Method for predicting and evaluating dangerousness of goaf ponding on underlying mining activity

Abstract

The invention discloses a method for predicting and evaluating the risk of goaf ponding on underlying mining activities, relates to the technical field of mining risk prediction, and solves the technical problems that in traditional risk prediction and evaluation of mining activities, it is difficult to integrate and analyze multivariate information, and ponding changes caused by environmental changes are neglected. The feature value of the ponding data is obtained by analyzing the ponding data, and the ponding influence factor is obtained based on the feature value of the ponding data; analyzing the basic data to obtain a mine safety factor, and analyzing the rock data to obtain a rock bearing factor; then integrating the ponding influence factor, the mine safety factor and the rock bearing factor to obtain an evaluation factor; inputting the evaluation factor into a risk prediction model to obtain a risk level, and sending out a safety early warning based on the risk level; according to the method, the safety risk of the mine can be evaluated more comprehensively, so that the prediction accuracy is improved.

Description

Technical Field

[0001] The invention belongs to the field of coal mine safety and relates to mining hazard prediction technology, in particular to a method for predicting and evaluating the hazard of water accumulation in goaf areas to underlying mining activities. Background Art

[0002] Water accidents during coal mining are one of the important factors affecting mine safety production. The presence of water in the goaf directly threatens the safe production of coal mines. How to safely and quickly solve the problem of water accumulation in the goaf of coal mines has become a problem that needs to be solved urgently.

[0003] Most methods for predicting and evaluating the hazard of water accumulation in goafs to underlying mining activities find it difficult to integrate and analyze multiple information during the hazard prediction and evaluation of mining activities, resulting in inaccurate assessment results. The methods are unable to truly reflect the actual risk of water accumulation in goafs, thus increasing the hazard of mining. At the same time, most methods for predicting and evaluating the hazard of water accumulation in goafs to underlying mining activities ignore the changes in water accumulation caused by environmental changes, and cannot accurately find a balance value in the water accumulation data that can simultaneously ensure safety and economic benefits, thus increasing the economic burden on enterprises.

[0004] Therefore, the present invention discloses a method for predicting and evaluating the danger of water accumulation in goaf areas to underlying mining activities, which is used to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities, which is used to solve the technical problems that it is difficult to integrate and analyze multivariate information and ignore the changes in water accumulation caused by environmental changes in traditional prediction and evaluation of the danger of mining activities. The present invention obtains characteristic values ​​of water accumulation data by analyzing water accumulation data, and obtains water accumulation influence factors based on the characteristic values ​​of water accumulation data; analyzes basic data to obtain mine safety factors, and analyzes rock data to obtain rock bearing factors; comprehensively obtains evaluation factors for water accumulation influence factors, mine safety factors and rock bearing factors; inputs the evaluation factors into a hazard prediction model to obtain risk levels, and issues safety warnings based on the risk levels to solve the above problems.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides a method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities, comprising:

[0007] Obtain water accumulation data of the goaf and basic data and rock data covering the goaf; water accumulation data include the area, volume and height of the water accumulation area; basic data include the straight line distance and mining height; rock data include the strength, hardness and toughness of the rock;

[0008] The characteristic value of water accumulation data is obtained by analyzing the water accumulation data, and the water accumulation impact factor is obtained based on the characteristic value of water accumulation data; the mine safety factor is obtained by analyzing the basic data, and the rock bearing factor is obtained by analyzing the rock data; the evaluation factor is obtained by comprehensively analyzing the water accumulation impact factor, mine safety factor and rock bearing factor;

[0009] The evaluation factors are input into the hazard prediction model to obtain the risk level, and a safety warning is issued based on the risk level; wherein, the hazard prediction model is obtained through artificial intelligence model training.

[0010] Preferably, the step of obtaining water accumulation data of the goaf and basic data and rock data underlying the goaf includes:

[0011] The hydrogeological data, geological exploration data and rock detection data of the goaf are stored in the database; the daily waterlogging area and water volume as well as the waterlogging height at each location are extracted through the database, the mining height and the straight-line distance between the waterlogging area and the underlying mining working face are extracted from the database, and the straight-line distance is marked as the straight-line distance length; the strength, hardness and toughness of the underlying rock of the goaf are extracted through the database.

