Coal mine water disaster real-time early warning method based on big data analysis

Abstract

The invention discloses a coal mine water disaster real-time early warning method based on big data analysis, relates to the technical field of data processing, and solves the technical problem of carrying out early warning analysis on coal mine water disaster by utilizing a comprehensive deviation judgment value obtained by combining various data deviation values with an auxiliary judgment value. Comprising the following steps: cleaning and normalizing water level, micro-seismic frequency monitoring and rock stratum thickness data to obtain corresponding data standard values; obtaining a data simulation value and a standard value through a big data analysis method to obtain a comprehensive detection first deviation evaluation value, and obtaining a comprehensive detection second deviation evaluation value through the data measurement value and the data standard value; and combining the comprehensive detection first deviation evaluation value and the comprehensive detection second deviation evaluation value to obtain a comprehensive deviation evaluation value, performing comprehensive deviation judgment value analysis result according to the comprehensive deviation evaluation value and an auxiliary judgment detection value obtained through the chemical harmful substances, and dividing early warning signals of corresponding degrees for the monitoring area.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a real-time early warning method for coal mine water hazards based on big data analysis. Background Art

[0002] With the development of information technology, big data analysis technology is being used more and more widely in all walks of life, especially in the field of coal mine water hazards. After the various collected data are cleaned and normalized, the processed data are deeply analyzed through big data analysis methods, and the possibility of water hazards is predicted based on a variety of numerical data. A variety of factors and data sources are comprehensively considered, so that the water hazard risk warning signal covers the coal mine water hazard detection area more comprehensively.

[0003] Although the existing coal mine water hazard warning methods have achieved water hazard warning to a certain extent, the traditional coal mine water hazard warning methods mostly rely on manual reading and experience judgment, and have problems such as untimely response and low accuracy. There is a lack of simulation data obtained by analyzing a large amount of historical data through big data analysis methods, and it is difficult to comprehensively consider the deviation values ​​of multiple data combined with auxiliary judgment detection values ​​to divide water hazard risk warning signals. Summary of the invention

[0004] 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 real-time early warning method for coal mine water hazards based on big data analysis, which is used to solve the following technical problems:

[0005] Although the existing coal mine water hazard warning methods have achieved water hazard warning to a certain extent, the traditional coal mine water hazard warning methods mostly rely on manual reading and experience judgment, and have problems such as untimely response and low accuracy. There is a lack of simulation data obtained by analyzing a large amount of historical data through big data analysis methods, and it is difficult to comprehensively consider the deviation values ​​of multiple data combined with auxiliary judgment detection values ​​to divide water hazard risk warning signals.

[0006] To solve the above problems, the first aspect of the present invention provides a real-time early warning method for coal mine water hazards based on big data analysis, comprising the following modules:

[0007] Data acquisition module: collects mine water level data, microseismic frequency monitoring data, rock thickness data and chemical hazardous substances data through a sensor network installed in the fan-shaped area of ​​the coal mine;

[0008] Data transmission module: transmits mine water level data, microseismic frequency monitoring data, rock thickness data and chemical hazardous substances data to the data processing module in real time via wireless network;

[0009] Data processing module: pre-processes the received data, including cleaning and normalization, to obtain standard values ​​of water level data, microseismic frequency monitoring data and rock thickness data;

[0010] Data analysis module: Analyze historical data through big data analysis method, obtain simulated values ​​of water level data, microseismic frequency monitoring data and rock thickness data through the maximum and minimum values ​​of real-time data, obtain the first deviation value of data according to the standard value and simulated value, assign corresponding weights to obtain the first deviation evaluation value of comprehensive detection, obtain the second deviation value of data through the standard value and data measurement value, assign corresponding weights to obtain the second deviation evaluation value of comprehensive detection, and obtain auxiliary judgment detection value through chemical hazardous substance data;

[0011] Safety warning module: obtain a comprehensive deviation evaluation value through comprehensive detection of the first deviation evaluation value and the second deviation evaluation value, obtain a comprehensive deviation judgment value analysis result based on the comprehensive deviation evaluation value combined with the auxiliary judgment detection value, divide the safety level according to the potential water hazard risk level, and issue a warning.

[0012] As a further solution of the present invention: the data acquisition module collects mine water level data, microseismic frequency monitoring data, rock layer thickness data and chemical hazardous substance data through a sensor network in a coal mine, including the following steps:

[0013] Measure the curvature of the mine shaft inside the coal mine, divide it into several equal sectors, and install a sensor network in the sectors to collect data;

[0014] The data collected include: mine water level data, microseismic frequency monitoring data and rock thickness data. Water quality monitoring sensors are deployed in the mine water accumulation area inside the coal mine to monitor the data of harmful chemical substances in the water, including sulfate, chloride and fluoride.

