Method and system for judging spontaneous combustion dangerous area of goaf of coal face

Abstract

The invention provides a method and a system for judging a spontaneous combustion dangerous area of a goaf of a coal face, and relates to the technical field of coal mine safety monitoring. Geographic information system software is used for generating an initial geographic map, and a regular three-dimensional grid is created on the basis of the initial geographic map; accurate positioning and data consistency management of the goaf of the coal face are effectively realized, the abnormal sampling points can be accurately identified by setting a specific wavelength range, capturing spectral data of each sampling point by using an infrared spectrum and calculating the relative radiation intensity and the radiation deviation degree of each sampling point, and the accuracy of the abnormal sampling points is improved. Through obtaining neighbor sampling point data of an abnormal sampling point, calculating a uniform distribution index, realizing risk grade marking of the abnormal sampling point, comprehensively considering distribution density, relative radiation intensity and geographic position information of the abnormal sampling point, and generating a spontaneous combustion risk index, comprehensive assessment and timely early warning of goaf spontaneous combustion risk are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine safety monitoring, and in particular to a method and system for determining a spontaneous combustion hazard zone in a goaf of a coal mining face. Background Art

[0002] The goaf of a coal mining face refers to the empty area left after the coal resources have been mined during the coal mining process. This area may have gaps formed by stratum movement or collapse. Due to the lack of support, these areas are prone to accumulate gas and coal seam gas, which can easily cause safety problems such as spontaneous combustion or collapse. Therefore, in the process of modern coal mining, the goaf of a coal mining face faces major safety hazards due to the spontaneous combustion potential of the coal seam. The accumulation of gas and coal seam gas in the goaf, especially in the case of poor ventilation, can easily cause spontaneous combustion. This spontaneous combustion not only leads to a waste of coal resources, but also produces toxic and harmful gases, threatening the lives of miners and the normal production of coal mines. Therefore, how to effectively monitor and prevent spontaneous combustion in goafs has become an important issue in coal mine safety management.

[0003] Existing technologies mainly rely on the experience and judgment of miners and some simple monitoring equipment, such as temperature sensors and gas detectors. Although these devices can detect the early signs of spontaneous combustion to a certain extent, they have problems such as low monitoring accuracy, slow response speed and limited coverage. Some modern coal mines have tried to introduce infrared thermal imaging technology and gas analyzers for monitoring, but these methods often require complex equipment and high costs. In addition, in complex mine environments, data acquisition and processing are difficult, making it difficult to achieve real-time monitoring and accurate evaluation.

[0004] Compared with the method proposed in this application, the existing technology has obvious shortcomings. First, it is difficult to achieve comprehensive coverage of the entire goaf by relying on experience and simple monitoring equipment, and it is easy to miss potential spontaneous combustion points. Secondly, although technologies such as infrared thermal imaging have high monitoring accuracy in some cases, their data processing and analysis are less systematic, and it is difficult to comprehensively consider multiple factors for comprehensive evaluation. Furthermore, most of the data processing methods in the existing technology are relatively simple and cannot effectively integrate multi-dimensional information such as spatial position, radiation intensity and time change, resulting in low accuracy and reliability of spontaneous combustion risk assessment. Therefore, there is an urgent need for a method that can integrate geographic information systems, near-infrared spectral analysis and risk assessment models to achieve accurate judgment and real-time early warning of spontaneous combustion risk areas in goafs of coal mining faces.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for determining the spontaneous combustion risk zone in the goaf of a coal mining face, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for determining a spontaneous combustion hazard zone in a goaf of a coal mining face, the specific steps comprising:

[0009] Step 1: Use geographic information system software to import geographic information data of the goaf of the coal mining face to be determined to generate an initial geographic map, create a regular grid in the initial geographic map, take each grid intersection as a sampling point, obtain the geographic location information of the sampling points, and number them, collect the dielectric constant of each sampling point, and determine the signal enhancement sampling point;

[0010] Step 2: Capture the spectral data of each sampling point, set the wavelength analysis range, record the spectral intensity of each sampling point within the wavelength analysis range, map it with the geographical location information of each sampling point, and normalize the spectral intensity data of all sampling points;

[0011] Step 3: Calculate the relative radiation intensity of each sampling point based on the spectral intensity data of the normalized sampling points, calculate the mean and standard deviation of the relative radiation intensity of all sampling points, generate the radiation deviation degree of each sampling point, and identify the abnormal sampling points among the signal enhancement sampling points based on the radiation deviation degree of the sampling points;

[0012] Step 4: Obtain the relative radiation intensity of the neighboring sampling points of the abnormal sampling point in each signal enhancement sampling point, calculate the uniform distribution index of each abnormal sampling point, and mark the risk level of the abnormal sampling point according to the uniform distribution index;

[0013] Step 5: Based on the distribution density of all marked abnormal sampling points in the initial geographic map, as well as the relative radiation intensity data and geographic location information of each marked abnormal sampling point, a risk assessment model is constructed to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged, and the spontaneous combustion risk of the goaf is judged based on the spontaneous combustion risk index.

[0014] Furthermore, the logic for determining the signal enhancement sampling point is:

[0015] Use geological radar or electromagnetic detector to collect dielectric constant data of each sampling point, import the collected dielectric constant data into geographic information system software, associate it with the geographical location information of the sampling point, set the threshold of dielectric constant, and use points less than this value as signal enhancement sampling points.

[0016] Furthermore, the geographic information data of the goaf of the coal mining face includes the shape, range and elevation data of the goaf, as well as the geographic coordinate data of the goaf. The geographic location information of the sampling point is obtained specifically as follows:

[0017] Import the collected goaf shape, range, elevation and geographic coordinate data into the GIS software, ensuring that all imported data sets use a unified coordinate system. If they are inconsistent, perform coordinate system conversion;

[0018] Use the goaf shape data to crop the elevation data to ensure that only the goaf area is retained, set the size and range of the grid, generate a regular grid according to analysis requirements, cover the goaf, extract the grid intersections as sampling points, and record their geographic location information. The grid is a three-dimensional grid.

[0019] Furthermore, the wavelength analysis range set when recording the spectral intensity of each sampling point is 900nm to 1000nm, and the specific logic of normalizing the spectral intensity data of all sampling points is as follows:

[0020] Obtain the spectral intensity of each sampling point in the wavelength range of 900nm to 1000nm, and calculate the maximum and minimum values ​​of the spectral intensity of all sampling points in the wavelength range of 900nm to 1000nm, specifically:

[0021] I max =max[Iq1, Iq2, ..., Iq i ,…,I qn ]

[0022] I min =min[Iq1, Iq2, ..., Iq i ,…,I qn ]

[0023] Among them, I max and I min Respectively represent the maximum and minimum values ​​of the spectral intensity in the wavelength range of 900nm to 1000nm at the sampling point, Iq i It represents the spectral intensity data of the sampling point numbered i before normalization in the wavelength range of 900nm to 1000nm, i represents the number of the sampling point, and n represents the total number of sampling points;

[0024] The spectral intensity of all sampling points in the wavelength range of 900nm to 1000nm is scaled to the range of [0, 1], specifically:

[0025]

[0026] I iRepresents the spectral intensity data of the sampling point numbered i after normalization in the wavelength range of 900nm to 1000nm.

