Hamzehkolaei et al. | Performance evaluation of machine learning algorithms for seismic retrofit cost estimation using structural parameters | |
| CN114580940A (en) | Grouting effect fuzzy comprehensive evaluation method based on grey correlation degree analysis method | |
| Ahmad et al. | Probabilistic evaluation of cpt-based seismic soil liquefaction potential: Towards the integration of interpretive structural modeling and bayesian belief network | |
| Miao et al. | Deep learning–based inspection data mining and derived information fusion for enhanced bridge deterioration assessment | |
| CN117035465B (en) | Method and device for evaluating landslide susceptibility | |
| CN117009923A (en) | Tunnel advanced geological disaster intelligent judging and identifying method based on multi-source information fusion | |
| CN116933920A (en) | Prediction and early warning method and system for underground mine debris flow | |
| Li et al. | Improved catastrophe progression method of underground goaf risk evaluation | |
| Alla et al. | Seismic liquefaction analysis of MCDM weighted SPT data using support vector machine classification | |
| Nie et al. | The application of remote sensing technique and AHP-fuzzy method in comprehensive analysis and assessment for regional stability of Chongqing City, China | |
| CN114818493A (en) | Method for quantitatively evaluating integrity degree of tunnel rock mass |
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 |