Water source identification method based on big data

Abstract

The present invention relates to the technical field of water source identification, and is used to solve the problem that in existing methods for identifying water sources in mining areas, it is difficult to ascertain the environment of water sources in different aquifers and the strength and weakness of the alternating content of water sources, and it is even more difficult to identify the water sources of each aquifer based on the types of microorganisms contained in each aquifer and the content of microorganisms, so it is impossible to accurately identify and judge the water sources in the mining area. In particular, a water source identification method based on big data is disclosed. The present invention screens out common microbial factors of each aquifer, averages the screened common microbial factors, and obtains the proportion of each common microbial factor through a pie chart. The proportion of each microorganism is represented by the pie chart, and water source judgment is performed based on the proportion of microorganisms and with reference to a database source. This not only achieves accurate identification of water sources in the mining area, but also lays a foundation for mine water hazard early warning and ensures safe production in the mining area.

Description

Technical Field

[0001] The present invention relates to the technical field of water source identification, and in particular to a water source identification method based on big data. Background Art

[0002] Mine water inrush accidents refer to the phenomenon that when a tunnel exposes a water-conducting fracture, a water-rich cave, or a water-filled old hill during excavation or mining, a large amount of groundwater suddenly flows into the mine tunnel. Due to the complex hydrogeological conditions of coal mines, mine water disasters often occur during coal mining, seriously threatening the safe production of coal mines. In order to prevent the occurrence of mine water disasters, it is necessary to determine the water inrush situation of the aquifer in the mining area and identify the source of the water inrush.

[0003] However, existing methods for identifying water sources in mining areas are difficult to ascertain the environment of water sources in different aquifers and the strength and weakness of water source alternation. It is even more difficult to identify the water sources of each aquifer based on the types and content of microorganisms contained in each aquifer. Therefore, it is impossible to accurately identify and judge the water sources in mining areas.

[0004] In order to solve the above-mentioned defects, a technical solution is now provided. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem that in the existing method of identifying water sources in mining areas, it is difficult to ascertain the environment of water sources in different aquifers and the strength of the alternating content of water sources, and it is even more difficult to identify the water sources of each aquifer based on the types of microorganisms and the content of microorganisms contained in each aquifer, so it is impossible to accurately identify and judge the water sources in the mining area. By screening out the common microbial factors of each aquifer, averaging the screened common microbial factors, and obtaining the proportion of each common microbial factor through a pie chart, the proportion of each microorganism is represented by a pie chart, and the water source is judged based on the proportion of microorganisms and with reference to the database source. While achieving accurate identification of water sources in mining areas, it also lays the foundation for mine water hazard warning and ensures safe production in mining areas, and proposes a water source identification method based on big data.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The water source identification method based on big data includes a server, wherein the server is communicatively connected to a data acquisition unit, an aquifer division unit, a water source identification and analysis unit, a water-rich state analysis unit, a water hazard state analysis unit, a water inrush warning feedback unit, and a display terminal;

[0008] The data acquisition unit is used to collect stratum thickness, hydrogeological information and environmental microbial information of the coal mine area, and send them to the aquifer division unit, water source identification and analysis unit, water-rich state analysis unit and water hazard state analysis unit respectively;

[0009] The water source identification and analysis unit is used to obtain environmental microbial information of each aquifer, and perform water source direction identification, determination and analysis processing, thereby determining the direction of the water source of each aquifer;

[0010] The aquifer division unit is used to receive the stratum thickness of the coal mine area and perform aquifer determination and analysis processing, thereby obtaining the coal-bearing water aquifer, the Taihu ash water aquifer, the Ordovician ash water aquifer and the four-water aquifer, and sending them to the water-rich state analysis unit and the water hazard state analysis unit respectively;

[0011] The water-rich state analysis unit is used to receive hydrogeological information of the coal mine area and perform prejudgment analysis and processing of the water-rich state of the aquifer, thereby obtaining a first-level water-rich state aquifer, a second-level water-rich state aquifer, and a third-level water-rich state aquifer, and sending the information to the water inrush warning feedback unit;

[0012] The water hazard status analysis unit is used to receive hydrogeological information of each aquifer, and perform prejudgment analysis and processing of the water hazard degree of the aquifer, thereby obtaining aquifers in the first-level water hazard state, aquifers in the second-level water hazard state, and aquifers in the third-level water hazard state, and sends the information to the water inrush warning feedback unit;

[0013] The water inrush warning feedback unit is used to receive the calibration of each level of water-rich state and each level of water hazard state of each aquifer, and perform water inrush warning judgment analysis to obtain low-level water inrush warning signals, intermediate water inrush warning signals and high-level water inrush warning signals.