[0027] Furthermore, the logic for calculating the relative radiation intensity of each sampling point is:

[0028]

[0029] Among them, R i is the relative radiation intensity of the sampling point numbered i, I b Indicates the baseline radiation intensity, which means the radiation intensity between 900nm and 1000nm when there is no spontaneous combustion phenomenon at the same temperature and pressure intensity;

[0030] When generating the radiation offset degree of each sampling point, first calculate the relative radiation intensity mean and standard deviation of all sampling points, and use the z-score method to generate the radiation offset degree of each sampling point. The formula is:

[0031]

[0032] Among them, μ R and σ R Respectively represent the relative radiation intensity mean and standard deviation of all sampling points, z i Indicates the degree of radiation deviation of the sampling point numbered i. i |>z y , and when the point is a signal enhancement sampling point, the sampling point numbered i is identified as an abnormal sampling point, z y Indicates the offset threshold.

[0033] Furthermore, the neighbor sampling points of the abnormal points in the signal enhancement sampling points are the sampling points directly adjacent to the abnormal sampling points, including the directly adjacent sampling points in six directions of up and down, left and right, and front and back in the grid. The formula for calculating the uniform distribution index of each abnormal point is:

[0034]

[0035] Among them, μz j and σz j Respectively represent the mean and variance of the relative radiation intensity of the data set composed of the abnormal sampling point numbered j and its adjacent sampling points. If j Represents the uniform distribution index of the abnormal sampling point numbered j, R j , Rs j , Rx j , Rz j , Ry j , Rq j and Rh jRespectively represent the relative radiation intensity of the abnormal sampling point numbered j and the six sampling points above, below, left, right, front and back. If the abnormal sampling point does not have at least one neighbor sampling point among the six sampling points above, below, left, right, front and back, the relative radiation intensity of the sampling point is set to 0;

[0036] When marking the risk level of abnormal points according to the uniform distribution index, if Jf j >Jf y , then the abnormal sampling point is marked as a high-risk sampling point and marked, otherwise the sampling point is marked as a low-risk sampling point and not marked, Jf y represents the uniform distribution threshold, and j represents the number of the abnormal sampling point in the signal enhancement sampling point.

[0037] Furthermore, according to the distribution density of all marked abnormal sampling points in the initial geographic map, the number of all sampling points and the number of marked abnormal sampling points are counted to calculate the distribution density of the abnormal sampling points in the initial geographic map, specifically:

[0038]

[0039] Among them, ρ y is the distribution density of abnormal sampling points in the initial geographic map, n represents the total number of sampling points, and M represents the number of marked abnormal sampling points.

[0040] Furthermore, the specific logic of constructing a risk assessment model to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged is as follows:

[0041] According to the geographical location information of each marked abnormal sampling point, its distance from the center of the coal mining face is calculated, and the risk assessment model is constructed by combining the distribution density of the abnormal sampling points in the initial geographical map and the relative radiation intensity data of the marked abnormal sampling points. The formula is:

[0042]

[0043] Where RI represents the spontaneous combustion risk index, d m and Jf m They respectively represent the distance and relative radiation intensity between the marked abnormal sampling point numbered m and the center of the coal mining face, ∈ represents the denominator constant, and ∈>0, m represents the number of the marked abnormal sampling point, and e represents the base of the natural logarithm.

[0044] Furthermore, when judging the spontaneous combustion risk of the goaf based on the spontaneous combustion risk index, if RI ≥ RI y , judge that the risk of spontaneous combustion in the goaf is high and issue an early warning. <RI y , the risk of spontaneous combustion in the goaf is judged to be low, and no warning is issued, RIy Indicates the spontaneous combustion risk threshold.

[0045] The present invention further provides a system for determining the spontaneous combustion hazard zone in the goaf of a coal mining face, the system being used to execute the method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face, comprising:

[0046] The geographic map creation module is used to generate an initial geographic map by importing the geographic information data of the goaf of the coal mining face to be determined using the geographic information system software, create a regular grid in the initial geographic map, take each grid intersection as a sampling point, obtain the geographic location information of the sampling points, number them, collect the dielectric constant of each sampling point, and determine the signal enhancement sampling points;

[0047] The preprocessing module is used to capture the spectral data of each sampling point, set the wavelength analysis range, record the spectral intensity of each sampling point within the wavelength analysis range, map it with the geographical location information of each sampling point, and normalize the spectral intensity data of all sampling points;

[0048] The abnormality identification module is used to calculate the relative radiation intensity of each sampling point, the mean and standard deviation of the relative radiation intensity of all sampling points, generate the radiation offset degree of each sampling point, and identify the abnormal sampling points among the signal enhancement sampling points according to the radiation offset degree of the sampling points.

[0049] A risk assessment module is used to obtain the relative radiation intensity of the neighboring sampling points of the abnormal sampling point in each signal enhancement sampling point, calculate the uniform distribution index of each abnormal sampling point, and mark the risk level of the abnormal sampling point according to the uniform distribution index;

[0050] The comprehensive judgment module is used to construct a risk assessment model based on the distribution density of all marked abnormal sampling points in the initial geographic map, as well as the relative radiation intensity data and geographic location information of each marked abnormal sampling point, to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged, and judge the spontaneous combustion risk of the goaf based on the spontaneous combustion risk index.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention generates an initial geographic map using geographic information system software, and creates a regular three-dimensional grid based on this, thereby effectively realizing the precise positioning of the goaf area of ​​the coal mining face and data consistency management. By setting a specific wavelength range, using infrared spectrum to capture the spectral data of each sampling point, and performing normalization processing, the comparability and consistency of the data are ensured, thereby enhancing the analysis accuracy. In particular, by calculating the relative radiation intensity and radiation deviation degree of each sampling point, the abnormal sampling points in the signal enhancement sampling points can be accurately identified.

[0053] The present invention obtains the neighboring sampling point data of the abnormal sampling point in the signal enhancement sampling point, calculates the uniform distribution index, and realizes the risk level marking of the abnormal sampling point. This method not only takes into account the abnormal situation of the individual sampling point, but also integrates the data consistency of the adjacent area, greatly improving the reliability and accuracy of the risk assessment. Finally, by constructing a risk assessment model, the distribution density, relative radiation intensity and geographical location information of the abnormal sampling points are comprehensively considered to generate a spontaneous combustion risk index, which realizes a comprehensive assessment and timely warning of the spontaneous combustion risk of the goaf. By realizing accurate judgment and real-time warning of the spontaneous combustion risk of the goaf, the safety hazards in the coal mine production process are effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0055] Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0057] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0058] Example:

[0059] See also Figure 1 , the present invention provides a technical solution:

[0060] A method for determining a spontaneous combustion hazard zone in a goaf of a coal mining face, the specific steps comprising:

[0061] Step 1: Use geographic information system software to import the geographic information data of the goaf of the coal mining face to be judged to generate an initial geographic map, create a regular grid in the initial geographic map, take each grid intersection as a sampling point, obtain the geographic location information of the sampling point, and number it, collect the dielectric constant of each sampling point, and determine the signal enhancement sampling point.

