Mine underground environment safety evaluation method and system based on real-time seismic data

Abstract

The application provides a mine underground environment safety evaluation method and system based on real-time seismic data, relates to the technical field of mine safety management, generates a preliminary mine influence range by analyzing the influence of an earthquake on a mine; extracts ground displacement and crack information from video data, marks a local abnormal area and calculates a local abnormal damage level; corrects the local abnormal damage level through seismic wave propagation analysis; calls a risk evaluation model to perform static risk evaluation on the mine and generates a static risk evaluation result; and performs fusion risk evaluation in combination with the preliminary mine influence range, the locally corrected damage level and the static risk evaluation result, generates a risk evaluation value and performs safety early warning. The application solves the technical problems that the prior art cannot timely and accurately reflect the dynamic evolution process and local damage of the influence of an earthquake, leading to insufficient risk identification precision and lagging early warning response, and significantly improves the local risk identification precision and early warning accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mine safety management, in particular to a mine underground environment safety evaluation method and system based on real-time seismic data. BACKGROUND

[0002] Mine underground environment safety evaluation is an important technical means to protect the lives of mine workers and maintain the stability of mine structures. Especially in areas affected by frequent seismic activity, the dynamic changes of underground environment pose higher real-time and accuracy requirements for safety evaluation. In the prior art, mine underground environment safety evaluation is usually based on epicenter location, magnitude, seismic motion parameters and other seismic occurrence data collected by the seismic monitoring system, and uses empirical models or numerical simulation methods to calculate the potential impact range and damage degree of earthquakes on mine structures. At the same time, some systems also assist in historical earthquake case analysis to form a static risk level division to guide mine emergency response. However, these methods mainly rely on a single type of data source, such as seismic wave parameters, lack real-time perception of actual mine local damage details, and are difficult to discover small-scale crack expansion or displacement abnormalities in the underground. On the other hand, most of the existing evaluation models are statically set and cannot adjust the risk judgment in time according to the dynamic evolution process of the earthquake, leading to missed detection of local high-risk areas and delayed warning response, which is difficult to meet the urgent needs of real-time and accurate safety evaluation for mine safety production. SUMMARY

[0003] The present application provides a mine underground environment safety evaluation method and system based on real-time seismic data, which solves the technical problems that the prior art relies on a single type of data source and a static evaluation model, making it difficult to timely and accurately reflect the dynamic evolution process and local damage of the earthquake impact, resulting in insufficient accuracy of mine underground environment safety risk identification and delayed warning response, and achieves the technical effect of significantly improving the accuracy of mine underground local risk identification and the accuracy of early warning.

[0004] In view of the above problems, in one aspect, the application provides a mine underground environment safety evaluation method based on real-time seismic data, the method comprising: collecting seismic occurrence data in real time through a seismic monitoring system, analyzing the influence of the earthquake on the mine, and generating a preliminary mine influence range; collecting mine video data in real time to extract ground displacement and crack information, marking local abnormal areas, and calculating a local abnormal damage level of the local abnormal areas; collecting the spatial distance between the mine underground area and the epicenter for seismic wave propagation analysis, correcting the local abnormal damage level, and generating a locally corrected damage level; calling a risk evaluation model to perform static risk evaluation on the mine based on the seismic occurrence data, and generating a static risk evaluation result; using a dynamic weighting algorithm to perform fusion risk evaluation by dynamically adjusting the weight in combination with the preliminary mine influence range, the locally corrected damage level, and the static risk evaluation result, and generating a risk evaluation value; and performing safety warning according to the risk evaluation value.

[0005] In another aspect, the application also provides a mine underground environment safety evaluation system based on real-time seismic data, the system comprising: an influence range determination module for collecting seismic occurrence data in real time through a seismic monitoring system, analyzing the influence of the earthquake on the mine, and generating a preliminary mine influence range; a local abnormality identification module for collecting mine video data in real time to extract ground displacement and crack information, marking local abnormal areas, and calculating a local abnormal damage level of the local abnormal areas; an analysis correction module for collecting the spatial distance between the mine underground area and the epicenter for seismic wave propagation analysis, correcting the local abnormal damage level, and generating a locally corrected damage level; a static evaluation module for calling a risk evaluation model to perform static risk evaluation on the mine based on the seismic occurrence data, and generating a static risk evaluation result; a dynamic evaluation module for using a dynamic weighting algorithm to perform fusion risk evaluation by dynamically adjusting the weight in combination with the preliminary mine influence range, the locally corrected damage level, and the static risk evaluation result, and generating a risk evaluation value; and a safety warning module for performing safety warning according to the risk evaluation value.