[0014] Furthermore, the specific steps for determining and analyzing the aquifer are as follows:

[0015] Obtain the stratum thickness in the coal mining area and compare and analyze the stratum thickness with the preset water-bearing intervals Q1, Q2, Q3, and Q4;

[0016] When the formation thickness is within the preset judgment interval Q1, the aquifer area corresponding to the formation thickness is marked as a coal-bearing water aquifer;

[0017] When the stratum thickness is within the preset judgment interval Q2, the aquifer area corresponding to the stratum thickness is marked as the Taihuishui aquifer;

[0018] When the stratum thickness is within the preset judgment interval Q3, the aquifer area corresponding to the stratum thickness is marked as the Ordovician grey water aquifer;

[0019] When the formation thickness is within the preset determination interval Q4, the aquifer area corresponding to the formation thickness is marked as the fourth aquifer.

[0020] Furthermore, the specific steps for predicting and analyzing the water-rich state of the aquifer are as follows:

[0021] According to the classification of each aquifer, the void value, fracture value and rock formation value in the hydrogeological information of each type of aquifer are obtained and calibrated as kxl i 、lxl i and yrl i , and normalize it and analyze it according to the formula DZ i =e1*kxl i +e2*lxl i +e3*yrl i , the water-rich influence coefficient of each type of aquifer geological state is obtained, where e1, e2 and e3 are the weighting factor coefficients of the void value, fracture value and rock-forming value respectively, and e1, e2 and e3 are all positive integers, where i = 1, 2, 3, 4;

[0022] Set the gradient influence reference thresholds TH1 and TH2 of the water-rich influence coefficient, and compare and analyze the water-rich influence coefficients of various types of aquifers with the preset gradient influence reference thresholds TH1 and TH2;

[0023] When the water-rich influence coefficient is less than or equal to the preset gradient influence reference threshold TH1, a water-rich influence slight performance signal is generated, and the corresponding aquifer is calibrated as a first-level water-rich state aquifer;

[0024] When the water-rich impact coefficient is between the preset gradient impact reference thresholds TH1 and TH2, a water-rich impact moderate performance signal is generated, and the corresponding aquifer is calibrated as a secondary water-rich state aquifer;

[0025] When the water-rich influence coefficient is greater than or equal to the preset gradient influence reference threshold TH2, a water-rich influence severe performance signal is generated, and the corresponding aquifer is calibrated as a third-level water-rich state aquifer.

[0026] Furthermore, the specific steps for data establishment, analysis and processing are as follows:

[0027] Randomly extract k water samples from each type of aquifer, and obtain the number of microbial species in each water sample of each type of aquifer in real time;

[0028] Select the water sample with the largest number of microbial species from k water samples, and based on the number of microbial species in the water sample, obtain the microbial factors in the largest water sample, and establish the corresponding microbial factor set for each aquifer;

[0029] Among them, the microbial factor sets of each aquifer are the microbial factor set a1 of the coal-bearing water aquifer, the microbial factor set b1 of the Taihui water aquifer, the microbial factor set c1 of the Aohui water aquifer, and the microbial factor set d1 of the Sihe water aquifer;

[0030] According to the established microbial factor set of each aquifer, the content of each microbial factor in each water sample is obtained, and the content of each microbial factor in k water samples is cumulatively analyzed. Specifically, the content of each microbial factor in each water sample is calibrated as hl ikj , according to the formula Obtain the total content value of each microbial factor in each aquifer, and aggregate and normalize the content of each microbial factor in each aquifer to obtain a microbial factor content expression set for each aquifer;

[0031] Where k = 1, 2, 3 ... n1, and calculate the content of each microorganism in each water sample of each type of aquifer, j represents each microbial factor, and j = 1, 2, 3 ... n2;

[0032] Among them, the microbial factor content performance sets of each aquifer are the microbial factor content set a2 of the coal-bearing water aquifer, the microbial factor content set b2 of the Taihui water aquifer, the microbial factor content set c2 of the Aohui water aquifer, and the microbial factor content set d2 of the Si water aquifer.