[0062] In this embodiment, the geographic information data of the goaf of the coal mining face includes the shape, range and elevation data of the goaf, as well as the geographic coordinate data of the goaf. The geographic location information of the sampling point is obtained specifically as follows:

[0063] Import the collected goaf shape, range, elevation and geographic coordinate data into the GIS software, ensuring that all imported data sets use a unified coordinate system. If they are inconsistent, perform coordinate system conversion;

[0064] Use the goaf shape data to crop the elevation data to ensure that only the goaf area is retained, set the size and range of the grid, generate a regular grid according to analysis requirements, cover the goaf, extract the grid intersections as sampling points, and record their geographic location information. The grid is a three-dimensional grid.

[0065] The elevation data provides information in the vertical direction, so that the grid is not only flat, but also three-dimensional. By clipping the elevation data, only the area of ​​the goaf is retained and layered in the vertical direction, a three-dimensional space is formed. The position of each sampling point is recorded using a three-dimensional coordinate system to ensure the uniqueness and accuracy of each point in space. The three-dimensional coordinates are longitude, latitude and altitude, respectively. The length, width and height are set, and the generated grid has a fixed size in three directions to form a cube. The side length of the cube is 50 meters. The three-dimensional grid is composed of a plurality of such cube units arranged and combined according to a certain rule. These cubes are arranged alternately to form a complete grid structure. The intersection of the grid is the vertex of the cube unit. These intersections can be used as sampling points, and each intersection has its corresponding three-dimensional coordinates. Therefore, the above steps in this embodiment jointly ensure that a three-dimensional grid is generated, rather than a two-dimensional grid limited to a plane.

[0066] Collect the shape, scope, elevation data and geographic coordinate data of the goaf. The geographic information system software uses ArcGIS or QGIS. Create a new project in the geographic information system software to process and analyze the goaf data. Import the shape and scope data of the goaf. The shape and scope data of the goaf exist in the form of vector data. Import the elevation data, which exists in the form of raster data.

[0067] Ensure that all data sets use the same coordinate system. If they are inconsistent, convert the coordinate system. If the elevation data range is larger than the goaf range, use the goaf shape data to clip the elevation data and only retain the relevant parts. Integrate various types of data into one layer or multiple layers to ensure that the data in each layer can be used in conjunction with each other.

[0068] Define the size and resolution of the grid. Select an appropriate grid size based on analysis needs. The grid size in this embodiment is 20 meters. Create a regular grid in the initial geographic map to cover the entire goaf. The grid is a square unit. The intersection of each grid unit is used as a sampling point. Generate a geographic location of a sampling point for each grid intersection, record its longitude, latitude and elevation, and uniquely number each sampling point for subsequent identification and processing.

[0069] In this embodiment, QGIS is used as an example of geographic information system software for detailed description. The following are the specific operations of the above steps: Import data Open QGIS, select "Layer" > "Add Layer" > "Add Vector Layer" to import the goaf shape and range data. Select "Layer" > "Add Layer" > "Add Raster Layer" to import elevation data, check data consistency and clipping, check the coordinate system in "Layer Properties", if inconsistent, use the "Reproject Layer" tool to convert, use the "Raster" > "Extraction" > "Clip Raster by MaskLayer" tool to clip elevation data, select "Processing" > "Toolbox", search for "Create Grid", set the grid size and range, generate a regular grid, obtain the geographic location information of the sampling points, use "Vector" > "Research Tools" > "Extract Nodes" to extract the grid intersection, generate sampling points, use the "Field Calculator" tool to generate a unique number for each sampling point, overlay all layers in the map window, adjust the style and display effect, import and process the geographic information data of the goaf in the GIS software, and generate an initial geographic map containing the sampling points to provide a basis for subsequent analysis.

[0070] The purpose of determining the signal enhancement sampling points is to quickly identify areas that may be at risk of spontaneous combustion within a wide sampling area, thereby improving analysis efficiency. This step is achieved by analyzing changes in the dielectric constant, because an abnormally low dielectric constant may indicate changes in the composition of the material in the coal seam, such as oxidation and signs of spontaneous combustion.

[0071] Determining the signal enhancement sampling points is a key step. It can quickly identify areas with possible spontaneous combustion risks in a large area, facilitating in-depth analysis in subsequent steps. The dielectric constant is closely related to the material composition and state of the underground medium. An abnormally low dielectric constant may indicate changes in the material properties of the area, such as increased air content or decreased moisture content. These changes are usually related to the oxidation and spontaneous combustion process of the coal seam. By setting a threshold for the dielectric constant, areas with possible abnormalities can be quickly screened out. These areas may cause the enhancement of electromagnetic signals due to changes in medium properties. After determining the signal enhancement sampling points, more detailed spectral analysis and radiation intensity calculations can be concentrated on these points to provide a reliable data basis for subsequent risk assessment. By reducing the scope of analysis through preliminary screening, the probability of large-scale misjudgment can be reduced and the accuracy of subsequent analysis and judgment can be improved.

[0072] In the scheme of the entire embodiment, determining the signal enhancement sampling point is a preliminary screening process. Through this step, the scope of the focus area can be effectively narrowed. Using the change of the physical property of dielectric constant to identify the potential spontaneous combustion risk area provides a more targeted basis for subsequent spectral data capture and relative radiation intensity analysis.

[0073] By setting the threshold of dielectric constant, areas with potential risks can be preliminarily screened out. These areas show enhanced characteristics of electromagnetic signals, making subsequent spectral analysis and radiation intensity calculation more targeted, thus providing a reliable data basis for more in-depth risk assessment.

[0074] In this embodiment, the logic for determining the signal enhancement sampling point is:

[0075] Use geological radar or electromagnetic detector to collect dielectric constant data of each sampling point, import the collected dielectric constant data into geographic information system software, associate it with the geographical location information of the sampling point, set the threshold of dielectric constant, and use points less than this value as signal enhancement sampling points.

[0076] Use geological radar (GPR) or electromagnetic detectors to collect dielectric constant data at each sampling point in the goaf of the coal mining face. The dielectric constant is the response characteristic of the material to the electric field and can reflect the material composition and state of the underground medium.

[0077] The collected dielectric constant data are imported into the Geographic Information System (GIS) software and associated with the geographical location information of each sampling point. This step ensures that each dielectric constant data point has its corresponding geographical location, which is convenient for subsequent spatial analysis.

[0078] A reasonable threshold is set based on the distribution of dielectric constants in the area. This threshold is usually based on analysis of historical data and experience and may represent the lower limit of the normal range of dielectric constants. Points with dielectric constants below this threshold may indicate abnormal changes in the underground medium, such as reduced moisture or increased air content, which may be related to the oxidation and spontaneous combustion processes of the coal seam.