[0015] As a further solution of the present invention: the data transmission module transmits the mine water level data, microseismic frequency monitoring data, rock layer thickness data and chemical hazardous substance data to the data processing module in real time via a wireless network.

[0016] As a further solution of the present invention: the data processing module pre-processes the received data, including cleaning and normalization, to obtain standard values ​​of water level data, microseismic frequency monitoring data and rock thickness data, including the following steps:

[0017] S301: Cleaning the received water level data, microseismic frequency monitoring data and rock thickness data through a data cleaning tool of the pandas library of the Python high-level programming language;

[0018] S302: normalizing the cleaned water level data, microseismic frequency monitoring data and rock thickness data through the sklearn library of the Python high-level programming language;

[0019] S303: Calculate standard values ​​for the pre-processed water level data, microseismic frequency monitoring data, and rock layer thickness data.

[0020] As a further solution of the present invention: Step S303 includes the following steps:

[0021] The water level data value is recorded at intervals of time T, and the water level data standard value calculation formula is obtained through the maximum and minimum data values:

[0022]

[0023] Among them A 1 is the standard value of water level data, n is the number of detections, b i is the water level value detected at the i-th time, b max To detect the maximum water level, b min To detect the minimum water level;

[0024] The microseismic frequency monitoring data values ​​are recorded at intervals of T, and the standard value calculation formula of the microseismic frequency monitoring data is obtained through the maximum and minimum values ​​of the data:

[0025]

[0026] Among them, A 2 is the standard value of microseismic frequency monitoring data, n is the number of detections, c i is the microseismic monitoring value of the ith detection, c max To detect the maximum value of microseismic monitoring, c min To detect microseismic monitoring minimum value;

[0027] Record the rock thickness data value at every interval T, and use the maximum and minimum values ​​to get the standard value calculation formula of the rock thickness data:

[0028]

[0029] Among them, A 3 is the standard value of rock thickness data, n is the number of detections, d i is the thickness of the rock layer detected for the i-th time, d max To detect the maximum rock thickness, d min To detect the minimum thickness of rock formation.

[0030] As a further solution of the present invention: the data analysis module analyzes the historical data by a big data analysis method, obtains the simulated values ​​of the water level data, the microseismic frequency monitoring data and the rock thickness data by the maximum and minimum values ​​of the real-time data, and obtains the first deviation evaluation value of the comprehensive detection according to the standard value and the simulated value, including the following steps:

[0031] Water level data simulation value calculation formula:

[0032]

[0033] Among them, M 1 is the simulated value of water level data, e is a constant in this calculation formula, b max To detect the maximum water level, b min To detect the minimum water level;

[0034] Calculation formula for the simulated value of microseismic frequency monitoring data:

[0035]

[0036] Among them, M 2 is the simulated value of microseismic frequency monitoring data, e is a constant in this calculation formula, c max To detect the maximum value of microseismic monitoring, c min To detect microseismic monitoring minimum value;

[0037] The calculation formula of the simulated value of rock thickness data is:

[0038]

[0039] Among them, M 3 is the simulated value of rock thickness data, e is a constant in this calculation formula, d max To detect the maximum rock thickness, d min To detect the minimum thickness of rock formation;

[0040] By assigning corresponding weights to the differences between the standard values ​​and simulated values ​​of water level data, microseismic frequency monitoring data, and rock thickness data, the calculation formula for the first deviation evaluation value of comprehensive detection is obtained:

[0041] D 1 =α 1 ×(A 1 -M 1 )+α 2 ×(A 2 -M 2 )+α×(A 3 -M 3 )

[0042] Among them, D 1 is the first deviation evaluation value of comprehensive detection, A1 is the standard value of water level data, A 2 is the standard value of microseismic frequency monitoring data, A 3 is the standard value of rock thickness data, M 1 is the simulated value of water level data, M 2 is the simulated value of microseismic frequency monitoring data, M 3 is the simulated value of rock thickness data, α 1 , α 2 , α 3 are the corresponding weights, α 1 is 0.4, α 2 is 0.3, α 3 is 0.3.

