Safety early warning method based on while-mining seismic exploration, storage medium and electronic equipment

Abstract

The invention discloses a safety early warning method based on while-mining seismic detection, a storage medium and electronic equipment. The method comprises the following steps: determining the position of a while-mining area; according to the position of the mining-following area, a first safety radius with the mining-following area as the center is configured; arranging a first seismic sensing edge network on the first safety radius, performing real-time detection according to the first seismic sensing edge network, and outputting a first seismic sensing signal set corresponding to the first safety radius; performing signal restoration on the first seismic sensing signal set by using a signal restoration module, and outputting a seismic restoration signal set; and inputting the earthquake restoration signal set into an earthquake safety early warning module for safety analysis, outputting an earthquake risk index, and generating a safety early warning signal based on the earthquake risk index. According to the invention, the technical effect of improving the accuracy of seismic signal identification and the monitoring stability is achieved.

Description

Technical Field

[0001] This invention relates to the field of safety monitoring technology, and in particular to a safety early warning method, storage medium, and electronic equipment based on seismic detection during mining. Background Technology

[0002] In mining operations, complex and unstable geological structures often lead to geological disasters such as rock bursts and ground instability, seriously threatening miners' lives and affecting equipment operation. Existing seismic monitoring technologies typically rely on randomly deployed sensor networks and basic signal processing methods. Limited by the attenuation and phase changes of seismic waves caused by geological layers, the received signals are prone to distortion, thus affecting the accuracy and reliability of early warnings. Furthermore, traditional systems lack advanced signal reconstruction techniques and precise geological modeling capabilities, resulting in insufficient analysis of seismic wave propagation paths and identification of potential risks, failing to meet the needs of complex mining environments. Therefore, more precise and stable monitoring and early warning solutions are needed to improve the accuracy of seismic signal identification and ensure operational safety.

[0003] Currently, the relevant technologies suffer from low accuracy in seismic signal identification, leading to unstable monitoring results. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a safety early warning method, storage medium, and electronic device based on in-mining seismic detection. The method involves determining the location of the in-mining area, configuring a first safety radius centered on that area, and deploying a seismic sensing edge network on it for real-time detection, outputting a corresponding set of seismic sensing signals. This signal set is then processed by a signal reconstruction module to obtain a reconstructed signal set, and this module is connected to a 3D model of the in-mining area obtained through 3D geological modeling. The reconstructed signal set is then input into an earthquake safety early warning module for analysis, outputting seismic risk indicators and generating a safety early warning signal, thus achieving the technical effect of improving the accuracy of seismic signal identification and the stability of monitoring.

[0005] The technical solution of this invention provides a safety early warning method based on seismic detection during mining, including: Determine the location of the mining area; Based on the location of the mining area, a first safety radius centered on the mining area is configured. A first seismic sensing edge network is deployed on the first safety radius, and real-time detection is performed based on the first seismic sensing edge network to output the first seismic sensing signal set corresponding to the first safety radius. The first seismic sensing signal set is restored using a signal restoration module, and a restored seismic signal set is output. The signal restoration module is generated based on a three-dimensional model of the mining area, which is obtained by performing three-dimensional geological modeling on the mining area. The earthquake reconstruction signal set is input into the earthquake safety early warning module for safety analysis, and an earthquake risk index is output. A safety early warning signal is generated based on the earthquake risk index. In one of the alternative technical solutions, the three-dimensional model of the mining area is obtained by performing three-dimensional geological modeling of the mining area, including: Obtain geological strata modeling data for the mining area; The geological layer modeling data is divided into geological layers according to the density, wave velocity and thickness of the geological layers, and the geological layer division results are output. The geological stratification results are integrated using 3D modeling software to generate a 3D model of the mining area.

[0006] In one of the alternative technical solutions, the 3D model of the mining area includes a modeling granularity adjustment component. A preset modeling refinement granularity is input according to the modeling granularity adjustment component, and the 3D model of the mining area is refined by the preset modeling refinement granularity.

[0007] In one alternative technical solution, after the signal restoration module is connected to the three-dimensional model of the sampling area, it further includes: Determine the initial test signal sample; The three-dimensional model of the mining area is invoked to simulate seismic detection signals according to the initial test signal samples, and the first set of simulated signal samples based on the first safety radius are received. The first set of simulated signal samples is compared with the initial test signal samples to obtain signal attenuation index samples and signal phase change samples; Based on the initial test signal samples, the first set of simulated signal samples, the signal attenuation index samples, and the signal phase change samples, a deconvolutional network is trained to generate a signal restoration module.

[0008] In one of the alternative technical solutions, the method of inputting the first seismic sensing signal set into the signal restoration module for signal restoration and outputting the seismic restored signal set includes: The first seismic sensing signal set is input into the signal restoration module, and the first seismic sensing signal set is windowed according to the time series to obtain multiple sensing signal segments. The amplitude attenuation characteristics and phase change characteristics of each of the multiple sensing signal segments are deconvolved to output multiple restored signal segments; The multiple restored signal segments are reconstructed to output a set of earthquake restored signals.