[0079] Sampling points below the set threshold are marked as signal enhancement sampling points. These points show enhanced characteristics of electromagnetic signals due to abnormal dielectric constants, so further attention is needed. The dielectric constant reflects the changes in the material properties of the underground medium; the threshold is set to screen out points with abnormally low dielectric constants, indicating possible risk areas; these abnormal points are marked as signal enhancement sampling points as key areas for subsequent more in-depth analysis. Through this logic, key areas that may have spontaneous combustion risks can be effectively screened out in a wide sampling area, improving the efficiency and accuracy of subsequent analysis.

[0080] Geological radar (GPR) generates images of underground structures by emitting high-frequency electromagnetic waves and receiving their reflected signals. By analyzing these images, the changes in dielectric constants at different levels can be inferred. Geological radar performs systematic radar scanning in the area to be tested to generate two-dimensional or three-dimensional underground structure images. The collected data is processed using GPR data processing software to extract the time and intensity of the reflected signal. The dielectric constants at different locations are calculated based on the time delay and intensity of the reflected signal combined with known underground structure information. The electromagnetic detector generates electromagnetic property images of underground media by emitting low-frequency electromagnetic waves and measuring their conduction and reflection characteristics underground. The electromagnetic detector performs systematic electromagnetic scanning in the area to be tested to obtain continuous images of underground electromagnetic properties. The collected data is processed using special software to generate two-dimensional or three-dimensional images of the underground structure. The dielectric constants at different locations can be inferred based on the propagation speed and attenuation characteristics of the electromagnetic waves combined with known underground structure information.

[0081] Although GPR and electromagnetic detectors usually provide continuous images, by selecting a local area of ​​interest in the acquired image data, subdividing the data in the local area, extracting the reflection signal and propagation characteristics near the specific point, and then using the subdivided data to calculate the dielectric constant of the local point, therefore, although GPR and electromagnetic detectors mainly provide continuous electromagnetic characteristic images, the dielectric constant information of the local point can be extracted from these images through proper processing and analysis.

[0082] Signal-enhanced sampling points are usually at a higher risk of spontaneous combustion because the abnormally low dielectric constant at these points may indicate changes in the material in the underground coal seam, such as oxidation or heat accumulation, which are precursors to spontaneous combustion. Such changes may cause oxygen to penetrate more easily, promoting oxidation reactions, which in turn increase the risk of spontaneous combustion. In addition, material changes may be accompanied by increased temperatures, further exacerbating the possibility of spontaneous combustion. Therefore, by identifying these signal-enhanced sampling points, potential spontaneous combustion areas can be discovered earlier, allowing effective monitoring and prevention.

[0083] Step 2: Capture the spectral data of each sampling point, set the wavelength analysis range, record the spectral intensity of each sampling point within the wavelength analysis range, map it with the geographical location information of each sampling point, and normalize the spectral intensity data of all sampling points.

[0084] Use a near-infrared spectrometer that can cover a wavelength range of 900nm to 1000nm. Before measuring, ensure that the equipment has been calibrated to reduce measurement errors, select specific sampling points, and correctly place the spectrometer probe to ensure the accuracy and consistency of the measurement. The spectrometer will scan within the set wavelength range and record the spectral intensity corresponding to each wavelength. Usually, these data are output in the form of wavelength-intensity pairs to form a complete spectral curve. The collected data is processed and denoised and smoothed to improve data quality. Then, extract the spectral intensity data within the range of 900nm to 1000nm. In this embodiment, the maximum spectral intensity value within the range is selected as a representative and calibrated as the spectral intensity within the wavelength range of 900nm to 1000nm.

[0085] In this embodiment, the wavelength analysis range set when recording the spectral intensity of each sampling point is 900nm to 1000nm, and the specific logic of normalizing the spectral intensity data of all sampling points is:

[0086] Obtain the spectral intensity of each sampling point in the wavelength range of 900nm to 1000nm, and calculate the maximum and minimum values ​​of the spectral intensity of all sampling points in the wavelength range of 900nm to 1000nm, specifically:

[0087] I max =Max[Iq1, Iq2, ..., Iq i ,…,I qn ]

[0088] I min =min[Iq1, Iq2, ..., Iq i ,…,I qn ]

[0089] Among them, I max and Imin Respectively represent the maximum and minimum values ​​of the spectral intensity in the wavelength range of 900nm to 1000nm at the sampling point, Iq i Represents the spectral intensity data of the sampling point numbered i before normalization in the wavelength range of 900nm to 1000nm, i represents the number of the sampling point, and n represents the total number of sampling points.

[0090] The spectral intensity of all sampling points in the wavelength range of 900nm to 1000nm is scaled to the range of [0, 1], specifically:

[0091]

[0092] I i Represents the spectral intensity data of the sampling point numbered i after normalization in the wavelength range of 900nm to 1000nm.

[0093] In the wavelength range of 900nm to 1000nm, we first need to calculate the maximum value of the spectral intensity of all sampling points I max and minimum value I min , these values ​​represent the range of spectral intensity in the data set. The determination of the maximum and minimum values ​​lays the foundation for the subsequent normalization. For the spectral intensity value of each sampling point, the normalization formula is applied to scale each intensity value to between 0 and 1. This process makes the scale consistent between data, which is convenient for subsequent analysis. The original spectral data may have different dimensions due to acquisition conditions, equipment or other factors. Normalization eliminates the impact of dimension on data analysis by standardizing the data range, making the intensity values ​​of different sampling points comparable on the same scale. In data analysis or model training, the excessive range of original data may lead to unstable algorithm performance. Normalization adjusts the data to a unified standard, enhances the stability and convergence speed of the algorithm, and makes it easier for the model to capture the essential characteristics of the data. Through normalization, the spectral intensity of different sampling points is in the same range, which greatly enhances the comparability of the data. This is not only beneficial to numerical analysis, but also makes data visualization more intuitive, facilitating the identification of trends and patterns, thereby supporting more in-depth scientific analysis and decision-making.

[0094] Spectra of different wavelengths have specific sensitivities to different substances and phenomena. The wavelength range of 900nm to 1000nm is in the near-infrared region and is often used to detect temperature changes, flames and radiation characteristics. Within this wavelength range, changes in thermal radiation can better reflect high-temperature phenomena such as spontaneous combustion and fire. Therefore, by monitoring the spectral intensity within this wavelength range, natural hazardous areas can be effectively identified. In summary, selecting the 900nm to 1000nm wavelength range for analysis and normalizing the spectral intensity data can significantly improve the effectiveness and reliability of natural hazardous area determination. Through the sensitivity of a specific wavelength range and the standardization of normalization, abnormal spectral changes in the area can be more accurately captured and analyzed to ensure the efficient operation of the monitoring system.

[0095] Step 3: For the spectral intensity data of the normalized sampling points, calculate the relative radiation intensity of each sampling point, calculate the mean and standard deviation of the relative radiation intensity of all sampling points, generate the radiation offset degree of each sampling point, and identify the abnormal sampling points among the signal enhancement sampling points based on the radiation offset degree of the sampling points.