[0043] As a further solution of the present invention: the difference between the standard value and the data measurement value is used to obtain the second deviation value of the data, and a corresponding weight is assigned to obtain the comprehensive detection second deviation evaluation value, including the following steps:

[0044] Comprehensive detection second deviation evaluation calculation formula:

[0045] D 2 =α 1 ×(A 1 -N 1 )+α 2 ×(A 2 -N 2 )+α 3 ×(A 3 -N 3 )

[0046] Among them, D 2 is the second deviation evaluation value of comprehensive detection, A 1 is the standard value of water level data, A 2 is the standard value of microseismic frequency monitoring data, A 3 is the standard value of rock thickness data, N 1 is the measured value of water level data, N 2 is the measured value of microseismic frequency monitoring data, N 3 is the measured value of rock thickness data, α 1 , α 2 , α 3 are the corresponding weights, α 1 is 0.4, α 2 is 0.3, α 3 is 0.3.

[0047] As a further solution of the present invention: the auxiliary judgment detection value obtained by using the chemical hazardous substance data includes the following steps:

[0048] By testing the measured value content of chemical hazardous substances and the standard value content of chemical hazardous substances within the T time period, the auxiliary judgment detection calculation formula is obtained:

[0049]

[0050] Among them, Q is the auxiliary judgment detection value, s1, s2 and s3 are the types of chemical substances, namely sulfate, chloride and fluoride, respectively, and m (s1) , m (s2) , m (s3) are the measured values ​​of chemical substances s1, s2 and s3, n (s1) , n (s2) and n (s3) They are the standard value contents of s1, s2 and s3 chemical substances respectively.

[0051] As a further solution of the present invention: the safety warning module obtains a comprehensive deviation evaluation value according to the comprehensive detection first deviation evaluation value and the comprehensive detection second deviation evaluation value, obtains a comprehensive deviation judgment value analysis result by combining the comprehensive deviation evaluation value with the auxiliary judgment detection value, divides the safety level according to the potential water hazard risk level, and issues a warning, including the following steps:

[0052] The comprehensive deviation evaluation calculation formula is obtained by comprehensively testing the first deviation evaluation value and the second deviation evaluation value:

[0053]

[0054] Where D is the comprehensive deviation evaluation value, e is a constant in the calculation formula, and D 1 is the first deviation evaluation value of comprehensive detection, D 2 is the second deviation evaluation value of the comprehensive detection;

[0055] The comprehensive deviation judgment calculation formula is obtained through the comprehensive deviation evaluation value and the auxiliary judgment detection value:

[0056] E={D×log(Q+1)}×100%

[0057] Among them, E is the comprehensive deviation judgment calculation value, D is the comprehensive deviation evaluation value, and Q is the auxiliary judgment detection value;

[0058] According to the calculation results of the comprehensive deviation judgment value, the potential water damage risk can be divided into three situations:

[0059] If 0<E≤20%, the potential water damage risk level is low risk level;

[0060] If 20%<E≤60%, the potential water damage risk level is medium risk level;

[0061] If 60% < E, the potential water damage risk level is high;

[0062] Adjustments for three levels of flood risk:

[0063] If the risk level is low, a level 3 safety warning signal will be issued for the internal detection area of ​​the coal mine;

[0064] If the risk level is medium, a secondary safety warning signal will be issued for the internal detection area of ​​the coal mine;

[0065] If the risk level is high, a first-level safety warning signal will be issued for the internal detection area of ​​the coal mine.

[0066] Beneficial effects of the present invention:

[0067] The present invention collects a variety of data in the internal monitoring area of ​​the coal mine and transmits them to the data processing module in real time for cleaning and normalization to obtain the corresponding data standard value, thereby realizing the combination of a variety of data of different magnitudes;

[0068] The present invention transmits data to a data analysis module, analyzes a large amount of historical data through a big data analysis method to obtain a data simulation value, collects data measurement values ​​through sensors, and combines them with data standard values ​​to obtain a comprehensive deviation evaluation value, thereby realizing a comprehensive evaluation of the system status by combining multiple data sources and reducing the error caused by a single data source;

[0069] The present invention obtains a comprehensive deviation judgment value through comprehensive deviation evaluation value and auxiliary judgment detection value, and issues a water hazard risk warning signal for the detection area, thereby achieving early warning of water hazards in coal mines and improving the safety production level of coal mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] 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.

[0071] Figure 1 Schematic diagram of the system framework of the present invention.