[0009] In one alternative technical solution, the step of configuring a first safety radius centered on the mining area based on the location of the mining area further includes: Configure a second safety radius centered on the mining area, wherein the first safety radius is different from the second safety radius; A second seismic sensing edge network is deployed on the second safety radius, and real-time detection is performed based on the second seismic sensing edge network to output the second seismic sensing signal set corresponding to the second safety radius; The first seismic sensor signal set and the second seismic sensor signal set are input into the signal restoration module for signal restoration, and the restored seismic signal set is output.

[0010] In one of the alternative technical solutions, the step of inputting the first seismic sensor signal set and the second seismic sensor signal set into the signal restoration module for signal restoration includes: The first seismic sensor signal set and the second seismic sensor signal set are fused to output a fused seismic sensor signal set, wherein the fused seismic sensor signal set does not include redundant signals from adjacent areas; The fused seismic sensing signal set is input into the signal restoration module for signal restoration, and the restored seismic signal set is output.

[0011] In one of the alternative technical solutions, the first safety radius is smaller than the second safety radius, and the radius difference between the second safety radius and the first safety radius is greater than a preset difference.

[0012] The present invention also provides a computer-readable storage medium that stores computer instructions, which, when executed by a computer, are used to perform all the steps of the safety early warning method based on seismic detection during mining as described above.

[0013] The present invention also provides an electronic device, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform the safety early warning method based on seismic detection during mining as described above.

[0014] The above technical solution has the following beneficial effects: After determining the location of the mining area, a first safety radius centered on the mining area is configured, and a seismic sensing edge network is deployed on it for real-time detection, outputting a corresponding seismic sensing signal set. The signal restoration module is used to restore the signal set to obtain a restored signal set. The signal restoration module is generated based on the three-dimensional model of the mining area. The restored signal set is input into the seismic safety early warning module for analysis, outputting seismic risk indicators and generating a safety early warning signal, thus achieving the technical effect of improving the accuracy of seismic signal identification and monitoring stability. Attached Figure Description

[0015] The disclosure of this invention will become more readily understood by referring to the accompanying drawings. It should be understood that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings: Figure 1 A flowchart illustrating a safety early warning method based on seismic detection during mining, provided as an embodiment of the present invention; Figure 2 This is a flowchart illustrating the steps of acquiring a three-dimensional model of the sampling area in one embodiment of the present invention. Figure 3 This is a flowchart illustrating the steps of the signal restoration module in one embodiment of the present invention. Figure 4 This is a flowchart illustrating the steps involved in generating a seismic reconstruction signal set in one embodiment of the present invention. Figure 5 This is a schematic diagram of the hardware structure of an electronic device for safety early warning based on seismic detection during mining, provided as an embodiment of the present invention. Detailed Implementation

[0016] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0017] It is readily understood that, based on the technical solution of this invention, various structural and implementation methods can be interchanged by those skilled in the art without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of the invention.

[0018] The directional terms such as up, down, left, right, front, back, front, back, top, and bottom mentioned or possibly used in this specification are defined relative to the structures shown in the accompanying drawings. They are relative concepts and may therefore vary depending on their location and usage. Therefore, these or other directional terms should not be interpreted as restrictive.

[0019] like Figure 1 As shown, an embodiment of the present invention provides a safety early warning method based on seismic detection during mining, comprising: Step S101: Determine the location of the sampling area; Step S102: Configure a first safety radius centered on the mining area according to the location of the mining area; Step S103: Deploy a first seismic sensing edge network on the first safety radius, perform real-time detection based on the first seismic sensing edge network, and output the first seismic sensing signal set corresponding to the first safety radius; Step S104: Use the signal restoration module to restore the first seismic sensing signal set and output the seismic restored signal set. The signal restoration module is generated based on the three-dimensional model of the mining area, which is obtained by performing three-dimensional geological modeling on the mining area. Step S105: Input the earthquake reconstruction signal set into the earthquake safety early warning module for safety analysis, output earthquake risk indicators, and generate a safety early warning signal based on the earthquake risk indicators.

[0020] Specifically, this invention can be applied to electronic devices with processing capabilities, such as programmable logic controllers (PLCs).

[0021] In step S101, determining the location of the mining area requires extensive collection of historical geological exploration reports, mining records, satellite remote sensing images, and other data. Then, the geological exploration report data is processed using geostatistical methods. Based on the mining records and analysis results, candidate sites are initially determined. Next, on-site investigations are carried out in the candidate areas, including geological mapping and small-scale geophysical exploration using high-precision measuring instruments. Finally, the location of the mining area is corrected and accurately determined based on the new data.

[0022] In step S102, when configuring the first safety radius centered on the mining area, a fixed radius approach is adopted to improve the accuracy of signal identification. This requires comprehensive consideration of geological structure, lithology, mining activities, surrounding mining conditions, and historical seismic activity data. For example, it involves considering the distribution of strata types, thicknesses, dip angles, and faults in the mining area's geological data; the differences in seismic wave propagation speed and attenuation levels among different lithologies; the changes in disturbance to surrounding strata caused by increased mining depth and scale; and the range and intensity of vibration interference from surrounding mining operations and historical seismic activity. Existing technologies generally identify signals at random locations, resulting in low accuracy. Establishing a seismic model based on a fixed radius can increase the accuracy of signal identification.

