Intelligent control method of gas concentration in fully mechanized mining face in low-gas mines

Abstract

The present invention discloses an intelligent control method for gas concentration in a fully mechanized mining face of a low-gas mine. The system uses an environmental monitoring module to sense environmental parameters such as the ventilation state and gas concentration of the working face, and combines big data to predict the gas change trend. When the gas change trend in the predicted interval is about to exceed the limit, the air supply of the working face is first increased, and the analysis and decision-making module optimizes the adjustment model to determine the adjustment position and adjustment amount of the ventilation facility. The intelligent control module sends a control instruction to the underground remote controllable ventilation facility. After the adjustment is completed, the air supply of the working face is increased and the gas concentration is reduced. At the same time, the monitoring system reasonably controls the air supply of the working face based on the fire monitoring data of the goaf. When the air volume of the working face can no longer be increased under these two constraints, a control instruction is sent to the fully mechanized mining equipment to reduce the coal cutting speed or suspend coal cutting. Coal cutting is resumed after the gas trend state of the working face recovers to a safe range, thereby reducing the risk of gas exceeding the limit accident on the working face and facilitating safe production.

Description

Technical Field

[0001] The present invention relates to the field of intelligent coal mining, and in particular to an intelligent control method for gas concentration in a fully mechanized mining face in a low-gas mine. Background Art

[0002] Coal is still one of the most important basic energy sources in the world. With the development of Internet of Things technology, healthy, green and intelligent mining has become the mainstream trend of the coal industry. The development of intelligent mining technology in coal mines has enabled the underground fully-mechanized mining face of coal mines to develop towards less or even unmanned operation. This has not only greatly improved the production efficiency of coal mining enterprises, but also greatly reduced the probability of safety accidents. However, problems such as untimely gas control in the working face and frequent gas over-limit accidents still restrict the development of intelligent mining technology in coal mines. In the traditional gas control mode of the working face, prediction and forecasting rely solely on the threshold of the underground sensor, which cannot achieve early prevention. Moreover, after the alarm occurs, the system is not directly related to the underground ventilation system and coal mining system. It often has to go through the steps of underground sensor alarm, technical personnel analysis and decision-making, formulation of prevention and control measures, and implementation of prevention and control plans. The whole process is cumbersome and lengthy, and cannot be timely and effective. Summary of the invention

[0003] The purpose of the present invention is to solve the problems of untimely gas control and gas over-limit accidents in fully mechanized mining working faces.

[0004] To achieve the above object, the present invention provides a method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine, comprising:

[0005] Acquire historical environmental monitoring data, aggregate them into a historical data set, and obtain a gas concentration time series prediction model through a long short-term memory recurrent neural network time series prediction model based on the historical data set;

[0006] Acquire the real-time environmental monitoring data, analyze the real-time environmental monitoring data through the gas concentration time series prediction model and predict the change of gas concentration to obtain the gas concentration exceeding limit interval;

[0007] Determine whether the gas concentration exceeds the over-limit interval. If so, calculate the required air volume q1 in the fully mechanized mining face based on the initial air volume q0;

[0008] Determine whether the wind speed of the fully mechanized mining face exceeds the limit and the air supply capacity. If so, directly adjust the coal cutting speed of the coal mining machine to maintain the gas concentration within the gas concentration over-limit interval. If not, increase the wind speed to the required air volume q1;

[0009] Obtain the fire index gas in the goaf after one adjustment cycle of changing the wind speed to the required air volume q1, and determine whether the fire index gas in the goaf exceeds the limit and whether it increases continuously. If not, continue to monitor the fire index gas. If so, change the air volume to the initial air volume q0 and adjust the coal cutting speed of the coal mining machine.

[0010] According to one aspect of the present invention, the environmental monitoring data includes:

[0011] The gas sensor data of the fully mechanized mining working face, the absolute static pressure sensor data of the fully mechanized mining working face and the coal cutting speed of the coal mining machine.

[0012] According to one aspect of the present invention, the method for obtaining a gas concentration time series prediction model based on the historical data set is:

[0013] The gas concentration time series prediction model is obtained by combining the long short-term memory recurrent neural network time series prediction model with the historical environmental monitoring data. According to the predicted time step, the historical data set is cut forward with the current time as the starting point, and the average value is taken from the historical data set. N data samples and number them as x1~x N , divide the N data samples into M groups of data, the first group is x1~x (M-1) , predict x based on the first set of information M The second group is x2~x M , predict x (M+1) The information is used to predict the information in sequence to obtain the gas concentration time series prediction model for the next time step of the current time.