[0072] Figure 2 Schematic diagram of the system steps of the present invention. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0074] See also Figure 1-2 As shown, the present invention is a real-time early warning method for coal mine water hazards based on big data analysis, including the following modules:

[0075] Data acquisition module: collects mine water level data, microseismic frequency monitoring data, rock thickness data and chemical hazardous substances data through a sensor network installed in the fan-shaped area of ​​the coal mine;

[0076] Data transmission module: transmits mine water level data, microseismic frequency monitoring data, rock thickness data and chemical hazardous substances data to the data processing module in real time via wireless network;

[0077] Data processing module: pre-processes the received data, including cleaning and normalization, to obtain standard values ​​of water level data, microseismic frequency monitoring data and rock thickness data;

[0078] Data analysis module: Analyze historical data through big data analysis method, obtain simulated values ​​of water level data, microseismic frequency monitoring data and rock thickness data through the maximum and minimum values ​​of real-time data, obtain the first deviation value of data according to the standard value and simulated value, assign corresponding weights to obtain the first deviation evaluation value of comprehensive detection, obtain the second deviation value of data through the standard value and data measurement value, assign corresponding weights to obtain the second deviation evaluation value of comprehensive detection, and obtain auxiliary judgment detection value through chemical hazardous substance data;

[0079] Safety warning module: obtain a comprehensive deviation evaluation value through comprehensive detection of the first deviation evaluation value and the second deviation evaluation value, obtain a comprehensive deviation judgment value analysis result based on the comprehensive deviation evaluation value combined with the auxiliary judgment detection value, divide the safety level according to the potential water hazard risk level, and issue a warning.

[0080] Specifically, water level, microseismic frequency monitoring, rock thickness data and chemical hazardous substances data are collected through a variety of sensors, and the corresponding data standard values ​​are obtained after the water level, microseismic frequency monitoring and rock thickness data are cleaned and normalized; data simulation values ​​are obtained through big data analysis methods, and the differences between data measurement values ​​and data standard values ​​with different weights are respectively obtained to obtain the first deviation evaluation value and the second deviation evaluation value of comprehensive detection; the comprehensive deviation evaluation value is obtained through the first deviation evaluation value and the second deviation evaluation value of comprehensive detection, and the deviation judgment value analysis results can be combined according to the comprehensive deviation evaluation value and the auxiliary judgment detection value obtained through the measurement value and standard value of chemical hazardous substances, and the detection area is divided into safety warning signals of corresponding degrees. It can realize real-time monitoring and early warning of coal mine water hazards, and improve the accuracy and timeliness of early warning.

[0081] In one embodiment of the present invention, the data acquisition module collects mine water level data, microseismic frequency monitoring data, rock layer thickness data and chemical hazardous substance data from a sensor network in a coal mine, including the following steps:

[0082] Measure the curvature of the mine shaft inside the coal mine, divide it into several equal sectors, and install a sensor network in the sectors to collect data;

[0083] The data collected include: mine water level data, microseismic frequency monitoring data and rock thickness data. Water quality monitoring sensors are deployed in the mine water accumulation area inside the coal mine to monitor data on harmful chemical substances in the water, including sulfate, chloride and fluoride.

[0084] Specifically, by installing sensors in the fan-shaped area to collect mine water level data, microseismic frequency monitoring data, rock thickness data and chemical hazardous substance data, the sensor network monitors the environment and working conditions inside the mine in real time, providing important guarantees for the safe production of coal mines and effectively preventing the occurrence of safety accidents.

[0085] In one embodiment of the present invention, the data transmission module transmits the mine water level data, microseismic frequency monitoring data, rock layer thickness data and chemical hazardous substance data to the data processing module in real time via a wireless network.

[0086] Specifically, through advanced data transmission modules and wireless network technology, key monitoring data such as water level, microseismic frequency monitoring, rock thickness and hazardous chemical substances in the mine are transmitted to the data processing module in real time, providing great technical support for the safe production of coal mines and optimizing data transmission and processing efficiency.

[0087] In one embodiment of the present invention, the data processing module pre-processes the received data, including cleaning and normalization, to obtain standard values ​​of water level data, microseismic frequency monitoring data and rock thickness data, including the following steps:

[0088] S301: Cleaning the received water level data, microseismic frequency monitoring data and rock thickness data through a data cleaning tool of the pandas library of the Python high-level programming language;

[0089] S302: normalizing the cleaned water level data, microseismic frequency monitoring data and rock thickness data through the sklearn library of the Python high-level programming language;

[0090] S303: Calculate standard values ​​for the pre-processed water level data, microseismic frequency monitoring data, and rock layer thickness data.

[0091] Specifically, the received water level data, microseismic frequency monitoring data and rock thickness data are preprocessed, including cleaning and normalization. A series of functions in the pandas library of the Python high-level programming language are used to clean missing values, duplicate values ​​and outliers to ensure the quality of the data. The data collected by different monitoring devices vary greatly in magnitude. Through normalization, these data are converted to the same scale to eliminate these differences, making it convenient to calculate the standard values ​​of water level data, microseismic frequency monitoring data and rock thickness data, so that these data can be analyzed at the same scale, providing a scientific basis for coal mine water hazard safety warning.