[0033] Furthermore, the specific steps for determining and analyzing the source of aquifer water are as follows:

[0034] Based on the microbial factor sets of each aquifer, each set was subjected to intersection analysis using a Venn diagram, thereby obtaining the microbial factors common to each aquifer.

[0035] According to the shared microbial factors, the average content value of the shared microorganisms in the corresponding aquifer is obtained in real time;

[0036] According to the average content value of each common microorganism in each aquifer, the average content value of each common microorganism in each aquifer is plotted in the form of a pie chart, and the proportion of the content of each common microorganism in each aquifer is obtained accordingly;

[0037] The proportion of the common microbial content of each aquifer is substituted into the preset microbial reference database source for comparative analysis, and the water source direction of each aquifer is analyzed and judged based on the microbial reference database source.

[0038] Furthermore, the process of solving the mean content of microorganisms shared by the aquifer is as follows:

[0039] Obtain the microbial factors contained in k water samples of each type of aquifer, and select the common microbial factors existing in the k water samples;

[0040] Get the content of the common microbial factors in k water samples and mark it as ty ikp And the content of the common microbial factors in k water samples was analyzed by mean value, according to the formula The mean content value of each common microorganism in each aquifer is obtained, where p is a positive integer.

[0041] Furthermore, the specific steps for predicting, analyzing and treating the degree of water damage in aquifers are as follows:

[0042] Obtain the unit water inflow, mine water inflow and water burst in the hydrogeological information of each aquifer in real time, and calibrate them as ysl i 、kyl i and tsl i , and normalized it to obtain the water hazard coefficient of each aquifer according to the formula shxi=f1*ysl+f2*kyl+f3*tsl, where f1, f2 and f3 are the weighting factors of unit water inflow, mine water inflow and water inrush, respectively, and f1, f2 and f3 are all positive integers;

[0043] Set a water hazard reference threshold tv1 for the water hazard coefficient, and compare and analyze the water hazard coefficient of each aquifer with the preset water hazard reference threshold tv1;

[0044] When the water hazard coefficient of the aquifer is less than the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a first-level water hazard state aquifer; when the water hazard coefficient of the aquifer is equal to the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a second-level water hazard state aquifer; when the water hazard coefficient of the aquifer is greater than the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a third-level water hazard state aquifer.

[0045] Furthermore, the specific steps for water inrush warning judgment and analysis are as follows:

[0046] When the corresponding aquifer is simultaneously marked as a first-level water-rich aquifer and a first-level water-hazard aquifer, or a second-level water-rich aquifer and a first-level water-hazard aquifer, or a first-level water-rich aquifer and a second-level water-hazard aquifer, a low-level water inrush warning signal will be generated.

[0047] When the corresponding aquifer is simultaneously marked as a third-level water-rich aquifer and a third-level water-hazard aquifer, or a third-level water-rich aquifer and a second-level water-hazard aquifer, or a second-level water-rich aquifer and a third-level water-hazard aquifer, a high-level water inrush warning signal will be generated.

[0048] In other cases, a medium-level water inrush warning signal will be generated.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The present invention clearly divides the aquifers in the mining area through data analysis and comparative analysis using reference intervals. Based on this, the invention uses symbolic calibration, formulaic processing, and threshold comparative analysis to conduct early warning analysis and processing of water inrush in each aquifer from the perspectives of water-rich state determination and water hazard determination.

[0051] By using symbolic calibration, data processing, and set calibration, we analyzed and obtained the microbial factor sets of each aquifer and the microbial factor content expression sets of each aquifer. Based on this, we conducted intersection analysis on the microbial factor sets of each aquifer and obtained the microbial factors shared by all aquifers.

[0052] The microbial factors shared by each aquifer were analyzed for mean values to obtain the mean content values of each shared microorganism in each aquifer. The mean content values of each shared microorganism in each aquifer were plotted in the form of a pie chart, and the proportion of each shared microorganism content in each aquifer was obtained accordingly.