[0014] According to one aspect of the present invention, the method for calculating the required air volume q1 in the working surface according to the initial air volume q0 is:

[0015] q1=C 瓦斯1 q0 / C 瓦斯0

[0016] Wherein, q1 is the required air volume, m 3 / s;

[0017] C 瓦斯1 is the maximum gas concentration, volume fraction %;

[0018] C 瓦斯0 is the initial gas concentration, volume fraction %;

[0019] q0 is the initial air volume, m 3 / s.

[0020] According to one aspect of the present invention, the method of increasing the wind speed to the required air volume q1 is:

[0021] By adjusting the ventilation adjustment facilities connected in series with the fully mechanized mining face, including the adjustment windows and the adjustment doors with the windows, or the adjustment facilities at other air-using locations connected in parallel with the fully mechanized mining face, the wind speed reaches the required air volume q 1。

[0022] According to one aspect of the present invention, the fire indicator gas includes CO, C2H6, C2H4, C3H8, C2H2, a mixed gas of C2H4 and C2H6, and a mixed gas of C3H8 and C2H6.

[0023] According to one aspect of the present invention, a method for determining whether the fire index gas in the goaf exceeds the limit and whether it increases continuously is:

[0024] C 火灾指标气体2 >C max ;

[0025] C 火灾指标气体2 -C 火灾指标气体1 >0 and C 火灾指标气体1 -C 火灾指标气体0 >0;

[0026] Among them, C 火灾指标气体2 is the concentration of the current fire index gas, ppm;

[0027] C 火灾指标气体1 is the fire index gas concentration of the previous prediction period of the time step, ppm;

[0028] C 火灾指标气体0 is the fire indicator gas concentration in ppm for the first two predicted time steps.

[0029] According to one aspect of the present invention, the method for adjusting the coal cutting speed of the coal shearer is:

[0030] Δv=(C 瓦斯1 q0-C 瓦斯0 ·q0) / (L·H·w·r)

[0031] v1=v0+Δv

[0032] Wherein Δv is the speed difference of the coal mining machine, m / s;

[0033] q0 is the initial air volume, m 3 / s;

[0034] L is the penetration of each cut of the coal mining machine, m;

[0035] H is the mining height, m;

[0036] r is the specific gravity of coal, t / m 3 ;

[0037] w is the resolvable gas content of the coal in the fully mechanized mining face, m 3 / t;

[0038] v1 is the speed of the coal mining machine after adjustment, m / s;

[0039] v0 is the speed of the coal mining machine before adjustment, m / s.

[0040] To achieve the above object, the present invention provides a gas concentration intelligent control system for a fully mechanized mining face in a low-gas mine, comprising:

[0041] Prediction model building module: obtain historical environmental monitoring data, summarize to form a historical data set, and obtain a gas concentration time series prediction model through a long short-term memory recurrent neural network time series prediction model based on the historical data set;

[0042] An over-limit interval acquisition module: acquires the real-time environmental monitoring data, analyzes the real-time environmental monitoring data through the gas concentration time series prediction model, predicts the change of gas concentration, and obtains the over-limit interval of gas concentration;

[0043] Gas concentration judgment module: judges whether the gas concentration exceeds the over-limit interval. If it exceeds, the required air volume q1 in the fully mechanized mining face is calculated based on the initial air volume q0;

[0044] Wind speed judgment module: judge whether the wind speed of the fully mechanized mining face exceeds the limit and whether it exceeds the air supply capacity. If so, directly adjust the coal cutting speed of the coal mining machine to maintain the gas concentration within the gas concentration exceeding the limit interval. If not, increase the wind speed to the required air volume q1;

[0045] Index gas judgment module: obtain the fire index gas in the goaf after one adjustment cycle of changing the wind speed to the required air volume q1, and judge whether the fire index gas in the goaf exceeds the limit and whether it increases continuously. If not, continue to monitor the fire index gas; if so, change the air volume to the initial air volume q0 and adjust the coal cutting speed of the coal mining machine.

[0046] To achieve the above-mentioned purpose, the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the above-mentioned intelligent control method for gas concentration in a fully mechanized mining face in a low-gas mine is implemented.

[0047] To achieve the above objectives, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned intelligent control method for gas concentration in a fully mechanized mining face in a low-gas mine is implemented.

