Deep coal rock gas hybrid dynamic disaster risk identification method based on geophysical data driving

Abstract

The invention discloses a deep mine hybrid power disaster risk identification method based on geophysical data driving, which comprises the following steps of: firstly, acquiring multi-source geophysical data related to coal rock gas hybrid power disaster risks, then, optimizing the acquired multi-source geophysical data based on a rough set theory, and finally, selecting the optimized multi-source geophysical data according to the optimized multi-source geophysical data; selecting an index which is most sensitive to the response of the hybrid dynamic disaster, establishing a deep coal rock gas hybrid dynamic disaster risk identification index, and finally performing weighted reconstruction and comprehensive analysis on the identification index based on an entropy weight method. And constructing a multi-parameter index identification system for identifying the deep coal rock gas hybrid power disaster risk based on geophysical data driving. According to the method, the characteristics of the multi-source geophysical data are exerted, the advantages of the rough set theory and the entropy weight method are utilized, redundancy and conflicts existing in indexes are greatly reduced, weight distribution of index fusion is more reasonable, and efficient and accurate prediction of deep coal rock gas hybrid power disaster risks is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of deep coal, rock and gas composite power disaster risk identification, and in particular to a deep mine composite power disaster risk identification method based on geophysical data. Background Art

[0002] As one of my country's main energy sources, coal plays a vital role in energy production and consumption and is a key pillar of national energy security. With the increasing depletion of shallow coal resources, deep mining has become an inevitable trend. Deep coal mining, characterized by high geostress, high gas pressure, and low permeability, has led to significant changes in the mining environment. Under the influence of mining disturbances, the frequency and intensity of coal-rock dynamic disasters such as coal and gas outbursts and rock bursts have increased significantly, resulting in the coexistence of coal and gas outbursts and rock bursts in mines. The interaction between these disasters is intensifying, presenting a compound dynamic disaster that poses a serious threat to coal mine production safety.

[0003] The coupled nature of coal-gas outbursts and rock bursts complicates the mechanism of compound dynamic disasters, manifesting as mutual induction and compounding of these hazards, making disaster prevention and control increasingly difficult. Therefore, integrating the prevention and control of coal-gas outbursts and rock bursts into one comprehensive approach is a critical requirement for safe and efficient coal mining in deep mines. Geophysical methods, with their advantages of non-destructive detection, high efficiency, convenience, and low cost, are playing an increasingly important role in the risk identification and early warning of deep coal-rock gas compound dynamic disasters. Currently, a single geophysical method cannot fully capture the precursor information for compound dynamic disasters. Therefore, the integrated use of multiple geophysical methods is essential for risk identification of deep coal-rock gas compound dynamic disasters. While multiple geophysical methods can generate massive amounts of multi-source geophysical data, they often suffer from redundancy and conflict among multi-source geophysical data indicators, resulting in poor fusion and identification results, and inconsistent identification results. This severely impacts the accuracy of fusion-based early warnings and fails to meet the on-site needs of deep mines. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a deep coal-rock gas composite dynamic disaster risk identification method driven by geophysical data. It selects the indicators that are most sensitive to the response to composite dynamic disasters, and performs weighted reconstruction and comprehensive analysis on the identification indicators based on the entropy weight method to construct a multi-parameter indicator identification system for deep coal-rock gas composite dynamic disaster risk identification based on geophysical data, so as to accurately identify the deep coal-rock gas composite dynamic disaster risk.

[0005] To achieve the above object, the present invention provides the following technical solution, comprising the following steps:

[0006] A method for identifying the risk of deep coal-rock gas composite dynamic disasters based on geophysical data.

[0007] Step 1: Divide deep coal-rock gas compound dynamic disasters into rock burst and coal and gas outburst compound dynamic disasters;

[0008] Step 2: Collect multi-source geophysical data related to the risk of coal-rock gas combined dynamic disasters, including microseismic data, acoustic emission data, electromagnetic radiation data, microcurrent data, and seismic CT data;

[0009] Step 3: Based on the rough set theory, the collected multi-source geophysical data are optimized to select the indicators that are most sensitive to the response to the compound dynamic disaster. The microseismic identification indicators, acoustic emission identification indicators, electromagnetic radiation identification indicators, microcurrent identification indicators, and seismic CT identification indicators for deep coal, rock and gas compound dynamic disaster risk identification are established.