[0023] In step S103, within the circumference defined by the first safety radius, a first seismic sensing edge network is designed using a ring-distributed topology. Sensor nodes are evenly distributed, and the node spacing is carefully calculated. Based on the geological characteristics of the mining area and the expected seismic wave signal characteristics, seismic sensors of suitable type and performance with strong anti-interference capabilities are selected. The sensors are installed strictly according to regulations and calibrated for zero position, sensitivity, and linearity using standard vibration tables and other equipment. During mining operations, the sensors collect simulated seismic wave signals at preset sampling frequencies and time intervals and convert them into digital signals. These signals are then transmitted to the data central processing unit via wired or wireless communication (using reliable protocols and error correction coding technology). This unit amplifies and filters the signals, integrating the signals collected by all sensors, which contain information such as amplitude, frequency, and phase, into a first seismic sensing signal set corresponding to the first safety radius.

[0024] In step S104, a signal restoration module based on complex signal processing algorithms and mathematical models is constructed and connected to a three-dimensional model of the mining area constructed using advanced three-dimensional modeling software and technologies (such as interpolation algorithms based on geological exploration data and three-dimensional visualization technology of geological bodies) by collecting information on the lithology, thickness, density, and wave velocity of the strata in the mining area. Then, the first set of seismic sensing signals obtained from the seismic sensing edge network at the first safety radius, which is attenuated and deformed due to passing through geological layers, is input into the signal restoration module. Using the built-in algorithms and models of the module combined with the geological layer information in the three-dimensional model, and based on the theory of seismic wave propagation in different geological layers, the module calculates the propagation path and attenuation and uses an inversion algorithm to restore the original characteristics, based on the different effects of different geological layers on the amplitude, frequency, and phase of seismic waves. Finally, a seismic restoration signal set that is closer to the original signal is output, providing an accurate data basis for subsequent earthquake safety analysis and early warning.

[0025] In step S105, the processed earthquake reconstruction signal set is input into an earthquake safety early warning module that includes a variety of advanced analysis algorithms and models (constructed based on a large number of seismological research results and actual case data). From the perspective of amplitude, its peak value, mean value and frequency of change are statistically analyzed. Amplitude peak values ​​exceeding the threshold or rapid changes may indicate high risk. From the perspective of frequency, Fast Fourier Transform (FFT) or Wavelet Transform (WT) spectrum analysis is performed to identify the proportion and trend of different frequency components. Anomalies in low-frequency or high-frequency waves are associated with earthquakes of different types and degrees of hazard. From the perspective of phase information, its phase difference / delay, phase consistency or phase change index (PLI) changes are analyzed to reflect the propagation path and interaction. Anomalies suggest geological instability factors. Taking into account these factors, as well as the geological conditions of the mining area and the seismic resistance of buildings, signal indicators such as amplitude (weight 0.4), low-frequency proportion (weight 0.3), and phase coherence coefficient (weight 0.2) are combined with geological parameters (weight 0.3) and seismic parameters (weight 0.2) using a linear superposition model to calculate a comprehensive risk base (formula: risk base = Σ(indicator × weight)). Then, an S-shaped normalization function is used to compress the comprehensive risk base to a continuous interval of 0-1, outputting a quantified seismic risk index value. When the risk value is below 0.3, a green or blue safety signal is generated; for the range of 0.3 to 0.7... A yellow warning signal is generated when the risk level is between 0.7 and 0.7 (reminding people to pay close attention and take preventative measures). A red high-risk warning signal is generated when the risk level exceeds 0.7 (requiring the activation of emergency plans to minimize losses). A specific risk assessment algorithm outputs a quantified earthquake risk index, and a safety warning signal is generated based on this index. Low-risk indicators correspond to green or blue safety signals, while yellow or orange warning signals are generated when the risk level is above the intermediate threshold (reminding people to pay close attention and take preventative measures). High-risk values ​​(exceeding the red threshold) generate a red high-risk warning signal (requiring the activation of emergency plans to minimize losses). The assessment results are then clearly communicated to relevant personnel.

[0026] In this embodiment, after determining the location of the mining area, a first safety radius centered on that area is configured, and a seismic sensing edge network is deployed on it for real-time detection, outputting a corresponding seismic sensing signal set. The signal restoration module is used to restore the signal set to obtain a restored signal set. The signal restoration module is generated based on a three-dimensional model of the mining area. The restored signal set is input into the seismic safety early warning module for analysis, outputting seismic risk indicators and generating a safety early warning signal. This achieves the technical effect of improving the accuracy of seismic signal identification and the stability of monitoring.

