Geological disaster early warning and monitoring system and method

Abstract

The invention provides a geological disaster early warning and monitoring system and method, and relates to the technical field of geological disaster monitoring and early warning, the geological disaster early warning and monitoring system comprises an acquisition module, a preprocessing module and an analysis module; a geological disaster early warning monitoring method comprises the following steps: S1, data acquisition; s2, preprocessing the data; s3, transmitting the data; s4, data analysis processing; s5, outputting a prediction report; according to the invention, through cooperative work of the ultrasonic detector and the infrared sensor, comprehensive monitoring of the internal structure and moisture of the mine mountain is realized; according to the method, the dynamic change data and the moisture data are combined, the stability of the mining area is comprehensively evaluated, the comprehensiveness and accuracy of early warning are improved, the risk information of geological disasters can be rapidly and clearly conveyed to management personnel through the alarm levels of color codes and sound intensity, and accurate, comprehensive and timely support can be provided for early warning of the geological disasters of the mining area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological disaster monitoring and early warning, in particular to a geological disaster early warning and monitoring system, and also relates to a geological disaster early warning and monitoring method. BACKGROUND

[0002] Geological disasters (such as earthquakes, mudslides, landslides, rock avalanches, and land collapses) are extremely destructive and unpredictable events among natural disasters, posing a significant threat to human life and property safety and social stability. Traditional geological disaster monitoring methods mainly rely on a single sensor or traditional monitoring means, which is difficult to fully capture the multidimensional characteristics of geological disasters, resulting in insufficient accuracy and response speed of early warning.

[0003] In the existing technology, the roof fracture prediction of mine collapse mainly relies on traditional fracture sensors (such as fiber grating fracture sensors) and seismograph sensor data. However, this traditional method is difficult to fully capture the dynamic changes inside the geological body, especially the influence of complex changes in the internal structure of the geological body on the roof fracture expansion.

[0004] With the development of technology, in recent years, researchers have gradually realized that the occurrence of geological disasters is often accompanied by changes in some environmental parameters. For example, changes in the water content inside the geological body, dynamic changes in mineral content, and anomalies in the surface temperature distribution, although not directly reflecting traditional monitoring indicators, can provide important precursor signals for the occurrence of geological disasters.

[0005] Changes in the water content inside the geological body can reflect the dynamic changes in the water content inside the geological body, and the changes in the water content are closely related to the toughness of the geological body. By fusing and analyzing the water content inside the geological body with the dynamic change data of the internal structure of the geological body, the stability of the geological body can be more comprehensively evaluated.

[0006] In the prior art, a geological disaster monitoring and early warning method and system are disclosed in CN118197008A. Real-time geological monitoring data and historical geological monitoring data are obtained through high-resolution satellites and synthetic aperture radar. The real-time geological monitoring data is processed to obtain processed geological data. The deep generative adversarial network model is trained according to the processed geological data and the historical geological monitoring data to obtain a geological disaster monitoring and prediction model. The geological monitoring data to be predicted is obtained. The geological data to be predicted is input into the geological disaster monitoring and prediction model to obtain a geological disaster prediction result. The present application uses multiple remote sensing sources to effectively avoid the interference faced by a single remote sensing technology, thereby realizing efficient, fast, and accurate geological disaster early warning.

[0007] The above information disclosed in the Background section is only for enhancing the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art that is already known to those of ordinary skill in the art. SUMMARY

[0008] The purpose of the present application is to provide a geological disaster early warning monitoring system and method to solve the problems raised in the background.

[0009] To achieve the above purpose, the present application provides the following technical solutions: A geological disaster early warning monitoring system, comprising a collection module, a preprocessing module and an analysis module; The collection module is used to collect data of a mine area mountain through a plurality of sensors, and the collected data includes dynamic change data of the internal structure of a geological body and water data inside the geological body; The preprocessing module is used to preprocess the dynamic change data and water data collected by the collection module; The analysis module is used to analyze and process the processed dynamic change data and water data, extract the wave velocity change rate of the dynamic change data and water data, and convert the wave velocity change rate into a frequency domain, extract the lateral wave velocity change rate and vertical wave velocity change rate in the wave velocity change rate, and then analyze the position topology graph of the lateral wave velocity change rate and vertical wave velocity change rate, extract the change abnormal points between the lateral wave velocity change rate and vertical wave velocity change rate, and then identify the clustering density parameters of the change abnormal points through a machine learning model combined with a clustering method; and predict geological disasters combined with the water data inside the geological body to obtain a geological disaster prediction report.