[0092] In one embodiment of the present invention, step S303 includes the following steps:

[0093] The water level data value is recorded at intervals of time T, and the water level data standard value calculation formula is obtained through the maximum and minimum data values:

[0094]

[0095] Among them A 1 is the standard value of water level data, n is the number of detections, b i is the water level value detected at the i-th time, b max To detect the maximum water level, b min To detect the minimum water level;

[0096] The microseismic frequency monitoring data values ​​are recorded at intervals of T, and the standard value calculation formula of the microseismic frequency monitoring data is obtained through the maximum and minimum values ​​of the data:

[0097]

[0098] Among them, A 2 is the standard value of microseismic frequency monitoring data, n is the number of detections, c i is the microseismic monitoring value of the ith detection, c max To detect the maximum value of microseismic monitoring, c min To detect microseismic monitoring minimum value;

[0099] Record the rock thickness data value at every interval T, and use the maximum and minimum values ​​to get the standard value calculation formula of the rock thickness data:

[0100]

[0101] Among them, A 3 is the standard value of rock thickness data, n is the number of detections, d i is the thickness of the rock layer detected for the i-th time, d max To detect the maximum rock thickness, d min To detect the minimum thickness of rock formation.

[0102] Specifically, the pre-processed water level data, microseismic frequency monitoring data and rock thickness data are analyzed, and the standard values ​​of the water level data, microseismic frequency monitoring data and rock thickness data can be obtained by the average value of each monitoring value and the average value of the maximum and minimum values ​​in the monitoring values. By systematically calculating the corresponding standard values ​​of the pre-processed data, the safety status of the mine can be evaluated more scientifically for subsequent calculations, and corresponding defense measures can be taken.

[0103] In one embodiment of the present invention, the data analysis module analyzes historical data by a big data analysis method, obtains simulated values ​​of water level data, microseismic frequency monitoring data, and rock thickness data by the maximum and minimum values ​​of real-time data, and obtains a comprehensive detection first deviation evaluation value according to the standard value and the simulated value, including the following steps:

[0104] Water level data simulation value calculation formula:

[0105]

[0106] Among them, M 1 is the simulated value of water level data, e is a constant in this calculation formula, b max To detect the maximum water level, b min To detect the minimum water level;

[0107] Calculation formula for the simulated value of microseismic frequency monitoring data:

[0108]

[0109] Among them, M 2is the simulated value of microseismic frequency monitoring data, e is a constant in this calculation formula, c max To detect the maximum value of microseismic monitoring, c min To detect microseismic monitoring minimum value;

[0110] The calculation formula of the simulated value of rock thickness data is:

[0111]

[0112] Among them, M 3 is the simulated value of rock thickness data, e is a constant in this calculation formula, d max To detect the maximum rock thickness, d min To detect the minimum thickness of rock formation;

[0113] By assigning corresponding weights to the differences between the standard values ​​and simulated values ​​of water level data, microseismic frequency monitoring data, and rock thickness data, the calculation formula for the first deviation evaluation value of comprehensive detection is obtained:

[0114] D 1 =α 1 ×(A 1 -M 1 )+α 2 ×(A 2 -M 2 )+α×(A 3 -M 3 )

[0115] Among them, D 1 is the first deviation evaluation value of comprehensive detection, A 1 is the standard value of water level data, A 2 is the standard value of microseismic frequency monitoring data, A 3 is the standard value of rock thickness data, M 1 is the simulated value of water level data, M 2 is the simulated value of microseismic frequency monitoring data, M 3 is the simulated value of rock thickness data, α 1 , α 2 , α 3 are the corresponding weights, α 1 is 0.4, α 2 is 0.3, α 3 is 0.3.

[0116] Specifically, the collected historical data are analyzed through big data analysis methods, and the maximum and minimum values ​​of the current water level data, microseismic frequency monitoring data and rock thickness data are input as input parameters into the simulation calculation formula. These simulation values ​​represent the expected water level, microseismic frequency and rock thickness under specific conditions. The simulation values ​​are compared with the corresponding standard values, and the deviation of each parameter is calculated and assigned a corresponding weight coefficient. The weighted method is used to combine the deviations of all parameters into a comprehensive detection first deviation evaluation value to determine whether the current state is within an acceptable range, so as to improve the overall evaluation performance and achieve rapid early warning of coal mine water hazards.