[0006] The one or more technical solutions provided in the application have at least the following beneficial effects:

[0007] The seismic monitoring system is used to collect seismic occurrence data in real time, quickly capture seismic events and the preliminary mine influence range, and provide macro background information to lay the foundation for subsequent detailed analysis. The real-time collection of mine video data is used to extract ground displacement and crack information, mark local abnormal areas, and calculate the local abnormal damage level. The actual local damage phenomenon in the mine is perceived in detail, and the specific positions at risk and the severity of the damage in the preliminary influence range are identified. The spatial distance between the mine underground area and the seismic center is collected to analyze the propagation of seismic waves, and the local abnormal damage level is corrected to generate a locally corrected damage level. This step is based on the characteristics of seismic wave propagation, and corrects the preliminary perceived local damage level to improve the physical rationality and accuracy of the evaluation of the local damage. The risk assessment model is called to perform static risk assessment on the mine based on the seismic occurrence data to generate a static risk assessment result, and to give an overall static risk judgment independent of the local perception, which serves as a baseline for subsequent dynamic fusion. A dynamic weighting algorithm is used to combine the preliminary mine influence range, the locally corrected damage level, and the static risk assessment result to perform fusion risk assessment. The risk weight distribution is dynamically optimized to realize real-time and accurate quantification of the overall mine environmental safety state, and a risk assessment value is generated. According to the risk assessment value, a safety warning is given, and targeted safety warning measures are triggered in real time to improve the response speed and accuracy of the warning.

[0008] In summary, the application fuses seismic monitoring data and real-time video perception information of the mine, combines seismic wave propagation analysis and static risk models, and constructs a dynamic weighting mine underground environment safety evaluation mechanism. This scheme not only quickly identifies the overall affected area of the mine after an earthquake, but also finely perceives local displacement abnormalities and crack expansion, and corrects the local damage level in real time, improving the identification accuracy of local high-risk areas in the mine. At the same time, a dynamic weighting algorithm is used to fuse multi-source evaluation results, fully reflecting the influence of the dynamic evolution process of the earthquake on the risk state, significantly improving the real-time, accuracy and reliability of the mine underground environment safety evaluation, and enhancing the warning response capability and safety level of the mine in the event of an earthquake disaster.

[0009] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the application can be implemented in accordance with the content of the specification, and in order to make the above and other purposes, features and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 The flowchart of the mine underground environment safety evaluation method based on real-time seismic data provided by the embodiments of the application is shown.

[0011] Figure 2A schematic diagram of the structure of a mine underground environmental safety assessment system based on real-time seismic data provided in an embodiment of this application.

[0012] Explanation of reference numerals in the attached diagram: Module 10 for determining the scope of influence, Module 20 for identifying local anomalies, Module 30 for analysis and correction, Module 40 for static evaluation, Module 50 for dynamic evaluation, and Module 60 for safety early warning. Detailed Implementation

[0013] This application provides a method and system for assessing the safety of underground mining environments based on real-time seismic data. It solves the technical problems of existing technologies, which rely on a single type of data source and static assessment model, making it difficult to reflect the dynamic evolution process and local damage of earthquake impacts in a timely and accurate manner. This results in insufficient accuracy in identifying underground mining environmental safety risks and delayed early warning responses. By integrating real-time seismic monitoring data with video monitoring anomaly information, and combining seismic wave propagation analysis with a dynamic weighted fusion assessment mechanism, the technical effect of significantly improving the accuracy of identifying local risks in underground mines and the accuracy of early warning is achieved.

[0014] Example 1, as Figure 1 As shown in the embodiments of this application, a method for assessing the safety of the underground environment in mines based on real-time seismic data is provided. The method includes:

[0015] Step S100: Collect earthquake occurrence data in real time through the earthquake monitoring system, analyze the impact of earthquakes on the mine, and generate a preliminary impact range for the mine.

[0016] Specifically, the earthquake monitoring system consists of multiple earthquake sensors that can monitor the propagation of seismic waves in real time and accurately capture key data such as the time, intensity, and depth of earthquakes. The preliminary mine impact assessment is based on earthquake data, using earthquake impact models to estimate the area of ​​the mine that may be affected by an earthquake.