[0010] Further, the preprocessing module uploads the processed dynamic change data and water data after preprocessing the dynamic change data and water data, the preprocessing module is electrically connected with a communication module, the communication module is used to upload the processed dynamic change data and water data to an edge cloud calculator, and the analysis module analyzes and processes the processed dynamic change data and water data through the edge cloud calculator.

[0011] Further, after the analysis module calculates and analyzes to obtain a geological disaster prediction report, the edge cloud calculator transmits the geological disaster prediction report to a monitoring terminal through the communication module, and the geological disaster prediction report includes a text report and an image report.

[0012] Further, the monitoring terminal includes an alarm module, which alarms according to the prediction classification in the geological disaster prediction report. The grade of the geological disaster prediction report is set as follows: Light warning: color code is green, sound intensity is low frequency and low loudness; Moderate warning: color code is yellow, sound intensity is medium frequency and moderate loudness; Major warning: color code is red, sound intensity is high frequency and strong loudness.

[0013] Further, the dynamic change data uses an ultrasonic detector to collect the dynamic change data of the internal structure of the geological body in real time, extracts the wave velocity change rate in the dynamic change data, that is, the change rate of the wave velocity with time, for detecting the internal structure of the geological body; through Fourier transform, the wave velocity change rate signal is converted into frequency domain, the change characteristics of the transverse wave velocity change rate and the vertical wave velocity change rate components are extracted, through frequency domain analysis, the abnormal frequency components in the wave velocity change rate are identified, and the dynamic change of the internal structure of the geological body is reflected.

[0014] Further, the abnormal frequency components include change abnormal points between the transverse wave velocity change rate and the vertical wave velocity change rate, or between the transverse wave velocity change rates or between the vertical wave velocity change rates; The change abnormal point between the transverse wave velocity change rate and the vertical wave velocity change rate is a collision point between the transverse wave velocity change rate and the vertical wave velocity change rate, that is, an intersection point between the vertical cracks and the transverse cracks; The change abnormal point between the transverse wave velocity change rates is a collision point between the transverse wave velocity change rates, that is, an intersection point between the transverse cracks; The change abnormal point between the vertical wave velocity change rates is a collision point between the vertical wave velocity change rates, that is, an intersection point between the vertical cracks.

[0015] A geological disaster early warning and monitoring method, comprising the following steps: S1, data collection: the collection module periodically collects the water content in the internal geological body of the mountain area through an infrared sensor, and monitors the dynamic change data of the internal structure of the geological body through an ultrasonic detector; S2, data preprocessing: the collected dynamic change data and water data are preprocessed, including cleaning, denoising, filtering and normalization processing; S3, data transmission: the processed dynamic change data and water data are uploaded to an edge cloud calculator through a communication module; S4, data analysis and processing: the analysis module analyzes and processes the dynamic change data and the water data, identifies the aggregation density parameters of the change abnormal points in the dynamic change data, and predicts the geological disaster in combination with the water data in the internal geological body to obtain a geological disaster prediction report; S5, outputting a prediction report: the edge cloud computer transmits the geological disaster prediction report to the monitoring terminal through the communication module, and the monitoring terminal alarms through the alarm module.