[0096] In this embodiment, the logic for calculating the relative radiation intensity of each sampling point is:

[0097]

[0098] Among them, R i is the relative radiation intensity of the sampling point numbered i, I b Indicates the baseline radiation intensity, which means the radiation intensity between 900nm and 1000nm when there is no spontaneous combustion phenomenon at the same temperature and pressure intensity;

[0099] When generating the radiation offset degree of each sampling point, first calculate the relative radiation intensity mean and standard deviation of all sampling points, and use the z-score method to generate the radiation offset degree of each sampling point. The formula is:

[0100]

[0101] Among them, μ R and σ R Respectively represent the relative radiation intensity mean and standard deviation of all sampling points, z i Indicates the degree of radiation deviation of the sampling point numbered i. When |z i |>z y , and when the point is a signal enhancement sampling point, the sampling point numbered i is identified as an abnormal sampling point, z yRepresents the offset threshold. When using the z-score method to identify abnormal sampling points, the reason why we need to take the absolute value of the z-score is that we are concerned about the degree of deviation of the sampling point, regardless of whether the deviation is in the positive or negative direction. By taking the absolute value, we can unify the positive and negative deviations, and only pay attention to the size of the deviation without considering the direction of the deviation. The absolute value processing makes the anomaly detection standard consistent and will not miss any significantly deviated data points due to different directions. This processing method enables the detection to capture both extremely high value anomalies and extremely low value anomalies.

[0102] The relative radiation intensity specifically reflects the change in the radiation intensity of the sampling point relative to the baseline radiation intensity. The relative radiation intensity reflects the relative change between the radiation intensity of each sampling point and the baseline radiation intensity under the condition of no spontaneous combustion. Through this indicator, it can be observed whether the radiation intensity increases or decreases, and what changes are compared with the baseline. If the relative radiation intensity is large, it indicates that the radiation intensity of the sampling point has increased significantly compared with the baseline, which may mean that some changes have occurred under this condition, such as spontaneous combustion. The greater the relative radiation intensity, the greater the risk of spontaneous combustion. The spontaneous combustion process is usually accompanied by energy release, which is reflected in the increase in radiation intensity. The greater the relative radiation intensity, the higher the amplitude of energy release, which may mean the occurrence of spontaneous combustion reactions. Spontaneous combustion involves chemical reactions, and the heat and light radiation released during spontaneous combustion will increase. A significant increase in radiation intensity can be a sign of the intensification of these reactions. The radiation intensity is closely related to temperature. Temperature increase is an important condition for spontaneous combustion. A higher relative radiation intensity may indicate that the temperature exceeds a certain threshold, leading to spontaneous combustion. Therefore, a significant change in radiation intensity above the baseline can be used as a basis for abnormal detection, indicating the risk of spontaneous combustion. By monitoring the change in relative radiation intensity, potential spontaneous combustion risks can be identified in advance.

[0103] The baseline radiation intensity is the standard intensity value measured in the absence of spontaneous combustion. By ensuring the stability of temperature and pressure in a well-controlled experimental environment, the temperature and pressure can be set to standard values. Multiple spectral measurements are performed in the absence of spontaneous combustion. For example, constant temperature and pressure conditions are maintained in the laboratory, and a spectrometer is used to measure the radiation intensity in the wavelength range of 900nm to 1000nm. The results of multiple measurements are recorded, and the radiation intensity data measured multiple times are statistically processed to calculate the average of these measurements to ensure a stable baseline value. If the radiation intensities obtained from multiple measurements are 100, 102, and 101 respectively, then they are averaged to obtain a baseline radiation intensity of 101. The offset threshold is determined by statistical analysis of historical data. During the analysis, the z-score distribution under normal circumstances is observed, and a threshold that can effectively distinguish between normal and abnormal conditions is set. If the z-score of most normal sampling points is between -2 and 2, 3 may be selected as the offset threshold.

[0104] Step 4: Obtain the relative radiation intensity of the neighboring sampling points of the abnormal sampling point in each signal enhancement sampling point, calculate the uniform distribution index of each abnormal sampling point, and mark the risk level of the abnormal sampling point according to the uniform distribution index.

[0105] In this embodiment, the neighbor sampling points of the abnormal point in the signal enhancement sampling points are the sampling points directly adjacent to the abnormal sampling points, including the directly adjacent sampling points in six directions of up and down, left and right, and front and back in the grid. The formula for calculating the uniform distribution index of each abnormal point is:

[0106]

[0107] Among them, μz j and σz j They represent the mean and variance of the relative radiation intensity of the data set composed of the abnormal sampling point numbered j and its adjacent sampling points, Jf j Represents the uniform distribution index of the abnormal sampling point numbered j, R j , Rs j , Rx j , Rz j , Ry j , Rq j and Rh j They represent the relative radiation intensity of the abnormal sampling point numbered j and its six upper, lower, left, right, front and rear sampling points respectively. If the abnormal sampling point does not have at least one neighbor sampling point among the six upper, lower, left, right, front and rear sampling points, the relative radiation intensity of the sampling point is set to 0.

[0108] The higher radiation intensity of the abnormal point means that the risk of spontaneous combustion of the point itself increases, and the small variance means that the difference in radiation intensity between neighboring points is small, that is, the radiation intensity distribution of neighboring points is relatively uniform. The larger the uniform distribution index, the higher the radiation intensity of the abnormal point, and the more consistent the radiation intensity of the neighboring points. The higher the radiation intensity of the abnormal point, the greater the risk of local high temperature or fire. The smaller the difference in radiation intensity between the abnormal point and the neighboring points, the more uniform the radiation intensity of these points is. This suggests that the abnormal point not only has a high radiation intensity itself, but also the points around it have similar high radiation intensity levels.

[0109] When the radiation intensity of a point is abnormally high and the radiation intensity of the surrounding points is relatively uniform, this consistency may reflect a local abnormal area rather than just an isolated abnormal point. A small variance indicates that the data of the neighboring points are evenly distributed. Combined with the abnormal points with high radiation intensity, this situation is more likely to be a real high-risk area rather than an accidental fluctuation or measurement error. The uniform distribution index, as a comprehensive indicator, combines the intensity and distribution characteristics of the local area to more accurately assess the spontaneous combustion risk of the area.

[0110] The uniform distribution index can effectively identify those abnormal points that not only have high radiation intensity themselves, but also have consistent high radiation intensity in the surrounding areas. This method can more accurately evaluate and mark high-risk areas, which is helpful for early warning and response to potential dangers such as natural spontaneous combustion. The smaller the difference in radiation intensity between neighboring points, the higher the risk of spontaneous combustion. When the radiation intensity of an abnormal point is high and the difference in radiation intensity of its neighboring points is small, it indicates that the radiation intensity is relatively uniform and consistent in a local area. Such a situation usually means that it is not just an isolated abnormal point, but may be a large-scale high radiation area. Heat has the characteristic of diffusion in matter. If the radiation intensity of the surrounding neighboring points is also relatively uniform and high, it may mean that the heat has no obvious concentration point in the area, but has spread to the entire area. In this case, the temperature of the entire area is high, increasing the risk of spontaneous combustion. If the radiation intensity of only one point is high, it may be an accidental phenomenon. However, when multiple neighboring points show high radiation intensity and the difference is small, it means that the total heat of these points is high and the local heat accumulation is serious. The uniform and high radiation intensity means that the area is in a state of continuous high temperature. Under such conditions, the material or environment is more likely to reach the point of spontaneous combustion.