[0017] First, earthquake monitoring systems deployed in and around the mine are used to collect real-time earthquake data, including the time, intensity, and depth of the earthquake. Then, pre-trained earthquake impact models, such as machine learning models trained on historical earthquake impact data, are used to analyze the potential impact area on the mining area and delineate the initial scope of influence.

[0018] This step enables the identification of potentially affected areas of the mine immediately after an earthquake, providing timely assessment of the macro-risk scope and laying the foundation for subsequent fine-grained identification of local risks.

[0019] Step S200: Collect real-time video data from the mine to extract ground displacement and crack information, mark local abnormal areas, and calculate the local abnormal damage level of the local abnormal areas.

[0020] Specifically, the mine video monitoring system (such as a high-definition infrared camera or an intelligent inspection robot) is used to collect mine video data in real time, which is transmitted to the data processing center. The ground displacement and crack information are extracted from the video data by combining image processing algorithms, such as using edge detection algorithm to identify cracks and using optical flow method to calculate displacement. Then, the preset abnormality judgment logic is applied to analyze the extracted displacement and crack information, judge whether there is an abnormal area and mark it. For example, if the displacement exceeds 5 cm and the crack width exceeds 2 cm, it is judged as abnormal, and the area is automatically marked on the image. Next, according to the specific displacement amount and crack size of the marked area, the damage level evaluation model (such as through a linear weighting formula or a trained classification model) is called to evaluate the local abnormal damage level of each local abnormal area to measure the damage degree of the area.

[0021] This step realizes fine-grained perception and quantitative evaluation of the local damage state of the mine, greatly improves the accuracy and local positioning accuracy of risk identification, and provides key data support for dynamic correction of subsequent risks.

[0022] Step S300: Collect the spatial distance between the underground area of the mine and the epicenter for seismic wave propagation analysis, correct the local abnormal damage level, and generate a locally corrected damage level.

[0023] Specifically, the spatial distance refers to the straight-line distance in three-dimensional space between the underground area of the mine and the epicenter, which can be calculated according to the mine geographic coordinates and epicenter coordinates. Obtain the geographic coordinates of each monitoring point in the mine, and calculate the spatial distance from the epicenter.

[0024] Collect historical seismic propagation data and fit the seismic wave propagation law, such as the propagation speed and attenuation coefficient of seismic waves in different rock layers. Based on the earthquake occurrence data, combined with the seismic wave propagation law, the propagation distance and intensity attenuation of the seismic wave reaching the underground area of the mine are predicted. According to the prediction results, the local abnormal damage level is corrected to generate a locally corrected damage level. If a local abnormal area is located in a region far from the epicenter and the actual ground displacement anomaly is small, the damage level of the area is downgraded through propagation analysis, and a corrected level is generated.

[0025] This step corrects the level by introducing physical propagation characteristics, effectively avoiding misjudgment that may occur by relying only on apparent features, and improving the scientificity and accuracy of local damage evaluation.

[0026] Step S400: Call the risk assessment model to perform static risk assessment on the mine based on the earthquake occurrence data, and generate a static risk assessment result.

[0027] Specifically, the risk assessment model is a mathematical model established based on historical data to predict the risk level of the mine affected by earthquakes. Historical earthquake data, historical mine data (including geological stability, underground population density, building structure strength, etc.) and corresponding risk assessment sample data are collected. The historical earthquake data and historical mine data are taken as input, and the risk assessment sample data is taken as output supervision to train the risk assessment model, such as using machine learning algorithms (decision tree, neural network, etc.) for training to obtain the risk assessment model. The trained risk assessment model is called to take the real-time collected earthquake occurrence data (magnitude, depth, geological conditions) as input to predict the static risk level currently faced by the overall mine, and output the static risk assessment result.

[0028] This step evaluates the earthquake risk of the mine from a macro perspective, providing a comprehensive risk reference for subsequent fusion evaluation, which helps to comprehensively judge the safety status of the mine.

[0029] Step S500: A dynamic weighting algorithm is used to perform fusion risk assessment by dynamically adjusting the weights of the preliminary mine influence range, the local correction damage level and the static risk assessment result, and generate a risk assessment value.