[0016] Compared with the prior art, the present application has the following advantages: According to the multi-sensor data acquisition and efficient data analysis technology, the present application can quickly and clearly convey the risk information of geological disasters to the management personnel through the color code and the alarm level of sound intensity, and can provide accurate, comprehensive and timely support for the geological disaster warning of the mining area; significantly improve the safety management level of the mining area, promote the development of mine disaster prevention and mitigation technology, and lay a solid foundation for the construction of intelligent mining area; The present application also realizes comprehensive monitoring of the internal structure and moisture of the mining area mountain through the cooperative work of the ultrasonic detector and the infrared sensor; the frequency domain analysis of the wave velocity change rate is carried out through Fourier transform, and the key horizontal and vertical wave velocity change rate characteristics are extracted; and the internal cracks are predicted according to the wave velocity change rate, which is convenient for predicting the trend of the cracks, and the collision points of different cracks are taken as abnormal points, the machine learning model combines the clustering method to realize intelligent identification and analysis of the abnormal point density parameter, combines the dynamic change data and the moisture data, and comprehensively evaluates the stability of the mining area, improves the comprehensiveness and accuracy of the early warning. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 It is a whole system structure schematic diagram of the present application; Figure 2 It is a whole method flow schematic diagram of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application more clear and explicit, the present application is further described in detail below in combination with specific embodiments. EMBODIMENT

[0019] Please refer to Figure 1 The present application provides a technical scheme: a geological disaster early warning monitoring system, comprising a collection module, a preprocessing module and an analysis module; The collection module is used for collecting data of the mining area mountain through a plurality of sensors, and the collected data includes dynamic change data of the internal structure of the geological body and moisture data in the geological body; The preprocessing module is used for preprocessing the dynamic change data and moisture data collected by the collection module; The analysis module is used for analyzing and processing the processed dynamic change data and moisture data, extracting a wave velocity change rate from the dynamic change data and the moisture data, performing frequency domain conversion on the wave velocity change rate, extracting a lateral wave velocity change rate and a vertical wave velocity change rate in the wave velocity change rate, performing position topology analysis on the lateral wave velocity change rate and the vertical wave velocity change rate, extracting change abnormal points between the lateral wave velocity change rate and the vertical wave velocity change rate or between the lateral wave velocity change rates or between the vertical wave velocity change rates, and identifying an aggregation density parameter of the change abnormal points by a machine learning model in combination with a clustering method; and in combination with moisture data inside a geological body, predicting a geological disaster to obtain a geological disaster prediction report.

[0020] In the embodiment, preferably, the preprocessing module uploads the processed dynamic change data and moisture data after preprocessing the dynamic change data and the moisture data, the preprocessing module is electrically connected with a communication module, and the communication module is used for uploading the processed dynamic change data and moisture data to an edge cloud computer, and the analysis module analyzes and processes the processed dynamic change data and moisture data through the edge cloud computer. It should be noted that the communication module and the edge cloud computer realize rapid uploading and localized analysis of data, can quickly respond to geological disaster risks in a monitoring area, and the data cleaning, denoising and filtering technology of the preprocessing module can effectively eliminate environmental noise and data pollution, ensuring the stability of the data; the edge cloud computer realizes localized analysis and prediction of the data, reduces the delay and bandwidth consumption of data transmission, and ensures stable operation of the system.

[0021] In the embodiment, preferably, after the analysis module obtains the geological disaster prediction report through calculation and analysis, the edge cloud computer transmits the geological disaster prediction report to a monitoring terminal through the communication module, and the geological disaster prediction report includes a text report and an image report. It should be noted that the text report can describe the analysis results of the dynamic change data and the moisture data in detail, including specific calculation of an abnormal point density parameter and probability prediction of occurrence of a geological disaster, and according to a weighted coefficient of the abnormal point density and the moisture data, the text report can clearly divide low-risk, medium-risk and high-risk levels and provide corresponding risk assessment results. The image report directly displays spatial distribution and density change of abnormal points through a map and a position topology graph, which can help managers quickly locate potential dangerous areas; the image report can display a change trend of the dynamic change data through a time sequence graph and a frequency domain analysis graph, reflecting dynamic change characteristics of an internal structure of a geological body; the image report directly displays an influence of moisture on stability of the geological body through a moisture distribution graph and an abnormal point density graph, helping managers understand specific influences of moisture change on safety of a mining area. The text report and the image report are combined to provide comprehensive and multi-dimensional geological disaster risk assessment information, to help the manager to comprehensively understand the geological conditions of the monitoring area from multiple angles; through the detailed analysis of the text report and the intuitive visualization of the image report, the warning module of the monitoring terminal can provide clear and powerful decision support for the manager to ensure that the measures taken have scientific basis and effectiveness.