[0027] like Figure 2 As shown, in one embodiment of the present invention, the step of obtaining the three-dimensional model of the sampling area includes: Step S201: Obtain geological strata modeling data for the mining area; Step S202: Divide the geological layer modeling data into geological layers according to the density, wave velocity and thickness of the geological layers, and output the geological layer division results; Step S203: Use 3D modeling software to integrate the geological layer division results and generate a 3D model of the mining area.

[0028] Specifically, in step S201, firstly, comprehensive geological stratum modeling data of the mining area must be collected. Core samples are obtained through drilling, and detailed laboratory analysis is performed on the cores. Various geological exploration techniques and methods are employed, including mineral composition identification and porosity measurement. The data directly reflects the material composition of strata at different depths. For example, analyzing the mineral composition in the cores can determine whether it is sandstone, shale, or limestone, etc. Porosity is related to the physical properties of the rock and affects the propagation of seismic waves within it. Geophysical exploration methods are also indispensable. For example, using seismic exploration technology, artificial seismic waves are emitted underground, and reflected and refracted waves are received at different locations. By analyzing parameters such as wave propagation time, amplitude, and frequency, changes in underground geological structure and strata can be inferred. Gravity exploration and magnetic exploration can detect density and magnetic differences in underground geological bodies, further assisting in determining the distribution and characteristics of geological strata. It is necessary to collect historical geological exploration data from the area or nearby, including past drilling records and geological maps. This data can provide more comprehensive information and help improve the collection of geological stratum modeling data.

[0029] In step S201, after acquiring sufficient geological layer modeling data, geological layers are divided according to key parameters such as density, wave velocity, and thickness. Density is an important criterion for division, as different types of rocks have different density ranges. For example, granite is usually denser than shale. This density difference leads to different propagation speeds of seismic waves within them. By measuring the density of drill core samples and detecting density anomalies in geophysical exploration, strata with similar density characteristics are classified into the same category. Wave velocity is also a key factor in dividing geological layers. The propagation speed of seismic waves varies in different geological layers, depending on properties such as the elastic modulus and density of the rocks. Using seismic wave propagation data obtained from seismic exploration, wave velocities at different depths and in different regions are calculated, and areas with similar wave velocities are classified into the same geological layer. For example, if the seismic wave propagation velocity is stable around a specific value within a certain depth range, this indicates that the area may be a relatively homogeneous geological layer. Thickness information is also important. By combining drilling data and information such as seismic wave reflection time, the thickness of different geological layers can be determined. For strata with similar thickness and density and wave velocity, they can be merged into one geological layer. However, for strata with greater thickness and obvious changes in wave velocity or density, further subdivision is required. By comprehensively considering these parameters, the geological layer modeling data of the entire mining area can be divided in detail, and accurate geological layer division results can be output, clearly showing the distribution and characteristics of different geological layers.

[0030] In step S203, after obtaining the geological stratification results, a professional 3D modeling software is used to construct the model. The stratified geological data is imported into the 3D modeling software, which locates and models each geological layer in 3D space based on its attribute information (such as shape, boundary, thickness, etc.). For example, for each geological layer, its geometry can be constructed using its boundary data, and its range can be determined in the vertical direction based on its thickness information. During the modeling process, the contact relationship between different geological layers needs to be accurately processed. For example, if there is a fault, the location, strike, and displacement of the fault need to be determined based on the geological exploration data. The displacement and deformation of the geological layers at the fault need to be accurately represented in the 3D model. At the same time, for geological structures such as folds, accurate modeling is also required based on the actual curvature of the geological layers, so that the 3D model can realistically reflect the complex geological structure of the mining area. Through these steps, the 3D modeling software is used to integrate all the geological stratification results and generate a high-quality 3D model of the mining area, providing an intuitive and accurate geological model basis for subsequent seismic signal analysis, safety assessment, and other work.

[0031] In one embodiment, the 3D model of the mining area includes a modeling granularity adjustment component. A preset modeling refinement granularity is input according to the modeling granularity adjustment component, and the 3D model of the mining area is refined by the preset modeling refinement granularity.

[0032] Specifically, the modeling granularity adjustment component in the 3D model of the mining area is a key functional module built on advanced algorithms and technologies, which can be used to input preset modeling refinement granularity. Determining the preset modeling refinement granularity requires comprehensive consideration of research or application objectives, computational resources, and time costs, balancing resource consumption while ensuring accuracy. Data format conversion and verification are necessary during input. After input, model refinement begins. For each geological layer, a higher refinement granularity will further subdivide its internal rock types or physical property variations. For example, sandstone geological layers can be subdivided into sub-regions with different porosities or mineral compositions based on the new granularity. For geological structures, descriptions of features such as the distribution of fractured rocks and surface roughness within fault zones are added at fault locations, while details such as curvature changes and interlayer interactions are added at folds. For stratigraphic boundaries and contact relationships, their clarity and accuracy are adjusted according to the refinement granularity, more accurately presenting the contact conditions of stratigraphic transition areas, making the model more precise and detailed, and providing a reliable geological model foundation for subsequent analysis and applications.