[0053] The proportion of the common microbial content of each aquifer was substituted into the preset microbial reference database source for comparative analysis. Based on the microbial reference database source, the water source direction of each aquifer was accurately analyzed. This not only achieved accurate identification of the water source in the mining area, but also laid the foundation for mine water hazard early warning and ensured safe production in the mining area. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0055] Figure 1 It is the overall block diagram of the system of the present invention;

[0056] Figure 2 Flowchart of the present invention. DETAILED DESCRIPTION

[0057] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0058] Example 1:

[0059] like Figure 1 and Figure 2 As shown, the water source identification method based on big data includes a server, which is communicatively connected to a data acquisition unit, an aquifer division unit, a water source identification and analysis unit, a water-rich state analysis unit, a water hazard state analysis unit, a water inrush warning feedback unit, and a display terminal;

[0060] The data acquisition unit is used to collect the stratum thickness and hydrogeological information of the coal mine area, and send the information to the aquifer division unit, the water-rich state analysis unit, and the water hazard state analysis unit respectively;

[0061] When the aquifer division unit receives the stratum thickness of the coal mining area, it performs aquifer determination and analysis based on it. The specific operation process is as follows:

[0062] Obtain the stratum thickness in the coal mining area and compare and analyze the stratum thickness with the preset water-bearing intervals Q1, Q2, Q3, and Q4;

[0063] When the formation thickness is within the preset judgment interval Q1, the aquifer area corresponding to the formation thickness is marked as a coal-bearing water aquifer;

[0064] When the stratum thickness is within the preset judgment interval Q2, the aquifer area corresponding to the stratum thickness is marked as the Taihuishui aquifer;

[0065] When the stratum thickness is within the preset judgment interval Q3, the aquifer area corresponding to the stratum thickness is marked as the Ordovician grey water aquifer;

[0066] When the formation thickness is within the preset determination interval Q4, the aquifer area corresponding to the formation thickness is marked as a four-water aquifer;

[0067] The obtained coal-bearing water aquifer, Taihui water aquifer, Ordovician water aquifer and Sihe water aquifer are sent to the water-rich state analysis unit and the water hazard state analysis unit respectively;

[0068] When the water-rich state analysis unit receives the hydrogeological information of the coal mine area, it performs a pre-judgment analysis of the water-rich state of the aquifer based on the information. The specific operation process is as follows:

[0069] According to the classification of each aquifer, the void value, fracture value and rock formation value in the hydrogeological information of each type of aquifer are obtained and calibrated as kxl i 、lxl i and yrl i , and normalize it and analyze it according to the formula DZ i =e1*kxl i +e2*lxl i +e3*yrl i, the water-rich influence coefficient of each type of aquifer geological state is obtained, where e1, e2, and e3 are the weighting factors of the void value, fracture value, and rock-forming value, respectively, and e1, e2, and e3 are all positive integers. The weighting factor coefficient is used to balance the weight of each data in the formula calculation, thereby improving the accuracy of the calculation results;

[0070] Wherein, i represents each type of aquifer, i = 1, 2, 3, 4, when i = 1, it indicates a coal-bearing water aquifer, when i = 2, it indicates a Taihui water aquifer, when i = 3, it indicates an Ordovician water aquifer, and when i = 4, it indicates a Tetrahedron water aquifer;

[0071] It should be noted that the void value refers to the data value of the size of the pores formed between rocks, the crack value refers to the data value of the size of the cracks in the rocks in geology, and the karst development value refers to the data value of the degree of karst development. The larger the values of the void value, crack value, and karst development value, the stronger the water-richness of the aquifer.

