Mining area mining monitoring method and system

Abstract

The invention provides a mining area mining monitoring method and system. The system comprises a synthetic aperture radar interference monitoring module, an optical remote sensing monitoring module and a microseismic monitoring module. The method comprises the following steps: a synthetic aperture radar interference monitoring module obtains synthetic aperture radar image data of a mining area, carries out surface subsidence monitoring on the mining area according to the synthetic aperture radar image data, and determines a target monitoring area of the mining area; and the optical remote sensing monitoring module obtains optical remote sensing image data of the target area, determines surface damage information according to the optical remote sensing image data of the target area and the synthetic aperture radar image data, and monitors mining behaviors of the mining area according to the surface damage information. The optical remote sensing image data comprises satellite image data and aerial image data; and the micro-seismic monitoring module obtains underground micro-seismic data of the targeted monitoring area, and carries out real-time monitoring and positioning on mining behaviors of the targeted monitoring area according to the micro-seismic data so as to realize all-directional monitoring of mining area mining.

Description

Technical Field

[0001] This application relates to the technical field of mine safety and monitoring. Specifically, it relates to a method and system for monitoring mining in a mining area. Background Art

[0002] During coal mining, mine safety problems are likely to occur. Illegal mining behaviors mainly include unlicensed mining, cross - seam mining, boundary - crossing mining, and mining in other people's mining areas. These behaviors are characterized by high concealment, difficulty in discovery, and difficulty in supervision, and are extremely likely to induce major safety accidents such as mine water inrush and gas explosion, resulting in damage to surface buildings and transportation and power infrastructure, and even causing casualties.

[0003] Currently, the traditional supervision of illegal mining in mines mainly relies on manual investigation and screening. However, due to the large area of the mining area and the large number of mining rights, there are disadvantages such as high intensity and low efficiency of manual monitoring. Moreover, manual verification requires the high cooperation of the mining party, is highly subjective, and it is also difficult to achieve real - time monitoring.

[0004] Therefore, the existing technology cannot accurately identify and real - time sense illegal mining behaviors in mines, and there are certain limitations. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for monitoring mining in a mining area to solve the problem of the actual need in the existing technology that cannot accurately identify and real - time sense illegal mining behaviors in mines, aiming at the deficiencies in the above - mentioned existing technology.

[0006] To achieve the above purpose, the technical solutions adopted in the embodiments of this application are as follows:

[0007] In a first aspect, the embodiments of this application provide a method for monitoring mining in a mining area, which is applied to a mining area monitoring system. The mining area monitoring system includes: an InSAR (Interferometric Synthetic Aperture Radar) monitoring module, an optical remote sensing monitoring module, and a micro - seismic monitoring module. The method includes:

[0008] The InSAR monitoring module obtains InSAR image data of the mining area, and based on the InSAR image data, monitors the surface subsidence of the mining area and determines the targeted monitoring area of the mining area;

[0009] The optical remote sensing monitoring module obtains optical remote sensing image data of the target area, and based on the optical remote sensing image data of the target area and the InSAR image data, determines surface damage information, and monitors the mining behavior in the mining area according to the surface damage information. The optical remote sensing image data includes: satellite image data and aerial photography image data;

[0010] The microseismic monitoring module acquires microseismic data underground in the target monitoring area, and performs real-time monitoring and positioning of the mining behavior in the target monitoring area based on the microseismic data.

[0011] As an alternative implementation, the method for monitoring surface subsidence of the mining area based on the synthetic aperture radar image data and determining the target monitoring area of the mining area includes:

[0012] The synthetic aperture radar interferometric monitoring module performs time-series surface subsidence screening on the mining area according to the synthetic aperture radar image data and a pre-constructed mining subsidence model, and determines surface subsidence information;

[0013] The synthetic aperture radar interferometric monitoring module determines the target monitoring area of the mining area according to the surface subsidence information.

[0014] As an alternative implementation, the method for performing time-series surface subsidence screening on the mining area according to the synthetic aperture radar image data and a pre-constructed mining subsidence model to determine surface subsidence information includes:

[0015] The synthetic aperture radar interferometric monitoring module determines the phase information, amplitude information, and polarization information in the synthetic aperture radar image data;

[0016] The synthetic aperture radar interferometric monitoring module inputs the phase information, amplitude information, and polarization information in the synthetic aperture radar image data into a pre-constructed deep learning model, and the deep learning model extracts surface subsidence features;

[0017] The synthetic aperture radar interferometric monitoring module determines the surface subsidence information according to the surface subsidence features and the mining subsidence model.

[0018] As an alternative implementation, the optical remote sensing monitoring module acquires optical remote sensing image data of the target area, including:

[0019] The optical remote sensing monitoring module acquires satellite image data of the target area collected by an optical satellite;

[0020] The optical remote sensing monitoring module acquires aerial photography image data of the target area collected by an unmanned aerial vehicle, where the aerial photography image data is used to supplement the detail information of the synthetic aperture radar image data and the satellite image data.

[0021] As an alternative implementation, the method for determining surface damage information according to the optical remote sensing image data and synthetic aperture radar image data of the target area includes:

[0022] The optical remote sensing monitoring module respectively extracts features from the optical satellite image data, synthetic aperture radar image data, and aerial image data of the target area to obtain the optical satellite image features, synthetic aperture radar image features, and aerial image features of the target area;

[0023] The optical remote sensing monitoring module obtains a fusion feature based on the optical satellite image features, synthetic aperture radar image features, and aerial image features of the target area, and determines the surface damage information based on the fusion feature.

[0024] As an optional implementation manner, the obtaining a fusion feature based on the optical satellite image features, synthetic aperture radar image features, and aerial image features of the target area, and determining the surface damage information based on the fusion feature includes:

[0025] The optical remote sensing monitoring module performs spatial registration on the optical satellite image features, synthetic aperture radar image features, and aerial image features of the target area, and performs feature fusion on the registered optical satellite image features, synthetic aperture radar image features, and aerial image features to obtain a fusion feature;

[0026] The optical remote sensing monitoring module determines the surface damage information based on the fusion feature and the dynamic development law of ground fissures caused by mine exploitation.

[0027] As an optional implementation manner, the microseismic monitoring module obtains microseismic data underground in the targeted monitoring area, including:

[0028] The microseismic monitoring module obtains the microseismic data underground in the targeted monitoring area collected by microseismic sensors, where the microseismic sensors include multiple shallow-buried microseismic sensors and multiple deep-buried microseismic sensors, and each of the shallow-buried microseismic sensors is deployed at each monitoring point on the surface of the targeted monitoring area, and each of the deep-buried microseismic sensors is drilled and deployed at each monitoring point underground in the targeted monitoring area.

[0029] As an optional implementation manner, the performing real-time monitoring and positioning of the mining behavior in the targeted monitoring area based on the microseismic data includes:

[0030] The microseismic monitoring module determines whether a new microseismic event occurs through spectral analysis based on the microseismic waveforms in the microseismic data and a pre-constructed microseismic event template library, where the microseismic event template library includes the waveforms of various rock mass micro-rupture events induced by mine exploitation;

[0031] If so, the microseismic monitoring module determines two adjacent microseismic event pairs, and constructs a microseismic double-difference model for the microseismic event pairs according to the microseismic data;

[0032] The microseismic monitoring module determines the relative positions of the microseismic event pairs according to the microseismic double-difference model, and determines the mining positions in the mining area according to the relative positions of the microseismic event pairs.

[0033] As an optional implementation manner, the determining the relative positions of the microseismic event pairs according to the microseismic double-difference model includes:

[0034] The microseismic monitoring module determines the time difference of arrival of the microseismic event pairs at the same microseismic sensor according to the microseismic double-difference model, and the time difference of arrival is the residual between the observed value and the theoretically calculated value;

[0035] The microseismic monitoring module determines the relative positions of the microseismic event pairs according to the time difference of arrival.