[0033] like Figure 3 As shown, in one embodiment of the present invention, the signal restoration module generates the following steps: Step S301: Determine the initial test signal sample; Step S302: Call the three-dimensional model of the sampling area to simulate seismic detection signals according to the initial test signal samples, and receive the first set of simulated signal samples based on the first safety radius; Step S303: Compare the first set of simulated signal samples with the initial test signal samples to obtain signal attenuation index samples and signal phase change samples; Step S304: Based on the initial test signal samples, the first set of simulated signal samples, the signal attenuation index samples, and the signal phase change samples, perform deconvolution network training to generate a signal restoration module.

[0034] Specifically, in step S301, the initial test signal sample is determined based on the analysis of a large amount of historical earthquake data. The frequency, amplitude, waveform and other information of the seismic wave signals generated by different magnitudes, focal depths and earthquake types (such as tectonic earthquakes, volcanic earthquakes, etc.) are comprehensively considered. By statistically analyzing the earthquake records under similar geological conditions in the past, a signal with a representative frequency range and amplitude distribution is constructed. At the same time, it covers the waveform characteristics of typical seismic waves such as P waves and S waves, providing a comprehensive foundation for subsequent simulation and analysis.

[0035] In step S302, after determining the initial test signal samples, a three-dimensional model that accurately reflects the geological structure of the mining area (including the density, wave velocity, thickness of different geological layers, and geological structural information such as faults and folds) is called to conduct seismic detection signal simulation. The initial test signal samples are input into the model, and the propagation of the signal in the geological layers is simulated according to its built-in seismic wave propagation algorithm. The model considers the complex effects of attenuation, scattering, and reflection of seismic waves when they pass through each layer in the mining area. The propagation velocity and attenuation coefficient are calculated according to the physical properties of each geological layer. For example, when seismic waves encounter dense strata, the propagation velocity changes and the attenuation is enhanced. When they encounter geological structures, scattering and reflection occur. Finally, the first set of simulated signal samples that matches the actual seismic detection conditions is generated at the first safe radius.

[0036] In step S303, after obtaining the first set of simulated signal samples, it is compared in detail with the initial test signal samples. By comparing the amplitude information, the signal attenuation index samples are obtained. The difference or ratio of the amplitude of the two samples at each time point or within a specific frequency band is calculated to describe the degree of attenuation in signal propagation. At the same time, the phase information is compared to obtain the signal phase change samples. The phase shift and change trend are calculated using the phase analysis algorithm, such as observing the advance or lag of the seismic wave phase after passing through a specific geological layer.

[0037] In step S304, deconvolution network training is conducted using initial test signal samples, the first set of simulated signal samples, signal attenuation index samples, and signal phase change samples. The deconvolution network, a neural network structure specifically designed to handle signal convolution and deconvolution, is suitable for recovering seismic signals deformed by geological layers. During training, the initial test signal samples are used as the target output, the first set of simulated signal samples as the input, and the signal attenuation index samples and signal phase change samples as auxiliary information. Through extensive iterative training, the network masters the propagation laws of seismic waves in the three-dimensional model and the impact of attenuation and phase changes on the signal. Ultimately, a signal restoration module is generated that can accurately recover the original characteristics based on the attenuation and phase changes in the received seismic detection signals in practical applications, providing reliable data support for earthquake monitoring and analysis.

[0038] In one embodiment, the method of inputting the first seismic sensing signal set into the signal restoration module for signal restoration and outputting a restored seismic signal set includes: The first seismic sensing signal set is input into the signal restoration module, and the first seismic sensing signal set is windowed according to the time series to obtain multiple sensing signal segments. The amplitude attenuation characteristics and phase change characteristics of each of the multiple sensing signal segments are deconvolved to output multiple restored signal segments; The multiple restored signal segments are reconstructed to output a set of earthquake restored signals.

[0039] Specifically, firstly, the first set of seismic sensing signals is input into the signal reconstruction module. This set contains abundant seismic wave information collected from the seismic sensing edge network within the first safety radius. Subsequently, in the signal reconstruction module, the first set of seismic sensing signals is segmented into windows according to the time series. The appropriate window size and sliding step size need to be determined based on the characteristics of the seismic waves and the requirements of subsequent processing. For example, based on the analysis of the frequency range of seismic waves and the expected signal change period, a window size is selected that can contain sufficient signal information while ensuring the independence of each segment. At the same time, a reasonable sliding step size is set so that there is appropriate overlap or connection between adjacent windows, thereby obtaining multiple sensing signal segments. These segments will serve as the basic units for subsequent processing, and each segment carries local seismic wave information within a specific time range.

