An IoT-based method and system for monitoring geological disasters using edge computing

Abstract

This invention discloses an IoT-based geological disaster monitoring method and system based on edge computing. The method involves radiating an electromagnetic field to a target monitoring area using a signal generator, and collecting electromagnetic response signals from the target monitoring area under the electromagnetic field radiation using a signal acquisition device. An edge computing device uses these electromagnetic response signals to preliminarily assess the current geological disaster risk in the target monitoring area. When the current geological disaster risk meets preset risk conditions, all monitoring devices are activated, and the signal generator and signal acquisition device are shut down. The edge computing device then assesses the current geological disaster level based on the monitoring data collected by all monitoring devices. When the current geological disaster level meets alarm conditions, the current geological disaster level is sent to the cloud platform and user terminals. In this way, each monitoring device remains in a dormant state most of the time, reducing power consumption and thus lowering the cost of geological disaster monitoring.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to an IoT-based geological disaster monitoring method and system based on edge computing. Background Technology

[0002] Geological hazards include landslides, mudslides, debris flows, ground subsidence, ground fissures, and ground settlement—all geological disasters that endanger people's lives and property, caused by natural factors or human activities. Currently, real-time geological hazard monitoring is generally conducted using various types of monitoring equipment (such as fissure gauges and rain gauges). All monitoring equipment is constantly operational, resulting in high power consumption and consequently high costs for geological hazard monitoring.

[0003] For example, Chinese Patent Publication No. CN115035690A discloses a method for monitoring and early warning of geological disasters. This method involves installing automated monitoring equipment on the landslide body and enabling bidirectional data transmission and control with a remote monitoring and control system via wired or wireless transmission devices. The monitoring system uniquely encodes landslide hazard points and automated monitoring equipment. The landslide body is divided into zones according to hazard levels, and different colors are used to mark these zones on the site and on the landslide plan within the monitoring system. Alarms are installed on all automated monitoring equipment, and an early warning threshold is set for each monitoring device in the monitoring system. When the monitored value exceeds the threshold, the alarm on that device is activated, and the alarm displays the color corresponding to the hazard level. This type of existing technology uses real-time data acquisition and analysis from the monitoring instruments, requiring all monitoring equipment to be operational, resulting in high energy consumption, high system computational pressure, and high monitoring costs. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide an IoT-based method and system for monitoring geological disasters based on edge computing. This avoids the problem of high costs in existing geological disaster monitoring technologies.

[0005] To address the aforementioned technical problems, this invention provides an IoT-based geological disaster monitoring method based on edge computing, comprising the following steps: S1: Activate the signal generating device to radiate an electromagnetic field toward the target monitoring area; S2: Activate the signal acquisition device to acquire the electromagnetic response signal of the target monitoring area under the electromagnetic field radiation, and send the electromagnetic response signal to the edge computing device; S3: The edge computing device makes a preliminary assessment of the current geological disaster risk in the target monitoring area based on the electromagnetic response signal; S4: When the current geological disaster risk situation meets the preset risk conditions, the edge computing device wakes up all monitoring devices used to monitor the target monitoring area, and controls the signal generating device and the signal acquisition device to shut down; S5: The edge computing device receives monitoring data collected by all the monitoring devices and assesses the current geological hazard level based on the monitoring data; Step S6: When the current geological disaster level meets the alarm conditions, the edge computing device sends the current geological disaster level to the cloud platform and the user terminal.

[0006] The monitoring equipment includes at least one of the following: displacement sensor, soil pressure sensor, pore water pressure gauge, rain gauge, inclinometer, crack gauge, mud level sensor, soil temperature and humidity sensor, ground acoustic sensor, secondary sensor, vibration sensor, and monitoring camera.

[0007] Specifically, S3 includes the following steps: The edge computing device acquires various historical electromagnetic response signals collected within a preset time range prior to the current moment, and obtains a comparison set containing multiple historical electromagnetic response signals. The edge computing device compares the electromagnetic response signal with each historical electromagnetic response signal in the comparison set; When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is greater than a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be high risk. When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is less than or equal to a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be low risk.

[0008] The preset risk condition in S4 is to preliminarily determine that the current geological disaster risk situation in the target monitoring area is high risk.

[0009] Specifically, S5 includes the following steps: The edge computing device receives monitoring data collected by all the monitoring devices; The edge computing device inputs the monitoring data into a pre-trained geological hazard assessment model to obtain the current geological hazard level.

[0010] S6 further includes the following steps: The cloud platform divides the area that is within a preset distance from the target monitoring area into risk areas; The cloud platform sends a wake-up command to the edge computing device corresponding to the risk area, so that the edge computing device wakes up all monitoring devices in the risk area according to the wake-up command.