[0036] In a second aspect, an embodiment of the present application provides a mining area mining monitoring system, and the mining area mining monitoring system includes: an InSAR monitoring module, an optical remote sensing monitoring module, and a microseismic monitoring module;

[0037] Each module in the mining area mining monitoring system is respectively used for the corresponding method steps in the mining area mining monitoring method described in the first aspect above.

[0038] The beneficial effects of the present application are:

[0039] The present application provides a method and system for monitoring mining areas. The mining area monitoring system includes an InSAR (Interferometric Synthetic Aperture Radar) monitoring module, an optical remote sensing monitoring module, and a microseismic monitoring module. The InSAR monitoring module acquires InSAR image data of the mining area, conducts wide-area surface subsidence monitoring on the mining area based on the InSAR image data, and determines the targeted monitoring area of the mining area according to the surface subsidence monitoring results. The optical remote sensing monitoring module acquires optical remote sensing image data of the target area, including satellite image data of the target area obtained periodically from space and aerial photography image data of the target area obtained from airborne platforms. And based on the optical remote sensing image data and InSAR image data of the target area, refined collaborative detection of surface damage is carried out to determine the surface damage information of the target area. Periodic monitoring of mining activities in the mining area is carried out according to the surface damage information. The microseismic monitoring module monitors the microseismic activities underground in the targeted monitoring area, obtains the microseismic data underground in the targeted monitoring area in real time, and based on the microseismic data, continuous and normalized mining monitoring is implemented for the targeted monitoring area that requires key attention, realizing real-time monitoring and positioning of the mining activities in the targeted monitoring area. Through the InSAR monitoring module, optical remote sensing monitoring module, and microseismic monitoring module in the mining area monitoring system, a three-dimensional collaborative perception and monitoring system for illegal mining in mines with multi-source information fusion of "sky, land, surface, and underground" is created, realizing all-round perception of wide-area screening, key supplementary inspection, and real-time monitoring of illegal mining in mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a schematic diagram of the architecture of the mining area monitoring system provided by the embodiment of the present application;

[0042] Figure 2 It is a schematic diagram of the flow of the mining area monitoring method provided by the embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of the result of the targeted monitoring area determined by the InSAR monitoring module provided by the embodiment of the present application;

[0044] Figure 4 It is a schematic diagram of the result of the surface damage information determined by the optical remote sensing monitoring module provided by the embodiment of the present application;

[0045] Figure 5Schematic diagram of the all-round collaborative monitoring system for illegal mining in mines with "sky, ground, well" integration provided by the embodiments of the present application;

[0046] Figure 6 Schematic diagram of the process of determining the targeted monitoring area of the mining area in the mining area monitoring method provided by the embodiments of the present application;

[0047] Figure 7 Schematic diagram of the process of determining surface subsidence information in the mining area monitoring method provided by the embodiments of the present application;

[0048] Figure 8 Schematic diagram of the result of surface subsidence information determined by the synthetic aperture radar interferometry monitoring module provided by the embodiments of the present application;

[0049] Figure 9 Schematic diagram of the process of obtaining optical remote sensing image data of the target area in the mining area monitoring method provided by the embodiments of the present application;

[0050] Figure 10 Schematic diagram of the process of determining surface damage information in the mining area monitoring method provided by the embodiments of the present application;

[0051] Figure 11 Another schematic diagram of the process of determining surface damage information in the mining area monitoring method provided by the embodiments of the present application;

[0052] Figure 12 Schematic diagram of the deployment effect of shallow-buried microseismic sensors provided by the embodiments of the present application;

[0053] Figure 13 Schematic diagram of the deployment effect of deep-buried microseismic sensors provided by the embodiments of the present application;

[0054] Figure 14 Schematic diagram of the network topology of microseismic data transmission provided by the embodiments of the present application;

[0055] Figure 15 Schematic diagram of the process of real-time monitoring and positioning the mining behavior in the targeted monitoring area of the mining area monitoring method provided by the embodiments of the present application;

[0056] Figure 16 Schematic diagram of detecting new microseismic events through spectral analysis provided by the embodiments of the present application;

[0057] Figure 17 Schematic diagram of the process of determining the relative position of microseismic event pairs in the mining area monitoring method provided by the embodiments of the present application;

[0058] Figure 18 Schematic diagram of the result of accurately determining the mining location in the mining area based on microseismic events provided by the embodiments of the present application. Detailed implementation manners

[0059] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the accompanying drawings in the present application are only for the purposes of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn in actual proportions. The flowcharts used in the present application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowchart may not be implemented in sequence, and the steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present application.

[0060] In addition, the described embodiments are only some embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application usually described and illustrated in the accompanying drawings here may be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0061] It should be noted that the term "including" will be used in the embodiments of the present application to indicate the existence of the features stated thereafter, but does not exclude the addition of other features.

[0062] During the illegal coal mining process, mine safety problems are likely to occur. At present, the traditional supervision of illegal mine mining mainly relies on manual investigation and screening. The intensity of manual supervision is high, the difficulty is high, the efficiency is low, the timeliness is poor, the verification work requires the high cooperation of the mining party, has strong subjectivity, and it is also difficult to achieve real-time monitoring. There are problems of difficult discovery, difficult monitoring, and difficult supervision of illegal mining in the mining area. The prior art cannot achieve the accurate identification and real-time perception of illegal mine mining behaviors.

[0063] Based on the above problems, the embodiments of the present application propose a mining area monitoring method. By integrating the precise monitoring of synthetic aperture radar interferometry for surface subsidence, the multi-source optical remote sensing extraction of surface damage information, and the precise positioning of microseisms in underground mining sites, a comprehensive collaborative monitoring system for "sky-earth-shaft" integrated illegal mine mining is created, realizing the wide-area screening, key supplementary inspection, and real-time monitoring of illegal mine mining.

[0064] Figure 1 For the schematic diagram of the architecture of the mining area monitoring system provided by the embodiments of the present application, asFigure 1 As shown in the figure, the mining area exploitation monitoring system includes: an Interferometric Synthetic Aperture Radar (InSAR for short) monitoring module, an optical remote sensing monitoring module, and a microseismic monitoring module. Among them, the InSAR monitoring module, the optical remote sensing monitoring module, and the microseismic monitoring module can communicate with each other.

[0065] Specifically, the InSAR monitoring module is used to achieve wide-area screening of surface subsidence and precise identification of the targeted monitoring area in the mining area through space-based monitoring. The optical remote sensing monitoring module is used to achieve fine detection of surface damage and periodic monitoring of mining activities in the mining area through space-based and airborne monitoring. The microseismic monitoring module is used to achieve real-time monitoring and precise positioning of underground mining activities in the targeted monitoring area through ground-based and underground monitoring of the targeted monitoring area. Based on the mining area exploitation monitoring system, a three-dimensional collaborative perception and monitoring system for illegal mining in mines with multi-source information fusion of "sky, land, air, and well" is created, realizing all-round perception of wide-area screening, key supplementary inspection, and real-time monitoring of illegal mining in mines.

[0066] Figure 2 The flowchart of the mining area exploitation monitoring method provided by the embodiment of the present application is as follows Figure 2 As shown in the figure, the execution subject of this method is the mining area exploitation monitoring system shown above Figure 1 As shown in the figure, this method includes: Figure 2 As shown in the figure, this method includes:

[0067] S101. The Interferometric Synthetic Aperture Radar monitoring module acquires the synthetic aperture radar image data of the mining area, and based on the synthetic aperture radar image data, monitors the surface subsidence of the mining area and determines the targeted monitoring area of the mining area.