[0040] For each of the acquired multiple sensor signal segments, a deconvolution operation is performed to restore its amplitude attenuation and phase change characteristics. The deconvolution process is based on a mathematical model that is iteratively trained on data of the propagation law of seismic waves in geological layers. As seismic waves pass through different geological layers, their amplitude attenuates due to absorption and scattering by the geological layers, and their phase changes due to variations in propagation speed and geological structures. During the deconvolution process, a pre-established signal propagation model for the geological environment is used, combined with the actual data of each sensor signal segment, to solve for its original amplitude and phase information through complex calculations. For example, based on the known attenuation coefficient and phase change law of seismic waves by geological layers, the amplitude attenuation and phase change characteristics of each sensor signal segment are gradually restored through iterative calculations and optimization algorithms. Finally, multiple restored signal segments are output. Compared with the original sensor signal segments, the restored signal segments are closer to the state of seismic waves when they are not disturbed by geological layers.

[0041] After obtaining multiple reconstructed signal segments, a reconstruction operation is performed. The reconstruction process needs to ensure the continuity and rationality of each reconstructed signal segment in time and space. By analyzing the boundary conditions and characteristic parameters of each reconstructed signal segment, they are spliced ​​together in chronological order. During the splicing process, the transition between adjacent segments is smoothed to avoid abrupt changes or discontinuities in the signal. For example, for the amplitude and phase values ​​of two adjacent reconstructed signal segments at the splicing point, weighted averaging or other appropriate interpolation methods are used to ensure a natural transition, thereby ensuring that the entire reconstructed signal is physically reasonable. After the reconstruction process, the final output is a seismic reconstructed signal set. The signal set is the reconstruction result of the first seismic sensing signal set, which more accurately reflects the original information of the seismic waves and provides high-quality data support for subsequent seismic analysis and related applications.

[0042] like Figure 4 As shown, in one embodiment of the present invention, the steps for generating a seismic reconstruction signal set include: Step S401: Configure a second safety radius centered on the mining area, wherein the first safety radius is different from the second safety radius; Step S402: Deploy a second seismic sensing edge network on the second safety radius, perform real-time detection based on the second seismic sensing edge network, and output the second seismic sensing signal set corresponding to the second safety radius; Step S403: Input the first seismic sensor signal set and the second seismic sensor signal set into the signal restoration module for signal restoration, and output the seismic restoration signal set.

[0043] Specifically, after determining the first safety radius centered on the mining area, the controller executes step S401 to configure the second safety radius. Since the first and second safety radii are different, the difference is based on the need for more comprehensive and in-depth safety protection of the mining area. Configuring the second safety radius requires consideration of various factors, such as the geological complexity of the mining area, the scale and depth of mining activities, etc. If the geological structure of the mining area changes significantly, with many hidden geological hazards, or if the mining operation is large-scale and deep, a larger second safety radius needs to be set to expand the monitoring range and ensure that no seismic signals that may indicate danger are missed.

[0044] Then, step S402 is executed. After determining the second safety radius, a second seismic sensing edge network is deployed on the circumference defined by the radius. The deployment of sensors needs to follow scientific and reasonable layout principles to ensure uniform coverage and effective detection of the entire circumferential area. The type and performance of the sensors must match the first seismic sensing edge network and also adapt to the geological environment within the second safety radius. During the mining operation, the second seismic sensing edge network performs real-time detection and can capture seismic wave information within the radius. After the information is collected and processed by the sensors, the second seismic sensing signal set corresponding to the second safety radius is output. The signal set contains rich seismic data, such as the amplitude, frequency, and phase of seismic waves. These data are important evidence reflecting changes in the geological state within the second safety radius.

[0045] Finally, step S403 is executed, where the first and second seismic sensor signal sets are input together into the signal restoration module. Because seismic signals attenuate as they pass through geological layers, the received signal differs from the original signal, necessitating signal restoration. The signal restoration module utilizes a convolutional neural network (CNN) for signal restoration. First, a network structure specifically designed for seismic signal restoration is constructed. Its input layer receives the first and second seismic sensor signal sets. In the convolutional layers, the convolutional kernels are designed based on the structural characteristics of the geological layers. Different sized convolutional kernels are used to simulate the influence of different geological layers on the signal at different scales. This is specifically designed to address the signal attenuation at the second safety radius. In severe cases, specific layers are set up in the network to specifically handle the characteristics of such long-distance signals. During the training phase, a large amount of known original seismic signals and signal data after attenuation by geological layers are used to train the CNN model. During training, the network weights are adjusted to allow the model to learn the attenuation law of the geological layers on the signal. Signal features under different safety radii are used as different label information, and location information (corresponding to the first or second safety radius) is used as auxiliary input. This enables the model to accurately distinguish and reconstruct signals at different radii, thereby outputting a seismic reconstruction signal set that is closer to the original state when the earthquake occurred, providing more accurate data support for subsequent safety analysis and early warning.

[0046] In one embodiment, the step of inputting the first seismic sensor signal set and the second seismic sensor signal set into the signal restoration module for signal restoration includes: The first seismic sensor signal set and the second seismic sensor signal set are fused to output a fused seismic sensor signal set, wherein the fused seismic sensor signal set does not include redundant signals from adjacent areas; The fused seismic sensing signal set is input into the signal restoration module for signal restoration, and the restored seismic signal set is output.