[0022] In this embodiment, preferably, the monitoring terminal comprises a warning module, which alarms according to the prediction classification in the geological disaster prediction report; The grades of the geological disaster prediction report are set as follows: Light warning: color code is green, and sound intensity is low frequency and low loudness; Moderate warning: color code is yellow, and sound intensity is medium frequency and moderate loudness; Major warning: color code is red, and sound intensity is high frequency and strong loudness; It should be noted that the risk level in the geological disaster prediction report can be quickly identified through the color code (green, yellow, red), to help the manager to understand the geological disaster risk of the monitoring area at a glance; the sound intensity (low frequency and low loudness, moderate loudness, strong frequency and loudness) can provide auxiliary prompt when visual information is insufficient or inconvenient to view the device, to further strengthen the communication of risk information; The setting of the warning level (light, moderate, major) can clearly prompt the monitoring terminal manager to take corresponding measures, for example: Light warning: carefully check the abnormal points with less risk but need attention; Moderate warning: take intermediate measures such as strengthening support measures and increasing monitoring frequency; Major warning: immediately take emergency measures to assess whether the mine area needs to be closed or evacuated; Timeliness of alarm: through the division of warning levels and the timeliness of alarm, the manager can quickly respond to the potential risk of geological disasters and reduce the loss caused by geological disasters.

[0023] Through the combination of color code and sound intensity, the warning module of the monitoring terminal can realize multi-modal communication of information, which can not only perceive the risk level through vision, but also quickly identify abnormal conditions through hearing; the setting of the warning level can provide multi-dimensional risk information presentation by combining the analysis results of dynamic change data and moisture data, to help the manager to comprehensively understand the geological disaster risk of the monitoring area.

[0024] In this embodiment, preferably, the dynamic change data uses an ultrasonic detector to collect dynamic change data of the internal structure of the geological body in real time, extracts the wave velocity change rate in the dynamic change data, and the wave velocity change rate is the rate of change of the wave velocity over time, which is used to detect the internal structure of the geological body; the wave velocity change rate signal is converted into the frequency domain by Fourier transform, and the change characteristics of the transverse wave velocity change rate and the vertical wave velocity change rate components are extracted; through frequency domain analysis, the abnormal frequency components in the wave velocity change rate are identified to reflect the dynamic changes of the internal structure of the geological body; It should be noted that the ultrasonic detector collects dynamic change data of the internal structure of the geological body in real time, and performs frequency domain conversion through wave velocity change rate analysis and Fourier transform, so as to realize real-time monitoring and evaluation of the dynamic changes of the geological body. It identifies abnormal frequency components through frequency domain analysis, can quickly feedback the dynamic changes of the internal structure of the geological body, can locate dynamic change points such as crack expansion and landslide precursors inside the geological body, and provide specific risk area information.