[0011] Accordingly, this invention also provides an IoT-based geological disaster monitoring system based on edge computing, including a signal generating device, a signal acquiring device, an edge computing device, a monitoring device, a cloud platform, and a user terminal; The signal generating device is used to radiate an electromagnetic field to the target monitoring area; The signal acquisition device is used to acquire the electromagnetic response signal of the target monitoring area under electromagnetic field radiation, and send the electromagnetic response signal to the edge computing device; The edge computing device is used for: Based on the electromagnetic response signal, a preliminary assessment of the current geological hazard risk in the target monitoring area is conducted. When the current geological disaster risk situation meets the preset risk conditions, all monitoring devices used to monitor the target monitoring area are activated, and the signal generating device and the signal acquisition device are shut down. Receive monitoring data collected by all the monitoring devices, and assess the current geological hazard level based on the monitoring data; When the current geological hazard level meets the alarm conditions, the current geological hazard level is sent to the cloud platform and user terminal.

[0012] As a preferred embodiment, the edge computing device, based on the electromagnetic response signal, preliminarily assesses the current geological hazard risk of the target monitoring area, specifically including: The edge computing device acquires various historical electromagnetic response signals collected within a preset time range prior to the current moment, and obtains a comparison set containing multiple historical electromagnetic response signals. The edge computing device compares the electromagnetic response signal with each historical electromagnetic response signal in the comparison set; When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is greater than a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be high risk. When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is less than or equal to a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be low risk.

[0013] As a preferred option, the preset risk condition is that the current geological disaster risk situation in the target monitoring area is initially determined to be high risk.

[0014] As a preferred embodiment, the monitoring equipment includes at least one of the following: displacement sensor, soil pressure sensor, pore water pressure gauge, rain gauge, inclinometer, crack gauge, mud level sensor, soil temperature and humidity sensor, ground acoustic sensor, secondary sensor, vibration sensor, and monitoring camera.

[0015] Implementing the embodiments of the present invention has the following beneficial effects: The embodiments of the present invention provide an IoT-based geological disaster monitoring method and system based on edge computing. The method radiates an electromagnetic field to a target monitoring area via a signal generating device. A signal acquisition device collects the electromagnetic response signal of the target monitoring area under the electromagnetic field radiation and sends the electromagnetic response signal to an edge computing device. Based on the electromagnetic response signal, the edge computing device preliminarily assesses the current geological disaster risk status of the target monitoring area. When the current geological disaster risk status meets preset risk conditions, the edge computing device wakes up all monitoring devices used to monitor the target monitoring area and controls the signal generating device and the signal acquisition device to shut down. The edge computing device receives monitoring data collected by all monitoring devices and assesses the current geological disaster level based on the monitoring data. When the current geological disaster level meets alarm conditions, the edge computing device sends the current geological disaster level to the cloud platform and user terminal. Thus, when the edge computing device detects that the current geological disaster risk status meets preset risk conditions through the signal generating device and the signal acquisition device, it only wakes up all monitoring devices, allowing each monitoring device to remain in a dormant state most of the time, greatly reducing power consumption and thus reducing the cost of geological disaster monitoring. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the IoT-based geological disaster monitoring method based on edge computing in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 As shown, it is a flowchart illustrating the IoT-based geological disaster monitoring method based on edge computing in an embodiment of the present invention.

[0019] The IoT-based geological disaster monitoring method based on edge computing according to embodiments of the present invention includes: Step S11: Start the signal generating device so that the signal generating device radiates an electromagnetic field toward the target monitoring area; Step S12: Start the signal acquisition device so that the signal acquisition device can acquire the electromagnetic response signal of the target monitoring area under electromagnetic field radiation and send the electromagnetic response signal to the edge computing device; In specific implementation, the target monitoring area refers to the area where it is necessary to monitor whether a geological disaster has occurred. The signal generating device may include one or more electromagnetic field excitation sources, which are arranged in the target monitoring area. The signal acquisition device may be, for example, an electrical resistivity meter, which monitors the electromagnetic field through measuring sensors such as induction coils arranged in the target monitoring area. For example, when different geological disasters occur in the target monitoring area, such as landslides, the slope structure changes, and therefore the electromagnetic field characteristics such as magnetic flux density measured by the signal acquisition device also change with the slope structure. That is, the signal acquisition device collects the electromagnetic response signal of the target monitoring area under electromagnetic field radiation.

[0020] Step S13: The edge computing device performs a preliminary assessment of the current geological hazard risk in the target monitoring area based on the electromagnetic response signal; Step S14: When the current geological disaster risk situation meets the preset risk conditions, the edge computing device wakes up all monitoring devices used to monitor the target monitoring area and controls the signal generating device and the signal acquisition device to shut down. Step S15: The edge computing device receives monitoring data collected by all the monitoring devices and assesses the current geological hazard level based on the monitoring data; Step S16: When the current geological disaster level meets the alarm conditions, the edge computing device sends the current geological disaster level to the cloud platform and the user terminal.