[0010] The microseismic identification index (A) of the optimized multi-source geophysical data identification index is characterized by microseismic activity (Ae), which is described by the microseismic magnitude and number of events per day;

[0011] The acoustic emission identification index (B) of the optimized multi-source geophysical data identification index is composed of the acoustic emission average energy (B E ) and the frequency of acoustic emission events (B L ) representation;

[0012] The electromagnetic radiation identification index (C) of the optimized multi-source geophysical data identification index is composed of the electromagnetic radiation intensity (C E ) and the number of electromagnetic radiation pulses (C N ) representation;

[0013] The microcurrent identification index (D) of the optimized multi-source geophysical data identification index is composed of microcurrent energy (D E ) and micro-current speed increase (D K ) representation;

[0014] The seismic CT identification index (E) of the optimized multi-source geophysical data identification index is composed of the seismic wave velocity anomaly coefficient (E N ) and the seismic wave velocity gradient coefficient (E K ) representation.

[0015] Step 4: Based on the entropy weight method, weighted reconstruction and comprehensive analysis of multi-source geophysical data identification indicators are performed to build a multi-parameter indicator identification system for deep coal, rock and gas complex dynamic disaster risk identification driven by geophysical data;

[0016] The multi-parameter identification indicators for deep coal, rock and gas composite dynamic disaster risk identification based on geophysical data are:

[0017] F=k1A+k2B+k3C+k4D+k5E

[0018] Among them, A is the microseismic identification index, B is the acoustic emission identification index, C is the electromagnetic radiation identification index, D is the microcurrent identification index, E is the seismic CT identification index, F is the deep coal, rock and gas composite dynamic disaster risk identification index, and K is the indicator weight.

[0019] Step 5: Determine the identification criteria for comprehensive indicators and construct a risk grading table for comprehensive indicator identification;

[0020] The risk grading table for comprehensive indicator identification is as follows:

[0021]

[0022] Wherein, i is the value of F when each geophysical identification index takes 0.25 times the maximum value of the index, o is the value of F when each geophysical identification index takes 0.5 times the maximum value of the index, and p is the value of F when each geophysical identification index takes 0.75 times the maximum value.

[0023] By adopting the above technical solution, the beneficial effects of the present invention are:

[0024] (1) The method for identifying the risk of deep coal-rock gas composite dynamic disasters driven by geophysical data proposed in the present invention optimizes the collected multi-source geophysical data based on rough set theory, selects the indicators that are most sensitive to composite dynamic disasters and have higher application value, and establishes more scientific identification indicators of microseismic, acoustic emission, electromagnetic radiation, microcurrent, and seismic CT for the risk of deep coal-rock gas composite dynamic disasters, thereby greatly reducing the redundancy and conflict in the indicators, reducing the complexity of the deep coal-rock gas composite dynamic disaster risk identification system, and improving the accuracy and efficiency of the identification method of the present invention.

[0025] (2) The method for identifying the risk of deep coal-rock gas composite dynamic disasters based on geophysical data driving proposed in the present invention avoids the inability of a single geophysical method to fully reflect the precursor information of composite dynamic disasters, gives full play to the characteristics of multi-source geophysical data, and integrates, reconstructs and comprehensively analyzes the identification indicators of multi-source geophysical data based on the entropy weight method according to the actual contribution of geophysical data, establishes a comprehensive risk identification system, avoids the traditional way of obtaining weights relying on subjective judgment, makes the weight distribution of indicator fusion more reasonable, greatly improves the accuracy and reliability of the identification method of the present invention, and enables the identification method of the present invention to meet the actual needs of deep mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1This is a basic flow chart of the deep coal, rock and gas composite dynamic disaster risk identification method based on geophysical data in the example of the present invention.