[0025] In this embodiment, preferably, the abnormal frequency components include abnormal change points between the transverse wave velocity change rate and the vertical wave velocity change rate, between the transverse wave velocity change rates, or between the vertical wave velocity change rates; The abnormal point between the transverse wave velocity change rate and the vertical wave velocity change rate is the collision point of the transverse wave velocity change rate and the vertical wave velocity change rate, that is, the intersection point between the vertical crack and the transverse crack; The abnormal point between the transverse wave velocity change rates is the collision point between the transverse wave velocity change rates and the transverse wave velocity change rates, that is, the intersection point between the transverse cracks; The abnormal point of change between the vertical wave velocity change rates is the collision point between the vertical wave velocity change rates and the vertical wave velocity change rates, that is, the intersection point between the vertical cracks; It should be noted that the abnormal change points between the transverse wave velocity change rate and the vertical wave velocity change rate (crack intersection points) are key dangerous areas inside the geological body and are often the precursors of collapse or landslides; the abnormal change points between the transverse wave velocity change rates reflect the expansion and intersection of transverse cracks, which may affect the stability of the geological body; the abnormal change points between the vertical wave velocity change rates reflect the distribution and changes of vertical cracks, which may cause local collapse or fracture of the geological body; Through the spatial distribution analysis of abnormal frequency components, the dynamic changes of the internal structure of the geological body can be comprehensively understood, including the starting position, development speed and expansion direction of the changes. Through the comparative analysis of the frequency domain characteristics of different time periods, the trend and rule of the dynamic changes of the internal structure of the geological body can be identified, supporting long-term monitoring and prediction. The existence of abnormal frequency components indicates that there are dynamic changes in the internal structure of the geological body, which may pose a threat to the safety of the mining area. Combined with the number, position and weighted coefficient of the water content data of the abnormal frequency components, the stability of the geological body and the potential risk level can be objectively evaluated, providing data support for the prediction and disaster prevention and reduction of geological disasters.

[0026] In this embodiment, preferably, the machine learning model combines a clustering method to identify the calculation formula of the aggregation density parameter of the change abnormal point as follows: The abnormal point density parameter is calculated by the following formula: ; Wherein, represents the abnormal point density parameter, represents the number of abnormal points, represents the area size of the detected region; Clustering analysis of abnormal point density: ; Wherein, represents the abnormal point group with abnormal point density higher than the threshold value, represents the abnormal point group with abnormal point density lower than the threshold value; the set threshold value is 0.6, and and the output value of is between (0, 1); It should be noted that through the machine learning model combined with the clustering method, the density parameter of the change abnormal point can be accurately identified, ensuring the accuracy and reliability of the calculation results. The clustering method can stably divide the abnormal point group with abnormal point density higher than the threshold value and the abnormal point group with abnormal point density lower than the threshold value, avoiding randomness and subjectivity, and ensuring the reliability of the analysis results. The formula can analyze the spatial distribution of abnormal points, locate potential dangerous areas such as crack expansion and landslides in the internal structure of the geological body, and provide comprehensive geological disaster risk assessment. Through the analysis of the change trend of abnormal point density in different time periods, long-term monitoring and prediction can be supported, and multi-dimensional evaluation of dynamic change data can be provided. Moreover, the calculated data is convenient for subsequent analysis and calculation processing.

[0027] In this embodiment, preferably, the prediction of geological disasters is predicted and calculated by combining the aggregation density parameter and the water content data, and the formula for prediction and calculation is as follows: ; Wherein, water content inside the geological body, a weighted coefficient of water content to geological body stability, usually 0.5, an abnormal point density, an influence coefficient of abnormal points to collapse risk, usually 2.3, in the form of ensures that the output value range is within (0, 1), a collapse risk score; low risk, that is, tending to 0 indicates that the water content is low and the abnormal point density is sparse, and the geological body is stable; the warning level is slight warning; high risk, that is, tending to 1 indicates that the water content is high and the abnormal point density is dense, and the geological body is prone to collapse; the warning level is major warning; medium risk, that is, tending to 0.5 indicates that the water content is medium and the abnormal point density is medium, and the geological body is relatively stable and not prone to collapse; the warning level is moderate warning; It is to be noted that the collapse risk score is quickly calculated by the prediction model According to the warning level, the monitoring terminal can quickly trigger an alarm to ensure that disaster prevention and mitigation measures can be taken in time to avoid the occurrence or expansion of geological disasters; by analyzing the comprehensive influence of water content and abnormal point density, the stability of the geological body can be comprehensively evaluated, and potential collapse risks can be identified; by comparing and analyzing data of different time periods, the system can identify the dynamic change trend of the internal structure of the geological body, supporting long-term geological disaster monitoring and prediction.