[0111] A single high radiation point indicates that there may be a single hot spot, but if multiple adjacent points show high radiation with small differences, it means that the entire local area has a high thermal radiation level, which suggests that the risk in the area is more concentrated and serious. In the spontaneous combustion risk warning of goafs, the spread of fire is often due to the gradual increase in temperature in the local area, forming a high temperature zone. If the difference in radiation intensity between neighboring points is small and high, it means that the fire may be spreading or has spread to multiple points in the area.

[0112] When marking the risk level of abnormal points according to the uniform distribution index, if Jf j >Jf y , then the abnormal sampling point is marked as a high-risk sampling point and marked, otherwise the sampling point is marked as a low-risk sampling point and not marked, Jf y represents the uniform distribution threshold, j represents the number of the abnormal sampling point in the signal enhancement sampling point, when Jf j >Jf yWhen , it means that the radiation intensity of the abnormal point is significantly higher than that of the neighboring points, and the intensity difference between the neighboring points is small. This situation indicates that there is a high possibility of abnormal conditions in the area where the point is located, such as local high temperature or potential fire. Therefore, it is marked as a high-risk sampling point. On the contrary, the radiation intensity of the abnormal point is not significantly different from that of the neighboring points, and the risk is relatively low, so it is marked as a low-risk sampling point.

[0113] Through this logic, the system can more accurately identify potential high-risk areas, issue early warnings, concentrate resources and attention on already marked high-risk areas, improve monitoring and management efficiency, reduce false alarm rates, analyze historical abnormal data, identify uniform distribution index values ​​corresponding to different risk levels, set reasonable uniform distribution thresholds, test different uniform distribution thresholds through experiments in actual scenarios, and select values ​​that can effectively distinguish between high and low risks.

[0114] Step 5: Based on the distribution density of all marked abnormal sampling points in the initial geographic map, as well as the relative radiation intensity data and geographic location information of each marked abnormal sampling point, a risk assessment model is constructed to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged, and the spontaneous combustion risk of the goaf is judged based on the spontaneous combustion risk index.

[0115] In this embodiment, according to the distribution density of all marked abnormal sampling points in the initial geographic map, the number of all sampling points and the number of marked abnormal sampling points are counted to calculate the distribution density of the abnormal sampling points in the initial geographic map, specifically:

[0116]

[0117] Among them, ρ y is the distribution density of abnormal sampling points in the initial geographic map, n represents the total number of sampling points, and M represents the number of marked abnormal sampling points.

[0118] The distribution density indicates the proportion of abnormal sampling points to all sampling points in the entire initial geographic map. It reflects the spatial distribution of abnormal sampling points in the study area. The greater the distribution density, the higher the proportion of abnormal sampling points in the entire geographic map. This may mean that there are more high-risk points in the area, such as high-temperature areas, fire hazards, etc. The high distribution density means that the abnormal points are not just local phenomena, but may be widely distributed in the entire working face goaf area. The distribution density provides a macro risk assessment indicator, which helps to fully understand the risk level in the working face goaf area. By calculating the distribution density of abnormal sampling points, we can fully understand the spatial distribution of abnormal points in the initial geographic map. The greater the distribution density, the more abnormal points there are in the area, indicating a higher potential risk.

[0119] Furthermore, the specific logic of constructing a risk assessment model to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged is as follows:

[0120] According to the geographical location information of each marked abnormal sampling point, its distance from the center of the coal mining face is calculated, and the risk assessment model is constructed by combining the distribution density of the abnormal sampling points in the initial geographical map and the relative radiation intensity data of the marked abnormal sampling points. The formula is:

[0121]

[0122] Where RI represents the spontaneous combustion risk index, d m and Jf m They respectively represent the distance and relative radiation intensity between the marked abnormal sampling point numbered m and the center of the coal mining face, ∈ represents the denominator constant, and ∈>0, m represents the number of the marked abnormal sampling point, and e represents the base of the natural logarithm.

[0123] When determining the center of the coal mining face, for a coal mining face of regular shape, the coordinates of its center point are directly calculated. For example, for a rectangular coal mining face, its center point can be determined by the intersection of the diagonal lines. For an irregular coal mining face, it is difficult to determine the center point directly by geometric methods. Therefore, the centroid calculation method can be used. This method assumes that the coal mining face is divided into multiple small units, and the volume or area of ​​each small unit is equal. The centroid of each unit is calculated (the centroid refers to the geometric center of each small unit). The centroid of the entire coal mining face can be determined by taking the average of the coordinates of the centroids of all small units, and the centroid is calibrated as the center. When calculating the distance between the abnormal sampling point and the center of the coal mining face, since the distance is not large, it is not necessary to consider the spherical characteristics of the earth, and the Euclidean distance formula in three-dimensional space can be used.

[0124] Anomalies with high radiation intensity have a higher risk of spontaneous combustion because they indicate a large accumulation of heat in a local area. m As the numerator, it directly reflects the risk level of the abnormal point. Generally, the farther away from the center of the coal mining face, the lower the risk of spontaneous combustion. m The existence of reflects the attenuation effect of distance on risk. m e The influence of distance on the risk index is more significant, especially when the distance is large. The constant ∈ avoids the situation where the denominator is zero, while ensuring the stability of the model and the feasibility of calculation. The distribution density reflects the distribution of outliers in the entire area. A high density of outliers means that the overall risk in the area is higher. Therefore, the distribution density is used as a multiplier to further adjust the risk index to make it better reflect the actual situation.

[0125] As the distance between the abnormal sampling point and the center of the coal face increases, the risk of spontaneous combustion generally decreases. m e The attenuation effect of distance on risk can be emphasized. The exponent e is the base of the natural logarithm, which makes the influence of distance present a nonlinear relationship and simulates the actual physical situation more accurately. In this way, the influence of points farther away on the risk index is significantly weakened.

[0126] ∈ ensures that the denominator is not zero, thereby avoiding computational instability problems. It is usually set to a positive number less than but close to zero. The value of ∈ needs to ensure the numerical stability of the model. It can usually be debugged according to specific data to find a suitable value. The common value range may be 0.01 to 1. Through these settings, the model can more stably and accurately evaluate the spontaneous combustion risk index of the goaf of the coal mining face.

[0127] By accumulating and summing the risk contributions of all abnormal points, we can integrate the impact of multiple abnormal points on the entire coal mining face area to obtain an overall spontaneous combustion risk index. The relative radiation intensity directly affects the risk index, reflecting the risk level of the abnormal points. The distance attenuation effect reduces the impact of abnormal points farther away from the center on the overall risk, which is in line with the actual physical meaning. The distribution density serves as an amplification factor, reflecting the impact of the spatial distribution of abnormal points on the overall risk. The spontaneous combustion risk index is a comprehensive indicator that combines relative radiation intensity, geographical location and distribution density, and can comprehensively and accurately evaluate the spontaneous combustion risk of the coal mining face.

