Coal mine safety monitoring and early warning method and system based on artificial intelligence

Abstract

The present invention relates to the field of data control technology, and in particular to a coal mine safety monitoring and early warning method and system based on artificial intelligence. The method includes: obtaining the gas concentration sequence of the upwind and downwind outlets in real time during the coal mine collection process; determining the stability of the gas concentration sequence; determining the noise of each data point in the gas concentration sequence of the downwind outlet; determining the correction coefficient of each data point in the gas concentration sequence of the downwind outlet in a preset window during the SG filtering process; performing polynomial fitting according to the correction coefficient during the SG filtering process to obtain the concentration value of the gas concentration sequence of the downwind outlet after filtering; based on the concentration value of the gas concentration sequence of the downwind outlet after filtering, to perform coal mine safety monitoring and early warning based on artificial intelligence. The present invention participates in the SG filtering polynomial fitting process according to the correction coefficient, reduces the influence of noise data on the filtering result, improves the accuracy of the gas concentration sequence, and ensures the safety of the coal mine collection process.

Description

Technical Field

[0001] The present invention relates to the field of data control technology, and in particular to a coal mine safety monitoring and early warning method and system based on artificial intelligence. Background Art

[0002] During coal mining, coal seams and surrounding rock formations will release methane and other gasses. If ventilation is poor or the exhaust system fails, when the gas concentration increases to the critical explosion value, it will cause a gas explosion once it encounters a fire source or electric spark. In order to effectively reduce the occurrence of such accidents in coal mine production, an IoT sensing library can be built in the emergency management information platform to conduct safety monitoring and early warning of coal mines based on the monitoring data of coal mine gas concentration in the IoT sensing library.

[0003] The patent application document with publication number CN116820036A discloses a coal mine safety production monitoring method based on OPC UA, which uses the OPC UA Internet of Things terminal to collect and analyze the data fed back by the camera terminal and the machine motion detection terminal of each excavator robot, and realizes the linkage control of the excavator robot in each working sub-area, so that different excavator robots can be dispatched accordingly between different working sub-areas, ensuring that the excavator robots can carry out continuous mining and excavation in a safe working environment, thereby improving the overall mining efficiency of coal mining and the safety of mining work.

[0004] However, the above document mainly determines whether the operation sub-area belongs to the safe operation sub-area based on the wall structure information of the area, and does not monitor the gas. Savitzky-Golay (SG) filtering can usually be used to smooth the gas concentration data collected by the gas sensor to better analyze the changes in gas concentration based on the overall shape and trend of the gas data. However, due to the influence of the environment in which the gas sensor is located, there will be a certain amount of noise data in the collected gas data. For highly random noise, SG filtering cannot effectively remove it, which affects the judgment of gas concentration concentration and reduces the accuracy of coal mine safety monitoring and early warning. Summary of the invention

[0005] In order to solve the problem that SG filtering cannot effectively remove highly random noise, which affects the judgment of gas concentration and reduces the accuracy of coal mine safety monitoring and early warning, the present invention provides a coal mine safety monitoring and early warning method and system based on artificial intelligence.

[0006] In the first aspect, the present invention provides a coal mine safety monitoring and early warning method based on artificial intelligence, which adopts the following technical solutions:

[0007] The gas concentration sequence of the upwind and downwind outlets during coal mine collection is obtained in real time; the stability of the gas concentration sequence is determined, which is positively correlated with the concentration mean of the upwind and downwind concentration data sequences, and negatively correlated with the concentration mean of the data points in the upwind and downwind outlets that are greater than the concentration mean of the gas concentration sequence; the noise of each data point in the gas concentration sequence of the downwind outlet is determined, which is related to the concentration value of the data point in the gas concentration sequence of the downwind outlet corrected according to the wind speed value and the concentration of the data point in the gas concentration sequence of the upwind outlet corresponding to the data point. The correction coefficient of each data point in the gas concentration sequence of the downwind outlet in the preset window during the SG filtering process is determined, and the correction coefficient is negatively correlated with the difference between the concentration value of the data point and the preset concentration standard value of the gas concentration sequence, and the noise of the data point; in the SG filtering process, polynomial fitting is performed based on the correction coefficient to obtain the concentration value of the gas concentration sequence of the downwind outlet after filtering; according to the concentration value of the gas concentration sequence of the downwind outlet after filtering, coal mine safety monitoring and early warning based on artificial intelligence are performed.

