Method for judging reliability of abnormal gas fluctuation of fully mechanized coal mining face of coal mine

Abstract

The invention relates to a coal mine fully mechanized coal mining face gas abnormal fluctuation reliability discrimination method comprising the following steps: respectively establishing a gas concentration trapezoid function and a gas concentration fluctuation degree trapezoid function according to gas sensor concentration statistical data in a certain time; respectively establishing a gas concentration scoring function and a gas concentration fluctuation degree scoring function according to the gas concentration trapezoidal function and the gas concentration fluctuation degree trapezoidal function, calculating the concentration fluctuation score of the gas sensor of which the monitoring concentration fluctuates, and performing gas concentration abnormity judgment. A gas sensor concentration linear regression equation is obtained through multiple linear regression analysis, and the gas sensor concentration linear regression equation is used for secondary gas concentration abnormity judgment. By comprehensively analyzing the data of the plurality of gas sensors, the methane concentration fluctuation caused by the change in the normal production process is eliminated, the real abnormal methane emission event can be identified more accurately, the false alarm is reduced, and the reliability of the early warning event is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of coal mine safety, and in particular relates to a reliability judgment method for abnormal gas fluctuation in a fully mechanized mining face of a coal mine. Background Art

[0002] In the field of coal mine safety production, the monitoring and early warning of gas (methane) concentration is a key technology for preventing gas explosion accidents. In order to comprehensively monitor the gas concentration, gas sensors are arranged at three key positions of the working face, namely the upper corner (T0), the working face (T1) and the return air channel (T2). The purpose and monitoring focus of these sensors are different. Among them, T0 focuses on monitoring the gas outburst in the goaf and part of the working face, T1 pays more attention to the gas situation in the goaf and the working face, and T2 realizes the comprehensive monitoring of the gas outburst in the goaf, working face and coal wall. Scholars analyze the methane concentration time series of methane sensors and warn of abnormal conditions of methane outburst, in order to realize real-time monitoring and risk assessment of methane concentration in coal mine working faces. These studies use mathematical methods to analyze the methane concentration time series, find out the fluctuation anomalies with concentration values ​​above 1.0%, and publish them as methane outburst warning events. Although the above studies have achieved certain results in early warning of abnormal methane concentrations, these methods mainly focus on the analysis of the methane concentration time series itself, while ignoring the reasons behind the abnormal methane outburst fluctuations.

[0003] In actual applications, due to changes in normal production processes such as changes in working face operation flow, wind speed changes, equipment start-up and stop, and roof periodic pressure, the methane concentration fluctuations caused by these factors are often misjudged as warning events, resulting in a high false alarm rate. Therefore, the existing warning methods have certain limitations in practical applications, and it is necessary to conduct reliability identification of warning events such as methane concentration fluctuations to improve the accuracy and reliability of warning events.

[0004] Disadvantages of existing technology:

[0005] 1. Single monitoring point analysis: The existing gas concentration monitoring system mainly focuses on the time series analysis of a single sensor data, lacking comprehensive analysis and judgment of multiple sensor data.

[0006] 2. High false alarm rate: The existing early warning methods have a high false alarm rate due to the failure to distinguish between methane concentration fluctuations caused by normal production processes and real methane outburst anomalies.

[0007] 3. Lack of comprehensive identification mechanism: Existing technologies fail to effectively utilize data from multiple sensors for comprehensive analysis to determine the specific reasons why methane concentration exceeds the set threshold, and thus fail to accurately identify true methane outburst anomalies. Summary of the invention

[0008] In order to overcome the above shortcomings and improve the accuracy and reliability of gas disaster warning, it is necessary to develop a reliability judgment method for abnormal gas fluctuations in coal mine fully-mechanized mining working faces. The present invention aims to provide a reliability judgment method for abnormal gas fluctuations in coal mine fully-mechanized mining working faces. When the concentration monitored by a gas sensor on the working face fluctuates, the method first makes a first abnormal gas concentration judgment based on the current gas concentration and its degree of fluctuation, and then verifies and judges the cause of the current gas sensor concentration fluctuation through the concentration monitored by the remaining gas sensors on the working face, and eliminates gas warnings caused by reasonable gas concentration fluctuations. This method can more accurately identify methane gushing events that do exist abnormally, and provide strong technical support for safe production in coal mines.

[0009] In view of the above shortcomings of the prior art, the present invention aims to solve the related technical problems in the following ways:

[0010] 1. Comprehensive analysis of multiple sensor data: By analyzing the gas sensor data at three key positions (T0, T1, T2) on the working face, comprehensive monitoring and comprehensive judgment of abnormal methane concentration can be achieved.