[0068] Optionally, Synthetic Aperture Radar (SAR for short), as an active microwave remote sensing technology, SAR can work at any time (day or night) and under any weather conditions (sunny, cloudy, rainy, foggy, etc.), because microwaves can penetrate clouds, smoke, and a certain thickness of vegetation, and have the ability of all-weather and all-time observation.

[0069] The InSAR monitoring module takes advantage of the all-weather, all-day, wide coverage, and area observation characteristics of SAR devices installed on space-based platforms such as satellites. Based on the SAR on the satellite platform, it can achieve large-area and periodic monitoring of mining areas, and obtain SAR image data of mining areas at different times. The InSAR monitoring module conducts wide-area surface subsidence monitoring of the mining area based on the SAR image data of the mining area, and determines the targeted monitoring area of the mining area according to the results of the surface subsidence monitoring. Among them, the wide-area surface subsidence monitoring is to quickly screen for areas where illegal mining may exist within a large range, identify surface subsidence anomalies, and identify the areas with surface subsidence anomalies as the targeted monitoring areas of the mining area, so as to conduct further refined mining area monitoring of the targeted monitoring areas during subsequent monitoring.

[0070] The InSAR monitoring module realizes effective monitoring of surface subsidence in the mining area by acquiring and analyzing SAR image data, and determines the targeted monitoring areas that need to be focused on. Figure 3 The schematic diagram of the results of the targeted monitoring area determined by the synthetic aperture radar interference monitoring module provided by the embodiment of the present application is as Figure 3 shown, Figure 3 In the figure, multiple colored parts are all targeted monitoring areas identified through interference, that is, there are surface subsidence anomalies in the mining areas corresponding to the colored parts.

[0071] S102. The optical remote sensing monitoring module acquires optical remote sensing image data of the target area, determines surface damage information based on the optical remote sensing image data of the target area and the synthetic aperture radar image data, and monitors the mining area mining behavior according to the surface damage information. The optical remote sensing image data includes: satellite image data and aerial photography image data.

[0072] Optionally, the mining area has crisscrossed loess gullies, and illegal coal mining is extremely likely to cause loess landslides and landslides, resulting in decoherence of the InSAR technology in these areas and making it difficult to achieve surface subsidence monitoring. At this time, it is necessary to supplement and verify the surface subsidence monitoring results of the InSAR monitoring module through the optical remote sensing monitoring module.

[0073] The optical remote sensing monitoring module acquires optical remote sensing image data of the target area. Specifically, the optical remote sensing monitoring module periodically acquires satellite image data of the target area on a space-based platform and acquires aerial photography image data of the target area on an air-based platform.

[0074] The optical remote sensing monitoring module conducts refined collaborative detection of surface damage based on the satellite image data, aerial photography image data, and SAR image data of the target area, and determines the surface damage information of the target area. The surface damage information is closely related to the mining area mining behavior, and the optical remote sensing monitoring module conducts periodic monitoring of the mining area mining behavior according to the surface damage information of the target area.

[0075] It should be noted that the target area can be a preset mining area that needs to be monitored with emphasis or an area with InSAR decoherence, so as to conduct refined monitoring of surface damage in the target area through the optical remote sensing monitoring module.

[0076] Figure 4 It is a schematic diagram of the result of the surface damage information determined by the optical remote sensing monitoring module provided in the embodiment of the present application. As Figure 4 shown, Figure 4 The red marked part in it is the ground fissure caused by mining in the mining area identified by the optical remote sensing monitoring module, realizing the accurate perception and identification of surface damage information.

[0077] S103. The microseismic monitoring module obtains the microseismic data underground in the targeted monitoring area, and based on the microseismic data, conducts real-time monitoring and positioning of the mining behavior in the targeted monitoring area.

[0078] Optionally, the microseismic monitoring module is used to monitor the microseismic activities underground in the targeted monitoring area, so as to obtain the microseismic data underground in the targeted monitoring area in real time, and based on the microseismic data, implement continuous and regular mining monitoring of the targeted monitoring area that needs to be focused on, realizing real-time monitoring and positioning of the mining behavior in the targeted monitoring area.

[0079] Specifically, the targeted monitoring area determined in the above-mentioned surface subsidence monitoring process is used as the main monitoring range of the microseismic monitoring module. The microseismic monitoring module realizes real-time monitoring and precise positioning of the mining behavior in the targeted monitoring area on the ground foundation by obtaining and analyzing the microseismic data underground in the targeted monitoring area in real time.

[0080] Figure 5 It is a schematic diagram of the all-round collaborative monitoring system for illegal mining in mines with "sky, ground, well" integration provided in the embodiment of the present application. As Figure 5 shown, the InSAR monitoring module realizes wide-area monitoring of surface subsidence in the mining area on the space-based platform, the optical remote sensing monitoring module realizes refined monitoring of surface damage in the target area on the space-based and air-based platforms, the microseismic monitoring module realizes microseismic monitoring of the targeted monitoring area on the ground-based and underground platforms, creating a three-dimensional collaborative perception and monitoring system for illegal mining in mines with multi-source information fusion of "sky, ground, well", and realizing all-round perception of wide-area screening, key supplementary inspection and real-time monitoring of illegal mining in mines.

[0081] It should be noted that after the three-dimensional collaborative perception and monitoring system for illegal mining in mines with multi-source information fusion of "sky, ground, and well" monitors the mining behavior in the mine and locates the mining position, the mining right scope line can be obtained, and it can be determined whether the mining behavior in the mine is illegal according to the mining right scope line and the mining position. Among them, the mining right scope line can be the boundary line of the permitted mining area, which precisely defines the geographical scope of legal mining in the mine in the form of coordinates. If the located mining position exceeds the mining right scope line, it is determined as an illegal mining behavior in the mine.

[0082] In this embodiment, the mining area monitoring system includes an InSAR monitoring module, an optical remote sensing monitoring module, and a microseismic monitoring module. The InSAR monitoring module acquires InSAR image data of the mining area, and based on the InSAR image data, conducts wide-area surface subsidence monitoring of the mining area, and determines the targeted monitoring area of the mining area according to the surface subsidence monitoring results. The optical remote sensing monitoring module acquires optical remote sensing image data of the target area, including satellite image data of the target area acquired periodically from space and aerial image data of the target area acquired from airborne platforms. And based on the optical remote sensing image data and InSAR image data of the target area, conducts refined collaborative detection of surface damage, and determines the surface damage information of the target area. Conducts periodic monitoring of the mining behavior in the mining area according to the surface damage information. The microseismic monitoring module monitors the microseismic activities underground in the targeted monitoring area, acquires the microseismic data underground in the targeted monitoring area in real time, and based on the microseismic data, implements continuous and normalized mining monitoring of the targeted monitoring areas that need key attention, and realizes real-time monitoring and positioning of the mining behavior in the targeted monitoring area. Through the InSAR monitoring module, optical remote sensing monitoring module, and microseismic monitoring module in the mining area monitoring system, a three-dimensional collaborative perception and monitoring system for illegal mining in mines with multi-source information fusion of "sky, ground, and well" is created, realizing all-round perception of wide-area screening, key supplementary inspection, and real-time monitoring of illegal mining in mines.

[0083] Hereinafter, the process of conducting surface subsidence monitoring of the mining area according to the InSAR image data and determining the targeted monitoring area of the mining area will be described in detail.

[0084] Figure 6 It is a flow chart of determining the targeted monitoring area of the mining area monitoring method provided by the embodiment of the present application. As Figure 6 shown, in the above step S101, according to the InSAR image data, conducting surface subsidence monitoring of the mining area and determining the targeted monitoring area of the mining area includes:

[0085] S201. The InSAR monitoring module conducts time-series surface subsidence screening of the mining area according to the InSAR image data and a pre-constructed mining settlement model, and determines the surface subsidence information.