[0072] Set the gradient influence reference thresholds TH1 and TH2 of the water-rich influence coefficient, and compare and analyze the water-rich influence coefficients of various types of aquifers with the preset gradient influence reference thresholds TH1 and TH2, where TH1 and TH2 increase in a gradient;

[0073] When the water-rich influence coefficient is less than or equal to the preset gradient influence reference threshold TH1, a water-rich influence slight performance signal is generated, and the corresponding aquifer is calibrated as a first-level water-rich state aquifer;

[0074] When the water-rich impact coefficient is between the preset gradient impact reference thresholds TH1 and TH2, a water-rich impact moderate performance signal is generated, and the corresponding aquifer is calibrated as a secondary water-rich state aquifer;

[0075] When the water-rich impact coefficient is greater than or equal to the preset gradient impact reference threshold TH2, a water-rich impact severe performance signal is generated, and the corresponding aquifer is calibrated as a third-level water-rich state aquifer;

[0076] The obtained first-level water-rich aquifer, second-level water-rich aquifer and third-level water-rich aquifer are sent to the water inrush warning feedback unit;

[0077] When the water hazard status analysis unit receives the hydrogeological information of each aquifer, it performs a pre-judgment analysis of the water hazard degree of the aquifer based on the information. The specific operation process is as follows:

[0078] Obtain the unit water inflow, mine water inflow and water burst in the hydrogeological information of each aquifer in real time, and calibrate them as ysl i 、kyl i and tsli , and normalized it to obtain the water hazard coefficient of each aquifer according to the formula shxi=f1*ysl+f2*kyl+f3*tsl, where f1, f2 and f3 are the weighting factors of unit water inflow, mine water inflow and water inrush, respectively, and f1, f2 and f3 are all positive integers;

[0079] Set a water hazard reference threshold tv1 for the water hazard coefficient, and compare and analyze the water hazard coefficient of each aquifer with the preset water hazard reference threshold tv1;

[0080] When the water hazard coefficient of the aquifer is less than the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a first-level water hazard state aquifer; when the water hazard coefficient of the aquifer is equal to the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a second-level water hazard state aquifer; when the water hazard coefficient of the aquifer is greater than the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a third-level water hazard state aquifer;

[0081] The obtained first-level water hazard state aquifer, second-level water hazard state aquifer and third-level water hazard state aquifer are sent to the water inrush warning feedback unit;

[0082] When the water inrush warning feedback unit receives the calibration of each level of water-rich state and each level of water hazard state of each aquifer, it performs water inrush warning judgment and analysis based on the received information. The specific operation process is as follows:

[0083] When the corresponding aquifer is simultaneously marked as a first-level water-rich aquifer and a first-level water-hazard aquifer, or a second-level water-rich aquifer and a first-level water-hazard aquifer, or a first-level water-rich aquifer and a second-level water-hazard aquifer, a low-level water inrush warning signal will be generated.

[0084] When the corresponding aquifer is simultaneously marked as a third-level water-rich aquifer and a third-level water-hazard aquifer, or a third-level water-rich aquifer and a second-level water-hazard aquifer, or a second-level water-rich aquifer and a third-level water-hazard aquifer, a high-level water inrush warning signal will be generated.

[0085] In other cases, a medium-level water inrush warning signal is generated;

[0086] The obtained low-level water inrush warning signal, intermediate-level water inrush warning signal and high-level water inrush warning signal are sent to the display terminal for display and explanation.

[0087] Example 2:

[0088] like Figure 1 and Figure 2 As shown, the data acquisition unit is used to collect environmental microbial information in the coal mine area and send it to the water source identification and analysis unit;

[0089] When the water source identification and analysis unit receives the environmental microbial information of each aquifer, it performs water source direction identification, judgment and analysis based on the information. Specifically:

[0090] Randomly extract k water samples from each type of aquifer, and obtain the number of microbial species in each water sample of each type of aquifer in real time;

[0091] Select the water sample with the largest number of microbial species from k water samples, and based on the number of microbial species in the water sample, obtain the microbial factors in the largest water sample, and establish the corresponding microbial factor set for each aquifer;

[0092] It should be pointed out that when identifying the water sources of each aquifer, the contribution and P value of all environmental factors, as well as the approximate F test statistics and their P values, were first calculated;

[0093] Among them, the microbial factor sets of each aquifer are the microbial factor set a1 of the coal-bearing water aquifer, the microbial factor set b1 of the Taihui water aquifer, the microbial factor set c1 of the Aohui water aquifer, and the microbial factor set d1 of the Sihe water aquifer;