[0011] 2. Distinguishing between normal fluctuations and abnormal outbursts: The present invention can effectively distinguish between methane concentration fluctuations caused by changes in normal production processes and true methane outburst anomalies by comprehensively analyzing data from multiple sensors, thereby reducing false alarms.

[0012] 3. Reliability discrimination: Through comprehensive analysis and discrimination mechanism, the present invention can effectively reduce false alarms caused by changes in the normal production process and improve the reliability of gas disaster warning.

[0013] The present invention is achieved through the following technical solutions:

[0014] The present invention provides a method for distinguishing the reliability of abnormal gas fluctuation in a fully-mechanized coal mining face, comprising the following steps:

[0015] Step 1: When the concentration monitored by the gas sensor fluctuates, a gas concentration trapezoidal function and a gas concentration fluctuation degree trapezoidal function are established based on the concentration statistical data of the gas sensor within a certain period of time.

[0016] Gas concentration trapezoidal function:

[0017]

[0018] Where a1=min(x1,x2,…,x i ), b1=min(mode(X),median(X))c1=max(mode(X),median(X)), d1=max(x1,x2,…,x i ),

[0019] x1,x2,…,x i is the concentration statistics of the gas sensor within a certain period of time, X is the data set {x1,x2,…,x i}, mode(X) is (x1,x2,…,x i ), median(X) is the number that appears most often in (x1,x2,…,x i ) is the number in the middle after the data is sorted from small to large; if the data volume is an odd number, the median is the middle number; if the data volume is an even number, the median is the average of the two middle numbers; a1 takes (x1, x2, …, x i ), b1 takes the minimum value among (x1,x2,…,x i ), c1 is the smaller value of the mode or median in (x1, x2, …, x i ), d1 is the larger value of the mode or median in (x1, x2, …, x i ), x i The concentration value after the gas sensor monitors the concentration fluctuation;

[0020] Gas concentration fluctuation trapezoidal function:

[0021]

[0022] Among them, a2 = mean - standard deviation, b2 = mean - 0.5 standard deviation, c2 = mean + 0.5 standard deviation, d2 = mean + standard deviation, x j For x i and (x1,x2,…,x i ) the difference between the mean values;

[0023] Step 2: According to the trapezoidal function of gas concentration and the trapezoidal function of gas concentration fluctuation degree, a gas concentration scoring function and a gas concentration fluctuation degree scoring function are established respectively.

[0024] Gas concentration scoring function:

[0025]

[0026] Gas concentration fluctuation degree scoring function:

[0027]

[0028] Step 3: Calculate the concentration fluctuation fraction F of the gas sensor where the monitored concentration fluctuates, and make the first judgment on the abnormal gas concentration. The first abnormal gas concentration judgment is made based on the gas sensor concentration fluctuation score F. When F≥70, it is judged as normal gas concentration fluctuation. When F<70, the second abnormal gas concentration judgment is made by continuing to monitor the concentration through the remaining gas sensors on the working face.

[0029] Step 4: Set the concentration value of the gas sensor that monitors concentration fluctuations within a certain period of time as the dependent variable, and the concentration values ​​of the other gas sensors on the working face within the same period of time as the independent variable. The linear regression equation of the gas sensor concentration is obtained through multivariate linear regression analysis:

[0030] y=αT a +βT b +ε;

[0031] Among them, y is the dependent variable, that is, the predicted value of the gas sensor concentration with data fluctuation obtained by solving the gas sensor concentration without data fluctuation, T a , T b are the concentration data of two gas sensors without data fluctuation, α and β are T a , T b is the unknown coefficient of , and ε is the error term.

[0032] Step 5: Use the linear regression equation of the gas sensor concentration to make a second judgment on the abnormal gas concentration. Substitute the concentration values ​​of the other gas sensors on the working face when the gas sensor concentration fluctuates into the linear regression equation of the gas sensor concentration. If the concentration value after the gas sensor monitoring concentration fluctuates is within the range of ±10% of the y value obtained by solving the linear regression equation, it is judged as a gas concentration abnormality warning. If the concentration value after the gas sensor monitoring concentration fluctuates is not within the range of ±10% of the y value obtained by solving the linear regression equation, it is judged as a single gas concentration abnormality reminder.

[0033] Furthermore, in step one, the gas sensor includes T0, T1, and T2 gas sensors.

[0034] Furthermore, in step one, the statistical data of gas sensor concentration within a certain period of time refers to historical data of gas concentration of the gas sensor whose monitoring data fluctuates for no less than one day.