[0012] Preferably, the step of analyzing the waterlogging data to obtain characteristic values ​​of the waterlogging data includes:

[0013] Extract the area and volume of waterlogging every day, integrate the area of ​​waterlogging into group A1, and integrate the volume of waterlogging into group A2;

[0014] The maximum value ZD1, percentile BW1 and mode ZS1 of group A1 are extracted, and the characteristic value TZM of the waterlogged area is obtained based on the formula TZM=(α1×ZD1+α2×BW1+ZS1) / 2; wherein α1 and α2 are both proportional adjustment coefficients greater than 0, and α1+α2=1, α1≥α2;

[0015] The maximum value ZD2, percentile BW2 and mode ZS2 of group A2 are extracted, and the characteristic value TZL of the water volume is obtained based on the formula TZL=(α3×ZD2+α4×BW2+ZS2) / 2; wherein, the percentiles of percentile BW1 and percentile BW2 are obtained by manual setting; α3 and α4 are both proportional adjustment coefficients greater than 0, and α3+α4=1, α3≥α4; the characteristic values ​​of the waterlogging data include the characteristic value TZM of the waterlogging area, the characteristic value TZL of the water volume and the characteristic value of the waterlogging height;

[0016] The water accumulation height at different locations is analyzed to obtain the characteristic value of the water accumulation height.

[0017] Preferably, the analyzing the water accumulation heights at different locations to obtain characteristic values ​​of the water accumulation heights includes:

[0018] The water accumulation heights at different days and different locations in the goaf are integrated into a water accumulation data group, the variance of the water accumulation data group is obtained, and it is judged whether the variance is less than the defined variance threshold of the water accumulation data group; if yes, the data of the water accumulation data group is retained; if no, the data with the largest difference from the percentile in the water accumulation data group is removed, and the variance judgment is re-performed until the variance of the water accumulation data group is less than the defined variance threshold of the corresponding data group, and the remaining data of the water accumulation data group is retained; wherein the defined variance threshold is obtained through experience;

[0019] The characteristic value TZG of the water accumulation height is obtained by calculating the average value of the retained data in the water accumulation data group.

[0020] Preferably, the waterlogging impact factor obtained based on the characteristic value of the waterlogging data includes:

[0021] B1: extract the characteristic value TZL of the accumulated water volume, and determine whether the characteristic value TZL is greater than the water volume safety threshold; if yes, issue an alarm signal of excessive accumulated water volume; if no, jump to B2;

[0022] B2: Extract the characteristic value TZG of the water level, and determine whether the characteristic value TZG is greater than the water level safety threshold; if yes, issue an alarm signal of excessive water level; if no, jump to B3; wherein the water volume safety threshold and the water level safety threshold are both obtained through experience;

[0023] B3: Extract the characteristic value TZM of the waterlogging area, and obtain the waterlogging influence factor SZ based on the formula SZ=1 / exp(β1×(TZL-BTZL) / BTZL+β2×(TZG-BTZG) / BTZG+β3×(TZM-BTZM) / BTZM); wherein β1, β2 and β3 are all proportional adjustment coefficients greater than 0, and β1+β2+β3=1; BTZL is the standard characteristic value of the artificially set water volume, BTZG is the standard characteristic value of the artificially set water height, and BTZM is the standard characteristic value of the artificially set waterlogging area.

[0024] Preferably, the analysis of the basic data to obtain the mine safety factor includes:

[0025] C1: extract the straight line distance length ZC, and determine whether the straight line distance length ZC is less than the standard distance length BZC; if yes, issue a warning message that the straight line distance length is too small; if no, jump to C2;

[0026] C2: Extract the mining height CG, and obtain the mine safety factor AZ based on the formula AZ=γ1 / exp((CG-BCG) / BCG)+(γ2×ln((ZC-BZC) / BZC+1)+1); where γ1 and γ2 are amplitude adjustment coefficients, and the value ranges of γ1 and γ2 are both (0,2); the standard standoff length BZC and the standard mining height BCG are both obtained through manual settings.

[0027] Preferably, the step of analyzing the rock data to obtain the rock bearing factor includes:

[0028] Extract rock strength YQ, hardness YY and toughness YR as well as standard rock strength BYQ, standard rock hardness BYY and standard rock toughness BYR from the database;

[0029] The strength YQ, hardness YY, toughness YR, standard rock strength BYQ, standard rock hardness BYY and standard rock toughness BYR are normalized, and the rock bearing factor YZ is obtained based on the formula YZ=δ1×(YQ×YY) / (BYQ×BYY)+δ2×(YQ×YR) / (BYQ×BYR)+δ3×(YY×YR) / (BYY×BYR); among which δ1, δ2 and δ3 are all proportional adjustment coefficients ranging from [0,1].

[0030] Preferably, the evaluation factor obtained by comprehensively analyzing the water accumulation impact factor, the mine safety factor and the rock bearing factor includes:

[0031] The water accumulation influencing factor SZ, mine safety factor AZ and rock bearing factor YZ are extracted, and the evaluation factor PYZ is obtained based on the formula PYZ=(ρ1×SZ+ρ2×YZ)×AZ; among them, ρ1 and ρ2 are both manually set proportional adjustment coefficients, and the value range of ρ1 and ρ2 is [0,1], ρ1+ρ2=1.

