Goaf spontaneous ignition prediction method and system based on geologic mathematical model

Abstract

The invention provides a goaf spontaneous ignition prediction method and system based on a geologic mathematical model, and relates to the technical field of coal mine monitoring. Ferroelectric materials are buried in each subarea of a goaf to serve as mark points, and a ground penetrating radar is used for transmitting electromagnetic waves and receiving reflected signals; according to the invention, comprehensive temperature monitoring can be carried out on the goaf, the temperature change of the goaf can be comprehensively monitored in real time, a three-dimensional temperature field distribution model is generated by using an inverse distance weighted interpolation method, so that high-temperature abnormal points are accurately identified, and a fire source risk index can be generated for each sub-region in combination with an own risk assessment model. And dynamic prediction is carried out according to real-time temperature time sequence data, so that accurate data support is provided for safety management of the mining area, and timely and effective precautionary measures are taken in the mining area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal mine monitoring, in particular to a goaf spontaneous combustion prediction method and system based on a geological mathematical model. BACKGROUND

[0002] With the exploitation of mineral resources, especially in the process of coal mining, the safety problem of goaf is becoming increasingly serious. Due to long-term unmanaged, goaf is prone to abnormal phenomena such as high temperature and gas accumulation, and even may cause spontaneous combustion, which threatens the life safety of miners and the stability of production. Therefore, temperature monitoring and fire source prediction of goaf are particularly important. The existing technology mainly relies on manual inspection and temperature sensor monitoring, but this method has the disadvantages of slow response and limited spatial coverage, and it is difficult to monitor the fire risk of goaf in real time and comprehensively.

[0003] At present, the monitoring methods for goaf spontaneous combustion mainly include temperature monitoring, gas concentration detection and other traditional means. Some researches use ground penetrating radar technology to detect temperature anomalies in goaf, but these methods usually rely on a small amount of sensor data for risk assessment, and cannot accurately predict the specific location and time of fire occurrence. In addition, the existing goaf risk assessment model is mostly based on empirical formula, lacking dynamic and accurate assessment methods, and cannot effectively cope with complex underground environment.

[0004] The existing goaf spontaneous combustion prediction method has several significant shortcomings: first, the existing method generally relies on limited sensor data, which is difficult to cover the entire goaf, resulting in inaccurate and lagging fire risk warning; second, the risk assessment model is simple and fixed, and cannot consider the changes of coal seam thickness, rock density and other factors in real time; finally, the traditional technology is not accurate enough in identifying high-temperature abnormal points and determining the prediction position, and cannot effectively warn the fire source in advance.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present application is to provide a goaf spontaneous combustion prediction method and system based on a geological mathematical model to solve the problems raised in the background technology.

[0007] To achieve the above purpose, the present application provides the following technical solutions: A goaf spontaneous combustion prediction method based on a geological mathematical model, the specific steps comprising: Step 1: Obtain the planar range data of the goaf, divide the planar surface of the goaf into multiple uniform rectangular grids, each grid as a sub-region, and bury ferroelectric material as a marker point at the center of each sub-region at the top and bottom of the goaf, and obtain the position information of each marker point; Step 2: Obtain the thickness of the coal seam at the bottom of each sub-region and the geological data of the goaf, and construct a self-risk assessment model to generate a self-risk index for each sub-region, and the geological data includes the stratum thickness, rock density and porosity of each sub-region; Step 3: Use ground penetrating radar to emit electromagnetic waves and receive signals reflected by the ferroelectric material of each marker point, extract the real-time dielectric constant of the marker point, and use the Clausius-Mosotti equation to convert the real-time dielectric constant of the marker point to the real-time temperature of the marker point; Step 4: According to the real-time temperature data and position data of each marker point, generate a three-dimensional temperature field distribution model of the goaf using the inverse distance weighted interpolation method, extract the high temperature anomaly points of the goaf through the three-dimensional temperature field distribution model, and continuously obtain the real-time temperature time series data of the sub-region where the high temperature anomaly point is located through the ground penetrating radar and the ferroelectric material of the marker point; Step 5: Calculate the temperature change rate according to the real-time temperature time series data of the sub-region where the high temperature anomaly point is located, and construct a fire source risk model combining the corresponding self-risk index of the sub-region where the high temperature anomaly point is located, to generate a fire source risk index for each sub-region where the high temperature anomaly point is located; Step 6: Compare the fire source risk index of each sub-region where the high temperature anomaly point is located with the risk threshold value, and when the fire source risk index exceeds the risk threshold value, issue a spontaneous combustion warning, and generate a fire prediction location according to the position information of the high temperature anomaly point.

[0008] Further, the method for constructing a sub-region is: Obtain the planar range data of the goaf, construct the boundary contour of the planar surface of the goaf, and use the minimum bounding rectangle to enclose the boundary contour of the goaf; Divide the bounding rectangle uniformly according to a fixed grid size to generate a regular grid structure, and determine whether the center point of each grid is located within the boundary contour of the goaf; If the center point of the grid is located within the boundary contour of the goaf, retain the grid as an effective grid, otherwise delete the grid, and take each effective grid as a sub-region.

[0009] Further, the method for burying ferroelectric material as a marker point is: Calculate the center point of each effective grid, construct a perpendicular line perpendicular to the grid surface, and the intersection of the perpendicular line and the top and bottom surfaces of the goaf is the marker point of the corresponding grid, and the ferroelectric material is arranged on the rock or coal surface at the top and bottom of the goaf at the marker point. The thickness of the coal seam at the bottom of the sub-region is the thickness of the coal seam at the marker point at the bottom of the sub-region, the stratum thickness of the sub-region is the shortest distance from the ground at the marker point at the top of the sub-region, and the rock density and porosity of the sub-region are the rock density and porosity of the stratum at the marker point at the top of the sub-region.

[0010] Further, the self-risk assessment model is constructed, and the formula for generating the self-risk index of each sub-region is: wherein, the self-risk index of the i-th sub-region is represented by , , , and , respectively, the coal seam thickness, stratum thickness, rock density and porosity data of the i-th sub-region are represented by , the typical rock density is represented by ,

[0011] and , wherein, the real-time temperature and the detected real-time dielectric constant of the i-th marker point are represented by , and , respectively, the Curie temperature and the Curie constant of the buried ferroelectric material are represented by , the initial dielectric constant of the buried ferroelectric material is represented by ,

[0012] and , wherein, the temperature estimation value of the point in the three-dimensional temperature field distribution model is represented by , the total number of marker points is represented by , the distance between the point in the three-dimensional temperature field distribution model and the i-th marker point is represented by , wherein, , and , respectively, three-dimensional coordinate information of the i-th mark point, i.e., the position information of the i-th mark point, , three-dimensional coordinate information of the i-th point in the three-dimensional temperature field distribution model, and: the origin of the three-dimensional coordinate is the lowest elevation point in the goaf, the direction of the x-axis is the positive east direction, the direction of the y-axis is the positive south direction, the direction of the z-axis is perpendicular to the ground.