[0030] Specifically, according to the real-time earthquake activity intensity (such as aftershock frequency) and time change (post-seismic duration), a preset weight adjustment logic is called to dynamically adjust the weights of each evaluation index (preliminary mine influence range, local correction damage level, static risk assessment result) to more accurately reflect the importance of each index in the current situation. For example: the weight of local abnormal information is higher in the early post-earthquake period, and the weight of static risk is higher in the stable post-earthquake period. According to the weight adjustment result, a dynamic weighted fusion algorithm is applied to comprehensively calculate the preliminary influence range, the local correction damage level and the static assessment result to generate the final risk assessment value.

[0031] This step realizes the risk fusion analysis of time evolution and state change through dynamic weight adjustment, greatly improving the real-time and accuracy of the mine environmental risk assessment.

[0032] Step S600: Safety warning according to the risk assessment value.

[0033] Specifically, the fused risk assessment value is compared with the set safety threshold. If the risk assessment value is higher than the safety threshold, a multi-level warning mechanism is triggered immediately, such as broadcasting an alarm in the working area, LED warning at the shaft, automatic SMS notification to the mine manager, etc. If it is not exceeded, the data change is continuously monitored in real time to maintain continuous monitoring in the normal state.

[0034] This step ensures timely warning based on comprehensive risk judgment, which helps mine personnel to make quick response decisions and minimize casualties and property losses.

[0035] Further, step S100 includes:

[0036] Step S110: Real-time acquisition of seismic intensity, depth, and occurrence time by the seismic monitoring system to generate the seismic occurrence data.

[0037] Step S120: Calling a pre-established seismic influence model to analyze the seismic influence range to generate the preliminary mine influence range, wherein the seismic influence model is trained by historical seismic influence data.

[0038] Specifically, the seismograph in the seismic monitoring system senses seismic waves in real time, records the time, amplitude, and other information of the arrival of the seismic waves. Through the data acquisition and transmission network, these raw data are transmitted to the central data processing center in real time. The data processing center calculates the intensity, depth, and occurrence time of the earthquake using seismological algorithms (such as the time difference method of P and S waves) to generate seismic occurrence data. These seismic occurrence data are input into the pre-established seismic influence model to calculate the preliminary mine influence range.

[0039] The seismic influence model is obtained by training historical seismic influence data, and the specific training process is as follows: First, collect historical seismic event data of the mine and surrounding areas, including seismic intensity, depth, epicenter location, source type, and mine geological conditions, and simultaneously collect the corresponding mine damaged area range of each earthquake, to construct a basic data set; On this basis, design input features such as seismic intensity, depth, distance from the epicenter to the mine center, and geological stability index, and output labels such as actual affected area range, use machine learning models such as random forest regression, support vector regression, or deep neural network for model supervised learning training, use the training set for model fitting, use the validation set for performance evaluation, and use indicators such as mean absolute error, mean square error, and determination coefficient to verify and optimize the model, if the evaluation indicators do not meet the expectations, further optimize the model performance through feature selection and hyperparameter adjustment; Finally, the verified seismic influence model is deployed, and real-time seismic data such as magnitude, depth, and epicenter location collected by the seismic monitoring system are used as input to infer and generate the corresponding preliminary mine influence range, and the result is output as the influence radius or affected area boundary, providing basic data support for subsequent local anomaly analysis and risk assessment.

[0040] The above steps realize rapid and accurate prediction of the mine affected range after an earthquake through the combination of the seismic monitoring system and the seismic influence model, provide a basic range definition for subsequent more detailed mine underground environment safety assessment, and improve the efficiency of the entire assessment process.

[0041] Further, step S200 comprises:

[0042] Step S210: According to the ground displacement and crack information, call the preset anomaly judgment logic to judge and mark the abnormal area, and generate the marking result.

[0043] Step S220: Extract the local abnormal area based on the marking result, and evaluate the damage level based on the displacement and crack of the local abnormal area, and generate the local abnormal damage level.

[0044] Specifically, first, the mine video monitoring system is used to collect the ground displacement change data and surface crack image information in real time, which is the data basis for anomaly analysis. Then, the collected data is processed by calling the preset anomaly judgment logic, wherein the anomaly judgment logic determines the abnormal change area according to the determination rules such as ground displacement exceeding the set threshold, crack width greater than the set standard, crack expansion rate anomaly, etc. The abnormal area is automatically identified and marked, and the marking result is generated.