[0048] Based on this, the beneficial effects of the present invention are:

[0049] (1) Taking into account the impact of fire hazards in goaf areas, the risk of gas exceeding the limit in the coal mining face is reduced and safe production of the face is ensured by comprehensively utilizing technical means including gas concentration prediction, adjusting the working face air volume, and adjusting the speed of the coal mining machine, while ensuring the maximum production efficiency of the working face.

[0050] (2) Combined with the neural network algorithm, it can give early warning of changes in gas concentration, and directly cooperate with the underground ventilation system and coal mining system to respond to the warning content in advance. It is highly timely, helps to improve production safety, and reduces the possibility of accidents such as gas exceeding the limit. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A flow chart schematically showing a method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to the present invention;

[0052] Figure 2 The flowchart of a gas concentration intelligent control system for a fully mechanized mining face in a low-gas mine according to the present invention is schematically shown. DETAILED DESCRIPTION

[0053] The present invention will now be discussed with reference to exemplary embodiments. It should be understood that the embodiments discussed are only for enabling those skilled in the art to better understand and thereby implement the present invention, rather than implying any limitation on the scope of the present invention.

[0054] As used herein, the term “including” and variations thereof are to be interpreted as open-ended terms meaning “including but not limited to.” The term “based on” is to be interpreted as “based, at least in part, on,” and the terms “one embodiment” and “an embodiment” are to be interpreted as “at least one embodiment.”

[0055] Figure 1 A flow chart schematically shows a method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to the present invention, as shown in FIG. Figure 1 As shown, according to the present invention, a method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine comprises the following steps:

[0056] 101: historical environmental monitoring data is obtained and aggregated to form a historical data set, and a gas concentration time series prediction model is obtained based on the historical data set through a long short-term memory recurrent neural network time series prediction model;

[0057] 102: Acquire real-time environmental monitoring data, analyze the real-time environmental monitoring data through a gas concentration time series prediction model, predict changes in gas concentration, and obtain a gas concentration over-limit interval;

[0058] 103: Determine whether the gas concentration exceeds the limit range. If so, calculate the required air volume q1 in the fully mechanized mining face based on the initial air volume q0;

[0059] 104: Determine whether the wind speed of the fully mechanized mining face exceeds the limit and exceeds the air supply capacity. If so, directly adjust the coal cutting speed of the coal mining machine to maintain the gas concentration within the gas concentration over-limit interval. If not, increase the wind speed to the required air volume q1;

[0060] 105: Obtain the fire index gas in the goaf after one adjustment cycle of changing the wind speed to the required air volume q1, and determine whether the fire index gas in the goaf exceeds the limit and whether it increases continuously. If not, continue to monitor the fire index gas. If so, change the air volume to the initial air volume q0 and adjust the coal cutting speed of the coal mining machine.

[0061] According to one embodiment of the present invention, the environmental monitoring data includes:

[0062] The gas sensor data of the fully mechanized mining face, the absolute static pressure sensor data of the fully mechanized mining face and the coal cutting speed of the coal mining machine.

[0063] According to one embodiment of the present invention, a method for obtaining a gas concentration time series prediction model based on a historical data set is as follows:

[0064] The gas concentration time series prediction model is obtained by combining the long short-term memory recurrent neural network time series prediction model with the historical environmental monitoring data. According to the predicted time step, the historical data set is cut forward with the current time as the starting point, and 60 data samples are taken from the historical data set on average and numbered as x1~x60. The 60 data samples are divided into 30 groups of data, the first group is x1~x29, and the information of x30 is predicted based on the first group of information. The second group is x2~x30, and the information of x31 is predicted. The information is predicted in turn to obtain the gas concentration time series prediction model of the next time step of the current time. According to one embodiment of the present invention, the method for calculating the required air volume q1 in the working face based on the initial air volume q0 is:

[0065] q1=C 瓦斯1 q0 / C 瓦斯0

[0066] Among them, q1 is the required air volume, m 3 / s;

[0067] C 瓦斯1 is the maximum gas concentration, volume fraction %;

[0068] C 瓦斯0 is the initial gas concentration, volume fraction %;

[0069] q0 is the initial air volume, m 3 / s.

[0070] According to one embodiment of the present invention, the method for increasing the wind speed to the required air volume q1 is:

[0071] By adjusting the ventilation adjustment facilities connected in series with the fully mechanized mining face, including the adjustment windows and the adjustment doors with windows, or the adjustment facilities at other air-using locations connected in parallel with the fully mechanized mining face, the wind speed reaches the required air volume q 1。

[0072] According to one embodiment of the present invention, the fire indicator gas includes CO, C2H6, C2H4, C3H8, C2H2, a mixed gas of C2H4 and C2H6, and a mixed gas of C3H8 and C2H6.