[0032] Preferably, the risk prediction model is obtained through artificial intelligence model training, including:

[0033] The risk levels of the hazard prediction model are set as level 1 risk, level 2 risk, level 3 risk and level 4 risk, and the definition thresholds corresponding to level 1 risk, level 2 risk, level 3 risk and level 4 risk are set as the judgment thresholds of the artificial intelligence model;

[0034] Evaluation factors and corresponding risk levels are extracted from the database and combined into a number of training data and test data; the artificial intelligence model is trained using the training data, and the trained artificial intelligence model is tested using the test data. The artificial intelligence model is adjusted according to the test results, and finally a hazard prediction model is obtained with the evaluation factors as input and the risk level as output; wherein the artificial intelligence model includes a BP neural network model and a RBF neural network model.

[0035] Specifically, the trained artificial intelligence model is tested using the test data, and the specific steps for adjusting the artificial intelligence model according to the test results are as follows:

[0036] The evaluation factors in the test data are input into the trained artificial intelligence model to obtain the corresponding risk level. The corresponding risk level is compared with the corresponding risk level in the test data. When the two risk levels are the same, there is no need to adjust the parameters and the next set of test data is tested. If the two risk levels are different, the corresponding parameters are adjusted until the two risk levels are the same, and then the next set of test data is tested. When the number of tests with the same two risk levels accounts for 90% or more of the total number of tests, a hazard prediction model with evaluation factors as input and risk levels as output is obtained.

[0037] Preferably, issuing a safety warning based on the risk level includes:

[0038] D1: Extract the risk level and determine whether the risk level is level 1 risk; if yes, issue a warning that mining has an extremely high risk; if no, jump to D2;

[0039] D2: Determine whether the risk level is level 2 risk; if yes, issue a warning that mining has high risk; if no, jump to D3;

[0040] D3: Determine whether the risk level is level 3 risk; if yes, issue a warning that mining has medium risk; if no, issue a warning that mining has low risk.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. The present invention obtains characteristic values ​​of water accumulation data by analyzing water accumulation data, and obtains water accumulation influencing factors based on the characteristic values ​​of water accumulation data; obtains mine safety factors by analyzing basic data, and obtains rock bearing factors by analyzing rock data; obtains evaluation factors by comprehensively analyzing water accumulation influencing factors, mine safety factors and rock bearing factors; inputs the evaluation factors into a hazard prediction model to obtain risk levels, and issues safety warnings based on the risk levels, thereby solving the technical problems of difficulty in integrating and analyzing multivariate information and ignoring changes in water accumulation caused by environmental changes in hazard prediction and evaluation of traditional mining activities; the present invention can more comprehensively evaluate the safety risks of mines, thereby improving the accuracy of predictions.

[0043] 2. The water accumulation in the goaf above the mine may change with changes in the environment. For example, an increase in rainfall in a short period of time will lead to an increase in water accumulation. At this time, the calculation of the water accumulation influence factor needs to take into account the change in water accumulation caused by environmental changes. Therefore, the present invention extracts characteristic values ​​of the water volume, water height and water accumulation area before calculating the water accumulation influence factor to obtain a standard value that can express the current water accumulation in the goaf. This can make the calculated water accumulation influence factor more in line with the actual situation and increase the accuracy of the calculation results.

[0044] 3. The present invention obtains the risk level of the current mine through the evaluation factor. Through the risk level, the mining enterprise can predict the danger of water accumulation in the goaf before mining activities, so as to take corresponding early warning and prevention measures in advance, effectively avoid or reduce the occurrence of water disasters, and ensure the safety of mine production; and the mining enterprise can adjust and optimize the mining plan, such as changing the mining sequence, strengthening support measures, etc., to reduce the safety risks in the mining process and improve the stability of mining activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a schematic diagram of the operation steps of the present invention;

[0047] Figure 2 A schematic diagram of the operation steps for obtaining characteristic values ​​of water accumulation data according to the present invention;

[0048] Figure 3 The figure is a schematic diagram of the operation steps for obtaining the waterlogging influence factor of the present invention. DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] See also Figure 1-Figure 2 The first embodiment of the present invention provides a method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities, comprising:

[0051] Obtain water accumulation data of the goaf and basic data and rock data covering the goaf; water accumulation data include the area, volume and height of the water accumulation area; basic data include the straight line distance and mining height; rock data include the strength, hardness and toughness of the rock;

[0052] The characteristic value of water accumulation data is obtained by analyzing the water accumulation data, and the water accumulation impact factor is obtained based on the characteristic value of water accumulation data; the mine safety factor is obtained by analyzing the basic data, and the rock bearing factor is obtained by analyzing the rock data; the evaluation factor is obtained by comprehensively analyzing the water accumulation impact factor, mine safety factor and rock bearing factor;

[0053] The evaluation factors are input into the hazard prediction model to obtain the risk level, and a safety warning is issued based on the risk level; wherein, the hazard prediction model is obtained through artificial intelligence model training.