[0086] Optionally, considering various factors such as the geological structure of the mining area, the mining method, and the rock mechanical properties, a mining subsidence model is established in advance. The mining subsidence model can be a physical model or an empirical model of mining subsidence to describe the subsidence laws and characteristics that may occur on the surface of the mining area under different mining activities. For example, the mining subsidence model can predict the location, degree, and development trend of surface subsidence based on parameters such as the mining depth, scope, and speed.

[0087] The InSAR monitoring module performs preprocessing such as radiometric correction, geometric correction, and denoising on the SAR image data. Combining the preprocessed SAR image data and the pre-constructed mining subsidence model, it conducts time-series screening of surface subsidence in the mining area and analyzes the changes in the surface at different time points. Specifically, as time goes by, the surface of the mining area is continuously monitored and analyzed to screen whether surface subsidence has occurred and the changes in subsidence. For example, by comparing SAR image data from different periods, it is determined which areas have new subsidence, and which areas have an increasing or decreasing subsidence degree.

[0088] After the InSAR monitoring module conducts a wide-area screening of time-series surface subsidence in the mining area, it can determine the surface subsidence information. The surface subsidence information can include the location of subsidence (accurate to specific geographical coordinates or positions within the mining area), the degree of subsidence (such as the height of subsidence or displacement), the development trend of subsidence (gradually increasing, tending to be stable, or gradually recovering), and the scope of subsidence (the area size of the affected region), etc.

[0089] S202. The synthetic aperture radar interferometry monitoring module determines the targeted monitoring areas of the mining area based on the surface subsidence information.

[0090] Optionally, the InSAR monitoring module analyzes and evaluates different areas of the mining area according to the determined surface subsidence information. Specifically, areas with obvious changes in surface subsidence, large displacement amounts, unstable development trends, or potential geological hazard risks (such as ground collapse, landslide, etc.) are mainly screened out. For example, areas with a relatively fast subsidence speed and a displacement amount exceeding a certain threshold, or areas in complex geological sections with subsidence.

[0091] The areas with high risk or important monitoring value screened above are determined as the targeted monitoring areas. In subsequent monitoring work, these targeted monitoring areas are monitored more closely and refined to timely grasp the changes in the targeted monitoring areas and provide more accurate information support for the safe production and management of the mining area.

[0092] In this embodiment, the pre-established mining subsidence model is used to describe the subsidence laws and characteristics that may occur on the surface of the mining area under different mining activities. The synthetic aperture radar interferometry monitoring module combines the synthetic aperture radar image data and the pre-constructed mining subsidence model to conduct time-series surface subsidence screening for the mining area and determine the surface subsidence information. According to the determined surface subsidence information, the synthetic aperture radar interferometry monitoring module analyzes and evaluates different regions of the mining area, and focuses on screening out regions with obvious surface subsidence changes, large displacement amounts, unstable development trends or potential geological disaster risks as the targeted monitoring regions of the mining area. By comprehensively using the synthetic aperture radar image data and the mining subsidence model, the synthetic aperture radar interferometry monitoring module realizes wide-area screening of surface subsidence in the mining area from space and determines the targeted monitoring regions of the mining area for subsequent refined monitoring of the targeted monitoring regions of the mining area.

[0093] The following details the process of conducting time-series surface subsidence screening for the mining area based on the synthetic aperture radar image data and the pre-constructed mining subsidence model to determine the surface subsidence information.

[0094] Figure 7 It is a schematic flowchart of the process for determining surface subsidence information of the mining area monitoring method provided in the embodiment of the present application. As Figure 7 shown, in step S201 above, based on the synthetic aperture radar image data and the pre-constructed mining subsidence model, time-series surface subsidence screening is conducted for the mining area to determine the surface subsidence information, including:

[0095] S301. The synthetic aperture radar interferometry monitoring module determines the phase information, amplitude information, and polarization information in the synthetic aperture radar image data.

[0096] Optionally, the SAR device emits microwave signals to the mining area and receives the radar echo signals reflected back from the mining area, and forms the SAR image data of the mining area after processing. The SAR image data contains multi-dimensional information and can reflect various characteristics of the mining area.

[0097] The InSAR monitoring module determines the phase information, amplitude information, and polarization information in the SAR image data. Specifically, the phase information represents the phase value of the radar echo signal, and the phase value is very sensitive to the minute deformation of the surface. When the surface undergoes changes such as subsidence and uplift, the propagation path of the radar signal will change, resulting in a change in the phase. By analyzing the phase information, the deformation information of the surface can be obtained.

[0098] The amplitude information represents the intensity of the radar echo signal. Different ground objects have different reflection capabilities for radar signals. Therefore, the amplitude information can reflect characteristics such as the type of ground object, surface roughness, and dielectric constant. In the terrain subsidence monitoring of mining areas, the amplitude information is used to identify different terrains, buildings, mine pits, etc.

[0099] The polarization information represents the direction change of the electric field vector of the radar signal during propagation. The SAR device can emit signals with different polarization modes (such as horizontal polarization, vertical polarization, etc.) and receive the corresponding echoes. The polarization information can provide more detailed information about the ground object. For example, different vegetation, water bodies, rocks, etc. have obvious differences in the polarization characteristics of the ground object, so as to accurately identify and analyze the ground object.

[0100] S302. The synthetic aperture radar interferometry monitoring module inputs the phase information, amplitude information, and polarization information in the synthetic aperture radar image data into a pre-constructed deep learning model, and the deep learning model extracts the surface subsidence features.

[0101] Optionally, the InSAR monitoring module takes the phase information, amplitude information, and polarization information in the SAR image data as input features and inputs them into a pre-constructed deep learning model. The deep learning model deeply mines and extracts the surface subsidence features through deep learning algorithms.

[0102] As a machine learning model based on artificial neural networks, the deep learning model can automatically learn the features and patterns in the data through a large amount of data training. In surface subsidence monitoring, the pre-constructed deep learning model is trained using existing synthetic aperture radar image data and the corresponding actual surface subsidence situation (such as surface displacement data obtained through field measurements). Specifically, the deep learning model extracts the features related to surface subsidence through the calculation and learning of multi-layer neural networks, so as to more accurately describe the surface subsidence situation.

[0103] Exemplarily, a U2-Net network structure can be used to construct the deep learning model. The deep learning model is trained for the deformation, atmosphere, and noise phases included in the differential interferogram to form simulation samples. The trained deep learning model is used to identify the subsidence area of the differential interferogram of the mining area at different time intervals. The U2-Net network structure can effectively retain the detailed information and prevent information loss. Among them, U2-Net is a two-level nested U-shaped structure. The outer layer is a large U-shaped structure composed of an encoding block and a decoding block. Each encoding block and decoding block is filled with small residual U-shaped blocks. The nested and recursive U-structure can more effectively capture the significant targets in the image to efficiently extract multi-scale and multi-level features.

[0104] S303. The synthetic aperture radar interferometry monitoring module determines the surface subsidence information according to the surface subsidence features and the mining subsidence model.

[0105] Optionally, the surface subsidence features extracted by the deep learning model are an abstract representation of the surface subsidence situation. These features contain information about the location, degree, scope, etc. of the surface subsidence. For example, some features may correspond to local subsidence areas on the surface, while other features may reflect the development trend of the subsidence.

[0106] The InSAR monitoring module combines the surface subsidence features extracted by the deep learning model with the mining subsidence model for analysis. Through comparison and matching, and by using the theoretical and empirical knowledge of the mining subsidence model, the surface subsidence features are optimized to determine specific surface subsidence information.