[0073] According to one embodiment of the present invention, a method for determining whether the fire index gas in the goaf exceeds the limit and whether it increases continuously is as follows:

[0074] C 火灾指标气体2 >C max ;

[0075] C 火灾指标气体2 -C 火灾指标气体1 >0 and C 火灾指标气体1 -C 火灾指标气体0 >0;

[0076] Among them, C 火灾指标气体2 is the concentration of the current fire index gas, ppm;

[0077] C 火灾指标气体1 is the fire index gas concentration of the previous prediction period of the time step, ppm;

[0078] C 火灾指标气体0 is the fire indicator gas concentration in ppm for the first two predicted time steps.

[0079] According to one embodiment of the present invention, the method for adjusting the coal cutting speed of the coal shearer is:

[0080] Δv=(C 瓦斯1 q0-C 瓦斯0·q0) / (L·H·w·r)

[0081] v1=v0+Δv

[0082] Wherein Δv is the speed difference of the coal mining machine, m / s;

[0083] q0 is the initial air volume, m 3 / s;

[0084] L is the penetration of each cut of the coal mining machine, m;

[0085] H is the mining height, m;

[0086] r is the specific gravity of coal, t / m 3 ;

[0087] w is the resolvable gas content of the coal in the fully mechanized mining face, m 3 / t;

[0088] v1 is the speed of the coal mining machine after adjustment, m / s;

[0089] v0 is the speed of the coal mining machine before adjustment, m / s.

[0090] In addition, in order to achieve the above-mentioned purpose, the present invention also provides an intelligent control system for gas concentration in a fully mechanized mining face of a low-gas mine. Figure 2 A flow chart schematically shows a gas concentration intelligent control system for a fully mechanized mining face in a low-gas mine according to the present invention, as shown in FIG. Figure 2 As shown, according to the present invention, a gas concentration intelligent control system for a fully mechanized mining face in a low-gas mine comprises:

[0091] Prediction model building module: obtain historical environmental monitoring data, summarize them to form a historical data set, and obtain a gas concentration time series prediction model based on the historical data set through a long short-term memory recurrent neural network time series prediction model;

[0092] Exceeding-limit interval acquisition module: obtains real-time environmental monitoring data, analyzes the real-time environmental monitoring data through the gas concentration time series prediction model, predicts the change of gas concentration, and obtains the exceeding-limit interval of gas concentration;

[0093] Gas concentration judgment module: judge whether the gas concentration exceeds the limit range. If it exceeds, calculate the required air volume q1 in the fully mechanized mining face based on the initial air volume q0;

[0094] Wind speed judgment module: judge whether the wind speed of the fully mechanized mining face exceeds the limit and whether it exceeds the air supply capacity. If so, directly adjust the coal cutting speed of the coal mining machine to maintain the gas concentration within the gas concentration limit range. If not, increase the wind speed to the required air volume q1;

[0095] Index gas judgment module: obtain the fire index gas in the goaf after one adjustment cycle of changing the wind speed to the required air volume q1, and judge whether the fire index gas in the goaf exceeds the limit and whether it increases continuously. If not, continue to monitor the fire index gas. If so, change the air volume to the initial air volume q0 and adjust the coal cutting speed of the coal mining machine.

[0096] According to one embodiment of the present invention, the environmental monitoring data includes:

[0097] The gas sensor data of the fully mechanized mining face, the absolute static pressure sensor data of the fully mechanized mining face and the coal cutting speed of the coal mining machine.

[0098] According to one embodiment of the present invention, a method for obtaining a gas concentration time series prediction model based on a historical data set is as follows:

[0099] The gas concentration time series prediction model is obtained by combining the long short-term memory recurrent neural network time series prediction model with historical environmental monitoring data. According to the predicted time step, the historical data set is cut forward with the current time as the starting point, and N data samples are taken from the historical data set on average and numbered as x1~x N , divide N data samples into M groups of data, the first group is x1~x (M-1) , predict x based on the first set of information M The second group is x2~x M , predict x (M+1) The information is predicted in sequence to obtain the gas concentration time series prediction model for the next time step of the current time.