[0027] Figure 2 Schematic diagram of the basic data required for the multi-parameter index identification system for deep coal, rock and gas composite dynamic disaster risk identification based on geophysical data in the example of the present invention

[0028] Figure 3 Flowchart for optimizing multi-source geophysical identification indicators based on rough set theory

[0029] Figure 4 Flowchart for determining the weights of multi-source geophysical identification indicators based on the entropy weight method DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The embodiments described below are only part of the embodiments of the present invention, rather than all of the embodiments.

[0031] The embodiment of the present invention discloses a method for identifying the risk of deep coal-rock gas composite dynamic disasters based on geophysical data. Figure 1 As shown, the following steps are included:

[0032] Step 1: After deep mining, the mine faces the dual threat of coal and gas outburst and rock burst, which manifests as the mutual induction and combination of coal and gas outburst and rock burst. Therefore, the present invention divides deep coal and rock gas compound dynamic disasters into rock burst and coal and gas outburst compound dynamic disasters;

[0033] Step 2: Acquire multi-source geophysical data related to the risk of coal-rock gas combined dynamic disasters, including microseismic data, acoustic emission data, electromagnetic radiation data, microcurrent data, and seismic CT data;

[0034] Step 3: Based on the rough set theory, the collected multi-source geophysical data are optimized to select the indicators that are most sensitive to the response to the compound dynamic disaster. The microseismic identification indicators, acoustic emission identification indicators, electromagnetic radiation identification indicators, microcurrent identification indicators, and seismic CT identification indicators for deep coal, rock and gas compound dynamic disaster risk identification are established.

[0035] The specific process of optimizing the collected multi-source geophysical data based on rough set theory is as follows:

[0036] 1. Establish an identification indicator knowledge system

[0037] Establish a knowledge system (S) for identifying indicators of multi-source geophysical data for deep coal, rock and gas complex dynamic disaster risks, where S = (u, c, d).

[0038] Among them, u is the geophysical data sample set, the identification indicator set and the risk set are the condition attribute set c and the decision attribute set d respectively.

[0039] 2. Generalization of identification indicators

[0040] Replace the lower-level concept layer (value range of each identification indicator) with the higher-level concept (risk level).

[0041] 3. Calculate the discrimination matrix

[0042] The discriminability matrix represents the discriminability of each pair of samples in the dataset under a given geophysical indicator (conditional attribute c). Each element of the matrix represents the set of indicators that can distinguish each pair of samples. The specific calculation process is as follows:

[0043]

[0044] Where, α * (u i ,u j ) is the element of the discrimination matrix, which means it can distinguish the sample u i and u j The conditional attribute set, C A is the condition attribute set (geophysical indicator set), c(u i ) is the sample u i The value of conditional attribute c, d(u i ) is the sample u i The value of the decision attribute d.

[0045] 4. Calculate the distinguishing function

[0046] The discriminant function is a Boolean function derived from the discriminant matrix. It represents the combination of conditional attributes to distinguish all pairs of objects under a given set of attributes. The specific calculation process of the discriminant function is as follows:

[0047]

[0048] Where S is the conditional attribute set C A A subset of , ∧ is the logical AND, indicating that the distinction conditions of all sample pairs must be met at the same time. ∨ is the logical OR, indicating that at least one indicator is required to distinguish a pair of samples.

[0049] 5. Output the minimum identification index subset

[0050] The discrimination function is analyzed to obtain the smallest subset of identification indicators, so that the subset can maintain the same discrimination ability as the original indicator set.

[0051] The preferred specific process is explained in detail with the following example:

[0052] Assume the following geophysical dataset and identify the risks.

[0053] sample <![CDATA[Microseismic magnitude (c1)]]> <![CDATA[Acoustic emission energy (c2)]]> <![CDATA[Acoustic emission ring count (c3)]]> Whether a compound dynamic disaster occurs (d) <![CDATA[u1]]> High risk Medium risk Weak risk yes <![CDATA[u2]]> Medium risk Medium risk Medium risk no <![CDATA[u3]]> High risk High risk High risk yes

[0054] Note: The above table is for illustration only and is not real data.