[0013] Further, when extracting the high-temperature abnormal points of the goaf through the three-dimensional temperature field distribution model, the temperature estimate value of each point in the three-dimensional temperature field distribution model is compared with the temperature risk threshold value, if , the point is marked as a high-temperature abnormal point, temperature risk threshold value; When continuously acquiring the real-time temperature time series data of the sub-region where the high-temperature abnormal point is located, the real-time temperature time series data of the two mark points in the sub-region where the high-temperature abnormal point is located is synchronously acquired, and the real-time temperature time series data of the sub-region is generated, and the formula is: wherein, real-time temperature time series data of the i-th high-temperature abnormal point, real-time temperature time series data of the top and bottom mark points in the i-th high-temperature abnormal point, number of the sub-region where the high-temperature abnormal point is located, time variable.

[0014] Further, the logic for generating the fire source risk index of each sub-region where the high-temperature abnormal point is located is: wherein, fire source risk index and its own risk index of the i-th high-temperature abnormal point, real-time temperature time series data of the i-th high-temperature abnormal point, number of the sub-region where the high-temperature abnormal point is located, time variable, ​​​​​​​​​​These represent the first weighting coefficient and the second weighting coefficient, respectively. ,and .

[0015] Furthermore, the method for issuing a spontaneous combustion warning and generating a predicted fire source location based on the location information of high temperature anomalies is as follows: When the fire source risk index of any sub-region containing a high-temperature anomaly exceeds a preset risk threshold, a spontaneous combustion warning is issued. Simultaneously, the three-dimensional coordinates of the predicted fire source location are calculated. The predicted three-dimensional coordinates are... ,in: in, This indicates the number of sub-regions where the high-temperature anomaly point is located. , and They represent the first The three-dimensional coordinate information of the top marker point of the sub-region where each high temperature anomaly point is located. , and They represent the first The three-dimensional coordinate information of the bottom marker point of the sub-region where the high temperature anomaly point is located.

[0016] The present invention also provides a spontaneous combustion prediction system for goaf areas based on a geological mathematical model. The prediction system is used to execute the above-described spontaneous combustion prediction method for goaf areas based on a geological mathematical model, comprising: The data marking module is used to obtain the top-view plane range data of the goaf, divide the top-view plane of the goaf into multiple uniform rectangular grids, each grid is a sub-region, and ferroelectric material is buried as a marker point at the top and bottom of the goaf corresponding to the center of each sub-region, and the position information of each marker point is obtained. The regional risk assessment module is used to obtain the thickness of the coal seam at the bottom of each sub-region and the geological data of the goaf, and to construct its own risk assessment model to generate the risk index of each sub-region. The geological data includes the stratum thickness, rock density and porosity of each sub-region. The temperature detection module is used to emit electromagnetic waves using ground penetrating radar and receive the signals reflected by the ferroelectric material at each marker point, extract the real-time dielectric constant of the marker point, and use the Clausius-Mosotti equation to convert the real-time dielectric constant of the marker point into the real-time temperature of the marker point. An abnormality evaluation module generates a three-dimensional temperature field distribution model of the goaf by inverse distance weighted interpolation method according to real-time temperature data and position data of each marker point, extracts high-temperature abnormal points of the goaf through the three-dimensional temperature field distribution model, and continuously obtains real-time temperature time series data of a sub-region where the high-temperature abnormal points are located through the ground penetrating radar and the ferroelectric material of the marker point; A risk analysis module is configured to calculate a temperature change rate according to the real-time temperature time series data of the sub-region where the high-temperature abnormal points are located, and construct a fire source risk model in combination with a self risk index corresponding to the sub-region where the high-temperature abnormal points are located, to generate a fire source risk index of each sub-region where the high-temperature abnormal points are located. A fire ignition warning module is configured to compare the fire source risk index of each sub-region where the high-temperature abnormal points are located with a risk threshold value, and issue a spontaneous combustion warning when the fire source risk index exceeds the risk threshold value, and generate a fire source prediction position according to the position information of the high-temperature abnormal points.

[0017] Compared with the prior art, the present application has the following advantages: The present application can comprehensively monitor the temperature of the goaf by burying ferroelectric material as a marker point in each sub-region of the goaf and using the technology of transmitting electromagnetic waves and receiving reflected signals by the ground penetrating radar, can comprehensively and real-timely monitor the temperature change of the goaf, and can accurately identify high-temperature abnormal points by generating a three-dimensional temperature field distribution model by inverse distance weighted interpolation method. In combination with a self risk evaluation model, a fire source risk index can be generated for each sub-region, and dynamic prediction can be performed according to real-time temperature time series data, which provides precise data support for the safety management of the mining area and helps the mining area to take timely and effective preventive measures. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 The figure is a schematic diagram of the overall method of the present application. Figure 2 The figure is a schematic diagram of the overall system structure of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with specific embodiments.

[0020] It should be noted that, unless otherwise defined, technical terms or scientific terms used in the present application shall have the usual meaning understood by a person with ordinary skill in the art to which the present application belongs. The terms "first", "second", and similar words used in the present application do not represent any order, number, or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. The terms "connected" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right", and the like are only used to represent relative positional relationships, which may change accordingly when the absolute position of the described object changes.

[0021] Embodiments: Please refer to Figure 1 The present application provides a technical solution: A goaf spontaneous combustion prediction method based on a geological mathematical model, the specific steps comprising: Step 1: Obtain the range data of the goaf top view plane, divide the goaf top view plane into a plurality of uniform rectangular grids, each grid as a sub-region, and bury ferroelectric material as a marker point at the center of each sub-region corresponding to the top and bottom of the goaf, and obtain the position information of each marker point.

[0022] By dividing the goaf top view plane into a plurality of uniform rectangular grids and burying ferroelectric material as a marker point at the center of each grid corresponding to the top and bottom of the goaf, compared with the traditional sampling and monitoring method, the spatial position information of the goaf can be more accurately obtained, and through the scientific grid division method, the coverage range and uniformity of the data are ensured. The problem of local data deviation caused by uneven distribution of sampling points in the previous technology is solved.

[0023] Ferroelectric material as a marker point can exist stably in a complex underground environment for a long time, and has good signal response characteristics, providing a reliable target point for monitoring equipment. The goaf is a cavity or space left after the removal of ore bodies during the mining of underground mineral resources, and its top and bottom are naturally existing structural features. The top of the goaf (also known as "roof") refers to the rock layer or soil layer above the goaf, while the bottom (also known as "floor") refers to the unmined ore body or rock layer below the goaf. The formation of the goaf is similar to digging underground space and removing resources from it, like a "house", which naturally has an upper and lower boundary.

[0024] In this embodiment, the method for constructing sub-regions is: Obtain the top-view plane range data of the goaf, construct the boundary contour of the top-view plane of the goaf, and use the minimum bounding rectangle to enclose the boundary contour of the goaf; The outer rectangle is evenly divided according to a fixed grid size to generate a regular grid structure, and it is determined whether the center point of each grid is located within the boundary outline of the goaf. If the center point of a grid is located within the boundary outline of the goaf, the grid is retained as a valid grid; otherwise, the grid is deleted, and each valid grid is treated as a sub-region.

[0025] Data collection is conducted to determine the overall extent of the goaf and its distribution on a planar topography. This can be achieved through surveying techniques to obtain two-dimensional planar distribution data, or by utilizing technologies such as drones, radar mapping, and 3D laser scanning to convert the actual terrain data of the goaf into usable planar topography information. In this embodiment, the planar topography is essentially the projection of the goaf onto the ground. The planar topography data of the goaf is represented by the coordinates of its boundary points. After obtaining the goaf's extent data, its boundary outline is constructed. This outline represents the external shape of the goaf on the planar topography, forming a closed polygon by connecting the boundary points.