[0047] Specifically, within the signal fusion module of the signal restoration module, a fusion operation is performed on the input first and second seismic sensor signal sets. The aim is to eliminate redundant signals from adjacent areas caused by the propagation characteristics of seismic waves and the characteristics of the monitoring area. A wavelet transform-based signal decomposition and reconstruction algorithm is employed. Wavelet transform can decompose signals at different scales and frequencies. For the first and second seismic sensor signal sets, wavelet transforms are performed separately. The energy distribution characteristics of the signals are analyzed among the decomposed components at different scales and frequencies. Since redundant signals usually have similar energy distribution patterns at specific scales and frequencies, by setting a reasonable energy threshold range, components with highly similar energy distributions in the two signal sets are identified. These components are likely redundant signals generated from adjacent areas. Principal component analysis (PCA) is then used. PCA can transform multiple correlated variables into a few uncorrelated composite variables. Principal components (PCA) are used to process the matrix composed of the first and second seismic sensor signal sets to obtain their respective principal components. In the principal component space, the similarity of the principal components of the two signal sets is analyzed based on indicators such as contribution rate and eigenvalue. The signal parts corresponding to the principal component directions that have a high contribution rate and show a high degree of consistency in the two signal sets can be identified as redundant signals. Combined with geological layer information, the redundant signal parts identified by wavelet transform and PCA analysis are finally confirmed by constructing logical judgment rules. For example, if the geological model determines that a certain area is an adjacent area of ​​two safe radius monitoring areas, and the signal corresponding to that area is determined to be redundant by the above algorithm analysis, it is removed from the fusion process. The final output is a fused seismic sensor signal set. This signal set eliminates the interference of redundant signals and retains the most valuable seismic information, providing a cleaner data foundation for subsequent signal reconstruction work.

[0048] The fused seismic sensor signal set is then input back into the signal restoration module (after the fusion operation is complete) to continue signal restoration. This restoration process utilizes mathematical models and algorithms designed to address the propagation characteristics of seismic signals within geological layers. Considering the attenuation and deformation of seismic signals during propagation due to absorption and scattering by geological layers, the fused seismic sensor signal set is processed in reverse using the model and algorithms. For example, based on known variations in the attenuation coefficient and propagation velocity of seismic waves within geological layers, the amplitude, frequency, and phase of the signal in the fused signal set are compensated and corrected. Through calculation and iteration, the original characteristics of the signal are gradually restored, ultimately outputting a reconstructed seismic signal set. This reconstructed signal set more accurately reflects the original information of the seismic waves, providing reliable data support for subsequent earthquake safety early warning and analysis.

[0049] In one embodiment, the first safety radius is smaller than the second safety radius, and the radius difference between the second safety radius and the first safety radius is greater than a preset difference.

[0050] Specifically, in the earthquake sensing monitoring and safety early warning system, the setting of the first and second safety radii is based on a comprehensive assessment of the geological environment and safety requirements of the mining area. The determination of the radius difference is based on geological complexity assessment, including geological structure, stratigraphic conditions, and potential geological hazard risks. Areas with complex geological structures require a larger radius difference to comprehensively capture earthquake signals. Based on the analysis of seismic wave propagation characteristics, the absorption, reflection, and refraction of seismic waves by different strata are considered, and an appropriate radius difference is determined according to specific propagation conditions. Based on the assessment of the impact range of mining operations, different mining depths, scales, and methods will change the range of strata stress disturbance; large-scale deep operations require a sufficiently large radius difference. The preset difference is determined by studying historical data and drawing on similar engineering experience. Simultaneously, a geological-mining model is established using numerical simulation to simulate the situation under different radius differences, and the calibration is verified in conjunction with actual monitoring data to ensure that the difference between the second and first safety radii is greater than the preset value, thus optimizing the monitoring system performance.

[0051] One embodiment of the present invention provides a computer-readable storage medium for storing computer instructions, which, when executed by a computer, are used to perform all steps of the safety early warning method based on seismic detection during mining as described in any of the above method embodiments.

[0052] like Figure 5 As shown, a hardware structure diagram of an electronic device for safety early warning based on seismic detection during mining, according to an embodiment of the present invention, includes: At least one processor 501; and, Memory 502 is communicatively connected to at least one processor 501; wherein, The memory 502 stores instructions that can be executed by at least one processor 501, which enables the at least one processor 501 to perform the safety early warning method based on seismic exploration during mining as described in any of the above method embodiments.

[0053] Figure 5 Take a processor 501 as an example.

[0054] The electronic device is preferably a programmable logic controller (PLC).

[0055] The electronic device may also include an input device 503 and an output device 504.

[0056] The processor 501, memory 502, input device 503 and output device 504 can be connected by a bus or other means. The figure shows an example of connection by bus.

[0057] The memory 502, as a non-volatile computer-readable storage medium, can be used to obtain non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the safety early warning method based on seismic detection during mining in this embodiment of the application, for example, Figures 1-4 The method flow is shown. The processor 501 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules acquired in the memory 502, thereby realizing the safety early warning method based on seismic detection during mining as described in the above embodiments.