[0035] Furthermore, in step 4, multiple linear regression analysis is performed using data analysis tools such as EXCEL and SPSS to obtain a linear regression equation for the gas sensor concentration.

[0036] The beneficial effects of the present invention are:

[0037] 1. Reduce false alarm rate: The present invention can more accurately identify real abnormal methane outburst events and reduce false alarms by comprehensively analyzing the data of multiple gas sensors and eliminating the methane concentration fluctuations caused by changes in the normal production process;

[0038] 2. Reliability determination: The present invention provides a reliability determination method, which can verify and determine gas concentration fluctuations, distinguish reasonable fluctuations from abnormal fluctuations, and improve the reliability of early warning events. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The present invention is a flow chart of the reliability determination method of abnormal gas fluctuation in a fully mechanized coal mining face. DETAILED DESCRIPTION

[0040] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.

[0041] like Figure 1 A method for determining the reliability of abnormal gas fluctuations in a fully-mechanized coal mining face is shown, comprising the following steps:

[0042] Step 1: In this embodiment, the minimum value of the T0 gas sensor concentration within 1 day is 0.05, the median is 0.09, the mode is 0.1, the maximum value is 0.31, the mean is 0.11, and the standard deviation is 0.03. The concentration value of the T0 gas sensor after the concentration fluctuation is 0.13, and the concentration values ​​of the T1 and T2 gas sensors are 0.1 and 0.19 respectively. According to the historical data of the T0 gas sensor concentration within 1 day, the gas concentration trapezoidal function and the gas concentration fluctuation degree trapezoidal function are established respectively, and the gas concentration trapezoidal function of the T0 gas sensor is:

[0043]

[0044] x i The concentration value after the T0 gas sensor monitors the concentration fluctuation;

[0045] T0 gas sensor gas concentration fluctuation degree trapezoidal function:

[0046]

[0047] x j It is the difference between the concentration value after the concentration monitored by the T0 gas sensor fluctuates and the average concentration value of the gas sensor within 1 day;

[0048] Step 2: According to the trapezoidal function of gas concentration and the trapezoidal function of gas concentration fluctuation degree, the gas concentration scoring function of T0 gas sensor and the gas concentration fluctuation degree scoring function are established respectively. The gas concentration scoring function is:

[0049]

[0050] Gas concentration fluctuation degree scoring function:

[0051]

[0052] Step 3: Calculate the T0 gas sensor concentration fluctuation fraction F to make the first gas concentration abnormality judgment. It is judged that the concentration of T0 gas sensor fluctuates normally.

[0053] Example 2

[0054] A method for distinguishing the reliability of abnormal gas fluctuation in a fully-mechanized coal mining face comprises the following steps:

[0055] Step 1: In this embodiment, the minimum value of the T0 gas sensor concentration within 1 day is 0.05, the median is 0.09, the mode is 0.1, the maximum value is 0.31, the mean is 0.11, and the standard deviation is 0.03. The concentration value of the T0 gas sensor after the concentration fluctuation is 0.31. At the same time, the current concentrations of the T1 and T2 gas sensors are 0.08 and 0.22 respectively. According to the historical data of the T0 gas sensor concentration within 1 day, the gas concentration trapezoidal function and the gas concentration fluctuation degree trapezoidal function are established respectively, and the gas concentration trapezoidal function of the T0 gas sensor is:

[0056]

[0057] x i The concentration value after the T0 gas sensor monitors the concentration fluctuation;

[0058] T0 gas sensor gas concentration fluctuation degree trapezoidal function:

[0059]

[0060] x j It is the difference between the concentration value after the concentration monitored by the T0 gas sensor fluctuates and the average concentration value of the gas sensor within 1 day;

[0061] Step 2: According to the trapezoidal function of gas concentration and the trapezoidal function of gas concentration fluctuation degree, the gas concentration scoring function of T0 gas sensor and the gas concentration fluctuation degree scoring function are established respectively. The gas concentration scoring function is:

[0062]

[0063] Gas concentration fluctuation degree scoring function:

[0064]

[0065] Step 3: Calculate the T0 gas sensor concentration fluctuation fraction F to make the first gas concentration abnormality judgment. Continue to monitor the concentration through T1 and T2 gas sensors to make a second judgment on abnormal gas concentration;

[0066] Step 4: Set the concentration value of the T0 gas sensor within 1 day as the dependent variable, and the concentration values ​​of the T1 and T2 gas sensors within the same time as the independent variables, and obtain the linear regression equation of the gas concentration of the T0 gas sensor through multiple linear regression analysis:

[0067] T0: y=-0.022T1+0.183T2+0.065;

[0068] Step 5: Use the linear regression equation of gas concentration of T0 gas sensor to make a second judgment on gas concentration abnormality. Substitute the concentration values ​​of T1 and T2 gas sensors into the linear regression equation of gas concentration of T0 gas sensor: y=-0.022×0.08+0.183×0.22+0.065=0.10. The concentration value of T0 gas sensor after fluctuation is 0.31, which is not within the range of ±10% of the y value obtained by solving the linear regression equation. It is judged as a single gas concentration abnormality reminder.