[0054] In this application, water accumulation data of the goaf and basic data and rock data under the goaf are obtained, including:

[0055] The hydrogeological data, geological exploration data and rock detection data of the goaf are stored in the database; the daily waterlogging area and water volume as well as the waterlogging height at each location are extracted through the database; the mining height and the straight-line distance between the waterlogging area and the underlying mining working face are extracted from the database, and the straight-line distance is marked as the straight-line distance length; the strength, hardness and toughness of the underlying rock of the goaf are extracted through the database.

[0056] It should be noted that the position point in the water accumulation height at each position point is the position point where the water accumulation contacts the surface of the goaf.

[0057] It should be noted that mining height refers to the vertical distance from the top to the bottom of the ore body in an underground mine.

[0058] In this application, the waterlogging data is analyzed to obtain characteristic values ​​of the waterlogging data, including:

[0059] Extract the area and volume of waterlogging every day, integrate the area of ​​waterlogging into group A1, and integrate the volume of waterlogging into group A2;

[0060] The maximum value ZD1, percentile BW1 and mode ZS1 of group A1 are extracted, and the characteristic value TZM of the waterlogged area is obtained based on the formula TZM=(α1×ZD1+α2×BW1+ZS1) / 2; wherein α1 and α2 are both proportional adjustment coefficients greater than 0, and α1+α2=1, α1≥α2;

[0061] The maximum value ZD2, percentile BW2 and mode ZS2 of group A2 are extracted, and the characteristic value TZL of the water volume is obtained based on the formula TZL=(α3×ZD2+α4×BW2+ZS2) / 2; wherein, the percentiles of percentile BW1 and percentile BW2 are obtained by manual setting; α3 and α4 are both proportional adjustment coefficients greater than 0, and α3+α4=1, α3≥α4; the characteristic values ​​of the waterlogging data include the characteristic value TZM of the waterlogging area, the characteristic value TZL of the water volume and the characteristic value TZG of the waterlogging height;

[0062] The water accumulation height at different locations is analyzed to obtain the characteristic value of the water accumulation height.

[0063] It is worth noting that the present invention uses percentiles when calculating the characteristic value TZM of the waterlogged area and the characteristic value TZL of the water volume. The percentiles are used to avoid interference caused by abnormal values ​​or outliers in group A1 or group A2. These values ​​may have a significant impact on statistics such as the mean. The use of percentiles can reduce the fluctuation interference caused by these abnormal situations and improve the accuracy of the system's data analysis.

[0064] It should be noted that in the present invention, percentile BW1 and percentile BW2 are values ​​at a specific percentile in each group; if the data of each group are sorted in descending order, if the manually set percentile is 80%, then the data at the 80% position of each group is the percentile of the group. If there is no data at the 80% position of the group, the data closest to the 80% position is used as the percentile of the group.

[0065] In this application, the water accumulation height at different locations is analyzed to obtain characteristic values ​​of the water accumulation height, including:

[0066] The water accumulation heights at different days and locations in the goaf are integrated into a water accumulation data group, the variance of the water accumulation data group is obtained, and it is judged whether the variance is less than the defined variance threshold of the water accumulation data group; if yes, the data of the water accumulation data group is retained; if no, the data with the largest difference from the percentile in the water accumulation data group is removed, and the variance is judged again until the variance of the water accumulation data group is less than the defined variance threshold of the corresponding data group, and the remaining data of the water accumulation data group is retained; wherein the defined variance threshold is obtained through experience;

[0067] The characteristic value TZG of the water accumulation height is obtained by calculating the average value of the retained data in the water accumulation data group.

[0068] It is worth noting that the present invention uses a variance judgment method when obtaining the characteristic value of water accumulation height. When the variance in the water accumulation data group does not meet the requirements, it proves that there are values ​​in the current data group that affect data stability. At this time, the values ​​that affect data stability are removed and then variance judgment is performed until the variance of the water accumulation data group meets the requirements. At this time, a group of characteristic data that can represent water accumulation in the goaf is obtained. Then, characteristic value extraction is performed on this group of characteristic data to obtain a water accumulation characteristic that can represent the current goaf, which provides data support for subsequent analysis of water accumulation safety.