[0045] Then, based on the marking result, the specific local abnormal area is extracted, and the displacement amplitude, crack number, crack width and crack expansion trend of each local abnormal area are comprehensively evaluated, and the preset damage level division standard is called to assign the corresponding local abnormal damage level, and the local abnormal damage level result is generated to quantitatively describe the damage severity of the local area after the influence of the earthquake.

[0046] Through the above processing, the accurate identification and quantitative grading of the local abnormal situation of the mine surface are realized, which lays a data foundation for subsequent earthquake risk assessment based on local abnormal correction, and effectively improves the accuracy and real-time performance of the mine underground environment safety evaluation.

[0047] Further, step S300 comprises:

[0048] Step S310: Collect historical earthquake propagation data to fit the earthquake wave propagation law.

[0049] Step S320: Based on the earthquake wave propagation law, identify the earthquake propagation distance based on the earthquake occurrence data to generate the predicted propagation distance.

[0050] Step S330: Based on the predicted propagation distance, according to the spatial distance between the mine underground area and the epicenter, correct the local abnormal damage level.

[0051] Specifically, first, the historical earthquake propagation data of the mine and the surrounding area are collected, including the type of seismic wave, propagation speed, energy attenuation law, propagation path and medium characteristics, etc. A seismic wave propagation law model is established by using statistical modeling or machine learning fitting methods such as least squares regression, gradient boosting tree or neural network regressor to describe the quantitative relationship between the change of seismic wave energy with distance.

[0052] The predicted propagation distance is the distance range that the seismic wave can propagate calculated according to the seismic wave propagation law and the earthquake occurrence data. After the earthquake occurs, based on the real-time collected earthquake occurrence data, the seismic wave propagation law model is called to identify the seismic propagation distance, predict the effective influence radius that the seismic wave can reach, and generate the corresponding predicted propagation distance.

[0053] Then, combined with the spatial distance data between each key area in the mine and the epicenter, the preliminary damage level of the local abnormal area is corrected and adjusted according to the predicted propagation distance: for the area with actual spatial distance less than the predicted propagation distance, the damage level is appropriately raised to reflect higher risk, and for the area far away from the epicenter and beyond the propagation influence range, the original level is appropriately lowered or maintained.

[0054] Through the above-mentioned manner, the change trend of the local damage degree under the actual influence of the seismic wave propagation can be dynamically reflected, and the rationality and accuracy of the local risk assessment are significantly improved.

[0055] Further, the step S400 comprises:

[0056] Step S410: Collecting historical earthquake data, historical mine data and corresponding risk assessment sample data, wherein the historical mine data includes the geological stability of the mine, the underground population density and the building structure strength.

[0057] Step S420: Taking the historical earthquake data and the historical mine data as training input, and taking the risk assessment sample data as output supervision, training the risk assessment model.

[0058] Step S430: Collecting real-time mine data, inputting the real-time mine data and the earthquake occurrence data into the risk assessment model for analysis, and outputting the static risk assessment result.

[0059] Specifically, first, the historical earthquake data, the historical mine data and the corresponding risk assessment sample data are collected, wherein the historical earthquake data includes the magnitude, the focal depth, the epicenter location and the earthquake type, the historical mine data includes the geological stability parameters (such as rock structure, fault distribution, rock mechanical properties) of the mine, the underground population density and the building structure strength, and the risk assessment sample data is the risk level or damage degree label of the mine after being affected by the earthquake based on the actual historical event evaluation.

[0060] Then, taking historical earthquake data and historical mine data as training input and risk assessment sample data as supervised output, a supervised learning method (such as random forest, support vector machine or deep neural network algorithm) is used to train the risk assessment model, so that the model can learn the nonlinear mapping relationship between the earthquake characteristics and the mine safety risk level, and obtain the trained risk assessment model.

[0061] Real-time collection of current mine geological data, building structure state and population distribution data of the mine, together with real-time acquisition of earthquake occurrence data as input, calling the trained risk assessment model for analysis, outputting the current static risk assessment result of the mine, thereby realizing intelligent and quantitative assessment of the static risk of the mine affected by the earthquake, and providing a reliable foundation for subsequent dynamic fusion assessment and safety warning.

[0062] Further, step S500 includes:

[0063] Step S510: Based on the preliminary mine influence range, the local correction damage level and the static risk assessment result, according to the real-time earthquake activity intensity and time change, the preset weight adjustment logic is called to adjust the weight of each data type, and the weight adjustment result is generated.