[0028] Referring to Figure 2 A geological disaster warning and monitoring method, comprising the following steps: S1, data acquisition: the acquisition module periodically acquires the water content inside the geological body of the mining area mountain through an infrared sensor, and monitors the dynamic change data of the internal structure of the geological body through an ultrasonic detector; S2, data preprocessing: the collected dynamic change data and water content data are preprocessed, including cleaning, denoising, filtering and normalization processing; S3, data transmission: the processed dynamic change data and water content data are uploaded to an edge cloud calculator through a communication module; S4, data analysis and processing: the analysis module analyzes and processes the dynamic change data and water content data, and identifies the aggregation density parameters of the change abnormal points in the dynamic change data; and in combination with the water content data inside the geological body, the geological disaster is predicted to obtain a geological disaster prediction report; S5, outputting a prediction report: the edge cloud computer transmits the geological disaster prediction report to the monitoring terminal through the communication module, and the monitoring terminal alarms through the alarm module.

[0029] It should be noted that by combining dynamic change data, moisture data and abnormal point density parameters, the system can comprehensively evaluate the risk of geological disasters from multiple dimensions, and objectively reflect the actual state of the internal geological body; the system can continuously monitor the stability change of the geological body according to the real-time update of the dynamic change data, and provide timely risk prediction; according to the output risk score (0, 1), the system can clearly divide the low risk, medium risk and high risk levels, and provide a scientific basis for the early warning of geological disasters; through the output risk level (mild, moderate, major), the monitoring terminal can clearly take corresponding disaster prevention and mitigation measures, including strengthening the support of the monitoring area and limiting personnel from entering the dangerous area.

[0030] It should be noted that all the calculation formulas in the present application file use regression analysis in machine learning algorithms, including but not limited to machine learning algorithms, to deeply analyze the collected relevant parameters and identify their natural trends and mutual relationships. Professional software such as Python's Scikit-learn library or R language is used to automatically generate mathematical models that match the data. Then, the model performance is objectively evaluated through cross-validation and other methods, and combined with continuous feedback and optimization to ensure that the created formula truly reflects the inherent law of the data, thereby ensuring its effectiveness and accuracy. In all the calculation formulas in the present application, the parameters in each formula are processed by consistent range of dimensionless to ensure that different physical quantities are compared on the same scale; the dimensionless technique includes but is not limited to Min-Max Normalization, Z-Score standardization; The technical solutions of the present application can be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), FLASH, hard disk or optical disk, etc., including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the method of each embodiment of the present application.

[0031] The logic and / or steps represented in the flow diagrams and / or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0032] It should be noted that the above-mentioned embodiments are only used to illustrate but not to limit the technical solutions of the present application, and although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

[0033] It should be noted that the above-mentioned embodiments are only used to illustrate but not to limit the technical solutions of the present application, and although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A geological disaster early warning monitoring system, characterized in that: It includes acquisition module, pre-processing module and analysis module; The acquisition module is used to collect data from the mining area mountain through a variety of sensors, and the collected data includes dynamic change data of the internal structure of the geological body and moisture data inside the geological body; The preprocessing module is used to preprocess the dynamic change data and moisture data collected by the collection module; The analysis module is used to analyze and process the processed dynamic change data and moisture data, extract the wave velocity change rate from the dynamic change data and moisture data, perform frequency domain conversion on the wave velocity change rate, extract the transverse wave velocity change rate and the vertical wave velocity change rate from the wave velocity change rate, then perform position topology analysis on the transverse wave velocity change rate and the vertical wave velocity change rate, extract abnormal change points between the transverse wave velocity change rate and the vertical wave velocity change rate, between the transverse wave velocity change rate or between the vertical wave velocity change rate from the position topology, then identify the aggregation density parameters of the abnormal change points through a machine learning model combined with a clustering method; and predict geological disasters in combination with the moisture data inside the geological body to obtain a geological disaster prediction report.

2. A geological disaster early warning monitoring system according to claim 1, characterized in that: After preprocessing the dynamic change data and moisture data, the preprocessing module uploads the processed dynamic change data and moisture data. The preprocessing module is electrically connected to a communication module, and the communication module is used to upload the processed dynamic change data and moisture data to the edge cloud computing server. The analysis module analyzes and processes the processed dynamic change data and moisture data through the edge cloud computing server.