[0026] To facilitate subsequent mesh generation, the boundary contour needs to undergo simple geometric processing, namely, enclosing the boundary contour of the goaf with a minimum bounding rectangle. The minimum bounding rectangle is a mathematically compact rectangle that can completely cover the boundary contour of the goaf while minimizing redundancy within the rectangular area.

[0027] The minimum bounding rectangle is constructed using a geometric algorithm. The minimum and maximum horizontal and vertical coordinates of the boundary contour point set are found, and a rectangular frame is constructed using these extreme values. The four sides of the frame correspond to these extreme values. After constructing the minimum bounding rectangle, it is uniformly divided according to a predetermined grid size. The grid size is adjustable and is typically determined based on factors such as the size of the goaf, monitoring accuracy requirements, and computing resources. The specific division steps are as follows: the width and height of the bounding rectangle are divided by the grid size to determine the number of horizontal and vertical grids; a uniformly arranged grid structure is generated within the bounding rectangle, with each grid being a small rectangular unit.

[0028] In this embodiment, if the grid is square, the grid size is set to 10 meters × 10 meters. If the grid is rectangular, the length and width can be adjusted within a range of about 10 meters. A 10-meter × 10-meter grid can provide relatively high spatial resolution, ensuring that changes in the goaf can be captured in a timely and accurate manner. The amount of data generated by this grid size can be effectively processed and analyzed under conventional computing resources without causing a data processing bottleneck, while ensuring data processing speed and real-time performance.

[0029] After generating the regular grid, it is necessary to determine whether each grid belongs to the goaf range. The specific method is: extracting the center point coordinates of each grid; using the point-in-polygon algorithm to determine whether the grid center point is located within the boundary contour of the goaf, the point-in-polygon algorithm is a classic geometric calculation method, which can quickly determine whether a point is within a polygon range through the ray method or other determination methods.

[0030] If the center point of a certain grid is located within the boundary contour of the goaf, the grid is retained as an effective grid, if the center point of a certain grid is not within the boundary contour of the goaf, the grid is deleted and not included in the effective grid set. Finally, the remaining effective grids constitute the sub-regions of the goaf, and each effective grid corresponds to a sub-region inside the goaf.

[0031] All effective grids form a set of regularly distributed sub-regions, and the spatial position and range of these sub-regions can be accurately represented by their geometric information (such as center point coordinates, boundary range). These sub-regions will serve as the basis for subsequent processing, such as the layout of marker points, the installation of monitoring equipment, the division of data analysis areas, etc.

[0032] Through the above steps, this embodiment constructs sub-regions of the goaf in a scientific and systematic way. Through the combination method of the minimum bounding rectangle and grid division, not only the accurate coverage of the goaf range is realized, but also the redundant operation of the non-goaf area is avoided, providing an efficient spatial partitioning scheme for subsequent monitoring and analysis. This method is universal and can be applied to goaf scenarios of different sizes and shapes, while being flexible and efficient.

[0033] Step 2: Obtain the thickness of the coal seam at the bottom of each sub-region and the geological data of the goaf, and construct its own risk assessment model to generate its own risk index for each sub-region, the geological data includes the stratum thickness, rock density and porosity of each sub-region.

[0034] By obtaining the coal seam thickness and related geological data of each sub-region in the goaf, and constructing a risk assessment model based on this, the self-risk index is generated, which can provide personalized risk assessment for each sub-region. By measuring and analyzing data such as coal seam thickness, stratum thickness, rock density and porosity, the risk assessment model can more accurately reflect the geological characteristics and potential risks of each region.

[0035] In this embodiment, the method of burying ferroelectric materials as marker points is: The center point of each effective grid is calculated, a vertical line perpendicular to the surface of the grid is constructed, and the intersection of the vertical line and the top surface and the bottom surface of the goaf is the marking point of the corresponding grid. The rock or coal surface at the top and bottom of the goaf at the marking point is laid with ferroelectric material. The thickness of the coal seam at the bottom of the sub-region is the thickness of the coal seam at the marking point at the bottom of the sub-region, the stratum thickness of the sub-region is the shortest distance from the ground at the marking point at the top of the sub-region, and the rock density and porosity of the sub-region are the rock density and porosity of the rock layer at the marking point at the top of the sub-region.

[0036] In order to effectively locate the monitoring points in the grid management of the goaf, the center point of each effective grid needs to be calculated. This center point is the geometric center of the grid in the plan view, which is obtained by simple geometric calculation. The purpose of calculating the center point is to determine the starting position of the vertical line. A vertical line is constructed downward from the center point of each grid, which is perpendicular to the surface of the grid. The purpose is to find the specific positions of the goaf roof and floor, which are the setting positions of the marking points. The role of the vertical line is to ensure that the marking points can be accurately corresponded to the center of the grid at the top and bottom of the goaf.

[0037] The intersection of this vertical line with the goaf roof and floor is the position of the marking point. The goaf roof and floor refer to the rock or coal seam interface above and below the goaf. In this way, the marking points are accurately positioned at the key geological interfaces of the goaf. After determining the position of the marking point, ferroelectric material needs to be laid at these marking points. Ferroelectric material has good signal response characteristics and can exist stably in complex underground environments for a long time. The purpose of such layout is to facilitate subsequent effective monitoring of these marking points using ground penetrating radar and other equipment. Through the marking points, the geological parameters of the sub-region are obtained. Specifically, the coal seam thickness at the bottom marking point of the sub-region is used to represent the coal seam thickness of the region, and the shortest distance from the ground at the top marking point provides the stratum thickness of the sub-region. The rock density and porosity are also measured through the rock layer where the marking points are located.

[0038] By laying drill holes in the goaf and recording the starting depth and ending depth of the coal seam according to the rock core samples or coal core samples during drilling, the coal seam thickness is calculated. The depth range from the ground surface to the goaf roof can also be recorded by drilling, and the structure and depth of different stratum interfaces can be identified by seismic wave reflection and refraction, thereby calculating the stratum thickness. Rock samples are collected from the field, and the density and porosity are measured by laboratory methods.

[0039] Further, a self-risk assessment model is constructed, and the formula for generating the self-risk index of each sub-region is: wherein, Indicates the first The risk index of each sub-region , , and They represent the first Data on coal seam thickness, stratigraphic thickness, rock density, and porosity for each sub-region. Indicates the density of typical rocks, Indicates the sub-region number.

[0040] The self-risk index indicates the probability of spontaneous combustion in a region, or whether it is prone to spontaneous combustion due to its own reasons. The higher the self-risk index, the more prone the sub-region is to spontaneous combustion. The self-risk index provides the risk level of each sub-region, which facilitates the refined management of goaf areas. By quantifying the risk index, high-risk areas can be accurately identified.