[0064] Step S520: Based on the weight adjustment result, the preliminary mine influence range, the local correction damage level and the static risk assessment result are fused to generate the risk assessment value.

[0065] Specifically, taking the preliminary mine influence range, the local correction damage level and the static risk assessment result as the basic data source, comprehensively considering the real-time earthquake activity intensity change (such as the change trend of earthquake magnitude, the frequency of aftershocks, etc.) and the time evolution characteristics (such as the time elapsed after the earthquake, the duration of the danger window, etc.), the preset weight adjustment logic is called to dynamically adjust the weight of each data type, and the weight adjustment result is generated. The weight adjustment logic can be realized by using a rule-based weight adjustment strategy, a fuzzy control algorithm or a neural network prediction model, etc. For example, when the earthquake activity intensity increases or multiple aftershocks occur, the data weight of the local correction damage level is appropriately increased to enhance the response sensitivity to local abnormal damage.

[0066] Based on the generated weight adjustment result, the preliminary mine influence range, the local correction damage level and the static risk assessment result are weighted and fused, and a weighted average, weighted integration or other fusion method is used to integrate the dynamic information of the three, and output the fused risk assessment value.

[0067] Through the above steps, the multi-source evaluation data can be fully utilized, the real-time changing seismic environment characteristics can be dynamically adapted, the mine underground environment risk comprehensive evaluation can be more accurate and flexible, and more real-time and accurate decision basis can be provided for subsequent safety warning.

[0068] Further, step S600 comprises:

[0069] It is judged whether the risk evaluation value exceeds a preset safety threshold. If it exceeds, a warning signal is triggered. If it does not exceed, the data change is continuously monitored.

[0070] Specifically, based on the risk evaluation value generated by the foregoing fusion, first, threshold determination is performed, that is, it is judged whether the risk evaluation value exceeds a preset safety threshold. The safety threshold can be set according to the geological conditions, structural characteristics, historical seismic damage experience data and industry safety standards of the mine.

[0071] When the risk evaluation value exceeds the safety threshold, a warning signal is immediately triggered. The warning signal can include sound and light alarm, broadcast prompt, short message push, platform pop-up window warning and the like, prompting the mine management personnel and underground operation personnel to take emergency measures such as personnel evacuation, equipment shutdown and passage reinforcement. If the risk evaluation value does not exceed the safety threshold, the continuous collection and monitoring of real-time data are continuously maintained, and the risk evaluation value is dynamically updated according to the seismic activity change, so as to ensure the continuous safety monitoring of the mine environment.

[0072] Through the above steps, an automatic safety warning mechanism based on real-time evaluation results can be realized, the mine underground environment change caused by the earthquake can be responded in time, and the disaster prevention and control response speed and the warning accuracy can be effectively improved.

[0073] In summary, the mine underground environment safety evaluation method based on real-time seismic data provided by the embodiment has the following beneficial effects:

[0074] The embodiment of the present application fuses the seismic monitoring data and the mine real-time video sensing information, combines the seismic wave propagation analysis and the static risk model, and constructs a dynamic weighted mine underground environment safety evaluation mechanism. The scheme not only can quickly identify the overall affected area of the mine after the earthquake, but also can finely perceive the local displacement anomaly and crack expansion, and real-time correct the local damage level, thereby improving the identification accuracy of the local high-risk area of the mine. At the same time, the dynamic weighting algorithm is used to fuse the multi-source evaluation results, the influence of the seismic dynamic evolution process on the risk state is fully reflected, the real-time, accuracy and reliability of the mine underground environment safety evaluation are significantly improved, and the warning response ability and safety guarantee level of the mine in the event of an earthquake disaster are enhanced.

[0075] Embodiment two, as Figure 2As shown, based on the same inventive concept as the preceding embodiment one, the embodiment of the present application provides a mine underground environment safety evaluation system based on real-time seismic data, which comprises:

[0076] An influence range determination module 10 is configured to collect seismic occurrence data in real time through a seismic monitoring system, analyze the influence of the earthquake on the mine, and generate a preliminary mine influence range.

[0077] A local anomaly identification module 20 is configured to collect mine video data in real time to extract ground displacement and crack information, mark local anomaly areas, and calculate a local anomaly damage level of the local anomaly areas.