[0008] The beneficial effects are: real-time acquisition and processing of gas concentration sequences at upwind and downwind outlets can quickly identify potential safety hazards and provide timely warnings; by analyzing the stability and noise of the gas concentration sequence, the changes in the coal mine environment can be understood, providing a more reliable basis for subsequent decision-making; by performing polynomial fitting based on the correction coefficient during the SG filtering process, noise can be effectively removed, the reliability of the data can be enhanced, and the accuracy of gas concentration monitoring can be improved.

[0009] Furthermore, the stability satisfies the following relationship:

[0010] ; In the formula, is the stationarity of the gas concentration series, is the mean value of the concentration data sequence of the gas concentration sequence at the upwind outlet, is the mean value of the concentration data sequence of the gas concentration sequence at the downwind outlet, For the upwind area, it is greater than The mean concentration of the data points, Greater than The mean concentration of the data points, is the maximum value of the data points in the gas concentration sequence at the upwind and downwind outlets, is a natural exponential function.

[0011] The beneficial effects are: by providing a quantitative indicator through the degree of stability, it is convenient for systematic evaluation of the stability of gas concentration; by comparing the mean concentrations of the upwind and downwind outlets, abnormal changes in gas concentration can be identified more accurately, providing a reliable basis for subsequent monitoring and early warning.

[0012] Furthermore, the noise property satisfies the following relationship:

[0013] ; In the formula, is the gas concentration sequence at the downwind outlet. The noise of the data points, is the stationarity of the gas concentration series, is the gas concentration sequence of the downwind outlet. The concentration value of the data point in the gas concentration sequence at the upwind outlet corresponding to the data point, is the gas concentration sequence at the downwind outlet. The concentration value of the data point, is the gas concentration sequence at the downwind outlet. The wind speed value corresponding to the data point is is the maximum value of the wind speed values ​​corresponding to all data points in the gas concentration sequence at the downwind outlet, It is the maximum value of the data points in the gas concentration series at the upwind and downwind outlets.

[0014] The beneficial effects are: by evaluating the impact of wind speed on noise, the impact of environmental conditions on the stability of gas concentration can be more accurately determined and the monitoring strategy can be optimized; the noise level of each data point can be accurately quantified, which facilitates the identification of data quality and improves the reliability of overall monitoring.

[0015] Furthermore, the correction coefficient satisfies the following relationship:

[0016] ; In the formula, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The correction factor for each data point, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The noise of the data points, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The concentration value of the data point, It is the preset concentration standard value of the gas concentration series. is the natural exponential function, is the hyperbolic tangent function.

[0017] The beneficial effect is that the correction coefficient is adjusted according to the noise of each data point, so that when the noise is large, the correction coefficient is reduced, thereby enhancing the robustness of data processing. Combined with the characteristics of the hyperbolic tangent function, the correction coefficient can increase the weight when the data point is close to the mean of the concentration range of the preset gas concentration sequence, thereby more effectively smoothing the data and reducing the impact of abnormal fluctuations.

[0018] Furthermore, the polynomial fitting is performed by least squares method.

[0019] Furthermore, the polynomial fitting by least square method includes: in the process of polynomial fitting by least square method, when obtaining the residual of least square fitting, fitting is performed using the correction coefficient as the weight of the data point.

[0020] The beneficial effects are: the correction coefficient can adjust its weight according to the noisiness of the data point, so that more reliable data has a greater impact on the fitting result, thereby improving the fitting accuracy; by adjusting the square error, the interference of noisy data points on the fitting is reduced, ensuring that the fitting model can better reflect the real trend.

[0021] Furthermore, the artificial intelligence-based coal mine safety monitoring and early warning is performed based on the concentration value of the gas concentration sequence at the downwind outlet after filtering, including: in response to the fact that the concentration values ​​of the data point in the gas concentration sequence at the downwind outlet after filtering corresponding to the current moment and multiple consecutive data points before it are greater than the concentration threshold, it is determined that the current gas concentration exceeds the standard, and the alarm system is controlled to issue a warning prompt, thereby completing the artificial intelligence-based coal mine safety monitoring and early warning.