[0055] u1 and u2: d(u1)≠d(u2), and c1(u1)≠c1(u2), c2(u1)=c2(u2), c3(u1)≠c3(u2), so α * (u1,u2)={c1,c3}.

[0056] u1 and u3: d(u1) = d(u3), so

[0057] u2 and u3: d(u2)≠d(u3), and c1(u2)≠c1(u3), c2(u2)≠c2(u3), c3(u2)≠c3(u3), so α * (u2,u3)={c1,c2,c3}.

[0058] The discrimination matrix is ​​as follows:

[0059]

[0060] According to the discriminant matrix, the discriminant function is:

[0061] f(S)=(c1∨c3)∧(c1∨c2∨c3)

[0062] The analysis of the discrimination function shows that the minimum identification index subset is {c1, c3}.

[0063] Specifically, the microseismic identification indicators of the optimized multi-source geophysical data identification indicators include microseismic magnitude and event number; the acoustic emission identification indicators include acoustic emission energy and frequency; the electromagnetic radiation identification indicators include electromagnetic radiation intensity and pulse number; the microcurrent identification indicators include microcurrent energy and growth rate; the seismic CT identification indicators include seismic wave velocity anomaly coefficient and wave velocity gradient change coefficient.

[0064] The following is a detailed description of the specific contents of each identification indicator:

[0065] 1. Microseismic identification index (A)

[0066] The microseismic identification index (A) is composed of the microseismic activity (A E ) characterization, microseismicity (A E ) represents the strength of microseismic activity and is described by counting the daily microseismic magnitude and number of events. The calculation method is as follows:

[0067]

[0068] in,

[0069] Where m is the total number of magnitude classes, N is the total number of microseismic events within the statistical time period, and N i is the number of microseismic events corresponding to the i-th magnitude, M i is the magnitude corresponding to the i-th level.

[0070] Higher microseismic activity (A E ) value corresponds to a stronger risk of compound dynamic disasters, and the daily microseismic activity (A E ) for classification, and the value of the microseismic identification index (A) is as follows:

[0071]

[0072] 2. Acoustic emission identification index (B)

[0073] The acoustic emission identification index (B) is calculated by the average acoustic emission energy (B E ) and the frequency of acoustic emission events (B L ) characterization, the value of the acoustic emission identification index (B) is as follows:

[0074]

[0075] In the formula, x and y are the weight coefficients of the two parameters, and are both 0.5.

[0076] 3. Electromagnetic radiation identification index (C)

[0077] The electromagnetic radiation identification index (C) is determined by the electromagnetic radiation intensity (C E ) and the number of electromagnetic radiation pulses (C N ) characterization, the electromagnetic radiation identification index (C) value is determined as follows:

[0078]

[0079] In the formula, x and y are the weight coefficients of the two parameters, and are both 0.5.

[0080] 4. Microcurrent identification index (D)

[0081] The microcurrent identification index (D) is determined by the microcurrent energy (D E ) and micro-current speed increase (D K ) characterization, wherein the microcurrent growth rate calculation method is as follows:

[0082] D K =(D E2 -D E1) / (t2-t1)

[0083] Where t2 is the current moment, at which the microcurrent energy is D E2 , t1 is a certain moment before, at which the microcurrent energy is D E1 .

[0084] The method for determining the value of the microcurrent identification index (D) is as follows:

[0085]

[0086] In the formula, x and y are the weight coefficients of the two parameters, respectively, and are 0.5.

[0087] 5. Earthquake CT identification index (E)

[0088] The seismic CT identification index (E) is determined by the seismic wave velocity anomaly coefficient (E N ) and the seismic wave velocity gradient coefficient (E K ) characterization, where the seismic wave velocity anomaly coefficient (E N ) is calculated as follows:

[0089]

[0090] Where, v p is the wave velocity value at a point in the region, is the regional average wave velocity.