[0041] The thicker the coal seam, the stronger its internal heat accumulation capacity, the higher the oxidation and heating rate, and the easier it is to ignite spontaneously combust. Therefore, the thickness of the coal seam directly affects the risk index. The greater the stratum thickness, the more it can inhibit gas diffusion, thus suppressing the risk of ignition. Rock density reflects the compactness of the rock. The higher the density, the stronger the thermal conductivity, and the easier it is for heat to diffuse, relatively reducing the risk of ignition. Lower density leads to heat accumulation. Porosity reflects the permeability of the rock. When the porosity is low, heat diffusion becomes difficult, increasing the risk of localized heat accumulation.

[0042] Coal seam thickness is the primary driving force, directly influencing the risk index through oxidation and heat accumulation. This influence manifests as an exponential sum-square relationship: the greater the coal seam thickness, the wider the oxidation area and the stronger the oxidative heat accumulation effect, thus significantly increasing the risk of spontaneous combustion. Therefore, using… This emphasizes the significant amplifying effect of coal seam thickness on the risk index. Greater stratum thickness increases thermal conductivity, thus reducing overall risk. The reciprocal of the term represents the risk mitigation effect of formation thickness, combined with the exponential term. Reflecting the complex coupling relationship between thick coal seams and thick strata, higher rock density increases thermal conductivity, reduces local heat accumulation, and helps lower the risk of spontaneous combustion. Using a square root approach, the influence of rock density has a certain weight in the overall risk, but it is not overly significant. Higher porosity means more space for gas circulation within the rock strata, promoting heat dissipation and reducing local heat accumulation. This helps reduce the risk of self-heating and spontaneous combustion of the coal seam. Therefore, using... This indicates the role of porosity in mitigating risk. This is to highlight the nonlinear effect of porosity, because both excessively high and low porosity can significantly affect the risk index.

[0043] The squared term reflects the significant impact of coal seam thickness on risk, implying that coal seam thickness has an accelerating effect on the risk of spontaneous combustion. The greater the thickness, the wider the oxidized surface area of ​​the coal seam, and the more heat is accumulated. Therefore, the risk index increases with the square of the thickness. Increasing the coal seam thickness significantly increases the likelihood of spontaneous combustion because the heat generated during oxidation is more difficult to dissipate in thicker coal seams.

[0044] The square root form of rock density reflects the mildly enhancing effect of density on heat diffusion. Higher rock density promotes heat conduction and diffusion, thereby reducing local heat accumulation and lowering the risk of spontaneous combustion. Normalization aims to standardize rock density across different regions, making the risk indices of different goaf areas comparable. The thicker the strata, the more rock layers cover the goaf, which inhibits the risk of spontaneous combustion. The inhibitory effect of stratum thickness is actually reflected in its thermal insulation performance. Thick strata not only isolate oxygen but also limit heat loss, thus preventing heat accumulation. However, under thicker strata, risk reduction gradually becomes the dominant factor; therefore, the greater the stratum thickness, the lower the risk of spontaneous combustion.

[0045] Representing typical rock density, it is a constant used for normalization, standardizing the rock density of different subregions. It is the average density of the local rock strata selected based on the geological conditions of the mining area, for example, 2,500 kg / m³. 3 (General density of sandstone) or 2,700 kg / m³ 3 (General density of limestone) By using relative density, the influence of different rock layer densities on heat conduction and heat accumulation capacity can be reflected. The value can be flexibly set according to the specific research area and geological conditions, and can be selected based on the average density of local rock strata.

[0046] Step 3: Use ground-penetrating radar to emit electromagnetic waves and receive the signals reflected by the ferroelectric material at each marker point. Extract the real-time dielectric constant of the marker point and use the Clausius-Mosotti equation to convert the real-time dielectric constant of the marker point into the real-time temperature of the marker point.

[0047] Electromagnetic waves interact with the medium during propagation, and the dielectric constant is a key parameter that measures how materials respond to electric fields. Specifically, when electromagnetic waves propagate in different media, the size of the dielectric constant determines the speed and wavelength of the wave, and also affects the reflection, refraction, and other characteristics of electromagnetic waves. For ground penetrating radar, the transmitted electromagnetic waves will reflect when encountering different materials. By measuring the signal strength, delay, and other information of the reflected signal, the dielectric constant of the material can be indirectly calculated. Different materials have different dielectric constants, which are closely related to the physical parameters of the material such as temperature, density, and humidity. Therefore, ground penetrating radar can infer the electromagnetic properties of the material from the reflected signal, and thus infer temperature information.

[0048] Ground penetrating radar detects the marker points in the goaf by transmitting electromagnetic waves. These electromagnetic waves will reflect between different media (such as rock layers, coal seams, etc.), and the iron-electric material buried at the top and bottom of the goaf is the main reflection source. When the electromagnetic wave encounters the iron-electric material, the signal will be reflected and received by the radar.

[0049] Iron-electric materials are a class of materials with special electrical properties. They will undergo a "Curie point" change at a specific temperature, i.e., their electric polarization state and dielectric constant will change significantly with temperature changes. Below the Curie temperature, the dielectric constant of the iron-electric material changes significantly and nonlinearly with temperature. When the temperature approaches or exceeds the Curie temperature of the iron-electric material, the dielectric constant of the material changes rapidly. This change can be captured by the reflected signal of the ground penetrating radar, so the iron-electric material can be used as a sensitive marker point for temperature changes, accurately reflecting temperature changes.

[0050] When the temperature changes, the electromagnetic response (i.e., the reflected signal) of the iron-electric material also changes. By analyzing the reflected signal, the ground penetrating radar can extract the real-time dielectric constant of each marker point. The Clausius-Mossotti equation describes the relationship between the dielectric constant and temperature, especially in iron-electric materials. When the dielectric constant of the iron-electric material changes with temperature, this equation provides a theoretical model for calculating and predicting the temperature change of the material.

[0051] Goafs often have some temperature fluctuations, especially when natural fires occur in coal seams or rock layers, the temperature changes become exceptionally significant. The application of iron-electric materials, combined with the high-precision detection capability of ground penetrating radar, can monitor the temperature changes in the goaf in real time, especially the appearance of high-temperature abnormal points. This is of great significance for predicting natural fires and issuing timely warnings.

[0052] The method of inferring temperature using ground-penetrating radar and ferroelectric materials is based on the relationship between electromagnetic waves and dielectric constant, combined with the scientific principle of the temperature dependence of ferroelectric materials, and temperature calculation using the Clausius-Mosotti equation. This method enables high-precision temperature monitoring, and is particularly suitable for goaf areas with complex geological structures, thus providing reliable data support for spontaneous combustion prediction.

[0053] In this embodiment, the formula used to convert the real-time dielectric constant of the marker point into the real-time temperature of the marker point is as follows: in, and They represent the first The real-time temperature and the detected real-time dielectric constant of each marker point. and These represent the Curie temperature and Curie constant of the buried ferroelectric material, respectively. This indicates the initial dielectric constant of the buried ferroelectric material. The numbering indicates the marker point. The Curie temperature, Curie constant, and initial dielectric constant of the ferroelectric material are obtained through experimental means. By accurately measuring and calibrating these parameters, it is possible to ensure that the dielectric constant of the ferroelectric material is converted into an actual temperature value through the Clausius-Mosotti equation, thereby realizing real-time monitoring of the temperature of the goaf and prediction of ignition sources.