[0021] In this embodiment of the invention, all monitoring devices are only activated when the edge computing device detects that the current geological disaster risk situation meets preset risk conditions through the signal generating and signal acquiring devices. This allows each monitoring device to remain in a dormant state most of the time, significantly reducing power consumption and thus lowering the cost of geological disaster monitoring. Furthermore, when the current geological disaster risk situation meets the preset risk conditions, the edge computing device activates all monitoring devices used to monitor the target monitoring area and controls the signal generating and signal acquiring devices to shut down. This avoids interference from the signal generating and signal acquiring devices to other monitoring devices and reduces their power consumption. Moreover, by first conducting a preliminary assessment of the geological disaster risk situation and then accurately assessing the geological disaster level, the accuracy of geological disaster monitoring can be improved, and the computing load on the edge computing device can be reduced.

[0022] In this embodiment of the invention, the monitoring equipment includes at least one of the following: a displacement sensor, an earth pressure sensor, a pore water pressure gauge, a rain gauge, an inclinometer, a crack gauge, a mud level sensor, a soil temperature and humidity sensor, a ground acoustic sensor, a secondary sensor, a vibration sensor, and a monitoring camera. Of course, other types of equipment can also be selected according to actual usage requirements, which will not be elaborated further here. In practical applications, different types of monitoring equipment are usually required, and multiple devices of the same type are generally needed. Therefore, the power consumption of all monitoring equipment is relatively high. However, this embodiment of the invention allows the monitoring equipment to remain in a dormant state most of the time, only waking up all monitoring equipment for further monitoring when the current geological disaster risk is initially determined to be high, thereby effectively reducing the power consumption of each monitoring device.

[0023] In an optional implementation, step S13, "the edge computing device preliminarily assesses the current geological hazard risk of the target monitoring area based on the electromagnetic response signal," specifically includes: The edge computing device acquires various historical electromagnetic response signals collected within a preset time range prior to the current moment, and obtains a comparison set containing multiple historical electromagnetic response signals. The edge computing device compares the electromagnetic response signal with each historical electromagnetic response signal in the comparison set; When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is greater than a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be high risk. When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is less than or equal to a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be low risk.

[0024] It should be noted that, under normal circumstances, if no geological disaster occurs, the geological conditions will not change significantly. Therefore, in this embodiment, the currently acquired electromagnetic response signal is compared with several historical electromagnetic response signals. If the deviation between the currently acquired electromagnetic response signal and each historical electromagnetic response signal in the comparison set is greater than a preset deviation range, the current geological disaster risk of the target monitoring area can be preliminarily determined to be high risk. If the deviation between the currently acquired electromagnetic response signal and each historical electromagnetic response signal in the comparison set is less than or equal to a preset deviation range, the current geological disaster risk of the target monitoring area can be preliminarily determined to be low risk.

[0025] For example, in this embodiment of the invention, the preset risk condition in step S14 is to preliminarily determine that the current geological disaster risk situation of the target monitoring area is high risk.

[0026] In an optional implementation, step S15, "the edge computing device receives monitoring data collected by all the monitoring devices and assesses the current geological hazard level based on the monitoring data," specifically includes: The edge computing device receives monitoring data collected by all the monitoring devices; The edge computing device inputs the monitoring data into a pre-trained geological hazard assessment model to obtain the current geological hazard level.

[0027] In a specific embodiment, by pre-training the geological hazard assessment model, the monitoring data collected by the monitoring equipment is input into the geological hazard assessment model during actual application, thereby outputting the current geological hazard level.

[0028] For example, when training a geological hazard assessment model, historical monitoring data and corresponding historical geological hazard level data are first acquired. The historical monitoring data can be collected, for example, by monitoring equipment located in the target monitoring area. Then, the historical monitoring data and historical geological hazard level data are normalized. The normalized historical monitoring data and historical geological hazard level data are then divided into training datasets and test datasets. The geological hazard assessment model is trained using the data in the training dataset, and the network parameters of the geological hazard assessment model are optimized using the F1 evaluation model. The model parameters are then optimized in reverse. Finally, the geological hazard assessment model is tested using the data in the test dataset until the analysis accuracy of the geological hazard assessment model reaches a threshold, and the trained geological hazard assessment model is output. Specifically, the geological hazard assessment model is a neural network analysis model, which has an input layer, three convolutional layers, two depthwise separable convolutional layers, and an output layer. The training process includes: initializing the network parameters and loss function of the neural network analysis model, inputting the data in the training dataset into the neural network analysis model, calculating the actual output, the loss function of each layer, and the F1 evaluation model, minimizing the loss function in a stochastic gradient decreasing manner, and then using the minimized loss function to back-calculate the network parameters of the analysis model, updating the model parameters until the F1 evaluation model result is ideal.