[0058] Memory 502 may include an acquisition program area and an acquisition data area, wherein the acquisition program area may acquire an operating system and an application program required for at least one function; the acquisition data area may acquire data created based on the use of the seismic detection-based safety early warning method, etc. Furthermore, memory 502 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 502 may optionally include memory remotely located relative to processor 501, and these remote memories may be connected via a network to the apparatus performing the seismic detection-based safety early warning method. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0059] The input device 503 can receive user clicks and generate signal inputs related to user settings and function controls for the safety early warning method based on seismic mining detection. The output device 504 may include a display screen or other display device.

[0060] When the one or more modules are accessed in the memory 502 and are run by the one or more processors 501, the safety early warning method based on seismic detection during mining, as described in any of the above method embodiments, is executed.

[0061] The above-described product can perform the methods provided in the embodiments of this application, and has the corresponding functional modules and beneficial effects for performing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in the embodiments of this application.

[0062] The above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the embodiments of the present invention have been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A safety early warning method based on seismic detection during mining, characterized in that, include: Determine the location of the mining area; Based on the location of the mining area, a first safety radius centered on the mining area is configured. A first seismic sensing edge network is deployed on the first safety radius, and real-time detection is performed based on the first seismic sensing edge network to output the first seismic sensing signal set corresponding to the first safety radius. The first seismic sensing signal set is restored using a signal restoration module, and a restored seismic signal set is output. The signal restoration module is generated based on a three-dimensional model of the mining area, which is obtained by performing three-dimensional geological modeling on the mining area. The earthquake reconstruction signal set is input into the earthquake safety early warning module for safety analysis, and an earthquake risk index is output. A safety early warning signal is generated based on the earthquake risk index.

2. The safety early warning method based on seismic detection during mining as described in claim 1, characterized in that, The three-dimensional model of the mining area is obtained by performing three-dimensional geological modeling of the mining area, including: Obtain geological strata modeling data for the mining area; The geological layer modeling data is divided into geological layers according to the density, wave velocity and thickness of the geological layers, and the geological layer division results are output. The geological stratification results are integrated using 3D modeling software to generate a 3D model of the mining area.

3. The safety early warning method based on seismic detection during mining as described in claim 2, characterized in that, The 3D model of the mining area includes a modeling granularity adjustment component. A preset modeling refinement granularity is input according to the modeling granularity adjustment component, and the 3D model of the mining area is refined by the preset modeling refinement granularity.

4. The safety early warning method based on seismic detection during mining as described in claim 1, characterized in that, After the signal restoration module is connected to the three-dimensional model of the sampling area, it also includes: Determine the initial test signal sample; The three-dimensional model of the mining area is invoked to simulate seismic detection signals according to the initial test signal samples, and the first set of simulated signal samples based on the first safety radius are received. The first set of simulated signal samples is compared with the initial test signal samples to obtain signal attenuation index samples and signal phase change samples; Based on the initial test signal samples, the first set of simulated signal samples, the signal attenuation index samples, and the signal phase change samples, a deconvolutional network is trained to generate a signal restoration module.

5. The safety early warning method based on seismic detection during mining as described in claim 4, characterized in that, The method of inputting the first seismic sensing signal set into the signal restoration module for signal restoration and outputting a restored seismic signal set includes: The first seismic sensing signal set is input into the signal restoration module, and the first seismic sensing signal set is windowed according to the time series to obtain multiple sensing signal segments. The amplitude attenuation characteristics and phase change characteristics of each of the multiple sensing signal segments are deconvolved to output multiple restored signal segments; The multiple restored signal segments are reconstructed to output a set of earthquake restored signals.

6. The safety early warning method based on seismic detection during mining as described in claim 1, characterized in that, The step of configuring a first safety radius centered on the mining area based on its location further includes: Configure a second safety radius centered on the mining area, wherein the first safety radius is different from the second safety radius; A second seismic sensing edge network is deployed on the second safety radius, and real-time detection is performed based on the second seismic sensing edge network to output the second seismic sensing signal set corresponding to the second safety radius; The first seismic sensor signal set and the second seismic sensor signal set are input into the signal restoration module for signal restoration, and the restored seismic signal set is output.

7. The safety early warning method based on seismic detection during mining as described in claim 6, characterized in that, The step of inputting the first seismic sensor signal set and the second seismic sensor signal set into the signal restoration module for signal restoration includes: The first seismic sensor signal set and the second seismic sensor signal set are fused to output a fused seismic sensor signal set, wherein the fused seismic sensor signal set does not include redundant signals from adjacent areas; The fused seismic sensing signal set is input into the signal restoration module for signal restoration, and the restored seismic signal set is output.

8. The safety early warning method based on seismic detection during mining as described in claim 6, characterized in that, The first safety radius is smaller than the second safety radius, and the radius difference between the second safety radius and the first safety radius is greater than a preset difference.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when executed by a computer, are used to perform all the steps of the safety early warning method based on seismic detection during mining as described in any one of claims 1-8.

10. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the safety early warning method based on seismic exploration during mining as described in any one of claims 1-8.

Images