[0100] According to one embodiment of the present invention, the method for calculating the required air volume q1 in the working surface according to the initial air volume q0 is:

[0101] q1=C 瓦斯1 q0 / C 瓦斯0

[0102] Among them, q1 is the required air volume, m 3 / s;

[0103] C 瓦斯1 is the maximum gas concentration, volume fraction %;

[0104] C 瓦斯0 is the initial gas concentration, volume fraction %;

[0105] q0 is the initial air volume, m 3 / s.

[0106] According to one embodiment of the present invention, the method for increasing the wind speed to the required air volume q1 is:

[0107] By adjusting the ventilation adjustment facilities connected in series with the fully mechanized mining face, including the adjustment windows and the adjustment doors with windows, or the adjustment facilities at other air-using locations connected in parallel with the fully mechanized mining face, the wind speed reaches the required air volume q 1。

[0108] According to one embodiment of the present invention, the fire indicator gas includes CO, C2H6, C2H4, C3H8, C2H2, a mixed gas of C2H4 and C2H6, and a mixed gas of C3H8 and C2H6.

[0109] According to one embodiment of the present invention, a method for determining whether the fire index gas in the goaf exceeds the limit and whether it increases continuously is as follows:

[0110] C 火灾指标气体2 >C max ;

[0111] C 火灾指标气体2 -C 火灾指标气体1 >0 and C 火灾指标气体1 -C 火灾指标气体0 >0;

[0112] Among them, C 火灾指标气体2 is the concentration of the current fire index gas, ppm;

[0113] C 火灾指标气体1 is the fire index gas concentration in the period of the previous prediction time step, ppm;

[0114] C 火灾指标气体0 is the fire indicator gas concentration in ppm for the period of the first two prediction time steps.

[0115] According to one embodiment of the present invention, the method for adjusting the coal cutting speed of the coal shearer is:

[0116] Δv=(C 瓦斯1 q0-C 瓦斯0 ·q0) / (L·H·w·r)

[0117] v1=v0+Δv

[0118] Wherein Δv is the speed difference of the coal mining machine, m / s;

[0119] q0 is the initial air volume, m 3 / s;

[0120] L is the penetration of each cut of the coal mining machine, m;

[0121] H is the mining height, m;

[0122] r is the specific gravity of coal, t / m 3 ;

[0123] w is the resolvable gas content of the coal in the fully mechanized mining face, m 3 / t;

[0124] v1 is the speed of the coal mining machine after adjustment, m / s;

[0125] v0 is the speed of the coal mining machine before adjustment, m / s.

[0126] In order to achieve the above-mentioned purpose of the invention, the present invention also provides an electronic device, which includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the above-mentioned intelligent control method for gas concentration in a comprehensive mining face in a low-gas mine is implemented.

[0127] In order to achieve the above-mentioned purpose of the invention, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned intelligent control method of gas concentration in a comprehensive mining face in a low-gas mine is implemented.

[0128] Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0129] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0130] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0131] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0132] In addition, each functional module in the embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0133] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the energy-saving signal sending / receiving method of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0134] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0135] It should be understood that the size of the serial numbers of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. An intelligent control method for gas concentration in a fully mechanized mining face in a low-gas mine, characterized in that: include: Obtain historical environmental monitoring data, aggregate them into a historical data set, and obtain a gas concentration time series prediction model based on the historical data set through a long short-term memory recurrent neural network time series prediction model; Acquire the real-time environmental monitoring data, analyze the real-time environmental monitoring data through the gas concentration time series prediction model and predict the change of gas concentration to obtain the gas concentration exceeding limit interval; Determine whether the gas concentration exceeds the over-limit interval. If so, calculate the required air volume q1 in the fully mechanized mining face based on the initial air volume q0; Determine whether the wind speed of the fully mechanized mining face exceeds the limit and the air supply capacity. If so, directly adjust the coal cutting speed of the coal mining machine to maintain the gas concentration within the gas concentration over-limit interval. If not, increase the wind speed to the required air volume q1; Obtain the fire index gas in the goaf after one adjustment cycle of changing the wind speed to the required air volume q1, and determine whether the fire index gas in the goaf exceeds the limit and whether it increases continuously. If not, continue to monitor the fire index gas. If so, change the air volume to the initial air volume q0 and adjust the coal cutting speed of the coal mining machine.

2. The method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to claim 1 is characterized in that: The environmental monitoring data include: The gas sensor data of the fully mechanized mining working face, the absolute static pressure sensor data of the fully mechanized mining working face and the coal cutting speed of the coal mining machine.