[0094] According to the established microbial factor set of each aquifer, the content of each microbial factor in each water sample is obtained, and the content of each microbial factor in k water samples is cumulatively analyzed. Specifically, the content of each microbial factor in each water sample is calibrated as hl ikj , according to the formula The total content value of each microbial factor of each aquifer is obtained, and the content of each microbial factor of each aquifer is aggregated and normalized to obtain the microbial factor content expression set of each aquifer;

[0095] Where k = 1, 2, 3 ... n1, and calculate the content of each microorganism in each water sample of each type of aquifer, j represents each microbial factor, and j = 1, 2, 3 ... n2;

[0096] Among them, the microbial factor content performance sets of each aquifer are the microbial factor content set a2 of the coal-bearing water aquifer, the microbial factor content set b2 of the Taihui water aquifer, the microbial factor content set c2 of the Aohui water aquifer, and the microbial factor content set d2 of the Si water aquifer;

[0097] Based on the microbial factor sets of each aquifer, each set was subjected to intersection analysis using a Venn diagram, thereby obtaining the microbial factors common to each aquifer.

[0098] Based on the shared microbial factors, the mean content value of the shared microorganisms in the corresponding aquifer is obtained in real time. The process of solving the mean content value of the shared microorganisms in the aquifer is as follows:

[0099] Obtain the microbial factors contained in k water samples of each type of aquifer, and select the common microbial factors existing in the k water samples;

[0100] Get the content of the common microbial factors in k water samples and mark it as ty ikp And the content of the common microbial factors in k water samples was analyzed by mean value, according to the formula Obtain the mean content value of each common microorganism in each aquifer, where p refers to the number of common microbial factors and p is a positive integer;

[0101] According to the average content value of each common microorganism in each aquifer, the average content value of each common microorganism in each aquifer is plotted in the form of a pie chart, and the proportion of the content of each common microorganism in each aquifer is obtained accordingly;

[0102] The proportion of the common microbial content of each aquifer is substituted into the preset microbial reference database source for comparative analysis, and the water source direction of each aquifer is analyzed and judged based on the microbial reference database source.

[0103] When used, the present invention performs water-bearing layer determination and analysis based on the obtained stratum thickness of the coal mining area, and clearly divides the water-bearing layers of the mining area by using data analysis and reference interval substitution comparative analysis. Based on this, the present invention obtains the hydrogeological information of each aquifer, and uses symbolic calibration, formulaic processing, and threshold comparative analysis to conduct early warning analysis and processing of water inrush conditions of each aquifer from the perspectives of water-rich state determination and water hazard determination.

[0104] By obtaining the environmental microbial information of each aquifer and conducting data analysis and processing, the microbial factor set of each aquifer and the microbial factor content expression set of each aquifer are analyzed by using symbolic calibration, data processing and set calibration. Based on this, the intersection analysis of the microbial factor set of each aquifer is performed to obtain the microbial factors shared by each aquifer.

[0105] The microbial factors shared by each aquifer were analyzed for mean values to obtain the mean content values of each shared microorganism in each aquifer. The mean content values of each shared microorganism in each aquifer were plotted in the form of a pie chart, and the proportion of each shared microorganism content in each aquifer was obtained accordingly.

[0106] The proportion of the common microbial content of each aquifer was substituted into the preset microbial reference database source for comparative analysis. Based on the microbial reference database source, the water source direction of each aquifer was accurately analyzed. This not only achieved accurate identification of the water source in the mining area, but also laid the foundation for mine water hazard early warning and ensured safe production in the mining area.