[0107] Figure 8 This is a schematic diagram of the results of the surface subsidence information determined by the synthetic aperture radar interferometry monitoring module provided in the embodiment of the present application. As Figure 8 shown, it is a graphical representation of the surface subsidence information caused by coal mine mining identified by the InSAR monitoring module. The surface subsidence conditions in different regions are represented by each subsidence isoline.

[0108] In this embodiment, the synthetic aperture radar interferometry monitoring module determines the phase information, amplitude information, and polarization information in the synthetic aperture radar image data. Among them, the phase information is used to identify the deformation information of the surface, the amplitude information is used to identify different terrains, and the polarization information is used to provide detailed information about the ground objects. The synthetic aperture radar interferometry monitoring module takes the phase information, amplitude information, and polarization information in the synthetic aperture radar image data as input features and inputs them into a pre-constructed deep learning model. The deep learning model extracts surface subsidence features through the calculation and learning of a multi-layer neural network to more accurately describe the surface subsidence situation. The synthetic aperture radar interferometry monitoring module combines the surface subsidence features with the mining subsidence model for analysis. Through comparison and matching, and by using the theoretical and empirical knowledge of the mining subsidence model, the surface subsidence features are optimized to determine the surface subsidence information. Through the deep learning model, combined with the multi-dimensional information of the synthetic aperture radar image data, the monitoring accuracy of the wide-area terrain subsidence monitoring in the mining area is improved.

[0109] Hereinafter, the process of the optical remote sensing monitoring module obtaining the optical remote sensing image data of the target area will be described in detail.

[0110] Figure 9 This is a schematic flowchart of the optical remote sensing monitoring module obtaining the optical remote sensing image data of the mining area monitoring method provided in the embodiment of the present application. As Figure 9 shown, in the above step S102, the optical remote sensing monitoring module obtaining the optical remote sensing image data of the target area includes:

[0111] S401. The optical remote sensing monitoring module acquires satellite image data of the target area collected by an optical satellite.

[0112] Optionally, the optical satellite is an artificial satellite equipped with an optical sensor. The optical sensor can capture the electromagnetic waves reflected by the target area in space, mainly concentrated in visible light, near-infrared and other bands. Among them, the satellite can cover a large area and can obtain satellite image data regularly or irregularly, providing a data basis for long-term monitoring. The optical remote sensing monitoring module receives the satellite image data of the target area collected by the optical satellite through a specific data transmission link or protocol.

[0113] The resolution of the satellite image data is higher than that of the SAR image data. The optical remote sensing monitoring module performs preprocessing such as radiometric correction, geometric correction and atmospheric correction on the satellite image data to ensure the quality of the satellite image data.

[0114] S402. The optical remote sensing monitoring module acquires aerial image data of the target area collected by a drone. The aerial image data is used to supplement the detailed information of the synthetic aperture radar image data and the satellite image data.

[0115] Optionally, the drone can carry equipment such as a high-resolution optical camera, fly over the target area according to a predetermined route, and take images. The flight altitude of the drone is flexibly variable and can be adjusted according to actual needs for aerial photography to obtain aerial image data of the target area with different resolutions in space.

[0116] The optical remote sensing monitoring module receives the aerial image data transmitted by the drone and performs preprocessing such as image stitching and geometric correction on the aerial image data. Compared with the satellite image data and the SAR image data, the resolution of the aerial image data collected by the drone is higher, and it can show the detailed features of the target area more clearly to supplement the detailed information of the SAR image data and the satellite image data. For example, in mine area monitoring, the aerial image data can clearly show the details of specific facilities such as roads, buildings, and mine pits in the mine area.

[0117] In this embodiment, the optical remote sensing monitoring module receives the satellite image data of the target area collected by the optical satellite in space and the aerial image data of the target area collected by the drone in space. By supplementing the detailed information of the synthetic aperture radar image data and the satellite image data with the aerial image data, multi-source acquisition of image data is realized when the optical remote sensing monitoring module performs surface damage monitoring.

[0118] Next, the process of determining the surface damage information based on the optical remote sensing image data and the synthetic aperture radar image data of the target area will be described in detail.

[0119] Figure 10 This is a schematic flowchart of determining surface damage information for the mining area exploitation monitoring method provided by the embodiments of this application. As Figure 10 shown, in the above step S102, based on the optical remote sensing image data and synthetic aperture radar image data of the target area, determining the surface damage information includes:

[0120] S501. The optical remote sensing monitoring module respectively extracts features from the optical satellite image data, synthetic aperture radar image data, and aerial photography image data of the target area, and obtains the optical satellite image features, synthetic aperture radar image features, and aerial photography image features of the target area.

[0121] Optionally, the optical satellite image data can present features such as the color, shape, and texture of the ground objects in the target area. The optical remote sensing monitoring module extracts features from the optical satellite image data of the target area, extracts key information that can represent the attributes and changes of the ground objects from the image, and obtains the optical satellite image features of the target area.

[0122] The SAR image data contains multi-dimensional information such as phase information, amplitude information, and polarization information. The phase information is sensitive to small surface deformations, the amplitude information reflects the reflection ability of the ground objects to microwaves, and the polarization information can provide information about the surface structure and medium characteristics of the ground objects. The optical remote sensing monitoring module extracts features from the SAR image data and extracts the SAR image features related to the target area.

[0123] The aerial photography image data of the target area taken by an optical camera or sensor carried by an aerial platform such as a drone has a high resolution and can clearly display the details of the target area. The optical remote sensing monitoring module extracts features from the aerial photography image data, excavates detailed features such as the specific structure of buildings and the damage condition of roads, and obtains the aerial photography image features.

[0124] S502. The optical remote sensing monitoring module obtains the fusion features based on the optical satellite image features, synthetic aperture radar image features, and aerial photography image features of the target area, and determines the surface damage information according to the fusion features.

[0125] Optionally, different types of remote sensing image data have their own advantages and limitations. Among them, the optical satellite image data can intuitively reflect the color and texture of the ground objects, but is restricted by weather conditions; the SAR image data is not affected by weather and is sensitive to surface deformations, but it is difficult to obtain effective deformation information in areas prone to decoherence such as vegetation-covered areas and loess gully areas; the aerial photography image data has a high resolution but a limited coverage range. Therefore, the optical remote sensing monitoring module needs to fuse their features, which can comprehensively utilize their respective advantages and understand the situation of the target area more comprehensively.

[0126] Specifically, the optical remote sensing monitoring module uses a data fusion algorithm to integrate the optical satellite image features, SAR image features, and aerial photo image features of the target area at the feature level. For example, it combines texture features, geometric features, etc. in different data to form new and more representative fusion features. Through feature fusion, the fusion features can more comprehensively describe the ground objects and changes in the target area.

[0127] The fusion features contain multi-faceted information of the ground objects in the target area. Based on the fusion features, the optical remote sensing monitoring module combines the mining subsidence theory to determine whether there is surface damage in the target area. For example, if the vegetation color in the optical satellite image features of a certain area in the fusion features is abnormal, there is a phase change in the SAR image features, and the aerial photo image features show signs of land excavation, it can be inferred that there may be surface damage in this area based on these features. According to the analysis results of the fusion features, the optical remote sensing monitoring module can determine specific surface damage information, including the location of the damage (accurate to specific geographical coordinates or area range), the type of damage (such as vegetation damage, land collapse, building damage, etc.), the degree of damage, and the scope of damage, etc.