[0022] In the second aspect, the present invention provides a coal mine safety monitoring and early warning system based on artificial intelligence, which adopts the following technical solutions:

[0023] The coal mine safety monitoring and early warning system based on artificial intelligence includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned coal mine safety monitoring and early warning method based on artificial intelligence is implemented.

[0024] By adopting the above technical solution, the above-mentioned artificial intelligence-based coal mine safety monitoring and early warning method is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made based on the memory and the processor for easy use.

[0025] The present invention has the following technical effects:

[0026] The stability of the gas concentration sequence is determined according to the concentration value of each data point in the gas concentration sequence of the upwind and downwind outlets, and the overall change of the gas concentration sequence in the coal mine scene under general circumstances is measured to reduce the impact of normal fluctuations in the gas concentration sequence on data noise; the noise of each data point in the real-time gas concentration sequence is calculated according to the stability of the gas concentration sequence and the difference between the concentration value of the data point in the gas concentration sequence of the upwind outlet and the concentration value of the data point in the gas concentration sequence of the downwind outlet, and the possibility that the data point in the gas concentration sequence is noise data is more accurately measured; the correction coefficient of the gas concentration sequence is determined according to the noise of each data point in the gas concentration sequence and the concentration value of each data point, and then the polynomial fitting process of the SG filter is involved according to the correction coefficient to reduce the impact of noise data on the filtering result and obtain a more accurate gas concentration sequence; finally, the coal mine safety monitoring and early warning are carried out through the more accurate concentration value of the gas concentration sequence of the downwind outlet after filtering, which improves the accuracy of coal mine safety monitoring and early warning and ensures the safety of the coal mine collection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0028] Figure 1 It is a method flow chart of the coal mine safety monitoring and early warning method based on artificial intelligence in an embodiment of the present invention.

[0029] Figure 2 It is a schematic diagram of the arrangement positions of gas sensors in the coal mine safety monitoring and early warning method based on artificial intelligence in an embodiment of the present invention.

[0030] Figure 3 It is the first gas concentration sequence of the downwind outlet in the coal mine safety monitoring and early warning method based on artificial intelligence in the embodiment of the present invention. Schematic diagram of the time difference between the corresponding moments of the data points when located at the upwind side. DETAILED DESCRIPTION

[0031] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0033] The embodiment of the present invention discloses a coal mine safety monitoring and early warning method based on artificial intelligence, referring to Figure 1 , comprising steps S1 to S6:

[0034] S1: Real-time acquisition of gas concentration sequences at the upwind and downwind outlets during coal mine collection.

[0035] In the coal mine, a gas sensor is arranged at each of two interconnected locations with the same wind direction (the specific location of the sensor is not limited, but the two locations are required to have the same wind direction, that is, one location is at the upwind outlet and the other location is at the downwind outlet, and the distance between them is at least 5 meters, see Figure 2 ), collect gas concentration sequence (i.e. the sequence of concentration data from history to the present, with the collection frequency of data points in the sequence being 1s / time).

[0036] S2: Determine the stability of the gas concentration series.

[0037] It should be noted that during the coal mining process, gas is occasionally released and its concentration is displayed by the gas sensor. Due to the effect of the coal mine ventilation system, the detected gas concentration will fluctuate. In order to reduce its determination of the noise value in the gas concentration sequence, the stability of the gas concentration sequence is calculated based on the concentration values ​​of the data points of the gas concentration sequence.

[0038] Specifically, the stability satisfies the following relationship:

[0039] ;

[0040] In the formula, is the stationarity of the gas concentration series, is the mean value of the concentration data sequence of the gas concentration sequence at the upwind outlet, is the mean value of the concentration data sequence of the gas concentration sequence at the downwind outlet, For the upwind area, it is greater than The mean concentration of the data points, Greater than The mean concentration of the data points, is the maximum value of the data points in the gas concentration sequence at the upwind and downwind outlets, is a natural exponential function.