[0091] Among them, the wave velocity gradient variation coefficient (E K ) is calculated as follows:

[0092] E K =K·v p

[0093] Where K is the velocity gradient at a point in the region, v p is the wave velocity value at a point in the area.

[0094] The method for determining the value of the earthquake CT identification index (E) is as follows:

[0095]

[0096] In the formula, x and y are the weight coefficients of the two parameters, and are both 0.5.

[0097] Step 4: Based on the entropy weight method, the multi-source geophysical data identification indicators obtained in step 3 are weighted reconstructed and comprehensively analyzed to build a multi-parameter indicator identification system for deep coal, rock and gas complex dynamic disaster risk identification driven by geophysical data;

[0098] The specific process of determining the entropy weight of the multi-source geophysical data identification index is as follows:

[0099] 1. Quantification of basic geophysical data

[0100] The entropy weights of five geophysical methods are calculated by taking the existing multi-source geophysical exploration data as samples, and r is defined as ij is the jth level corresponding to the i-th geophysical method, and the data matrix of m evaluation indicators and n evaluation objects is R=(r ij ) m×n , the quantitative results R are as follows:

[0101]

[0102] Among them, level 1 is quantized to 0, level 2 is quantized to 0.33, level 3 is quantized to 0.66, and level 4 is quantized to 1.

[0103] Note: The above quantization values ​​are set based on past experience and can be reset according to actual conditions. The present invention does not limit this.

[0104] 2. Determine the entropy value of the identification index

[0105] In a problem with n evaluation objects and m evaluation indicators for each object, the entropy of the i-th indicator is:

[0106]

[0107] in, k=1 / ln n

[0108] 3. Determine the entropy weight of the identification index

[0109] After calculating the entropy of the i-th indicator, the entropy weight calculation process of the i-th indicator is:

[0110]

[0111] Where, 0≤k i ≤1, The indicator weights of the five geophysical methods are K = [k1k2k3k4k5]

[0112] Specifically, the multi-parameter indicator identification system for deep coal, rock and gas complex dynamic disaster risk identification driven by geophysical data is:

[0113] F=k1A+k2B+k3C+k4D+k5E

[0114] Among them, A is the microseismic identification index, B is the acoustic emission identification index, C is the electromagnetic radiation identification index, D is the microcurrent identification index, E is the seismic CT identification index, F is the deep coal, rock and gas composite dynamic disaster risk identification index, and k is the index weight.

[0115] Step 5: Determine the identification criteria for comprehensive indicators and construct a risk grading table for comprehensive indicator identification;

[0116] The risk grading table for comprehensive indicator identification is as follows:

[0117]

[0118] Wherein, i is the value of F when each geophysical identification index takes 0.25 times the maximum value of the index, o is the value of F when each geophysical identification index takes 0.5 times the maximum value of the index, and p is the value of F when each geophysical identification index takes 0.75 times the maximum value.

[0119] The parameter values ​​and parameter ranges shown in the embodiments of the present invention are determined by past experience and can be reset according to specific circumstances during actual application. The present invention does not limit the specific parameter values ​​and parameter ranges.

[0120] The types and quantities of geophysical data collected and used in the embodiments of the present invention may be increased, decreased or modified according to the actual conditions of the mining area. The present invention does not limit the specific types and quantity ranges of geophysical data.

[0121] The above embodiments are merely examples for the purpose of illustrating the present invention clearly, and are not intended to limit the embodiments. Other variations or modifications may be made based on the above description, and such modifications are still within the scope of protection of the present invention.