[0128] In this embodiment, the optical remote sensing monitoring module extracts features from the optical satellite image data of the target area, extracts key information that can represent the attributes and changes of the ground objects from the images, and obtains the optical satellite image features of the target area. It extracts features from the synthetic aperture radar image data and extracts the synthetic aperture radar image features related to the target area. It extracts features from the aerial photo image data to obtain the aerial photo image features. The optical remote sensing monitoring module uses a data fusion algorithm to integrate the optical satellite image features, synthetic aperture radar image features, and aerial photo image features of the target area at the feature level to form fusion features. Through feature fusion, the fusion features can more comprehensively describe the ground objects and changes in the target area. The optical remote sensing monitoring module combines the mining subsidence theory based on the fusion features to determine whether there is surface damage in the target area and determine specific surface damage information. By fusing the optical satellite image data, synthetic aperture radar image data, and aerial photo image data, the collaborative holographic interpretation of the surface damage in the target area is realized.

[0129] Next, the process of obtaining fusion features based on the optical satellite image features, synthetic aperture radar image features, and aerial photo image features of the target area and determining surface damage information based on the fusion features will be described in detail.

[0130] Figure 11 This is another schematic flowchart of determining surface damage information for the mining area monitoring method provided by the embodiment of the present application, as Figure 11As shown in the figure, in the above step S502, the fusion features are obtained based on the optical satellite image features, synthetic aperture radar image features, and aerial image features of the target area, and the surface damage information is determined according to the fusion features, including:

[0131] S601. The optical remote sensing monitoring module performs spatial registration on the optical satellite image features, synthetic aperture radar image features, and aerial image features of the target area, and performs feature fusion on the registered optical satellite image features, synthetic aperture radar image features, and aerial image features to obtain fusion features.

[0132] Optionally, spatial registration refers to the process of making the image features obtained from different sources and at different times, including optical satellite image features, SAR image features, and aerial image features, reach unity and match in spatial position through a specific algorithm. Since the image data to which these image features belong are obtained by different sensors at different times and positions, there may be differences in coordinate systems and scales, and spatial registration is required so that subsequent feature fusion and analysis can be accurately carried out.

[0133] The optical remote sensing monitoring module uses information such as geographic coordinates and control points for the optical satellite image features, SAR image features, and aerial image features of the target area, and adopts geometric transformation and image matching algorithms to align these features in space so that they can accurately correspond to the same geographical location of the target area. For example, a certain building feature on the optical satellite image is accurately matched with the building features at the same position on the SAR image and the aerial image. Among them, geometric transformation can include translation, rotation, scaling, etc., and the image matching algorithm can be a feature point-based matching algorithm.

[0134] After the optical remote sensing monitoring module completes spatial registration, it uses a specific feature fusion algorithm, such as a feature-based fusion algorithm, to perform fusion processing on the registered optical satellite image features, SAR image features, and aerial image features. For example, in feature-based fusion, the texture features of the optical satellite image, the phase features of the SAR image, and the high-resolution detail features of the aerial image are combined to generate new fusion features, so as to more comprehensively describe the ground objects and changes in the target area.

[0135] S602. The optical remote sensing monitoring module determines the surface damage information according to the fusion features and the dynamic development law of ground fissures caused by mine exploitation.

[0136] Optionally, during the process of mine exploitation, due to the extraction of underground ore bodies, the stress of the strata is redistributed, often leading to the generation and development of ground fissures. In the theory of mining subsidence, there are dynamic development characteristics of ground fissures caused by mine exploitation, including early development - first increasing and then decreasing - late healing.

[0137] After obtaining the fusion features, the optical remote sensing monitoring module combines them with the dynamic development law of ground fissures caused by mine exploitation for analysis. According to the terrain changes, ground object damages, etc. information of the target area reflected in the fusion features, combined with the dynamic development law of ground fissures, it is judged whether there is surface damage and the specific situation of the damage. For example, if the fusion features show that a new linear feature appears in a certain area and is consistent with the development pattern of ground fissures, and at the same time this area is within the influence range of mine exploitation, it can be inferred that there are ground fissures caused by mine exploitation in this area, and then the surface damage information such as the location, degree and scope of surface damage can be determined.

[0138] In this embodiment, for the optical satellite image features, synthetic aperture radar image features and aerial photograph image features of the target area, the optical remote sensing monitoring module performs spatial registration by using geometric transformation and image matching algorithms. After completing the spatial registration, a specific feature fusion algorithm is used to fuse the registered optical satellite image features, synthetic aperture radar image features and aerial photograph image features to generate new fusion features, so as to more comprehensively describe the ground objects and changes in the target area. The optical remote sensing monitoring module combines the fusion features with the dynamic development law of ground fissures caused by mine exploitation for analysis. According to the terrain changes, ground object damages, etc. information of the target area reflected in the fusion features, combined with the dynamic development law of ground fissures, it is judged whether there is surface damage and the specific situation of the damage to determine the surface damage information. The optical remote sensing monitoring module comprehensively utilizes different types of image features and combines the knowledge related to mine exploitation to accurately determine the surface damage information of the target area.

[0139] As an alternative implementation manner, in the above step S103, the microseismic monitoring module acquires the microseismic data underground in the targeted monitoring area, including:

[0140] The microseismic monitoring module acquires the microseismic data underground in the targeted monitoring area collected by the microseismic sensors. Among them, the microseismic sensors include multiple shallow-buried microseismic sensors and multiple deep-buried microseismic sensors. Each shallow-buried microseismic sensor is deployed at each monitoring point on the surface of the targeted monitoring area, and each deep-buried microseismic sensor is drilled and deployed at each monitoring point underground in the targeted monitoring area.

[0141] Optionally, the microseismic monitoring module acquires the microseismic data underground in the targeted monitoring area in real time and accurately through each microseismic sensor deployed in the targeted monitoring area. Among them, the microseismic sensors include two types: shallow-buried microseismic sensors and deep-buried sensors.

[0142] Specifically, Figure 12 is a schematic diagram of the deployment effect of the shallow-buried microseismic sensor provided by the embodiment of the present application. Refer to Figure 12, Shallow-buried microseismic sensors are deployed at each monitoring point on the surface of the targeted monitoring area. The shallow-buried microseismic sensors deployed at each monitoring point form a monitoring network. Each monitoring point covers a certain area. The collaborative work of the shallow-buried microseismic sensors at multiple monitoring points can improve the monitoring accuracy and coverage. The burial depth of the shallow-buried microseismic sensors is from a few tenths of a meter to dozens of meters, and the monitoring range is relatively small, but it is easy to install, without the need for underground construction, and can be flexibly arranged and moved. Shallow-buried microseismic sensors are preferably used in cases where the monitoring points need to be frequently adjusted. Moreover, the shallow-buried microseismic sensors can use 4G signals for data transmission and solar energy for power supply.

[0143] Figure 13 Schematic diagram of the deployment effect of the deep-buried microseismic sensors provided by the embodiments of the present application. Refer to Figure 13 , Figure 13 (a) and Figure 13 (b) are both the location diagrams of each deep-buried microseismic sensor. Figure 13 (c) is the schematic diagram of the actual deployment effect of the deep-buried microseismic sensors. Each deep-buried microseismic sensor is drilled and deployed at each monitoring point underground in the targeted monitoring area. The burial depth is relatively deep, and drilling layout is required. It is suitable for monitoring illegal mining in deeper coal seams. The burial depth of the deep-buried microseismic sensors is from dozens to hundreds of meters, and the monitoring range is relatively small. Underground construction or drilling layout is required, and the deployment position is relatively fixed. Deep-buried microseismic sensors are preferably used in the case of monitoring deeper coal seams. Moreover, the deep-buried microseismic sensors can transmit data through WiFi wireless devices.

[0144] Figure 14 Schematic diagram of the network topology for microseismic data transmission provided by the embodiments of the present application. Taking the deep-buried microseismic sensors as an example, each deep-buried microseismic sensor transmits microseismic data to the microseismic monitoring module through the mine-side ring network formed by wireless terminals.