[0117] In one embodiment of the present invention, the method of obtaining the second deviation value of the data by calculating the difference between the standard value and the data measurement value and assigning a corresponding weight to obtain the second deviation evaluation value of the comprehensive detection includes the following steps:

[0118] Comprehensive detection second deviation evaluation calculation formula:

[0119] D 2 =α 1 ×(A 1 -N 1 )+α 2 ×(A 2 -N 2 )+α 3 ×(A 3 -N 3 )

[0120] Among them, D 2 is the second deviation evaluation value of comprehensive detection, A 1 is the standard value of water level data, A 2 is the standard value of microseismic frequency monitoring data, A 3 is the standard value of rock thickness data, N 1 is the measured value of water level data, N 2 is the measured value of microseismic frequency monitoring data, N 3 is the measured value of rock thickness data, α 1 , α 2 , α 3 are the corresponding weights, α 1 is 0.4, α 2 is 0.3, α 3 is 0.3.

[0121] Specifically, the second deviation values ​​of the data are obtained by dividing the standard values ​​of the water level data, microseismic frequency monitoring data and rock thickness data by the measured values ​​of the water level data, microseismic frequency monitoring data and rock thickness data collected by the sensors. Different weight coefficients are assigned according to the importance of each parameter, and the second deviation value of each parameter is multiplied by its corresponding weight. Then, the three weighted deviation values ​​are added to obtain the comprehensive detection second deviation evaluation value. By judging whether the current state is within an acceptable range, we can have a more comprehensive understanding of the reliability of the system and effectively control the risk range.

[0122] In one embodiment of the present invention, the method of obtaining the auxiliary judgment detection value through the chemical hazardous substance data includes the following steps:

[0123] By testing the measured value content of chemical hazardous substances and the standard value content of chemical hazardous substances within the T time period, the auxiliary judgment detection calculation formula is obtained:

[0124]

[0125] Among them, Q is the auxiliary judgment detection value, s1, s2 and s3 are the types of chemical substances, namely sulfate, chloride and fluoride, respectively, and m (s1) , m (s2) , m (s3) The measured values ​​of chemical substances s1, s2 and s3, n (s1) , n (s2) and n (s3) They are the standard value contents of s1, s2 and s3 chemical substances respectively.

[0126] Specifically, by comparing the measured values ​​of hazardous chemicals detected within a specific time period T with the standard values ​​of hazardous chemicals, it is possible to quickly detect and identify that the exposure level of hazardous chemicals exceeds the standard value level, which can effectively serve as a factor in assessing potential safety risk warnings.

[0127] In one embodiment of the present invention, the safety warning module obtains a comprehensive deviation evaluation value according to the comprehensive detection first deviation evaluation value and the comprehensive detection second deviation evaluation value, obtains a comprehensive deviation judgment value analysis result by combining the comprehensive deviation evaluation value with the auxiliary judgment detection value, divides the safety level according to the potential water hazard risk level, and issues a warning, including the following steps:

[0128] The comprehensive deviation evaluation calculation formula is obtained by comprehensively testing the first deviation evaluation value and the second deviation evaluation value:

[0129]

[0130] Where D is the comprehensive deviation evaluation value, e is a constant in the calculation formula, and D1 is the first deviation evaluation value of comprehensive detection, D 2 is the second deviation evaluation value of the comprehensive detection;

[0131] The comprehensive deviation judgment calculation formula is obtained through the comprehensive deviation evaluation value and the auxiliary judgment detection value:

[0132] E={D×log(Q+1)}×100%

[0133] Among them, E is the comprehensive deviation judgment calculation value, D is the comprehensive deviation evaluation value, and Q is the auxiliary judgment detection value;

[0134] According to the calculation results of the comprehensive deviation judgment value, the potential water damage risk can be divided into three situations:

[0135] If 0<E≤20%, the potential water damage risk level is low risk level;

[0136] If 20%<E≤60%, the potential water damage risk level is medium risk level;

[0137] If 60% < E, the potential water damage risk level is high;

[0138] Adjustments for three levels of flood risk:

[0139] If the risk level is low, a level 3 safety warning signal will be issued for the internal detection area of ​​the coal mine;

[0140] If the risk level is medium, a secondary safety warning signal will be issued for the internal detection area of ​​the coal mine;

[0141] If the risk level is high, a first-level safety warning signal will be issued for the internal detection area of ​​the coal mine.

[0142] Specifically, a comprehensive deviation evaluation value is obtained according to the first deviation evaluation value of the comprehensive detection and the second deviation evaluation value of the comprehensive detection. The comprehensive deviation judgment value obtained by the comprehensive deviation evaluation value and the auxiliary judgment detection value is very important for the accuracy and reliability of the evaluation data. The comprehensive deviation judgment value can be used to predict potential water hazards of different degrees, and corresponding adjustments can be made for the three levels of water hazards risks, and different safety warning signals can be issued to the detection area for warning.