Claims

1. A method for identifying the risk of deep coal, rock and gas complex dynamic disasters based on geophysical data, characterized in that: include: Step 1: Divide deep coal-rock gas compound dynamic disasters into rock burst and coal and gas outburst compound dynamic disasters; Step 2: Collect multi-source geophysical data related to the risk of coal-rock gas combined dynamic disasters, including microseismic data, acoustic emission data, electromagnetic radiation data, microcurrent data, and seismic CT data; Step 3: Based on the rough set theory, the collected multi-source geophysical data are optimized to select the indicators that are most sensitive to the response to the compound dynamic disaster. The microseismic identification indicators, acoustic emission identification indicators, electromagnetic radiation identification indicators, microcurrent identification indicators, and seismic CT identification indicators for deep coal, rock and gas compound dynamic disaster risk identification are established. Step 4: Based on the entropy weight method, weighted reconstruction and comprehensive analysis of multi-source geophysical data identification indicators are performed to build a multi-parameter indicator identification system for deep coal, rock and gas complex dynamic disaster risk identification driven by geophysical data; Step 5: Determine the identification criteria for comprehensive indicators and construct a risk grading table for comprehensive indicator identification.

2. The method for identifying deep coal, rock and gas complex dynamic disaster risks based on geophysical data drive according to claim 1 is characterized in that: The process of optimizing the collected multi-source geophysical data based on rough set theory is as follows: Step 3.1: Establish a knowledge system for identifying indicators of deep coal, rock and gas combined dynamic disaster risk using multi-source geophysical data; Step 3.2: Replace the lower-level concepts (value ranges of each identification indicator) with higher-level concepts (risk levels); Step 3.3: Calculate the set of indicators in the discrimination matrix that can distinguish each pair of samples; Step 3.4: Derive the discriminant function from the discriminant matrix to distinguish all object pairs by the combination of conditional attributes; Step 3.5: Analyze the discrimination function and output the minimum identification index subset.

3. The method for identifying deep coal, rock and gas complex dynamic disaster risks based on geophysical data drive according to claim 1 is characterized in that: The multi-source geophysical indicators that are most sensitive to compound dynamic disasters after optimization specifically include: The microseismic identification index (A) of the optimized multi-source geophysical data identification index is composed of microseismic activity (A e ) characterization, using the daily microseismic magnitude and number of events for description; The acoustic emission identification index (B) of the optimized multi-source geophysical data identification index is composed of the acoustic emission average energy (B E ) and the frequency of acoustic emission events (B L ) representation; The electromagnetic radiation identification index (C) of the optimized multi-source geophysical data identification index is composed of the electromagnetic radiation intensity (C E ) and the number of electromagnetic radiation pulses (C N ) representation; The microcurrent identification index (D) of the optimized multi-source geophysical data identification index is composed of microcurrent energy (D E ) and micro-current speed increase (D K ) representation; The seismic CT identification index (E) of the optimized multi-source geophysical data identification index is composed of the seismic wave velocity anomaly coefficient (E N ) and seismic wave velocity gradient coefficient (E K ) representation.

4. The method for identifying deep coal, rock and gas complex dynamic disaster risks based on geophysical data drive according to claim 1 is characterized in that: The process of weighted reconstruction and comprehensive analysis of multi-source geophysical data identification indicators based on the entropy weight method is as follows: Step 4.1: Quantitative processing of basic geophysical data; Step 4.2: Calculate the entropy value of the multi-source geophysical data identification index; Step 4.3: Determine the entropy weight of the multi-source geophysical data identification indicator.

5. The method for identifying deep coal, rock and gas complex dynamic disaster risks based on geophysical data drive according to claim 1 is characterized in that: The multi-parameter indicator identification system for deep coal, rock and gas complex dynamic disaster risk identification based on geophysical data is: F=k1A+k2B+k3C+k4D+k5E Among them, A is the microseismic identification index, B is the acoustic emission identification index, C is the electromagnetic radiation identification index, D is the microcurrent identification index, E is the seismic CT identification index, F is the deep coal, rock and gas composite dynamic disaster risk identification index, and K is the indicator weight.

6. The method for identifying deep coal, rock and gas complex dynamic disaster risks based on geophysical data drive according to claim 1 is characterized in that: The risk grading table for comprehensive indicator identification is as follows: Wherein, i is the value of F when each geophysical identification index takes 0.25 times the maximum value of the index, o is the value of F when each geophysical identification index takes 0.5 times the maximum value of the index, and p is the value of F when each geophysical identification index takes 0.75 times the maximum value.

Images