[0145] In this embodiment, the microseismic monitoring module obtains the microseismic data of the underground in the targeted monitoring area collected by the microseismic sensors. The shallow-buried microseismic sensors deployed at each monitoring point on the surface of the targeted monitoring area capture the microseismic data from a relatively shallow depth range below the surface, and the deep-buried microseismic sensors deployed at each monitoring point underground in the targeted monitoring area capture the microseismic data from a relatively deep underground. The comprehensive collection of the microseismic data of the underground in the targeted monitoring area is realized to improve the microseismic monitoring accuracy.

[0146] Next, the process of real-time monitoring and positioning of the mining behavior in the mining area of the targeted monitoring area based on the microseismic data will be described in detail.

[0147] Figure 15 Schematic diagram of the process of real-time monitoring and positioning of the mining behavior in the mining area of the targeted monitoring area by the mining area monitoring method provided by the embodiments of the present application. As shown in Figure 15As shown, in the above step S103, based on the microseismic data, real-time monitoring and positioning of the mining behavior in the targeted monitoring area are performed, including:

[0148] S701. The microseismic monitoring module determines whether a new microseismic event occurs through spectral analysis according to the microseismic waveform in the microseismic data and the pre-constructed microseismic event template library, where the microseismic event template library includes the waveforms of various rock mass microfracture events induced by mining in the mining area.

[0149] Optionally, the microseismic data obtained by the microseismic monitoring module contains microseismic waveform information, and the pre-constructed microseismic event template library stores the waveforms of various rock mass microfracture events induced by mining in the mining area. The microseismic monitoring module performs spectral analysis to convert the real-time monitored microseismic waveform into the frequency domain for analysis. Spectral analysis can reveal the distribution of different frequency components in the microseismic waveform and extract information such as its frequency characteristics. These characteristics are compared with the spectral characteristics of the waveforms in the microseismic event template library. If the spectral characteristics of the new microseismic waveform match a certain template in the microseismic event template library to a high degree, it indicates that the waveform is similar to the waveform of the known microfracture event induced by mining in the mining area, thereby determining that a new microseismic event has occurred.

[0150] Similar waveforms often correspond to similar physical processes (i.e., the rock mass microfracture process). Different types of microseismic events usually have different waveform characteristics, and similar microseismic event waveforms also show similarity in the frequency spectrum. Based on this, the microseismic waveforms generated by rock mass microfractures induced by illegal mining in mines can be effectively identified, avoiding the omission of illegal mining microseismic events and reducing the misjudgment probability of microseismic events, improving the accuracy and pertinence of microseismic event identification.

[0151] Figure 16 It is a schematic diagram for detecting new microseismic events through spectral analysis provided by an embodiment of the present application. As Figure 16 shown, according to the microseismic waveform in the microseismic data, its amplitude is analyzed, and the waveform similarity between this amplitude and the waveforms of the shearer event or the caving roof event in the microseismic event template library is compared to determine whether a new microseismic event occurs.

[0152] S702. If so, the microseismic monitoring module determines two adjacent microseismic event pairs and constructs a microseismic double-difference model for the microseismic event pairs according to the microseismic data.

[0153] Optionally, after determining that a new microseismic event has occurred, the microseismic monitoring module selects two adjacent microseismic events to form a pair of microseismic events. Adjacent microseismic events have a certain correlation in time and space. They may be caused by the same mining area or similar mining activities, or they may be consecutive events during the rock mass fracture process. Among them, "adjacent" can be based on the proximity in time (i.e., the time interval between the occurrences of two microseismic events is short), or the spatial correlation can also be considered (such as being relatively close in spatial position). By analyzing the pair of microseismic events, the relative relationship between microseismic events and their connection with mining activities can be studied more accurately. Specifically, outside the source area, the ray paths of two adjacent microseismic events to the same microseismic sensor are almost coincident.

[0154] Based on the microseismic data of the pair of microseismic events, a microseismic double-difference model of the pair of microseismic events is constructed. Specifically, the microseismic data of the pair of microseismic events can include information such as microseismic waveforms, arrival times, and azimuth angles. The microseismic monitoring module constructs a microseismic double-difference model that combines microseismic arrival times and azimuth angles through phase picking, time difference calculation, and function construction, so as to effectively eliminate common error factors, such as station position errors, velocity model errors, etc., through the microseismic double-difference model.

[0155] S703. The microseismic monitoring module determines the relative position of the pair of microseismic events according to the microseismic double-difference model, and determines the mining position of the mining area according to the relative position of the pair of microseismic events.

[0156] Optionally, the microseismic monitoring module determines the relative position of the pair of microseismic events by solving the parameters of the microseismic double-difference model, such as relative coordinate offsets, etc., to reflect the relative position relationship in space between the two microseismic events in the pair of microseismic events, that is, the relative difference in the occurrence positions of the two microseismic events.

[0157] Since microseismic events are usually generated by microfractures of the rock mass caused by mining activities in the mining area, the positions of microseismic events are closely related to the positions of mining activities. After determining the relative position of the pair of microseismic events, the microseismic monitoring module combines the known geological structure information (such as ore body distribution, stratigraphic structure, etc.) and the positions of microseismic sensors, and inversely deduces the mining position of the mining area through geometric relationships and positioning algorithms. For example, if multiple pairs of microseismic events all show a relatively concentrated distribution near a certain area, then it can be inferred that this area may be the current mining position of the mining area. Exemplarily, the positioning algorithm can be the triangulation method.

[0158] In this embodiment, the microseismic monitoring module converts the waveform in the real-time monitored microseismic data into the frequency domain through spectral analysis for analysis, so as to reveal the distribution of different frequency components in the microseismic waveform and extract its frequency characteristics. The frequency characteristics are compared with the spectral characteristics of the waveforms of each rock mass microfracture event induced by mining in the mining area in the microseismic event template library to determine whether a new microseismic event occurs. If so, the microseismic monitoring module selects two adjacent microseismic events to form a microseismic event pair, and based on the microseismic data of the microseismic event pair, through phase picking, arrival time difference calculation, and construction of an objective function, constructs a microseismic double-difference model for the microseismic event pair. The microseismic monitoring module determines the relative position of the microseismic event pair by solving the parameters of the microseismic double-difference model, and combines the known geological structure information and the positions of the microseismic sensors to reverse infer the mining position in the mining area. This improves the accuracy and pertinence of microseismic event recognition and realizes real-time monitoring and precise positioning of the mining behavior in the targeted monitoring area.

[0159] Hereinafter, the process of determining the relative position of the microseismic event pair according to the microseismic double-difference model will be described in detail.

[0160] Figure 17 It is a schematic flow chart of determining the relative position of the microseismic event pair for the mining area monitoring method provided by the embodiment of the present application. As Figure 17 shown, in the above step S703, determining the relative position of the microseismic event pair according to the microseismic double-difference model includes:

[0161] S801. The microseismic monitoring module determines the arrival time difference of the microseismic event pair to the same microseismic sensor according to the microseismic double-difference model, and the arrival time difference is the residual between the observed value and the theoretically calculated value.

[0162] Optionally, the microseismic monitoring module can reduce the error influence of the microseismic event pair on the common path and eliminate the velocity error of the microseismic event pair on the common path by calculating the relative arrival time of the microseismic event pair to the same microseismic sensor according to the microseismic double-difference model.

[0163] Specifically, calculate the arrival time difference of the two adjacent microseismic events in the microseismic event pair to the same microseismic sensor. Among them, the arrival time difference is the residual between the observed value and the theoretically calculated value, which includes model errors, differences between the actual medium and the theoretical model, etc. By calculating the arrival time difference, the common errors caused by the deployment position of the microseismic sensor and the uncertainty of the microseismic wave propagation speed can be eliminated.