[0078] An analysis correction module 30 is configured to collect the spatial distance between the mine underground area and the epicenter to perform seismic wave propagation analysis, correct the local anomaly damage level, and generate a locally corrected damage level.

[0079] A static evaluation module 40 is configured to call a risk evaluation model to perform static risk evaluation on the mine based on the seismic occurrence data and generate a static risk evaluation result.

[0080] A dynamic evaluation module 50 is configured to perform fusion risk evaluation by dynamically adjusting weights through a dynamic weighting algorithm in combination with the preliminary mine influence range, the locally corrected damage level, and the static risk evaluation result, and generate a risk evaluation value.

[0081] A safety warning module 60 is configured to perform safety warning according to the risk evaluation value.

[0082] Further, the influence range determination module 10 of the embodiment of the present application is further configured to perform the following steps:

[0083] The seismic intensity, depth, and occurrence time are collected in real time through a seismic monitoring system to generate the seismic occurrence data; a pre-established seismic influence model is called to perform seismic influence range analysis to generate the preliminary mine influence range, wherein the seismic influence model is trained through historical seismic influence data.

[0084] Further, the local anomaly identification module 20 of the embodiment of the present application is further configured to perform the following steps:

[0085] According to the ground displacement and crack information, a preset anomaly judgment logic is called to perform anomaly area judgment and marking to generate a marking result; a local anomaly area is extracted based on the marking result, and a damage level is evaluated based on the displacement and cracks of the local anomaly area to generate the local anomaly damage level.

[0086] Further, the analysis correction module 30 of the embodiment of the present application is further configured to perform the following steps:

[0087] Collect historical earthquake propagation data to fit the law of seismic wave propagation; based on the law of seismic wave propagation, identify the propagation distance of the earthquake based on the earthquake occurrence data to generate a predicted propagation distance; based on the predicted propagation distance, according to the spatial distance between the underground area of the mine and the epicenter, correct the local abnormal damage level.

[0088] Further, the static evaluation module 40 of the embodiment of the application is further used to perform the following steps:

[0089] Collect historical earthquake data, historical mine data and corresponding risk assessment sample data, wherein the historical mine data includes the geological stability of the mine, the underground population density and the building structure strength; use the historical earthquake data and the historical mine data as training input and use the risk assessment sample data as output supervision to train the risk assessment model; collect real-time mine data and input the real-time mine data into the risk assessment model together with the earthquake occurrence data for analysis to output the static risk assessment result.

[0090] Further, the dynamic evaluation module 50 of the embodiment of the application is further used to perform the following steps:

[0091] Based on the preliminary mine influence range, the local corrected damage level and the static risk assessment result, according to the real-time seismic activity intensity and the time change, call a preset weight adjustment logic to adjust the weight of each data type to generate a weight adjustment result; based on the weight adjustment result, fuse the preliminary mine influence range, the local corrected damage level and the static risk assessment result to generate the risk assessment value.

[0092] Further, the safety warning module 60 of the embodiment of the application is further used to perform the following steps:

[0093] Determine whether the risk assessment value exceeds a preset safety threshold; if yes, trigger a warning signal; if no, continue to monitor the data change.

[0094] Through the foregoing detailed description of the method for evaluating the safety of the underground environment of a mine based on real-time earthquake data, those skilled in the art can clearly know that the system for evaluating the safety of the underground environment of a mine based on real-time earthquake data in the embodiment, for the system disclosed in embodiment two, has corresponding functional modules and beneficial effects due to its correspondence with the method disclosed in embodiment one, and the related parts are described in the method part.

[0095] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and that the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for safety assessment of mine underground environment based on real-time seismic data, characterized in that, Comprise: Real-time acquisition of earthquake occurrence data by a seismic monitoring system, analysis of the impact of the earthquake on the mine, and generation of a preliminary mine impact range; Real-time acquisition of mine video data to extract ground displacement and crack information, marking of local abnormal areas, and calculation of the local abnormal damage level of the local abnormal area; Collecting the spatial distance between the underground area of the mine and the epicenter for seismic wave propagation analysis, correcting the local abnormal damage level, and generating a locally corrected damage level; Calling a risk assessment model to conduct static risk assessment of the mine based on the earthquake occurrence data, and generating a static risk assessment result; Using a dynamic weighting algorithm, combining the preliminary mine impact range, the locally corrected damage level, and the static risk assessment result for fusion risk assessment, and generating a risk assessment value; According to the risk assessment value, a safety warning is given.