[0128] The larger the spontaneous combustion risk index is, the higher the spontaneous combustion risk is in the goaf of the coal mining face. The early warning signal indicates the potential risk of spontaneous combustion, suggesting that preventive measures need to be taken to reduce the possibility of spontaneous combustion accidents. By constructing the above risk assessment model, we can comprehensively consider the relative radiation intensity of the abnormal sampling points, the distance from the center of the coal mining face, and the distribution density, and generate a comprehensive spontaneous combustion risk index. This comprehensive indicator can help more accurately assess the spontaneous combustion risk in the goaf of the coal mining face, and support scientific decision-making and effective risk management.

[0129] In this embodiment, when judging the spontaneous combustion risk of the goaf according to the spontaneous combustion risk index, if RI ≥ RI y , judge that the risk of spontaneous combustion in the goaf is high and issue an early warning. <RI y , the risk of spontaneous combustion in the goaf is judged to be low, and no warning is issued, RI y Indicates the spontaneous combustion risk threshold.

[0130] When RI ≥ RI y, a high-risk warning signal is issued, which means that there is a high risk of spontaneous combustion in the goaf of the coal mining face, and immediate measures need to be taken, such as intensive monitoring, increased ventilation, spraying fire extinguishing agents, etc., to prevent the occurrence of spontaneous combustion accidents. <RI y The risk of spontaneous combustion in the goaf of the coal mining face is low, and no emergency measures are needed immediately. However, regular monitoring and maintenance are still required to prevent a sudden increase in risk. The spontaneous combustion risk threshold is determined by collecting data on historical spontaneous combustion events and using statistical methods (such as distribution analysis and regression analysis) to determine a significant threshold.

[0131] The geographic information data of the goaf of the coal mining face is imported through geographic information system (GIS) software (such as ArcGIS or QGIS), an initial geographic map is generated, and a regular three-dimensional grid is created. Each grid intersection is used as a sampling point to record its geographic location information. This step ensures the consistency of the data and the accuracy of spatial positioning, providing an accurate basis for subsequent analysis. A near-infrared spectrometer is used to capture the spectral data of each sampling point in the wavelength range of 900nm to 1000nm, and the spectral intensity is recorded. Subsequently, the spectral intensity data of all sampling points are normalized, and the data are adjusted to the range of 0 to 1 to ensure that the spectral intensity of different sampling points is comparable on the same scale.

[0132] By calculating the relative radiation intensity of each sampling point and using the z-score method to generate the degree of radiation deviation, abnormal sampling points can be identified. The relative radiation intensity reflects the difference between the sampling point and the baseline radiation intensity, and the z-score helps quantify this difference, thereby accurately identifying areas with higher spontaneous combustion risks. For each abnormal sampling point, the relative radiation intensity of its neighboring sampling points is obtained, and the uniform distribution index is calculated. The risk level of abnormal sampling points is marked according to the uniform distribution index to distinguish high-risk and low-risk sampling points. The uniform distribution index not only takes into account the radiation intensity of the abnormal point, but also combines the data consistency of the adjacent area, providing a more reliable risk assessment standard.

[0133] Combining the distribution density, relative radiation intensity and geographic location information of all marked abnormal sampling points, a risk assessment model is constructed to generate a spontaneous combustion risk index. The spontaneous combustion risk of the goaf is judged based on the spontaneous combustion risk index, and then an early warning is issued or monitoring is maintained. Through this comprehensive assessment method, the spontaneous combustion risk of the coal mining face can be comprehensively and accurately assessed, providing a solid basis for scientific decision-making and risk management.

[0134] See also Figure 2 The present invention also provides a system for determining the spontaneous combustion hazard zone in the goaf of a coal mining face. The system is used to execute the method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face, and includes:

[0135] The geographic map creation module is used to generate an initial geographic map by importing the geographic information data of the goaf of the coal mining face to be determined using the geographic information system software, create a regular grid in the initial geographic map, take each grid intersection as a sampling point, obtain the geographic location information of the sampling points, number them, collect the dielectric constant of each sampling point, and determine the signal enhancement sampling points;

[0136] The preprocessing module is used to capture the spectral data of each sampling point, set the wavelength analysis range, record the spectral intensity of each sampling point within the wavelength analysis range, map it with the geographical location information of each sampling point, and normalize the spectral intensity data of all sampling points;

[0137] The abnormality identification module is used to calculate the relative radiation intensity of each sampling point, the mean and standard deviation of the relative radiation intensity of all sampling points, generate the radiation offset degree of each sampling point, and identify the abnormal sampling points among the signal enhancement sampling points according to the radiation offset degree of the sampling points.

[0138] A risk assessment module is used to obtain the relative radiation intensity of the neighboring sampling points of the abnormal sampling point in each signal enhancement sampling point, calculate the uniform distribution index of each abnormal sampling point, and mark the risk level of the abnormal sampling point according to the uniform distribution index;

[0139] The comprehensive judgment module is used to construct a risk assessment model based on the distribution density of all marked abnormal sampling points in the initial geographic map, as well as the relative radiation intensity data and geographic location information of each marked abnormal sampling point, to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged, and judge the spontaneous combustion risk of the goaf based on the spontaneous combustion risk index.

[0140] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0141] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face, characterized in that: The specific steps include: Step 1: Use geographic information system software to import geographic information data of the goaf of the coal mining face to be determined to generate an initial geographic map, create a regular grid in the initial geographic map, take each grid intersection as a sampling point, obtain the geographic location information of the sampling points, and number them, collect the dielectric constant of each sampling point, and determine the signal enhancement sampling point; Step 2: Capture the spectral data of each sampling point, set the wavelength analysis range, record the spectral intensity of each sampling point within the wavelength analysis range, map it with the geographical location information of each sampling point, and normalize the spectral intensity data of all sampling points; Step 3: Calculate the relative radiation intensity of each sampling point based on the spectral intensity data of the normalized sampling points, calculate the mean and standard deviation of the relative radiation intensity of all sampling points, generate the radiation deviation degree of each sampling point, and identify the abnormal sampling points among the signal enhancement sampling points based on the radiation deviation degree of the sampling points; Step 4: Obtain the relative radiation intensity of the neighboring sampling points of the abnormal sampling point in each signal enhancement sampling point, calculate the uniform distribution index of each abnormal sampling point, and mark the risk level of the abnormal sampling point according to the uniform distribution index; Step 5: Based on the distribution density of all marked abnormal sampling points in the initial geographic map, as well as the relative radiation intensity data and geographic location information of each marked abnormal sampling point, a risk assessment model is constructed to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged, and the spontaneous combustion risk of the goaf is judged based on the spontaneous combustion risk index.

2. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 1, characterized in that: The geographic information data of the goaf of the coal mining face includes the shape, range and elevation data of the goaf, as well as the geographic coordinate data of the goaf. The geographic location information of the sampling point is obtained as follows: Import the collected goaf shape, range, elevation and geographic coordinate data into the GIS software, ensuring that all imported data sets use a unified coordinate system. If they are inconsistent, perform coordinate system conversion; Use the goaf shape data to crop the elevation data to ensure that only the goaf area is retained, set the size and range of the grid, generate a regular grid according to analysis requirements, cover the goaf, extract the grid intersections as sampling points, and record their geographic location information. The grid is a three-dimensional grid.

3. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 2, characterized in that: The logic for determining the signal enhancement sampling point is: Use geological radar or electromagnetic detector to collect dielectric constant data of each sampling point, import the collected dielectric constant data into geographic information system software, associate it with the geographical location information of the sampling point, set the threshold of dielectric constant, and use points less than this value as signal enhancement sampling points.

4. The method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 1 is characterized by: The wavelength analysis range set when recording the spectral intensity of each sampling point is 900nm to 1000nm. The specific logic for normalizing the spectral intensity data of all sampling points is as follows: Obtain the spectral intensity of each sampling point in the wavelength range of 900nm to 1000nm, and calculate the maximum and minimum values ​​of the spectral intensity of all sampling points in the wavelength range of 900nm to 1000nm, specifically: I max =max[Iq1、Iq2、…、Iq i 、…、Iq n ] I min =min[Iq1、Iq2、…、Iq i 、…、Iq n ] Among them, I max and I min Respectively represent the maximum and minimum values ​​of the spectral intensity in the wavelength range of 900nm to 1000nm at the sampling point, Iq i It represents the spectral intensity data of the sampling point numbered i before normalization in the wavelength range of 900nm to 1000nm, i represents the number of the sampling point, and n represents the total number of sampling points; The spectral intensity of all sampling points in the wavelength range of 900nm to 1000nm is scaled to the range of [0, 1], specifically: I i Represents the spectral intensity data of the sampling point numbered i after normalization in the wavelength range of 900nm to 1000nm.

5. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 4, characterized in that: The logic for calculating the relative radiation intensity of each sampling point is: Among them, R i is the relative radiation intensity of the sampling point numbered i, I b Indicates the baseline radiation intensity, which means the radiation intensity between 900nm and 1000nm when there is no spontaneous combustion phenomenon at the same temperature and pressure intensity; When generating the radiation offset degree of each sampling point, first calculate the relative radiation intensity mean and standard deviation of all sampling points, and use the z-score method to generate the radiation offset degree of each sampling point. The formula is: Among them, μ R and σ R Respectively represent the relative radiation intensity mean and standard deviation of all sampling points, z i Indicates the degree of radiation deviation of the sampling point numbered i. When |z i |>z y , and when the point is a signal enhancement sampling point, the sampling point numbered i is identified as an abnormal sampling point, z y Indicates the offset threshold.

6. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 1, characterized in that: The neighbor sampling points of the abnormal points in the signal enhancement sampling points are the sampling points directly adjacent to the abnormal sampling points, including the directly adjacent sampling points in the six directions of up and down, left and right, front and back in the grid. The formula for calculating the uniform distribution index of each abnormal point is: Among them, μz j and σz j They represent the mean and variance of the relative radiation intensity of the data set composed of the abnormal sampling point numbered j and its adjacent sampling points, Jf j Represents the uniform distribution index of the abnormal sampling point numbered j, R j , Rs j , Rx j , Rz j , Ry j , Rq j and Rh j Respectively represent the relative radiation intensity of the abnormal sampling point numbered j and the six sampling points above, below, left, right, front and back. If the abnormal sampling point does not have at least one neighbor sampling point among the six sampling points above, below, left, right, front and back, the relative radiation intensity of the sampling point is set to 0; When marking the risk level of abnormal points according to the uniform distribution index, if Jf j >Jf y , then the abnormal sampling point is marked as a high-risk sampling point and marked, otherwise the sampling point is marked as a low-risk sampling point and not marked, Jf y represents the uniform distribution threshold, and j represents the number of the abnormal sampling point in the signal enhancement sampling point.

7. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 6, characterized in that: According to the distribution density of all marked abnormal sampling points in the initial geographic map, the number of all sampling points and the number of marked abnormal sampling points are counted to calculate the distribution density of abnormal sampling points in the initial geographic map, specifically: Among them, ρ y is the distribution density of abnormal sampling points in the initial geographic map, n represents the total number of sampling points, and M represents the number of marked abnormal sampling points.

8. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 7, characterized in that: The specific logic for constructing a risk assessment model and generating the spontaneous combustion risk index of the goaf of the coal mining face to be judged is as follows: According to the geographical location information of each marked abnormal sampling point, its distance from the center of the coal mining face is calculated, and the risk assessment model is constructed by combining the distribution density of the abnormal sampling points in the initial geographical map and the relative radiation intensity data of the marked abnormal sampling points. The formula is: Where RI represents the spontaneous combustion risk index, d m and Jf m They respectively represent the distance between the marked abnormal sampling point numbered m and the center of the coal mining face and the relative radiation intensity, ∈ represents the denominator constant, and ∈>0, m represents the number of the marked abnormal sampling point, and e represents the base of the natural logarithm.

9. A method for determining the spontaneous combustion hazard zone in the goaf of a coal mining face according to claim 8, characterized in that: When judging the spontaneous combustion risk of goaf based on the spontaneous combustion risk index, if RI ≥ RI y , judge that the risk of spontaneous combustion in the goaf is high and issue an early warning. <RI y , the risk of spontaneous combustion in the goaf is judged to be low, and no warning is issued, RI y Indicates the spontaneous combustion risk threshold.

10. A system for determining the spontaneous combustion hazard zone in the goaf of a coal mining face, characterized in that: The judgment system is used to execute the judgment method of the spontaneous combustion hazard zone in the goaf of a coal mining face according to any one of claims 1 to 9, comprising: The geographic map creation module is used to generate an initial geographic map by importing the geographic information data of the goaf of the coal mining face to be determined using the geographic information system software, create a regular grid in the initial geographic map, take each grid intersection as a sampling point, obtain the geographic location information of the sampling points, number them, collect the dielectric constant of each sampling point, and determine the signal enhancement sampling points; The preprocessing module is used to capture the spectral data of each sampling point, set the wavelength analysis range, record the spectral intensity of each sampling point within the wavelength analysis range, map it with the geographical location information of each sampling point, and normalize the spectral intensity data of all sampling points; The abnormality identification module is used to calculate the relative radiation intensity of each sampling point, the mean and standard deviation of the relative radiation intensity of all sampling points, generate the radiation offset degree of each sampling point, and identify the abnormal sampling points among the signal enhancement sampling points according to the radiation offset degree of the sampling points. A risk assessment module is used to obtain the relative radiation intensity of the neighboring sampling points of the abnormal sampling point in each signal enhancement sampling point, calculate the uniform distribution index of each abnormal sampling point, and mark the risk level of the abnormal sampling point according to the uniform distribution index; The comprehensive judgment module is used to construct a risk assessment model based on the distribution density of all marked abnormal sampling points in the initial geographic map, as well as the relative radiation intensity data and geographic location information of each marked abnormal sampling point, to generate the spontaneous combustion risk index of the goaf of the coal mining face to be judged, and judge the spontaneous combustion risk of the goaf based on the spontaneous combustion risk index.

Images