[0164] S802. The microseismic monitoring module determines the relative position of the microseismic event pair according to the arrival time difference.

[0165] Optionally, the microseismic monitoring module uses the arrival time difference data on multiple microseismic sensors and combines optimization algorithms such as the least squares method to solve the relative positions of microseismic event pairs. Specifically, taking the arrival time difference as the observation data, a target function is established, which is a function of the relative position parameters of the microseismic event pair (such as the coordinate offset in three-dimensional space). The goal is to minimize the sum of the arrival time difference residuals on all microseismic sensors. By continuously adjusting the relative position parameters, the target function reaches the minimum value, and the obtained relative position parameters are the relative positions of the microseismic event pair.

[0166] Figure 18 The result schematic diagram for accurately determining the mining location in the mining area provided by the embodiment of the present application is as Figure 18 shown. The microseismic monitoring module determines the microseismic position by picking up the arrival time of microseismic events, and then determines the long-term working face trend during the monitoring process, realizing the real-time monitoring and positioning of underground mining microseismic events in the targeted monitoring area.

[0167] In this embodiment, the microseismic monitoring module determines the arrival time difference of the microseismic event pair to the same microseismic sensor according to the microseismic double-difference model. The arrival time difference is the residual between the observed value and the theoretically calculated value, so as to eliminate the velocity error of the microseismic event pair on the common path. The microseismic monitoring module uses the arrival time differences on multiple microseismic sensors to solve the relative positions of the microseismic event pair, realizing the accurate determination of the relative position relationship in space between the two microseismic events in the microseismic event pair.

[0168] The embodiment of the present application also provides a mining area monitoring system, as Figure 1 shown. The mining area monitoring system includes: an InSAR monitoring module, an optical remote sensing monitoring module, and a microseismic monitoring module.

[0169] Each module in the mining area monitoring system is respectively used to execute the corresponding method steps in the mining area monitoring method described in the foregoing embodiment.

[0170] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the method embodiments, and will not be elaborated herein. In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For another example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed among each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0171] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered within the protection scope of the present application.

Claims

1. A mining area mining monitoring method, characterized in that: Applied to a mining area mining monitoring system, the mining area mining monitoring system includes: a synthetic aperture radar interferometric monitoring module, an optical remote sensing monitoring module and a microseismic monitoring module; the method includes: The synthetic aperture radar interferometry monitoring module acquires synthetic aperture radar image data of the mining area, and performs surface subsidence monitoring on the mining area according to the synthetic aperture radar image data, and determines a targeted monitoring area of ​​the mining area; The optical remote sensing monitoring module acquires optical remote sensing image data of the target area, and determines surface damage information based on the optical remote sensing image data and synthetic aperture radar image data of the target area, and monitors mining behavior in the mining area based on the surface damage information, wherein the optical remote sensing image data includes: satellite image data and aerial image data; The microseismic monitoring module acquires underground microseismic data in the targeted monitoring area, and performs real-time monitoring and positioning of mining activities in the targeted monitoring area based on the microseismic data.

2. The method according to claim 1, characterized in that The step of monitoring the surface subsidence of the mining area according to the synthetic aperture radar image data and determining the targeted monitoring area of ​​the mining area includes: The synthetic aperture radar interferometry monitoring module performs a time series surface subsidence screening on the mining area according to the synthetic aperture radar image data and a pre-constructed mining subsidence model to determine the surface subsidence information; The synthetic aperture radar interferometry monitoring module determines a targeted monitoring area of ​​the mining area according to the surface subsidence information.

3. The method according to claim 2, characterized in that The method of screening the surface subsidence of the mining area in time series according to the synthetic aperture radar image data and the pre-constructed mining subsidence model to determine the surface subsidence information includes: The synthetic aperture radar interference monitoring module determines phase information, amplitude information and polarization information in the synthetic aperture radar image data; The synthetic aperture radar interferometry monitoring module inputs the phase information, amplitude information and polarization information in the synthetic aperture radar image data into a pre-built deep learning model, and the deep learning model extracts the surface subsidence characteristics; The synthetic aperture radar interferometry monitoring module determines the surface subsidence information according to the surface subsidence characteristics and the mining subsidence model.

4. The method according to claim 1, characterized in that: The optical remote sensing monitoring module acquires optical remote sensing image data of the target area, including: The optical remote sensing monitoring module acquires satellite image data of the target area collected by an optical satellite; The optical remote sensing monitoring module obtains aerial image data of the target area collected by a drone, wherein the aerial image data is used to supplement the detailed information of the synthetic aperture radar image data and the satellite image data.

5. The method according to claim 4, characterized in that Determining the surface damage information according to the optical remote sensing image data and synthetic aperture radar image data of the target area includes: The optical remote sensing monitoring module extracts features from the optical satellite image data, synthetic aperture radar image data and aerial image data of the target area respectively to obtain the optical satellite image features, synthetic aperture radar image features and aerial image features of the target area; The optical remote sensing monitoring module obtains fusion features according to the optical satellite image features, the synthetic aperture radar image features and the aerial image features of the target area, and determines the surface damage information according to the fusion features.

6. The method according to claim 5, characterized in that The obtaining of fusion features according to the optical satellite image features, the synthetic aperture radar image features and the aerial image features of the target area, and determining the surface damage information according to the fusion features, includes: The optical remote sensing monitoring module spatially registers the optical satellite image features, the synthetic aperture radar image features and the aerial image features of the target area, and performs feature fusion on the registered optical satellite image features, synthetic aperture radar image features and aerial image features to obtain fused features; The optical remote sensing monitoring module determines the surface damage information according to the fusion characteristics and the dynamic development law of ground fissures caused by mining.

7. The method according to claim 1, characterized in that The microseismic monitoring module acquires underground microseismic data of the target monitoring area, including: The microseismic monitoring module obtains underground microseismic data of the target monitoring area collected by microseismic sensors, wherein the microseismic sensors include multiple shallowly buried microseismic sensors and multiple deeply buried microseismic sensors, each of the shallowly buried microseismic sensors is deployed at each monitoring point on the surface of the target monitoring area, and each of the deeply buried microseismic sensors is deployed by drilling at each monitoring point underground in the target monitoring area.

8. The method according to claim 1, characterized in that The real-time monitoring and positioning of mining activities in the targeted monitoring area based on the microseismic data includes: The microseismic monitoring module determines whether a new microseismic event occurs through spectrum analysis based on the microseismic waveform in the microseismic data and a pre-constructed microseismic event template library, wherein the microseismic event template library includes waveforms of various rock mass microfracture events induced by mining in the mining area; If yes, the microseismic monitoring module determines two adjacent microseismic event pairs, and constructs a microseismic double-difference model of the microseismic event pairs based on the microseismic data; The microseismic monitoring module determines the relative positions of the microseismic event pairs according to the microseismic double-difference model, and determines the mining position of the mining area according to the relative positions of the microseismic event pairs.

9. The method according to claim 8, characterized in that Determining the relative positions of the microseismic event pairs according to the microseismic double-difference model includes: The microseismic monitoring module determines the arrival time difference of the microseismic event to the same microseismic sensor according to the microseismic double-difference model, wherein the arrival time difference is the residual between the observed value and the theoretical calculated value; The microseismic monitoring module determines the relative positions of the microseismic event pairs according to the arrival time differences.

10. A mining area mining monitoring system, characterized in that: The mining area mining monitoring system includes: a synthetic aperture radar interferometry monitoring module, an optical remote sensing monitoring module and a microseismic monitoring module; Each module in the mining area mining monitoring system is used to execute the corresponding method steps in the mining area mining monitoring method described in any one of claims 1-9.

Images