[0107] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A water source identification method based on big data, characterized in that: Includes the following methods: Step 1: Collect stratum thickness, hydrogeological information and environmental microbial information of the coal mining area; Step 2: Obtain the stratum thickness of the coal mining area and substitute it into the preset aquifer determination interval to perform aquifer determination analysis and processing, thereby obtaining the coal-bearing water aquifer, Taihui water aquifer, Ordovician water aquifer and four water aquifers; Step 3: Based on the analyzed aquifers, obtain the hydrogeological information of the coal mine area to perform pre-judgment analysis of the water-rich state of the aquifers, and thereby obtain a slight water-rich impact performance signal, a moderate water-rich impact performance signal, and a severe water-rich impact performance signal. Based on the generated various types of water-rich impact performance signals, the corresponding aquifers are calibrated as a first-level water-rich state aquifer, a second-level water-rich state aquifer, and a third-level water-rich state aquifer; Step 4: Based on the analyzed aquifers, obtain the hydrogeological information of each aquifer to perform pre-judgment analysis of the water damage degree of the aquifer, and thereby obtain the first-level water damage state aquifer, the second-level water damage state aquifer, and the third-level water damage state aquifer; Step 5: Based on the generated aquifer's various levels of water-rich state calibration and various levels of water hazard state calibration, water inrush warning judgment analysis is performed to obtain low-level water inrush warning signals, intermediate water inrush warning signals, and high-level water inrush warning signals; Step 6: Obtain environmental microbial information of each aquifer and perform data analysis and processing to obtain the microbial factor sets a1, b1, c1, and d1 of each aquifer and the microbial factor content expression sets a2, b2, c2, and d2 of each aquifer; Step 7: Perform intersection analysis on the microbial factor sets of each aquifer to obtain the microbial factors shared by each aquifer, and obtain the mean content value of each shared microorganism in each aquifer. The mean content value of each shared microorganism in each aquifer is plotted in the form of a pie chart, and the proportion of each shared microorganism content in each aquifer is obtained. Step 8: Substitute the proportion of the common microbial content of each aquifer into the preset microbial reference database source for comparative analysis, and analyze the water source direction of each aquifer based on the microbial reference database source.

2. The water source identification method based on big data according to claim 1, characterized in that: The specific steps for determining and analyzing aquifers are as follows: Obtain the stratum thickness in the coal mining area and compare and analyze the stratum thickness with the preset water-bearing intervals Q1, Q2, Q3, and Q4; When the formation thickness is within the preset judgment interval Q1, the aquifer area corresponding to the formation thickness is marked as a coal-bearing water aquifer; When the stratum thickness is within the preset judgment interval Q2, the aquifer area corresponding to the stratum thickness is marked as the Taihuishui aquifer; When the stratum thickness is within the preset judgment interval Q3, the aquifer area corresponding to the stratum thickness is marked as the Ordovician grey water aquifer; When the formation thickness is within the preset determination interval Q4, the aquifer area corresponding to the formation thickness is marked as the fourth aquifer.

3. The water source identification method based on big data according to claim 1, characterized in that: The specific steps for predicting, analyzing and processing the water-rich state of aquifers are as follows: According to the classification of each aquifer, the void value, fracture value and rock formation value in the hydrogeological information of each type of aquifer are obtained and calibrated as kxl i 、lxl i and yrl i , and normalize it and analyze it according to the formula DZ i =e1*kxl i +e2*lxl i +e3*yrl i , the water-rich influence coefficient of each type of aquifer geological state is obtained, where e1, e2 and e3 are the weighting factor coefficients of the void value, fracture value and rock-forming value respectively, and e1, e2 and e3 are all positive integers, where i = 1, 2, 3, 4; Set the gradient impact reference thresholds TH1 and TH2 of the water-rich influence coefficient, and compare and analyze the water-rich influence coefficients of various types of aquifers with the preset gradient impact reference thresholds TH1 and TH2; When the water-rich influence coefficient is less than or equal to the preset gradient influence reference threshold TH1, a water-rich influence slight performance signal is generated, and the corresponding aquifer is calibrated as a first-level water-rich state aquifer; When the water-rich impact coefficient is between the preset gradient impact reference thresholds TH1 and TH2, a water-rich impact moderate performance signal is generated, and the corresponding aquifer is calibrated as a secondary water-rich state aquifer; When the water-rich influence coefficient is greater than or equal to the preset gradient influence reference threshold TH2, a water-rich influence severe performance signal is generated, and the corresponding aquifer is calibrated as a third-level water-rich state aquifer.