[0054] Step 4: Based on the real-time temperature and location data of each marker point, a three-dimensional temperature field distribution model of the goaf is generated using the inverse distance weighted interpolation method. High-temperature anomalies in the goaf are extracted using the three-dimensional temperature field distribution model. Real-time temperature time series data of the sub-regions where the high-temperature anomalies are located are continuously obtained using ground penetrating radar and the ferroelectric materials of the marker points.

[0055] In this embodiment, the three-dimensional temperature field distribution model of the goaf is generated using the inverse distance weighted interpolation method as follows: in, In the three-dimensional temperature field distribution model Temperature estimate of the point, This indicates the total number of marked points. In the three-dimensional temperature field distribution model Point and the The distance between the marker points is calculated using the following formula: in, , and They represent the first three-dimensional coordinate information of the i-th marker point, i.e., the position information of the i-th marker point, the origin of the three-dimensional coordinate is the lowest elevation point in the goaf, the direction of the x-axis is the positive east direction, the direction of the y-axis is the positive south direction, the direction of the z-axis is perpendicular to the ground.

[0056] The real-time temperature data of each marker point is successfully obtained through the ground penetrating radar and the buried ferroelectric material. These temperature data are measured in real time at different positions at the same time point, so the temperature data of each marker point not only reflects the current temperature of the point, but also provides the spatial distribution information of the temperature in the goaf. The temperature data of each marker point is closely related to its position. At this time, the temperature distribution of the goaf is still discrete, and only has specific temperature values on these marker points. In order to calculate the temperature field of the entire goaf, it is also necessary to convert these discrete temperature data into a continuous three-dimensional temperature field through a mathematical interpolation method.

[0057] In order to derive the temperature distribution of the entire goaf from these discrete temperature data, the inverse distance weighted interpolation method is adopted. The core idea of this method is that the closer the known marker point to the target point, the greater the influence of the marker point on the temperature estimation of the target point, and vice versa. For the target point, its temperature estimation value is a weighted average of the temperatures of all known marker points, and the weight is determined by the distance between the marker point and the target point. The closer the distance, the greater the weight; the farther the distance, the smaller the weight.

[0058] In order to realize the inverse distance weighted interpolation described above, it is necessary to first calculate the spatial distance between the target point and each marker point. Since the space is three-dimensional, the distance calculation formula adopts the classical three-dimensional Euclidean distance formula. This distance calculation method considers the three-dimensional spatial characteristics of the goaf and can accurately measure the spatial relationship between the target point and the marker point. In order to uniformly process the spatial data of the goaf, it is necessary to set the coordinate system. In this embodiment, the origin of the three-dimensional coordinate is selected as the lowest elevation point of the goaf. This coordinate system ensures that the spatial position of each point in the goaf can be accurately represented by three-dimensional coordinates, thereby ensuring the accuracy of the position during interpolation calculation.

[0059] ​​​​​By the above steps, the inverse distance weighted interpolation method is used to calculate the temperature estimate of the target point based on the real-time temperature data and position data of the known marker points. By performing the same interpolation calculation for multiple target points in the goaf, a three-dimensional temperature field distribution model can be obtained. This model can represent the temperature value of each point in the goaf, thereby obtaining the spatial distribution of the temperature in the entire goaf.

[0060] By generating a three-dimensional temperature field distribution model, high-temperature abnormal points in the goaf can be identified. Generally, these high-temperature abnormal points are associated with potential fire sources, because spontaneous combustion often occurs in areas with higher temperature anomalies. In the temperature field distribution model, a temperature threshold can be set, and when the temperature estimate of a point is greater than the threshold, the point is considered a high-temperature abnormal point. In this way, the model not only helps to identify areas with higher temperatures, but also provides data support for subsequent fire risk assessment.

[0061] In the three-dimensional coordinate system of the goaf, the target point must be located within the coordinate range of all marker points. By selecting the minimum coordinate value of all marker points to limit the position of the target point, the target point is always located within the area covered by the marker points, avoiding the situation of exceeding the actual measurement range. Because if the target point exceeds the range of known data points, the interpolation result no longer has physical meaning. In practical applications, the space of the goaf is not infinite, but has certain physical boundaries. If the target point is allowed to exceed the boundary of the goaf (i.e., beyond the area covered by the marker points), it will introduce temperature prediction results that do not conform to reality. Through this constraint condition, it is ensured that the temperature field distribution generated by interpolation is limited.

[0062] Further, when extracting high-temperature abnormal points in the goaf through the three-dimensional temperature field distribution model, the temperature estimate of each point in the three-dimensional temperature field distribution model is compared with the temperature risk threshold value, and if , the point is marked as a high-temperature abnormal point, represents the temperature risk threshold value.

[0063] In the process of predicting spontaneous combustion in the goaf through the three-dimensional temperature field distribution model, the main purpose of extracting high-temperature abnormal points is to identify areas that may have fire risk. In specific operations, the temperature estimate of each point in the three-dimensional temperature field distribution model is compared with the temperature risk threshold value, thereby determining which areas have potential high-temperature anomalies.

[0064] Temperature is a key factor in spontaneous combustion, especially in coal mine goaf areas, where chemical reactions between the coal seam and rock, heat accumulation, and other factors can lead to localized temperature increases. Once the temperature rises to a certain level, it may trigger spontaneous combustion of the coal seam, subsequently causing a fire. Therefore, setting a temperature risk threshold to identify high-temperature anomalies can help detect potential ignition sources early and implement appropriate preventative measures.

[0065] Temperature risk thresholds are essentially a standardized definition of high-temperature areas. They determine, based on the characteristics of the actual goaf, which points exhibit abnormal temperatures and which may exceed safe thresholds, thus posing a fire risk. Generally, points where temperatures exceed the threshold indicate a potential fire risk in the area, requiring further monitoring or emergency preventative measures.

[0066] High-temperature anomalies in goaf areas are defined as temperatures exceeding 60% of the spontaneous combustion critical temperature, i.e., temperatures reaching approximately 300°C. If the spontaneous combustion temperature of a coal seam is 500°C, we can set the risk threshold to 300°C. That is, when the estimated temperature at a point is 300°C, that point is considered a high-temperature anomaly, indicating that the temperature in that area may be approaching or exceeding the critical temperature for spontaneous combustion of the coal seam. The spontaneous combustion temperature of most coal seams is between 350°C and 500°C. Therefore, setting a relatively low threshold in advance can issue an early warning when the temperature begins to approach the spontaneous combustion temperature, preventing higher temperatures from causing spontaneous combustion of the coal seam.

[0067] While continuously acquiring real-time temperature time-series data of the sub-region where the high-temperature anomaly point is located, the real-time temperature time-series data of two marked points in the sub-region where the high-temperature anomaly point is located are simultaneously acquired in real time to generate the real-time temperature time-series data of the sub-region. The formula used is as follows: in, Indicates the first Real-time temperature time series data of the sub-region where each high temperature anomaly point is located. and They represent the first Real-time temperature time-series data of the top and bottom markers within the sub-region where each high-temperature anomaly is located. This indicates the sub-region number where the high-temperature anomaly point is located. Represents a time variable.