[0069] See also Figure 3 In this application, the waterlogging impact factor is obtained based on the characteristic value of the waterlogging data, including:

[0070] B1: Extract the characteristic value TZL of the accumulated water volume, and determine whether the characteristic value TZL is greater than the water volume safety threshold; if yes, issue an alarm signal of excessive accumulated water volume; if no, jump to B2;

[0071] B2: Extract the characteristic value TZG of the water level, and determine whether the characteristic value TZG is greater than the water level safety threshold; if yes, issue an alarm signal of excessive water level; if no, jump to B3; the water volume safety threshold and water level safety threshold are both obtained through experience;

[0072] B3: Extract the characteristic value TZM of the waterlogging area, and obtain the waterlogging influence factor SZ based on the formula SZ=1 / exp(β1×(TZL-BTZL) / BTZL+β2×(TZG-BTZG) / BTZG+β3×(TZM-BTZM) / BTZM); wherein β1, β2 and β3 are all proportional adjustment coefficients greater than 0, and β1+β2+β3=1; BTZL is the standard characteristic value of the artificially set water volume, BTZG is the standard characteristic value of the artificially set water height, and BTZM is the standard characteristic value of the artificially set waterlogging area.

[0073] It is worth noting that the water accumulation in the goaf above the mine may change with changes in the environment. For example, an increase in rainfall in a short period of time will lead to an increase in water accumulation. At this time, the calculation of the water accumulation impact factor needs to take into account the change in water accumulation caused by environmental changes. Therefore, before calculating the water accumulation impact factor, the present invention extracts characteristic values ​​of the water volume, water height and water accumulation area to obtain a standard value that can express the current water accumulation in the goaf. This can make the calculated water accumulation impact factor more in line with the actual situation and increase the accuracy of the calculation results.

[0074] In this embodiment, if the characteristic value of the water volume TZL = 10,000 cubic meters, the characteristic value of the water height TZG = 15 meters, and the characteristic value of the water area TZM = 1,000 square meters;

[0075] Based on the formula SZ=1 / exp(β1×(TZL-BTZL) / BTZL+β2×(TZG-BTZG) / BTZG+β3×(TZM-BTZM) / BTZM)=1 / exp(0.5×(10000-6000) / 6000+0.3×(15-10) / 10+0.2×(1000-600) / 600)=0.539, the waterlogging influence factor SZ=0.539 is obtained; wherein, in this embodiment, the proportional adjustment coefficient β1 takes a value of 0.5, the proportional adjustment coefficient β2 takes a value of 0.3, and the proportional adjustment coefficient β3 takes a value of 0.2; the standard characteristic value of the water volume BTZL=6000 cubic meters, the standard characteristic value of the water height BTZG=10 meters, and the standard characteristic value of the waterlogging area BTZM=600 square meters.

[0076] In this application, the basic data is analyzed to obtain the mine safety factors, including:

[0077] C1: Extract the straight line distance length ZC and determine whether the straight line distance length ZC is less than the standard distance length BZC; if yes, issue a warning message that the straight line distance length is too small; if no, jump to C2;

[0078] C2: Extract the mining height CG, and obtain the mine safety factor AZ based on the formula AZ=γ1 / exp((CG-BCG) / BCG)+(γ2×ln((ZC-BZC) / BZC+1)+1); where γ1 and γ2 are amplitude adjustment coefficients, and the value ranges of γ1 and γ2 are both (0,2); the standard standoff length BZC and the standard mining height BCG are both obtained through manual settings.

[0079] In this embodiment, if the straight-line distance ZC = 50 meters and the mining height CG = 4 meters; based on the formula AZ = γ1 / exp((CG-BCG) / BCG)+(γ2×ln((ZC-BZC) / BZC+1)+1)=0.9 / exp((4-3) / 3)+(0.8×ln((50-40) / 40+1)+1)=1.82, the mine safety factor AZ=1.82 is obtained; wherein, in this embodiment, the amplitude adjustment coefficient γ1 takes a value of 0.9, and the amplitude adjustment coefficient γ2 takes a value of 0.8; the standard distance length BZC takes a value of 40 meters, and the standard mining height BCG takes a value of 3 meters.

[0080] In this application, the rock data is analyzed to obtain the rock bearing factor, including:

[0081] Extract rock strength YQ, hardness YY and toughness YR as well as standard rock strength BYQ, standard rock hardness BYY and standard rock toughness BYR from the database;

[0082] The strength YQ, hardness YY, toughness YR, standard rock strength BYQ, standard rock hardness BYY and standard rock toughness BYR are normalized, and the rock bearing factor YZ is obtained based on the formula YZ=δ1×(YQ×YY) / (BYQ×BYY)+δ2×(YQ×YR) / (BYQ×BYR)+δ3×(YY×YR) / (BYY×BYR); among which δ1, δ2 and δ3 are all proportional adjustment coefficients ranging from [0,1].