[0069] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for distinguishing the reliability of abnormal gas fluctuation in a fully-mechanized coal mining face, characterized in that: The steps include: Step 1: When the concentration monitored by the gas sensor fluctuates, a gas concentration trapezoidal function and a gas concentration fluctuation degree trapezoidal function are established based on the concentration statistical data of the gas sensor within a certain period of time. Gas concentration trapezoidal function: such as,a1=min(x1,x2,...,x i ),b1=min(mode(X),median(X))c1=max(mode(X),median(X)),d1=max(x1,x2,…,x i ), x1,x2,…,x i is the concentration statistics of the gas sensor within a certain period of time, X is the data set {x1,x2,…,x i }, mode(X) is (x1,x2,…,x i ), median(X) is the number that appears most often in (x1,x2,…,x i ) is the number in the middle after the data is sorted from small to large; if the amount of data is an odd number, the median is the middle number; if the amount of data is an even number, the median is the average of the two middle numbers; a1 takes (x1, x2, …, x i ), b1 takes the minimum value among (x1,x2,…,x i ), c1 is the smaller value of the mode or median in (x1, x2, …, x i ), d1 is the larger value of the mode or median in (x1, x2, …, x i ), x i The concentration value after the gas sensor monitors the concentration fluctuation; Gas concentration fluctuation trapezoidal function: Among them, a2 = mean - standard deviation, b2 = mean - 0.5 standard deviation, c2 = mean + 0.5 standard deviation, d2 = mean + standard deviation, x j For x i and (x1,x2,…,x i ) the difference between the mean values; Step 2: According to the trapezoidal function of gas concentration and the trapezoidal function of gas concentration fluctuation degree, a gas concentration scoring function and a gas concentration fluctuation degree scoring function are established respectively. Gas concentration scoring function: Gas concentration fluctuation degree scoring function: Step 3: Calculate the concentration fluctuation fraction F of the gas sensor where the monitored concentration fluctuates, and make the first judgment on the abnormal gas concentration. The first abnormal gas concentration judgment is made based on the gas sensor concentration fluctuation score F. When F≥70, it is judged as normal gas concentration fluctuation. When F<70, the second abnormal gas concentration judgment is made by continuing to monitor the concentration through the remaining gas sensors on the working face. Step 4: Set the concentration value of the gas sensor that monitors concentration fluctuations within a certain period of time as the dependent variable, and the concentration values ​​of the other gas sensors on the working face within the same period of time as the independent variable. The linear regression equation of the gas sensor concentration is obtained through multivariate linear regression analysis: y=αT a +βT b +e; Where y is the dependent variable, that is, the predicted value of the gas sensor concentration with data fluctuation obtained by solving the gas sensor concentration without data fluctuation, T a , T b are the concentration data of two gas sensors without data fluctuation, α and β are T a , T b The unknown coefficient of , ε is the error term; Step 5: Use the linear regression equation of the gas sensor concentration to make a second judgment on the abnormal gas concentration. Substitute the concentration values ​​of the other gas sensors on the working face when the gas sensor concentration fluctuates into the linear regression equation of the gas sensor concentration. If the concentration value after the gas sensor monitoring concentration fluctuates is within the range of ±10% of the y value obtained by solving the linear regression equation, it is judged as a gas concentration abnormality warning. If the concentration value after the gas sensor monitoring concentration fluctuates is not within the range of ±10% of the y value obtained by solving the linear regression equation, it is judged as a single gas concentration abnormality reminder.

2. The reliability determination method of abnormal gas fluctuation in fully mechanized coal mining working face according to claim 1 is characterized in that: In step 1, the gas sensor includes T0, T1, and T2 gas sensors.

3. The reliability determination method of abnormal gas fluctuation in a fully mechanized coal mining face according to claim 1 or 2, characterized in that: In step 1, the statistical data of gas sensor concentration within a certain period of time refers to historical data of gas concentration of the gas sensor whose monitoring data fluctuates for no less than 1 day.

Images