[0068] In the prediction of spontaneous combustion in goaf, real-time temperature monitoring is crucial for identifying fire risk. It is necessary to obtain real-time temperature data of two marker points related to high-temperature abnormal points, which are usually set at the top and bottom of each sub-region. This is because the temperature distribution in goaf may differ vertically, especially between different depth levels, and the temperature difference between the top and bottom may be more significant. By synchronously obtaining temperature data from the top and bottom, more comprehensive temperature information can be obtained, ensuring that no local temperature anomalies that may lead to fire are missed. The average value of the top and bottom marker point temperatures is taken to generate a temperature estimate representing the entire sub-region. Taking the average value is to avoid the deviation caused by uneven temperature distribution, especially if the temperature changes greatly at the top and bottom. Simply selecting a certain temperature point may lead to misjudgment. By taking the average value, the temperature difference between the top and bottom can be better balanced, thus more accurately reflecting the thermal state of the entire sub-region.

[0069] Temperature time series data is crucial for determining the rate of temperature change, trend, and stability. By analyzing real-time temperature data, the following information can be inferred: temperature change rate: real-time temperature data can reflect the speed of temperature rise, and if the temperature rises rapidly, it may be a sign of potential spontaneous combustion or fire; heat accumulation trend: by observing the long-term trend of temperature change, it can be predicted whether the temperature is stable in the high-temperature interval, which in turn affects the assessment of fire risk.

[0070] By generating real-time temperature time series data for each high-temperature abnormal point in the sub-region, the temperature change in the goaf can be more accurately monitored, thus predicting whether there is a further warming trend. By obtaining and analyzing the real-time temperature data of the top and bottom marker points in the sub-region, average temperature data for the sub-region is generated, thus more comprehensively reflecting the temperature state of the region. By monitoring real-time temperature time series data, the temperature change trend of high-temperature abnormal points can be effectively captured, and possible fire risks can be warned in advance.

[0071] Step 5: Calculate the temperature change rate based on the real-time temperature time series data of the sub-region where the high-temperature abnormal point is located, and construct a fire risk model combining the self-risk index of the sub-region where the high-temperature abnormal point is located to generate the fire risk index of each sub-region where the high-temperature abnormal point is located.

[0072] In this embodiment, the logic for generating the fire risk index of each sub-region where the high-temperature abnormal point is located is as follows: wherein, and represent the fire risk index and self-risk index of the sub-region where the i-th high-temperature abnormal point is located, represent the fire risk index and self-risk index of the sub-region where the i-th high-temperature abnormal point is located, represent the fire risk index and self-risk index of the sub-region where the i-th high-temperature abnormal point is located, Real-time temperature time series data of the sub-region where each high temperature anomaly point is located. This indicates the sub-region number where the high-temperature anomaly point is located. Represents a time variable. and These represent the first weighting coefficient and the second weighting coefficient, respectively. ,and .

[0073] The ignition source risk index reflects the potential danger of ignition sources in a region. It measures the probability and severity of spontaneous combustion in the area. The temperature change rate reflects the speed at which the temperature rises within the region; the faster the temperature rises, the higher the probability of ignition. The intrinsic risk index is a risk assessment value constructed based on the geological conditions of the region. It represents the inherent fire risk potential of a sub-region due to geological conditions. By combining the risk indices of temperature change rate and geological conditions, the ignition source risk index provides a more accurate basis for actual monitoring and early warning. By calculating this index in real time, high-risk areas can be better identified, allowing for the implementation of corresponding safety measures.

[0074] This index helps assess which areas in a goaf have a higher fire risk, allowing for early prediction and prevention of potential natural fires. A greater rate of temperature change (faster temperature rise) indicates a higher ignition risk in that area. Rapid temperature increases typically mean an accumulation of oxygen and heat, making fires more likely. Therefore, a higher rate of temperature change results in a higher ignition risk index. The intrinsic risk index is primarily determined by geological factors; a higher value indicates more fire-prone geological conditions in the area. Thus, a higher intrinsic risk index also correlates with a higher ignition risk index. The rate of temperature change is positively correlated with the ignition risk index. As the rate of temperature increase increases, the risk of ignition also increases. This relationship can be moderated by multiplying by a constant to adjust the importance of the rate of temperature change in ignition risk assessment. The intrinsic risk index is also positively correlated with the ignition risk index.

[0075] right The purpose of taking the logarithm is to prevent the impact of high-risk areas from being too drastic and to prevent extreme values ​​from causing excessive bias in risk assessment. This logarithmic function helps to smooth the risk value of high-risk areas, so that the fire source risk index will not be distorted due to excessive extreme geological factors.

[0076] This represents the rate of temperature change at a high-temperature anomaly point; it describes how quickly the temperature at that point changes over time. A higher rate of temperature change indicates a greater increase in temperature over a short period. Rapid temperature increases usually mean a rapid accumulation of energy in the area, which provides conditions for the formation of ignition sources. This product term means that the rate of temperature change (representing the speed of heat accumulation) and geological conditions are combined to quantify the risk of ignition. If the temperature in a sub-region changes very rapidly, but the geological conditions are also conducive to ignition (such as thick coal seams and low density), then the risk of ignition in that region will be high. Through this combination, we not only consider the rapid temperature change, but also fully consider the responsiveness of the region's geological factors to temperature changes.

[0077] The geological risk index is square-rooted to balance the impact of geological conditions on ignition source risk, preventing the weighting of high-risk areas from becoming excessively extreme. The square root of the geological risk index reflects the relative contribution of the region's geological conditions to ignition source risk. Using the square root avoids over-amplification of high-risk areas (such as extremely thick coal seams or low-density areas) when calculating ignition source risk, thus maintaining the rationality and stability of the calculation.

[0078] The rate of temperature change is a direct indicator of ignition source formation; a rapid rise in temperature often signifies heat accumulation, providing conditions for ignition. Fire risk is often directly related to the rate of temperature change. Therefore, the weight of the rate of temperature change should be relatively large. The geological risk index is determined by geological factors such as coal seam thickness, rock density, and porosity. Although these factors play an important role in the ignition process, their influence on the rate of ignition is slower than that of temperature change and may accumulate gradually over time. Therefore, the weight of geological risk should be relatively small. This reflects the greater importance of the rate of temperature change in fire source risk prediction, while geological conditions are used as an auxiliary factor to weight and adjust the risk value.

[0079] set up This is to ensure that the sum of the two weighting coefficients is 1, thus avoiding over-amplification of the influence of any one factor while maintaining the overall balance of the model. Normalization ensures that the combined impact of the temperature change rate and the geological risk index is within a reasonable scale.

[0080] The weighting coefficients are used to analyze past fire incidents and compare the importance of temperature change rates and geological conditions in fire occurrence. These two weighting coefficients can be automatically adjusted using regression analysis, machine learning algorithms, and other methods to optimally fit historical data.

[0081] Step 6: Compare the fire source risk index and risk threshold of each sub-region where the high temperature anomaly point is located. When the fire source risk index exceeds the risk threshold, issue a spontaneous combustion warning and generate the predicted fire source location based on the location information of the high temperature anomaly point.