[0083] In this embodiment, the rock has a strength of YQ = 20 MPa, a hardness of YY of 6.5 Mohs hardness, and a toughness of YR = 800 J / m2; based on the formula YZ = δ1×(YQ×YY) / (BYQ×BYY)+δ2×(YQ×YR) / (BYQ×BYR)+δ3×(YY×YR) / (BYY×BYR)=0.6×(20×6.5) / (15×6)+0.5×(20×800) / (15×70 0)+0.7×(6.5×800) / (6×700)=2.49, and the rock bearing factor YZ=2.49 is obtained; wherein, in this embodiment, the proportional adjustment coefficient δ1 is taken as 0.6, the proportional adjustment coefficient δ2 is taken as 0.5, and the proportional adjustment coefficient δ3 is taken as 0.7; the standard rock strength BYQ is taken as 15Mpa, the standard rock hardness BYY is taken as 6 Mohs hardness, and the standard rock toughness BYR is taken as 700J / square meter.

[0084] In this application, the water accumulation impact factor, mine safety factor and rock bearing factor are comprehensively evaluated to obtain the evaluation factors, including:

[0085] The water accumulation influencing factor SZ, mine safety factor AZ and rock bearing factor YZ are extracted, and the evaluation factor PYZ is obtained based on the formula PYZ=(ρ1×SZ+ρ2×YZ)×AZ; among them, ρ1 and ρ2 are both manually set proportional adjustment coefficients, and the value range of ρ1 and ρ2 is [0,1], ρ1+ρ2=1.

[0086] It is worth noting that the present invention obtains an evaluation factor that can indicate the current safety of mine mining by comprehensively analyzing the water accumulation data of the goaf, mine data and the mechanical properties of the rock in the goaf. This can predict possible production safety problems in the mine, thereby taking preventive measures in advance and improving the safety of mine mining.

[0087] It should be noted that the mechanical properties of rock in the goaf are the strength, hardness and toughness of the rock.

[0088] In this embodiment, the water accumulation influence factor SZ=0.539, the mine safety factor AZ=1.82 and the rock bearing factor YZ=2.49, based on the formula PYZ=(ρ1×SZ+ρ2×YZ)×AZ=(0.8×0.539+0.2×2.49)×1.82=1.69, the evaluation factor PYZ=1.69 is obtained; wherein, in this embodiment, the value of the proportional adjustment coefficient ρ1 is 0.8, and the value of the proportional adjustment coefficient ρ2 is 0.2.

[0089] The risk prediction model in this application is obtained through artificial intelligence model training, including:

[0090] The risk levels of the hazard prediction model are set as level 1 risk, level 2 risk, level 3 risk and level 4 risk, and the definition thresholds corresponding to level 1 risk, level 2 risk, level 3 risk and level 4 risk are set as the judgment thresholds of the artificial intelligence model;

[0091] Evaluation factors and corresponding risk levels are extracted from the database and combined into a number of training data and test data; the artificial intelligence model is trained using the training data, and the trained artificial intelligence model is tested using the test data. The artificial intelligence model is adjusted according to the test results, and finally a hazard prediction model is obtained with the evaluation factors as input and the risk level as output; wherein the artificial intelligence model includes a BP neural network model and a RBF neural network model.

[0092] Specifically, the trained artificial intelligence model is tested using the test data, and the specific steps for adjusting the artificial intelligence model according to the test results are as follows:

[0093] The evaluation factors in the test data are input into the trained artificial intelligence model to obtain the corresponding risk level. The corresponding risk level is compared with the corresponding risk level in the test data. When the two risk levels are the same, there is no need to adjust the parameters and the next set of test data is tested. If the two risk levels are different, the corresponding parameters are adjusted until the two risk levels are the same, and then the next set of test data is tested. When the number of tests with the same two risk levels accounts for 90% or more of the total number of tests, a hazard prediction model with evaluation factors as input and risk levels as output is obtained.

[0094] It is worth noting that the present invention obtains the risk level of the current mine through the evaluation factor. Through the risk level, the mining enterprise can predict the danger of water accumulation in the goaf before mining activities, so as to take corresponding early warning and prevention measures in advance, effectively avoid or reduce the occurrence of water disasters, and ensure the safety of mine production; and the mining enterprise can adjust and optimize the mining plan, such as changing the mining sequence, strengthening support measures, etc., to reduce the safety risks in the mining process and improve the stability of mining activities.