[0041] in, It is the difference between the average value of the higher gas concentration collected by the gas sensor at the upper air outlet and the average value of the gas concentration. Since the appearance of noise data is an occasional phenomenon, this value can, to a certain extent, indicate the prominence of the gas concentration when the gas is released in the coal mine. The larger the value, the more prominent the gas concentration is when the gas release occurs, and the lower the stability of the gas concentration series. The smaller the value, the less prominent the gas concentration is when the gas release occurs, and the higher the stability of the gas concentration series. In order to facilitate the calculation, right Normalize it and get ;for The principle is similar and will not be elaborated here. In order to avoid the randomness of gas diffusion and the impact on the stability of the gas concentration sequence, and The average To measure the prominence of gas concentration when gas is released during coal mining, and then Get the stationarity of the gas concentration series.

[0042] S3: Determine the noise characteristics of each data point in the gas concentration sequence at the downwind outlet.

[0043] It should be noted that since the noise data in the data will have an adverse effect on the data processing results, in order to apply appropriate correction coefficients to different data and better utilize the characteristics of SG filtering to process data, the noise of the real-time gas concentration sequence is calculated based on the stability of the gas concentration sequence and the gap between the gas concentration sequences collected by sensors at different locations, as well as the wind speed value and the maximum wind speed value at the downwind outlet (the wind speed value is obtained by setting a wind speed sensor at a position adjacent to the gas sensor); the downwind outlet is usually the main area for gas diffusion, so monitoring the gas concentration sequence at the downwind outlet can more accurately reflect the changes in gas concentration, thereby helping to assess the safety status of the environment. By focusing on the data at the downwind outlet, the monitoring resource allocation can be optimized and the efficiency and accuracy of data analysis can be improved.

[0044] Specifically, the noise property satisfies the following relationship:

[0045] ;

[0046] In the formula, is the gas concentration sequence at the downwind outlet. The noise of the data points, is the stationarity of the gas concentration series, is the gas concentration sequence of the downwind outlet. The concentration value of the data point in the gas concentration sequence at the upwind outlet corresponding to the data point, is the gas concentration sequence at the downwind outlet. The concentration value of the data point, is the gas concentration sequence at the downwind outlet. The wind speed value corresponding to the data point is is the maximum value of the wind speed values ​​corresponding to all data points in the gas concentration sequence at the downwind outlet, It is the maximum value of the data points in the gas concentration series at the upwind and downwind outlets.

[0047] Among them, Figure 3 As shown, is the gas concentration sequence of the downwind outlet. The concentration value of the data point in the gas concentration sequence of the upwind outlet corresponding to the data point is calculated by the gas concentration sequence of the downwind outlet. Data points corresponding to the time Subtract the distance between the upper and lower air outlets and the gas concentration sequence at the downwind outlet The wind speed value corresponding to the data point The ratio of At the moment, the concentration value of the data point in the gas concentration sequence of the upwind outlet corresponding to the moment is the value of the data point in the gas concentration sequence of the downwind outlet. The concentration value of the data point in the gas concentration sequence at the upwind outlet corresponding to the data point; because the gas has a certain diffusion effect under the action of wind, when the gas is transmitted from the upwind outlet to the downwind outlet, its concentration will be diluted to a certain extent. In order to measure the difference between the concentration of the gas at the upwind outlet and the concentration at the downwind outlet, right Make an upward correction when When the value is larger, the wind speed is higher, and the gas is more likely to be diluted when it is transmitted to the downwind outlet, so it should be corrected upward. ,when The smaller the wind speed, the lower the possibility of gas being diluted when it is transmitted to the downwind outlet. The smaller the degree of the gas concentration, the corrected gas concentration at the downwind outlet can be obtained. ; is the gas concentration sequence at the downwind outlet. The concentration value of the data point and the The difference in the concentration values ​​of the data points of the gas concentration sequence of the upwind outlet corresponding to the data points. Since the appearance of noise data is sporadic, when the gas is transmitted to the upwind outlet and the downwind outlet, the possibility that the noise data collected is noise at the same time is extremely low. Therefore, the larger the value, the greater the possibility that there is noise data in the two data, and the smaller the value, the smaller the possibility that there is noise data in the two data. For the convenience of calculation, here we divide by The way to Normalization is performed; because the gas concentration sequence has a certain volatility under normal circumstances, it may affect the judgment of the noise of the gas concentration sequence, so right Make corrections, The smaller it is, the less stable the change of gas concentration series is. When noise data appears, it is less likely to be found. Due to the danger of gas in coal mine scenarios, it is necessary to more carefully measure whether the data is noise data. The smaller the right The greater the degree of correction, the greater the noise of the gas concentration series. The larger the The closer it is to 1, the The closer , because the more stable the change of gas concentration series is, the easier it is to detect when noise data appears, so there is no need to Make a major correction.