3. The method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to claim 2 is characterized in that: The method for obtaining the gas concentration time series prediction model according to the historical data set is: The gas concentration time series prediction model is obtained by combining the long short-term memory recurrent neural network time series prediction model with the historical environmental monitoring data. According to the predicted time step, the historical data set is cut forward with the current time as the starting point, and N data samples are taken from the historical data set on average and numbered as x1~x N , divide the N data samples into M groups of data, the first group is x1~x (M-1) , predict x based on the first set of information M The second group is x2~x M , predict x (M+1) The information is predicted in sequence to obtain the gas concentration time series prediction model for the next time step of the current time.

4. The method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to claim 3 is characterized in that: The method for calculating the required air volume q1 in the fully mechanized mining face based on the initial air volume q0 is: q1=C 瓦斯1 ·q0 / C 瓦斯0 Wherein, q1 is the required air volume, m 3 / s; C 瓦斯1 is the maximum gas concentration, volume fraction %; C 瓦斯0 is the initial gas concentration, volume fraction %; q0 is the initial air volume, m 3 / s.

5. The method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to claim 4 is characterized in that: The method for increasing the wind speed to the required air volume q1 is: By adjusting the ventilation adjustment facilities connected in series with the fully mechanized mining face, including the adjustment windows and the adjustment doors with the windows, or the adjustment facilities at other air-using locations connected in parallel with the fully mechanized mining face, the wind speed reaches the required air volume q 1。 6. The method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to claim 5 is characterized in that: The fire indicator gas includes CO, C2H6, C2H4, C3H8, C2H2, a mixed gas of C2H4 and C2H6, and a mixed gas of C3H8 and C2H6.

7. The method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to claim 6 is characterized in that: The method for judging whether the fire index gas in the goaf exceeds the limit and whether it increases continuously is as follows: C 火灾指标气体2 >C max ; C 火灾指标气体2 -C 火灾指标气体1 >0 and C 火灾指标气体1 -C 火灾指标气体0 >0; Among them, C 火灾指标气体2 is the current concentration of the fire index gas, ppm; C 火灾指标气体1 is the fire index gas concentration of the previous prediction period of the time step, ppm; C 火灾指标气体0 is the fire indicator gas concentration in ppm for the first two predicted time steps.

8. The method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine according to claim 7 is characterized in that: In one adjustment cycle τ, C 瓦斯1 , C 瓦斯0 , adjust the coal cutting speed of the coal mining machine according to the following method: Δv=(C 瓦斯1 ·q0-C 瓦斯0 ·q0) / (L·H·w·r) v1=v0+Δv Wherein Δv is the speed difference of the coal mining machine, m / s; q0 is the initial air volume, m 3 / s; L is the penetration of each cut of the coal mining machine, m; H is the mining height, m; r is the specific gravity of coal, t / m 3 ; w is the resolvable gas content of the coal in the fully mechanized mining face, m 3 / t; v1 is the speed of the coal mining machine after adjustment, m / s; v0 is the speed of the coal mining machine before adjustment, m / s.

9. An intelligent control system for gas concentration in fully mechanized mining working faces in low-gas mines, characterized in that: include: Prediction model building module: obtain historical environmental monitoring data, summarize to form a historical data set, and obtain a gas concentration time series prediction model through a long short-term memory recurrent neural network time series prediction model based on the historical data set; An over-limit interval acquisition module: acquires the real-time environmental monitoring data, analyzes the real-time environmental monitoring data through the gas concentration time series prediction model, predicts the change of gas concentration, and obtains the over-limit interval of gas concentration; Gas concentration judgment module: judges whether the gas concentration exceeds the over-limit interval. If it exceeds, the required air volume q1 in the fully mechanized mining face is calculated based on the initial air volume q0; Wind speed judgment module: judge whether the wind speed of the fully mechanized mining face exceeds the limit and whether it exceeds the air supply capacity. If so, directly adjust the coal cutting speed of the coal mining machine to maintain the gas concentration within the gas concentration over-limit interval. If not, increase the wind speed to the required air volume q1; Index gas judgment module: obtain the fire index gas in the goaf after one adjustment cycle of changing the wind speed to the required air volume q1, and judge whether the fire index gas in the goaf exceeds the limit and whether it increases continuously. If not, continue to monitor the fire index gas; if so, change the air volume to the initial air volume q0 and adjust the coal cutting speed of the coal mining machine.

10. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine is implemented as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for intelligently controlling gas concentration in a fully mechanized mining face in a low-gas mine is implemented as described in any one of claims 1 to 8.

Images