[0143] 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 real-time early warning method for coal mine water hazards based on big data analysis, characterized in that: Includes the following modules: Data acquisition module: collects mine water level data, microseismic frequency monitoring data, rock thickness data and chemical hazardous substances data through a sensor network installed in the fan-shaped area of ​​the coal mine; Data transmission module: transmits mine water level data, microseismic frequency monitoring data, rock thickness data and chemical hazardous substances data to the data processing module in real time via wireless network; Data processing module: pre-processes the received data, including cleaning and normalization, to obtain standard values ​​of water level data, microseismic frequency monitoring data and rock thickness data; Data analysis module: Analyze historical data through big data analysis method, obtain simulated values ​​of water level data, microseismic frequency monitoring data and rock thickness data through the maximum and minimum values ​​of real-time data, obtain the first deviation value of data according to the standard value and simulated value, assign corresponding weights to obtain the first deviation evaluation value of comprehensive detection, obtain the second deviation value of data through the standard value and data measurement value, assign corresponding weights to obtain the second deviation evaluation value of comprehensive detection, and obtain auxiliary judgment detection value through chemical hazardous substance data; Safety warning module: obtain a comprehensive deviation evaluation value through comprehensive detection of the first deviation evaluation value and the second deviation evaluation value, obtain a comprehensive deviation judgment value analysis result based on the comprehensive deviation evaluation value combined with the auxiliary judgment detection value, divide the safety level according to the potential water hazard risk level, and issue a warning.

2. A method for real-time early warning of coal mine water hazards based on big data analysis according to claim 1, characterized in that: The data acquisition module collects mine water level data, microseismic frequency monitoring data, rock layer thickness data and chemical hazardous substance data through a sensor network in the coal mine, including the following steps: Measure the curvature of the mine shaft inside the coal mine, divide it into several equal sectors, and install a sensor network in the sectors to collect data; The data collected include: mine water level data, microseismic frequency monitoring data and rock thickness data. Water quality monitoring sensors are deployed in the mine water accumulation area inside the coal mine to monitor the data of harmful chemical substances in the water, including sulfate, chloride and fluoride.

3. The method for real-time early warning of coal mine water hazards based on big data analysis according to claim 1 is characterized in that: The data transmission module transmits the mine water level data, microseismic frequency monitoring data, rock layer thickness data and chemical hazardous substance data to the data processing module in real time via a wireless network.

4. The method for real-time early warning of coal mine water hazards based on big data analysis according to claim 1 is characterized in that: The data processing module pre-processes the received data, including cleaning and normalization, to obtain standard values ​​of water level data, microseismic frequency monitoring data and rock thickness data, including the following steps: S301: Cleaning the received water level data, microseismic frequency monitoring data and rock thickness data through a data cleaning tool of the pandas library of the Python high-level programming language; S302: normalizing the cleaned water level data, microseismic frequency monitoring data and rock thickness data through the sklearn library of the Python high-level programming language; S303: Calculate standard values ​​for the pre-processed water level data, microseismic frequency monitoring data, and rock layer thickness data.

5. A method for real-time early warning of coal mine water hazards based on big data analysis according to claim 4, characterized in that: The step S303 includes the following steps: The water level data value is recorded at intervals of time T, and the water level data standard value calculation formula is obtained through the maximum and minimum data values: A1 is the standard value of water level data, n is the number of detections, b i is the water level value detected at the i-th time, b max To detect the maximum water level, b min To detect the minimum water level; The microseismic frequency monitoring data values ​​are recorded at intervals of T, and the standard value calculation formula of the microseismic frequency monitoring data is obtained through the maximum and minimum values ​​of the data: Among them, A2 is the standard value of microseismic frequency monitoring data, n is the number of detections, c i is the microseismic monitoring value of the ith detection, c max To detect the maximum value of microseismic monitoring, c min To detect microseismic monitoring minimum value; Record the rock thickness data value at every interval T, and use the maximum and minimum values ​​to get the standard value calculation formula of the rock thickness data: Among them, A3 is the standard value of rock thickness data, n is the number of detections, d i is the thickness of the rock layer detected for the i-th time, d max To detect the maximum rock thickness, d min To detect the minimum thickness of rock formation.