3. A geological disaster early warning monitoring system according to claim 2, characterized in that: After the analysis module obtains the geological disaster prediction report through calculation and analysis, the edge cloud computing machine transmits the geological disaster prediction report to the monitoring terminal through the communication module, and the geological disaster prediction report includes a text report and an image report.

4. A geological disaster early warning monitoring system according to claim 3, characterized in that: The monitoring terminal includes an alarm module, which issues an alarm based on the prediction classification in the geological disaster prediction report; The levels of geological disaster prediction reports are as follows: Mild warning: The color code is green, and the sound intensity is low frequency and low loudness; Moderate warning: The color code is yellow, the sound intensity is medium frequency and moderate loudness; Major warning: The color code is red, and the sound intensity is high frequency and strong loudness.

5. A geological disaster early warning monitoring system according to claim 4, characterized in that: The dynamic change data uses an ultrasonic detector to collect dynamic change data of the internal structure of the geological body in real time, and extracts the wave velocity change rate in the dynamic change data. The wave velocity change rate is the rate of change of the wave velocity over time, which is used to detect the structure inside the geological body; the wave velocity change rate signal is converted into the frequency domain through Fourier transform, and the change characteristics of the transverse wave velocity change rate and the vertical wave velocity change rate components are extracted. Through frequency domain analysis, the abnormal frequency components in the wave velocity change rate are identified to reflect the dynamic changes of the internal structure of the geological body.

6. A geological disaster early warning monitoring system according to claim 5, characterized in that: The abnormal frequency components include abnormal change points between the transverse wave velocity change rate and the vertical wave velocity change rate, between the transverse wave velocity change rates, or between the vertical wave velocity change rates; The abnormal point between the transverse wave velocity change rate and the vertical wave velocity change rate is the collision point of the transverse wave velocity change rate and the vertical wave velocity change rate, that is, the intersection point between the vertical crack and the transverse crack; The abnormal point between the transverse wave velocity change rates is the collision point between the transverse wave velocity change rates and the transverse wave velocity change rates, that is, the intersection point between the transverse cracks; The abnormal point of change between the vertical wave velocity change rates is the collision point between the vertical wave velocity change rates and the vertical wave velocity change rates, that is, the intersection point between the vertical cracks and the vertical cracks.

7. A geological disaster early warning and monitoring system according to claim 6, characterized in that: The predicted geological disaster is calculated by combining the aggregation density parameter and the moisture data; Low risk, that is Approaching 0 indicates low moisture content and sparse density of anomalies, indicating high stability of the geological body; The warning level is mild warning; High risk, i.e. A value close to 1 indicates high moisture content and dense anomaly density, indicating that the geological body is prone to collapse; the warning level is a major warning; Medium risk, i.e. A value close to 0.5 indicates that the moisture content is medium and the density of abnormal points is medium, the geological body is relatively stable and not prone to collapse; the warning level is moderate warning.

8. A geological disaster early warning monitoring method, characterized by: The method is used to implement the system according to any one of claims 1 to 7, comprising the following steps: S1. Data collection: The collection module uses infrared sensors to regularly collect the moisture content inside the geological body of the mining area, and uses ultrasonic detectors to monitor the dynamic changes in the internal structure of the geological body; S2. Data preprocessing: preprocess the collected dynamic change data and moisture data, including cleaning, denoising, filtering and normalization; S3, data transmission: upload the processed dynamic change data and moisture data to the edge cloud computing server through the communication module; S4. Data analysis and processing: The analysis module analyzes and processes the dynamic change data and moisture data, and identifies the cluster density parameters of abnormal change points in the dynamic change data; and predicts geological disasters in combination with the moisture data within the geological body to obtain a geological disaster prediction report; S5. Output prediction report: The edge cloud computing machine transmits the geological disaster prediction report to the monitoring terminal through the communication module, and the monitoring terminal issues an alarm through the warning module.

Images