[0048] S4: Determine the correction coefficient of each data point in the gas concentration sequence of the downwind outlet within the preset window during the SG filtering process.

[0049] It should be noted that during the SG filtering process, a polynomial fitting will be performed on the data in the preset window. However, the presence of noise data will make the gas concentration sequence after filtering have certain inaccuracies. Controlling the ventilation system, i.e., the alarm system, in the coal mine through the inaccurate gas concentration sequence filtering results will cause false alarms or missed alarms. To avoid this situation, the correction coefficient of each data point of the gas concentration sequence at the downwind outlet is calculated based on the noise and concentration value of the real-time gas concentration sequence.

[0050] Specifically, the correction coefficient satisfies the following relationship:

[0051] ;

[0052] In the formula, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The correction factor for each data point, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The noise of the data points, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The concentration value of the data point, It is the preset concentration standard value of the gas concentration series. is the natural exponential function, is the hyperbolic tangent function.

[0053] Implementers can set the window size and concentration standard value according to specific implementation conditions. For example, the window size is 7 and the concentration standard value is 0.8.

[0054] Among them, the noise of the gas concentration series The larger the value, the The more likely a data point is noise data, the smaller the influence of the square error corresponding to the data on the final result should be during the subsequent fitting. The smaller the correction coefficient of the square difference corresponding to the data is, The smaller the The smaller the possibility that a data is noise data, the greater the influence of the square error corresponding to the data on the final result in the subsequent fitting. The larger the correction coefficient of the square difference corresponding to the data is, the larger the correction coefficient of the square difference is. It measures the possibility of noise in the noise data collected at the downwind outlet and its corresponding upwind outlet data (noise), that is, When larger, It may not be noise data, so by right Make corrections, The larger the The more likely it is to be greater than 1, the greater the gap between the data collected by the gas sensor at the downwind outlet and the average level of the gas concentration sequence. The more likely it is noise data, so The bigger it is, right Play a downward correction role, so that the window The smaller the correction coefficient of the square error corresponding to each data is, the The smaller the impact on the fitting results, The smaller the The more likely it is to be less than 1, the smaller the gap between the data collected by the downwind sensor and the average level of the gas concentration sequence is. The more likely it is not noise data, so The more hours, right Play an upward correction role, so that the window The larger the correction coefficient of the square error corresponding to each data is, the The greater the impact on the fitting results.

[0055] S5: During the SG filtering process, polynomial fitting is performed according to the correction coefficient to obtain the concentration value of the gas concentration sequence at the downwind outlet after filtering.

[0056] Specifically, the polynomial fitting is performed by least square method.

[0057] Specifically, the polynomial fitting by the least square method includes:

[0058] In the process of fitting the polynomial using the least square method, the correction coefficient is used as the weight of the data point for fitting when obtaining the residual of the least square fitting.

[0059] S6: Based on the concentration value of the gas concentration sequence at the downwind outlet after filtering, artificial intelligence-based coal mine safety monitoring and early warning can be carried out.

[0060] Specifically, the coal mine safety monitoring and early warning based on artificial intelligence is performed according to the concentration value of the gas concentration sequence at the downwind outlet after filtering, including:

[0061] In response to the fact that the data point in the gas concentration sequence of the filtered downwind outlet corresponding to the current moment and the concentration values ​​of multiple consecutive data points before it are all greater than the concentration threshold, it is determined that the current gas concentration exceeds the standard, and the alarm system is controlled to issue a warning prompt, thereby completing the coal mine safety monitoring and early warning based on artificial intelligence; wherein, when the alarm system is controlled to issue a warning prompt, the ventilation system in the coal mine is also controlled to accelerate the dissipation of gas. If the concentration value still exceeds the gas concentration standard after adjusting the ventilation system, the alarm system is controlled to issue an evacuation alarm to remind on-site personnel to evacuate.