[0082] In this embodiment, a natural ignition warning is issued, and the method for generating the predicted location of the fire source based on the location information of the high-temperature abnormal point is as follows: When the fire source risk index of any one sub-region where the high-temperature abnormal point is located is greater than the preset risk threshold, a natural ignition warning is issued, and the three-dimensional coordinate information of the predicted location of the fire source is calculated. The predicted three-dimensional coordinate information is wherein: wherein, represents the number of sub-regions where the high-temperature abnormal point is located, , and respectively represent the three-dimensional coordinate information of the top marker point of the sub-region where the i-th high-temperature abnormal point is located, , and respectively represent the three-dimensional coordinate information of the bottom marker point of the sub-region where the i-th high-temperature abnormal point is located. When the fire source risk index of any one sub-region where the high-temperature abnormal point is located exceeds the preset risk threshold, the system will issue a natural ignition warning. In the case of triggering the warning, the system will predict the three-dimensional coordinate position of the fire source based on the location information of the high-temperature abnormal point to help determine the possible occurrence position of the fire source. The predicted fire source position is based on the weighted average of the location information of the top marker point and the bottom marker point, and the fire source risk index of each high-temperature abnormal point is used as a weighting coefficient for the calculation.

[0083] The three-dimensional position of the predicted fire source is calculated by weighted average. In this calculation, the fire source risk index is used as the weight, and the higher the fire source risk index, the greater the possibility of fire in that region. Therefore, the predicted location of the fire source depends more on the region with a higher fire source risk index, and the location of the fire source is usually near the high-temperature abnormal point. Therefore, the midpoint of the top and bottom coordinates is used to estimate the location of the fire source, and the influence of the fire source risk index on the predicted location of the fire source is weighted according to the risk level of the region. The region with a high fire source risk index will have a greater impact on the calculation of the fire source location because it has a higher risk and a higher possibility of fire. Therefore, the predicted location of the fire source will be biased towards these high-risk regions.

[0084] The three-dimensional position of the predicted fire source is calculated by weighted average. In this calculation, the fire source risk index is used as the weight, and the higher the fire source risk index, the greater the possibility of fire in that region. Therefore, the predicted location of the fire source depends more on the region with a higher fire source risk index, and the location of the fire source is usually near the high-temperature abnormal point. Therefore, the midpoint of the top and bottom coordinates is used to estimate the location of the fire source, and the influence of the fire source risk index on the predicted location of the fire source is weighted according to the risk level of the region. The region with a high fire source risk index will have a greater impact on the calculation of the fire source location because it has a higher risk and a higher possibility of fire. Therefore, the predicted location of the fire source will be biased towards these high-risk regions.

[0085] ​The weighted average method combines the risk level of each high-temperature anomaly point in the sub-region with the position coordinates to obtain a more practically meaningful fire source prediction position. This method takes into account the risk differences in different regions, avoids the deviation of simply calculating the position midpoint, improves the accuracy of fire source prediction, and can avoid relying on the deviation of a single point by comprehensively considering the top and bottom marker point positions of all high-temperature anomaly points in the sub-region, thereby obtaining a more stable and reliable fire source position prediction.

[0086] By adopting the strategy of issuing a warning when the fire risk of any one high-temperature anomaly point exceeds the threshold value, the system can respond to the possibility of fire occurrence as early as possible, start warning before the fire occurs, and predict the fire location, which helps to prevent the spread of fire. The setting of the risk threshold is a key problem in the fire risk warning system, which affects the accuracy and timeliness of the warning. If the threshold is set too high, it may lead to a missed report (i.e. ignoring some high-risk areas), and if the threshold is too low, it may lead to a false alarm (i.e. too frequent warnings). By analyzing the historical fire occurrence data and understanding the relationship between different fire risk indexes and actual fire occurrence, a reasonable empirical threshold can be obtained. For example, by comparing the fire risk indexes of the areas where fires have occurred in history, a threshold based on statistical and historical data can be set.

[0087] Referring to Figure 2 The application further provides a goaf spontaneous combustion prediction system based on a geological mathematical model, which is used to execute the goaf spontaneous combustion prediction method based on the geological mathematical model. A data marking module is configured to obtain the overhead plane range data of the goaf, divide the overhead plane of the goaf into multiple uniform rectangular grids, take each grid as a sub-region, bury ferroelectric materials as marker points at the top and bottom of the goaf in the center of each sub-region, and obtain the position information of each marker point. A region risk assessment module is configured to obtain the thickness of the coal seam at the bottom of each sub-region and the geological data of the goaf, construct a self-risk assessment model, generate a self-risk index of each sub-region, and the geological data includes the stratum thickness, rock density and porosity of each sub-region. A temperature detection module is configured to emit electromagnetic waves by using a ground penetrating radar and receive the signals reflected by the ferroelectric materials of each marker point, extract the real-time dielectric constant of the marker point, and convert the real-time dielectric constant of the marker point into the real-time temperature of the marker point by using the Clausius-Mossotti equation. The abnormality evaluation module generates a three-dimensional temperature field distribution model of the goaf by using an inverse distance weighted interpolation method according to real-time temperature data and position data of each marker point, extracts high-temperature abnormal points of the goaf through the three-dimensional temperature field distribution model, and continuously obtains real-time temperature time series data of a sub-region where the high-temperature abnormal points are located through the ground penetrating radar and the ferroelectric material of the marker points; The risk analysis module is configured to calculate a temperature change rate according to the real-time temperature time series data of the sub-region where the high-temperature abnormal points are located, construct a fire source risk model in combination with a self risk index corresponding to the sub-region where the high-temperature abnormal points are located, and generate a fire source risk index of each sub-region where the high-temperature abnormal points are located. The fire ignition warning module is configured to compare the fire source risk index of each sub-region where the high-temperature abnormal points are located with a risk threshold value, issue a spontaneous combustion warning when the fire source risk index exceeds the risk threshold value, and generate a fire source prediction position according to position information of the high-temperature abnormal points.

[0088] The above formulas are all dimensionless values, and the formulas are obtained by collecting a large amount of data to simulate a formula of the nearest real situation, and preset parameters in the formulas are set by a person skilled in the art according to actual conditions.

[0089] The above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part. A person skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0090] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0091] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for predicting spontaneous combustion in goaf areas based on a geological mathematical model, characterized in that, The specific steps include: Step 1: Obtain the top-view plane range data of the goaf, divide the top-view plane of the goaf into multiple uniform rectangular grids, each grid as a sub-region, and bury ferroelectric material as marker points at the top and bottom of the goaf corresponding to the center of each sub-region, and obtain the position information of each marker point; Step 2: Obtain the thickness of the coal seam at the bottom of each sub-region and the geological data of the goaf, and construct its own risk assessment model to generate the risk index of each sub-region. The geological data includes the stratum thickness, rock density and porosity of each sub-region. Step 3: Use ground-penetrating radar to emit electromagnetic waves and receive the signals reflected by the ferroelectric material at each marker point. Extract the real-time dielectric constant of the marker point and use the Clausius-Mosotti equation to convert the real-time dielectric constant of the marker point into the real-time temperature of the marker point. Step 4: Based on the real-time temperature and location data of each marker point, a three-dimensional temperature field distribution model of the goaf is generated using the inverse distance weighted interpolation method. High-temperature anomalies in the goaf are extracted using the three-dimensional temperature field distribution model. Real-time temperature time series data of the sub-regions where the high-temperature anomalies are located are continuously obtained using ground penetrating radar and the ferroelectric materials of the marker points. Step 5: Calculate the temperature change rate based on the real-time temperature time series data of the sub-region where the high temperature anomaly point is located, and construct a fire source risk model by combining the risk index of the sub-region where the high temperature anomaly point is located, and generate the fire source risk index of the sub-region where each high temperature anomaly point is located. Step 6: Compare the fire source risk index and risk threshold of each sub-region where the high temperature anomaly point is located. When the fire source risk index exceeds the risk threshold, issue a spontaneous combustion warning and generate the predicted fire source location based on the location information of the high temperature anomaly point.

2. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 1, characterized in that, The method for constructing sub-regions is as follows: Obtain the top-view plane range data of the goaf, construct the boundary contour of the top-view plane of the goaf, and enclose the boundary contour of the goaf using the minimum bounding rectangle; The outer rectangle is evenly divided according to a fixed grid size to generate a regular grid structure, and it is determined whether the center point of each grid is located within the boundary outline of the goaf. If the center point of a grid is located within the boundary outline of the goaf, the grid is retained as a valid grid; otherwise, the grid is deleted, and each valid grid is treated as a sub-region.

3. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 2, characterized in that, The method of burying ferroelectric materials as marker points is as follows: Calculate the center point of each effective grid, construct a vertical line perpendicular to the grid surface, and mark the intersection of the vertical line with the roof and floor surfaces of the goaf as the corresponding grid point. Place ferroelectric material on the rock or coal seam surface at the top and bottom of the goaf at the marked point. The thickness of the coal seam at the bottom of the sub-region is the thickness of the coal seam at the bottom marker point of the sub-region. The stratum thickness of the sub-region is the shortest distance from the ground at the top marker point of the sub-region. The rock density and porosity of the sub-region are the rock density and porosity of the strata at the top marker point of the sub-region.

4. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 3, characterized in that, The formula used to construct the risk assessment model and generate the risk index for each sub-region is as follows: in, Indicates the first The risk index of each sub-region , , and They represent the first Data on coal seam thickness, stratigraphic thickness, rock density, and porosity for each sub-region. Indicates the density of typical rocks, Indicates the sub-region number.

5. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 1, characterized in that, The formula used to convert the real-time dielectric constant of a marker point to its real-time temperature is as follows: in, and They represent the first The real-time temperature and the detected real-time dielectric constant of each marker point. and These represent the Curie temperature and Curie constant of the buried ferroelectric material, respectively. This indicates the initial dielectric constant of the buried ferroelectric material. Indicates the number of the marker point.

6. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 5, characterized in that: The three-dimensional temperature field distribution model of the goaf is generated using the inverse distance weighted interpolation method as follows: in, In the three-dimensional temperature field distribution model Temperature estimate of the point, This indicates the total number of marked points. In the three-dimensional temperature field distribution model Point and the The distance between the marker points is calculated using the following formula: in, , and They represent the first The three-dimensional coordinate information of the nth marker point, i.e., the nth Location information of each marker point , and These respectively represent the three-dimensional temperature field distribution model. The three-dimensional coordinate information of the point, and: The origin of the three-dimensional coordinate system is the lowest elevation point in the goaf area. The axis is oriented due east. The axis is oriented due south. The axis is perpendicular to the ground.

7. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 6, characterized in that, When extracting high-temperature anomaly points in the goaf using a three-dimensional temperature field distribution model, the estimated temperature value of each point in the three-dimensional temperature field distribution model is compared with the temperature risk threshold. If... Then, this point is marked as a high temperature anomaly point. Indicates the temperature risk threshold; While continuously acquiring real-time temperature time-series data of the sub-region where the high-temperature anomaly point is located, the real-time temperature time-series data of two marked points in the sub-region where the high-temperature anomaly point is located are simultaneously acquired in real time to generate the real-time temperature time-series data of the sub-region. The formula used is as follows: in, Indicates the first Real-time temperature time series data of the sub-region where each high temperature anomaly point is located. and They represent the first Real-time temperature time-series data of the top and bottom markers within the sub-region where each high-temperature anomaly is located. This indicates the sub-region number where the high-temperature anomaly point is located. Represents a time variable.

8. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 1, characterized in that, The logic behind generating the fire source risk index for each sub-region where a high-temperature anomaly point is located is as follows: in, and They represent the first The fire source risk index and the self-risk index of the sub-region where each high temperature anomaly point is located. Indicates the first Real-time temperature time series data of the sub-region where each high temperature anomaly point is located. This indicates the sub-region number where the high-temperature anomaly point is located. Represents a time variable. and These represent the first weighting coefficient and the second weighting coefficient, respectively. ,and .

9. The method for predicting spontaneous combustion in goaf areas based on a geological mathematical model according to claim 8, characterized in that, The method for issuing a spontaneous combustion warning and generating a predicted fire source location based on the location information of high temperature anomalies is as follows: When the fire source risk index of any sub-region containing a high-temperature anomaly exceeds a preset risk threshold, a spontaneous combustion warning is issued. Simultaneously, the three-dimensional coordinates of the predicted fire source location are calculated. The predicted three-dimensional coordinates are... ,in: in, This indicates the number of sub-regions where the high-temperature anomaly point is located. , and They represent the first The three-dimensional coordinate information of the top marker point of the sub-region where each high temperature anomaly point is located. , and They represent the first The three-dimensional coordinate information of the bottom marker point of the sub-region where the high temperature anomaly point is located.

10. A system for predicting spontaneous combustion in goaf areas based on a geological mathematical model, characterized in that: The prediction system is used to execute the spontaneous combustion prediction method for goaf areas based on a geological mathematical model as described in any one of claims 1-9, comprising: The data marking module is used to obtain the top-view plane range data of the goaf, divide the top-view plane of the goaf into multiple uniform rectangular grids, each grid is a sub-region, and ferroelectric material is buried as a marker point at the top and bottom of the goaf corresponding to the center of each sub-region, and the position information of each marker point is obtained. The regional risk assessment module is used to obtain the thickness of the coal seam at the bottom of each sub-region and the geological data of the goaf, and to construct its own risk assessment model to generate the risk index of each sub-region. The geological data includes the stratum thickness, rock density and porosity of each sub-region. The temperature detection module is used to emit electromagnetic waves using ground penetrating radar and receive the signals reflected by the ferroelectric material at each marker point, extract the real-time dielectric constant of the marker point, and use the Clausius-Mosotti equation to convert the real-time dielectric constant of the marker point into the real-time temperature of the marker point. The anomaly assessment module generates a three-dimensional temperature field distribution model of the goaf using inverse distance weighted interpolation based on the real-time temperature and location data of each marker point. It then extracts high-temperature anomaly points in the goaf through the three-dimensional temperature field distribution model and continuously acquires real-time temperature time series data of the sub-regions where the high-temperature anomaly points are located through ground-penetrating radar and the ferroelectric materials of the marker points. The risk analysis module is used to calculate the rate of temperature change based on the real-time temperature time series data of the sub-region where the high temperature anomaly point is located, and to construct a fire source risk model by combining the risk index of the sub-region where the high temperature anomaly point is located, and to generate the fire source risk index of the sub-region where each high temperature anomaly point is located. The fire warning module is used to compare the fire source risk index and risk threshold of each sub-region where the high temperature anomaly point is located. When the fire source risk index exceeds the risk threshold, a spontaneous combustion warning is issued, and the predicted fire source location is generated based on the location information of the high temperature anomaly point.

Images