6. A method for real-time early warning of coal mine water hazards based on big data analysis according to claim 5, characterized in that: The data analysis module analyzes historical data by using a big data analysis method, obtains simulated values ​​of water level data, microseismic frequency monitoring data, and rock thickness data by using the maximum and minimum values ​​of real-time data, and obtains a first deviation evaluation value of comprehensive detection according to the standard value and the simulated value, including the following steps: Water level data simulation value calculation formula: Among them, M1 is the simulated value of water level data, e is a constant in the calculation formula, and b max To detect the maximum water level, b min To detect the minimum water level; Calculation formula for the simulated value of microseismic frequency monitoring data: Among them, M2 is the simulated value of microseismic frequency monitoring data, e is a constant in the calculation formula, and c max To detect the maximum value of microseismic monitoring, c min To detect microseismic monitoring minimum value; The calculation formula of the simulated value of rock thickness data is: Among them, M3 is the simulated value of rock thickness data, e is a constant in the calculation formula, and d max To detect the maximum rock thickness, d min To detect the minimum thickness of rock formation; By assigning corresponding weights to the differences between the standard values ​​and simulated values ​​of water level data, microseismic frequency monitoring data, and rock thickness data, the calculation formula for the first deviation evaluation value of comprehensive detection is obtained: D1=α1×(A1-M1)+α2×(A2-M2)+α×(A3-M3) Among them, D1 is the first deviation evaluation value of comprehensive detection, A1 is the standard value of water level data, A2 is the standard value of microseismic frequency monitoring data, A3 is the standard value of rock thickness data, M1 is the simulated value of water level data, M2 is the simulated value of microseismic frequency monitoring data, M3 is the simulated value of rock thickness data, α1, α2, and α3 are the corresponding weights, α1 is 0.4, α2 is 0.3, and α3 is 0.

3.

7. A method for real-time early warning of coal mine water hazards based on big data analysis according to claim 6, characterized in that: The method of obtaining the second deviation value of the data by calculating the difference between the standard value and the data measurement value and assigning a corresponding weight to obtain the second deviation evaluation value of the comprehensive detection includes the following steps: Comprehensive detection second deviation evaluation calculation formula: D2=α1×(A1-N1)+α2×(A2-N2)+α3×(A3-N3) Among them, D2 is the second deviation evaluation value of comprehensive detection, A1 is the standard value of water level data, A2 is the standard value of microseismic frequency monitoring data, A3 is the standard value of rock thickness data, N1 is the measured value of water level data, N2 is the measured value of microseismic frequency monitoring data, N3 is the measured value of rock thickness data, α1, α2, and α3 are the corresponding weights, α1 is 0.4, α2 is 0.3, and α3 is 0.

3.

8. The method for real-time early warning of coal mine water hazards based on big data analysis according to claim 1 is characterized in that: The method of obtaining the auxiliary judgment detection value through the chemical hazardous substance data includes the following steps: By testing the measured value content of chemical hazardous substances and the standard value content of chemical hazardous substances within the T time period, the auxiliary judgment detection calculation formula is obtained: Among them, Q is the auxiliary judgment detection value, s1, s2 and s3 are the types of chemical substances, namely sulfate, chloride and fluoride, respectively, and m (s1) , m (s2) , m (s3) The measured values ​​of chemical substances s1, s2 and s3, n (s1) , n (s2) and n (s3) They are the standard value contents of s1, s2 and s3 chemical substances respectively.

9. The method for real-time early warning of coal mine water hazards based on big data analysis according to claim 1, characterized in that: The safety warning module obtains a comprehensive deviation evaluation value according to the comprehensive detection first deviation evaluation value and the comprehensive detection second deviation evaluation value, obtains a comprehensive deviation judgment value analysis result by combining the comprehensive deviation evaluation value with the auxiliary judgment detection value, divides the safety level according to the potential water hazard risk level, and issues a warning, including the following steps: The comprehensive deviation evaluation calculation formula is obtained by comprehensively testing the first deviation evaluation value and the second deviation evaluation value: Wherein, D is the comprehensive deviation evaluation value, e is a constant in the calculation formula, D1 is the comprehensive detection first deviation evaluation value, and D2 is the comprehensive detection second deviation evaluation value; The comprehensive deviation judgment calculation formula is obtained through the comprehensive deviation evaluation value and the auxiliary judgment detection value: E={D×log(Q+1)}×100% Among them, E is the comprehensive deviation judgment calculation value, D is the comprehensive deviation evaluation value, and Q is the auxiliary judgment detection value; According to the calculation results of the comprehensive deviation judgment value, the potential water damage risk can be divided into three situations: If 0<E≤20%, the potential water damage risk level is low risk level; If 20%<E≤60%, the potential water damage risk level is medium risk level; If 60% < E, the potential water damage risk level is high; Adjustments for three levels of flood risk: If the risk level is low, a level 3 safety warning signal will be issued for the internal detection area of ​​the coal mine; If the risk level is medium, a secondary safety warning signal will be issued for the internal detection area of ​​the coal mine; If the risk level is high, a first-level safety warning signal will be issued for the internal detection area of ​​the coal mine.

Images