4. The water source identification method based on big data according to claim 1, characterized in that: The specific steps for data establishment, analysis and processing are as follows: Randomly extract k water samples from each type of aquifer, and obtain the number of microbial species in each water sample of each type of aquifer in real time; Select the water sample with the largest number of microbial species from k water samples, and based on the number of microbial species in the water sample, obtain the microbial factors in the largest water sample, and establish the corresponding microbial factor set for each aquifer; Among them, the microbial factor sets of each aquifer are the microbial factor set a1 of the coal-bearing water aquifer, the microbial factor set b1 of the Taihui water aquifer, the microbial factor set c1 of the Aohui water aquifer, and the microbial factor set d1 of the Sihe water aquifer; According to the established microbial factor set of each aquifer, the content of each microbial factor in each water sample is obtained, and the content of each microbial factor in k water samples is cumulatively analyzed. Specifically, the content of each microbial factor in each water sample is calibrated as hl ikj , according to the formula The total content value of each microbial factor of each aquifer is obtained, and the content of each microbial factor of each aquifer is aggregated and normalized to obtain the microbial factor content expression set of each aquifer; Where k = 1, 2, 3 ... n1, and calculate the content of each microorganism in each water sample of each type of aquifer, j represents each microbial factor, and j = 1, 2, 3 ... n2; Among them, the microbial factor content performance sets of each aquifer are the microbial factor content set a2 of the coal-bearing water aquifer, the microbial factor content set b2 of the Taihui water aquifer, the microbial factor content set c2 of the Aohui water aquifer, and the microbial factor content set d2 of the Si water aquifer.

5. The water source identification method based on big data according to claim 1, characterized in that: The specific steps for determining and analyzing the source of aquifer water are as follows: Based on the microbial factor sets of each aquifer, each set was subjected to intersection analysis using a Venn diagram, thereby obtaining the microbial factors common to each aquifer. According to the shared microbial factors, the average content value of the shared microorganisms in the corresponding aquifer is obtained in real time; According to the average content value of each common microorganism in each aquifer, the average content value of each common microorganism in each aquifer is plotted in the form of a pie chart, and the proportion of the content of each common microorganism in each aquifer is obtained accordingly; The proportion of the common microbial content of each aquifer is substituted into the preset microbial reference database source for comparative analysis, and the water source direction of each aquifer is analyzed and judged based on the microbial reference database source.

6. The water source identification method based on big data according to claim 5, characterized in that: The process of solving the mean content of microorganisms shared by the aquifer is as follows: Obtain the microbial factors contained in k water samples of each type of aquifer, and select the common microbial factors existing in the k water samples; Get the content of the common microbial factors in k water samples and mark it as ty ikp And the content of the common microbial factors in k water samples was analyzed by mean value, according to the formula The mean content value of each common microorganism in each aquifer is obtained, where p is a positive integer.

7. The water source identification method based on big data according to claim 1, characterized in that: The specific steps for predicting, analyzing and treating the degree of water damage in aquifers are as follows: Obtain the unit water inflow, mine water inflow and water burst in the hydrogeological information of each aquifer in real time, and calibrate them as ysl i 、kyl i and tsl i , and normalized it to obtain the water hazard coefficient of each aquifer according to the formula shxi=f1*ysl+f2*kyl+f3*tsl, where f1, f2 and f3 are the weighting factors of unit water inflow, mine water inflow and water inrush, respectively, and f1, f2 and f3 are all positive integers; Set a water hazard reference threshold tv1 for the water hazard coefficient, and compare and analyze the water hazard coefficient of each aquifer with the preset water hazard reference threshold tv1; When the water hazard coefficient of the aquifer is less than the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a first-level water hazard state aquifer; when the water hazard coefficient of the aquifer is equal to the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a second-level water hazard state aquifer; when the water hazard coefficient of the aquifer is greater than the preset water hazard reference threshold tv1, the corresponding aquifer is calibrated as a third-level water hazard state aquifer.

8. The water source identification method based on big data according to claim 1, characterized in that: The specific steps for water inrush warning judgment and analysis are as follows: When the corresponding aquifer is simultaneously marked as a first-level water-rich aquifer and a first-level water-hazard aquifer, or a second-level water-rich aquifer and a first-level water-hazard aquifer, or a first-level water-rich aquifer and a second-level water-hazard aquifer, a low-level water inrush warning signal will be generated. When the corresponding aquifer is simultaneously marked as a third-level water-rich aquifer and a third-level water-hazard aquifer, or a third-level water-rich aquifer and a second-level water-hazard aquifer, or a second-level water-rich aquifer and a third-level water-hazard aquifer, a high-level water inrush warning signal will be generated. In other cases, a medium-level water inrush warning signal will be generated.

Images