2. The real-time seismic data based mine environment safety assessment method of claim 1, wherein, Real-time acquisition of earthquake occurrence data by a seismic monitoring system, analysis of the impact of the earthquake on the mine, and generation of a preliminary mine impact range, comprising: Real-time acquisition of earthquake intensity, depth, and occurrence time by a seismic monitoring system to generate the earthquake occurrence data; Calling a pre-established earthquake impact model to analyze the earthquake impact range and generate the preliminary mine impact range, wherein the earthquake impact model is trained by historical earthquake impact data.

3. The real-time seismic data based mine environment safety assessment method of claim 1, wherein, Real-time acquisition of mine video data to extract ground displacement and crack information, marking of local abnormal areas, and calculation of the local abnormal damage level of the local abnormal area, comprising: According to the ground displacement and crack information, calling a pre-set abnormal judgment logic to judge and mark the abnormal area, and generating a marking result; Based on the marking result, extract the local abnormal area, and based on the displacement and crack of the local abnormal area, evaluate the damage level to generate the local abnormal damage level.

4. The real-time seismic data based mine environment safety assessment method of claim 1, wherein, Collecting the spatial distance between the underground area of the mine and the epicenter for seismic wave propagation analysis, correcting the local abnormal damage level, and generating a locally corrected damage level, comprising: Collecting historical earthquake propagation data to fit the law of seismic wave propagation; Based on the law of seismic wave propagation, identify the earthquake propagation distance based on the earthquake occurrence data to generate a predicted propagation distance; Based on the predicted propagation distance, according to the spatial distance between the underground area of the mine and the epicenter, correct the local abnormal damage level.

5. The real-time seismic data based mine environment safety assessment method of claim 1, wherein, Calling a risk assessment model to conduct static risk assessment of the mine based on the earthquake occurrence data, and generating a static risk assessment result, comprising: Collecting historical earthquake data, historical mine data, and corresponding risk assessment sample data, wherein the historical mine data includes the geological stability, underground population density, and building structure strength of the mine; Using the historical earthquake data and historical mine data as training input and the risk assessment sample data as output supervision to train the risk assessment model; Collecting real-time mine data and inputting it together with the earthquake occurrence data into the risk assessment model for analysis, and outputting the static risk assessment result.

6. The real-time seismic data based mine environment safety assessment method of claim 1, wherein, The dynamic weighting algorithm is adopted to combine the preliminary mine influence range, the local correction damage level and the static risk assessment result to perform fusion risk assessment through dynamic adjustment of weights, and generate a risk assessment value, including: Based on the preliminary mine influence range, the local correction damage level and the static risk assessment result, the weight adjustment logic is called to adjust the weight of each data type according to real-time seismic activity intensity and time variation, and a weight adjustment result is generated; Based on the weight adjustment result, the preliminary mine influence range, the local correction damage level and the static risk assessment result are fused to generate the risk assessment value.

7. The real-time seismic data based mine environment safety assessment method of claim 1, wherein, According to the risk assessment value, a safety warning is performed, including: determining whether the risk assessment value exceeds a preset safety threshold; if yes, triggering a warning signal; if no, continuing to monitor data changes.

8. A mine underground environment safety assessment system based on real-time seismic data, characterized in that, The system is used to perform the mine underground environment safety assessment method based on real-time seismic data according to any one of claims 1-7, including: an influence range determination module for collecting seismic occurrence data in real time through a seismic monitoring system, analyzing the influence of earthquakes on mines, and generating a preliminary mine influence range; a local anomaly identification module for collecting mine video data to extract ground displacement and crack information, marking local anomaly areas, and calculating the local anomaly damage level of the local anomaly areas; an analysis correction module for collecting the spatial distance between the mine underground area and the epicenter to perform seismic wave propagation analysis, correcting the local anomaly damage level, and generating a local correction damage level; a static assessment module for calling a risk assessment model to perform static risk assessment on the mine based on the seismic occurrence data, and generating a static risk assessment result; a dynamic assessment module for adopting a dynamic weighting algorithm to combine the preliminary mine influence range, the local correction damage level and the static risk assessment result to perform fusion risk assessment through dynamic adjustment of weights, and generate a risk assessment value; a safety warning module for performing a safety warning according to the risk assessment value.

Images