[0062] Implementers can set the specific number of previous consecutive data points and the concentration threshold according to the specific implementation situation. For example, the previous consecutive data points are 59 and the concentration threshold is 1% (i.e. 10,000 ppm).

[0063] An embodiment of the present invention also discloses an artificial intelligence-based coal mine safety monitoring and early warning system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the artificial intelligence-based coal mine safety monitoring and early warning method according to the present invention is implemented.

[0064] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0065] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0066] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0067] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A coal mine safety monitoring and early warning method based on artificial intelligence, characterized in that: include: Real-time acquisition of gas concentration sequences at the upwind and downwind outlets during coal mining; Determine the stability of the gas concentration sequence, which is positively correlated with the mean concentration of the concentration data series of the upwind and downwind outlets, and negatively correlated with the mean concentration of the data points in the upwind and downwind outlets that are greater than the mean concentration of the gas concentration sequence; determine the noise of each data point in the gas concentration sequence of the downwind outlet, which is positively correlated with the difference between the concentration value of the data point in the gas concentration sequence of the downwind outlet corrected according to the wind speed value and the concentration value of the data point in the gas concentration sequence of the upwind outlet corresponding to the data point, and negatively correlated with the stability; Determine the correction coefficient of each data point in the gas concentration sequence of the downwind outlet in the preset window during the SG filtering process. The correction coefficient is negatively correlated with the difference between the concentration value of the data point and the preset concentration standard value of the gas concentration sequence, and the noise of the data point; In the SG filtering process, polynomial fitting is performed according to the correction coefficient to obtain the concentration value of the gas concentration sequence at the downwind outlet after filtering; The degree of stability satisfies the following relationship: ; In the formula, is the stationarity of the gas concentration series, is the mean value of the concentration data sequence of the gas concentration sequence at the upwind outlet, is the mean value of the concentration data sequence of the gas concentration sequence at the downwind outlet, For the upwind area, it is greater than The mean concentration of the data points, Greater than The mean concentration of the data points, is the maximum value of the data points in the gas concentration sequence at the upwind and downwind outlets; The noise property satisfies the following relationship: ; In the formula, The gas concentration in the downwind outlet is The noise of the data points, is the gas concentration sequence of the downwind outlet. The concentration value of the data point in the gas concentration sequence at the upwind outlet corresponding to the data point, is the gas concentration sequence at the downwind outlet. The concentration value of the data point, is the gas concentration sequence at the downwind outlet. The wind speed value corresponding to the data point is It is the maximum value of the wind speed values ​​corresponding to all data points of the gas concentration sequence at the downwind outlet; The correction coefficient satisfies the following relationship: ; In the formula, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The correction factor for each data point, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The noise of the data points, The gas concentration sequence of the downwind outlet in the preset window during SG filtering. The concentration value of the data point, It is the preset concentration standard value of the gas concentration series; According to the concentration value of the gas concentration sequence at the downwind outlet after filtering, coal mine safety monitoring and early warning based on artificial intelligence are carried out.

2. The coal mine safety monitoring and early warning method based on artificial intelligence according to claim 1 is characterized in that: The polynomial fitting is performed by least square method.

3. The coal mine safety monitoring and early warning method based on artificial intelligence according to claim 2 is characterized in that: The polynomial fitting is performed by the least square method, comprising: In the process of fitting the polynomial using the least square method, the correction coefficient is used as the weight of the data point for fitting when obtaining the residual of the least square fitting.

4. The coal mine safety monitoring and early warning method based on artificial intelligence according to claim 1 is characterized in that: The coal mine safety monitoring and early warning based on artificial intelligence is performed according to the concentration value of the gas concentration sequence at the downwind outlet after filtering, including: In response to the fact that the data point in the gas concentration sequence of the filtered downwind outlet corresponding to the current moment and the concentration values ​​of multiple consecutive data points before it are greater than the concentration threshold, it is determined that the current gas concentration exceeds the standard, and the alarm system is controlled to issue a warning prompt, completing the coal mine safety monitoring and early warning based on artificial intelligence.

5. The coal mine safety monitoring and early warning system based on artificial intelligence is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the coal mine safety monitoring and early warning method based on artificial intelligence according to any one of claims 1 to 4 is implemented.

Images