[0095] It should be noted that the evaluation factors and corresponding risk levels are extracted from the database by comparing the evaluation factors with the defined thresholds.

[0096] In this application, security warnings are issued based on risk levels, including:

[0097] D1: Extract the risk level and determine whether it is a level 1 risk; if yes, issue a warning that mining has an extremely high risk; if no, jump to D2;

[0098] D2: Determine whether the risk level is level 2 risk; if yes, issue a warning that mining is high risk; if no, jump to D3;

[0099] D3: Determine whether the risk level is level 3 risk; if yes, issue a warning that mining has medium risk; if no, issue a warning that mining has low risk.

[0100] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0101] Working principle of the present invention:

[0102] Acquire water accumulation data of the goaf and basic data and rock data underlying the goaf; analyze the water accumulation data to obtain characteristic values ​​of the water accumulation data; obtain water accumulation influencing factors based on the characteristic values ​​of the water accumulation data. In this step, the present invention extracts characteristic values ​​of water volume, water accumulation height and water accumulation area to obtain a standard value that can express the current water accumulation in the goaf, so that the calculated water accumulation influencing factors are more in line with the actual situation and the accuracy of the calculation results is increased; analyze the basic data to obtain the mine safety factor, and analyze the rock data to obtain the rock bearing factor; comprehensively obtain the evaluation factor of the water accumulation influencing factor, the mine safety factor and the rock bearing factor. In this step, the present invention obtains an evaluation factor that can indicate the current safety of mine mining by comprehensively analyzing the water accumulation data, mine data and mechanical properties of the rock in the goaf, so that it can predict possible safety production problems in the mine, thereby taking preventive measures in advance and improving the safety of mine mining; input the evaluation factor into the hazard prediction model to obtain the risk level, and issue a safety warning based on the risk level.

[0103] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities, characterized in that: Obtain water accumulation data of the goaf and basic data and rock data covering the goaf; water accumulation data include the area, volume and height of the water accumulation area; basic data include the straight line distance and mining height; rock data include the strength, hardness and toughness of the rock; The characteristic value of water accumulation data is obtained by analyzing the water accumulation data, and the water accumulation impact factor is obtained based on the characteristic value of water accumulation data; the mine safety factor is obtained by analyzing the basic data, and the rock bearing factor is obtained by analyzing the rock data; the evaluation factor is obtained by comprehensively analyzing the water accumulation impact factor, mine safety factor and rock bearing factor; The evaluation factors are input into the hazard prediction model to obtain the risk level, and a safety warning is issued based on the risk level; wherein, the hazard prediction model is obtained through artificial intelligence model training.

2. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 1 is characterized in that: The method of obtaining water accumulation data of the goaf and basic data and rock data underlying the goaf includes: The hydrogeological data, geological exploration data and rock detection data of the goaf are stored in the database; the daily waterlogging area and water volume as well as the waterlogging height at each location are extracted through the database, the mining height and the straight-line distance between the waterlogging area and the underlying mining working face are extracted from the database, and the straight-line distance is marked as the straight-line distance length; the strength, hardness and toughness of the underlying rock of the goaf are extracted through the database.

3. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 1 is characterized in that: The step of analyzing the waterlogging data to obtain characteristic values ​​of the waterlogging data includes: Extract the area and volume of waterlogging every day, integrate the area of ​​waterlogging into group A1, and integrate the volume of waterlogging into group A2; The maximum value ZD1, percentile BW1 and mode ZS1 of group A1 are extracted, and the characteristic value TZM of the waterlogged area is obtained based on the formula TZM=(α1×ZD1+α2×BW1+ZS1) / 2; wherein α1 and α2 are both proportional adjustment coefficients greater than 0, and α1+α2=1, α1≥α2; The maximum value ZD2, percentile BW2 and mode ZS2 of group A2 are extracted, and the characteristic value TZL of the water volume is obtained based on the formula TZL=(α3×ZD2+α4×BW2+ZS2) / 2; wherein α3 and α4 are both proportional adjustment coefficients greater than 0, and α3+α4=1, α3≥α4; the characteristic values ​​of the waterlogging data include the characteristic value TZM of the waterlogging area, the characteristic value TZL of the water volume and the characteristic value TZG of the waterlogging height; The water accumulation height at different locations is analyzed to obtain the characteristic value of the water accumulation height.

4. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 3 is characterized in that: The analysis of the water accumulation height at different locations to obtain the characteristic value of the water accumulation height includes: Integrate the water accumulation heights of different days and different locations in the goaf into a water accumulation data group, obtain the variance of the water accumulation data group, and determine whether the variance is less than the defined variance threshold of the water accumulation data group; if yes, retain the data of the water accumulation data group; if no, remove the data with the largest difference from the percentile in the water accumulation data group, and re-determine the variance until the variance of the water accumulation data group is less than the defined variance threshold of the corresponding data group, and retain the remaining data of the water accumulation data group; The characteristic value TZG of the water accumulation height is obtained by calculating the average value of the retained data in the water accumulation data group.

5. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 1 is characterized in that: The waterlogging impact factor obtained based on the characteristic value of the waterlogging data includes: B1: extract the characteristic value TZL of the accumulated water volume, and determine whether the characteristic value TZL is greater than the water volume safety threshold; if yes, issue an alarm signal of excessive accumulated water volume; if no, jump to B2; B2: extract the characteristic value TZG of the water level, and determine whether the characteristic value TZG is greater than the water level safety threshold; if yes, issue an alarm signal that the water level is too high; if no, jump to B3; B3: Extract the characteristic value TZM of the waterlogged area, and obtain the waterlogging influencing factor SZ based on the formula SZ=1 / exp(β1×(TZL-BTZL) / BTZL+β2×(TZG-BTZG) / BTZG+β3×(TZM-BTZM) / BTZM); wherein β1, β2 and β3 are all proportional adjustment coefficients greater than 0, and β1+β2+β3=1; BTZL is the standard characteristic value of water volume, BTZG is the standard characteristic value of water height, and BTZM is the standard characteristic value of waterlogged area.

6. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 5 is characterized in that: The mine safety factor obtained by analyzing the basic data includes: C1: extract the straight line distance length ZC, and determine whether the straight line distance length ZC is less than the standard distance length BZC; if yes, issue a warning message that the straight line distance length is too small; if no, jump to C2; C2: Extract the mining height CG, and obtain the mine safety factor AZ based on the formula AZ=γ1 / exp((CG-BCG) / BCG)+(γ2×ln((ZC-BZC) / BZC+1)+1); where γ1 and γ2 are amplitude adjustment coefficients, and the value ranges of γ1 and γ2 are both (0,2).

7. A method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 6, characterized in that: The rock bearing factor obtained by analyzing the rock data includes: Extract rock strength YQ, hardness YY and toughness YR as well as standard rock strength BYQ, standard rock hardness BYY and standard rock toughness BYR from the database; The strength YQ, hardness YY, toughness YR, standard rock strength BYQ, standard rock hardness BYY and standard rock toughness BYR are normalized, and the rock bearing factor YZ is obtained based on the formula YZ=δ1×(YQ×YY) / (BYQ×BYY)+δ2×(YQ×YR) / (BYQ×BYR)+δ3×(YY×YR) / (BYY×BYR); among which δ1, δ2 and δ3 are all proportional adjustment coefficients ranging from [0,1].

8. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 7 is characterized in that: The evaluation factors obtained by comprehensively analyzing the water accumulation impact factor, the mine safety factor and the rock bearing factor include: The water accumulation influencing factor SZ, mine safety factor AZ and rock bearing factor YZ are extracted, and the evaluation factor PYZ is obtained based on the formula PYZ=(ρ1×SZ+ρ2×YZ)×AZ; among them, ρ1 and ρ2 are both proportional adjustment coefficients, and the value range of ρ1 and ρ2 is [0,1], ρ1+ρ2=1.

9. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 1 is characterized in that: The risk prediction model is obtained through artificial intelligence model training, including: The risk levels of the hazard prediction model are set as level 1 risk, level 2 risk, level 3 risk and level 4 risk, and the definition thresholds corresponding to level 1 risk, level 2 risk, level 3 risk and level 4 risk are set as the judgment thresholds of the artificial intelligence model; Evaluation factors and corresponding risk levels are extracted from the database and combined into a number of training data and test data; the artificial intelligence model is trained using the training data, and the trained artificial intelligence model is tested using the test data. The artificial intelligence model is adjusted according to the test results, and finally a hazard prediction model is obtained with the evaluation factors as input and the risk level as output; wherein the artificial intelligence model includes a BP neural network model and a RBF neural network model.

10. The method for predicting and evaluating the danger of water accumulation in goaf to underlying mining activities according to claim 1, characterized in that: The security warning issued based on the risk level includes: D1: Extract the risk level and determine whether the risk level is level 1 risk; if yes, issue a warning that mining has an extremely high risk; if no, jump to D2; D2: Determine whether the risk level is level 2 risk; if yes, issue a warning that mining has high risk; if no, jump to D3; D3: Determine whether the risk level is level 3 risk; if yes, issue a warning that mining has medium risk; if no, issue a warning that mining has low risk.

Images