[0029] In an optional implementation, after step S16 "when the current geological hazard level meets the alarm conditions, the edge computing device sends the current geological hazard level to the cloud platform and the user terminal", the method further includes: The cloud platform will divide the area that is within a preset distance from the target monitoring area into risk areas; The cloud platform sends a wake-up command to the edge computing device corresponding to the risk area, so that the edge computing device wakes up all monitoring devices in the risk area according to the wake-up command.

[0030] In practical implementation, if a geological disaster occurs in a certain area, then areas nearby also face a significant risk of geological disasters. To avoid the problem of inaccurate geological disaster risk assessment due to malfunctions in signal generating or acquiring devices in other areas, when a geological disaster is detected in a certain area, a risk zone can be defined centered on that area and extending within a preset range. All monitoring devices within this risk zone are then activated. For example, the cloud platform communicates with the edge computing devices in each area, and each edge computing device communicates with all monitoring devices within that area. When an edge computing device receives a wake-up command from the cloud platform, it controls all monitoring devices within the risk zone to activate, thus activating all monitoring devices within that area.

[0031] Accordingly, this invention also provides an IoT-based geological disaster monitoring system based on edge computing, including a signal generating device, a signal acquiring device, an edge computing device, a monitoring device, a cloud platform, and a user terminal; The signal generating device is used to radiate an electromagnetic field to the target monitoring area; The signal acquisition device is used to acquire the electromagnetic response signal of the target monitoring area under electromagnetic field radiation, and send the electromagnetic response signal to the edge computing device; The edge computing device is used for: Based on the electromagnetic response signal, a preliminary assessment of the current geological hazard risk in the target monitoring area is conducted. When the current geological disaster risk situation meets the preset risk conditions, all monitoring devices used to monitor the target monitoring area are activated, and the signal generating device and the signal acquisition device are shut down. Receive monitoring data collected by all the monitoring devices, and assess the current geological hazard level based on the monitoring data; When the current geological hazard level meets the alarm conditions, the current geological hazard level is sent to the cloud platform and user terminal.

[0032] In an optional implementation, the edge computing device, based on the electromagnetic response signal, makes a preliminary assessment of the current geological hazard risk in the target monitoring area, specifically including: The edge computing device acquires various historical electromagnetic response signals collected within a preset time range prior to the current moment, and obtains a comparison set containing multiple historical electromagnetic response signals. The edge computing device compares the electromagnetic response signal with each historical electromagnetic response signal in the comparison set; When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is greater than a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be high risk. When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is less than or equal to a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be low risk.

[0033] In one optional implementation, the preset risk condition is to initially determine that the current geological disaster risk situation in the target monitoring area is high risk.

[0034] In one optional implementation, the monitoring device includes at least one of the following: displacement sensor, soil pressure sensor, pore water pressure gauge, rain gauge, inclinometer, crack gauge, mud level sensor, soil temperature and humidity sensor, ground acoustic sensor, secondary sensor, vibration sensor, and monitoring camera.

[0035] In an optional implementation, the edge computing device receives monitoring data collected by all the monitoring devices and, based on the monitoring data, assesses the current geological hazard level, specifically including: The edge computing device receives monitoring data collected by all the monitoring devices; The edge computing device inputs the monitoring data into a pre-trained geological hazard assessment model to obtain the current geological hazard level.

[0036] In an optional implementation, after the edge computing device sends the current geological hazard level to the cloud platform and user terminal when the current geological hazard level meets the alarm conditions, the method further includes: The cloud platform will divide the area that is within a preset distance from the target monitoring area into risk areas; The cloud platform sends a wake-up command to the edge computing device corresponding to the risk area, so that the edge computing device wakes up all monitoring devices in the risk area according to the wake-up command.

[0037] It should be noted that the IoT geological disaster monitoring system based on edge computing provided in this embodiment corresponds to the IoT geological disaster monitoring method based on edge computing in the above embodiment. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0038] Compared to existing technologies, the beneficial effects of this invention are as follows: This invention provides an IoT-based geological disaster monitoring method and system based on edge computing. The method involves radiating an electromagnetic field to a target monitoring area via a signal generating device. A signal acquisition device collects the electromagnetic response signal of the target monitoring area under the electromagnetic field radiation and sends the signal to an edge computing device. Based on the electromagnetic response signal, the edge computing device preliminarily assesses the current geological disaster risk of the target monitoring area. When the current geological disaster risk meets preset risk conditions, the edge computing device activates all devices used to monitor the target area. The edge computing device receives monitoring data collected by all monitoring devices in the target area and, based on this data, assesses the current geological hazard level. When the current geological hazard level meets alarm conditions, the edge computing device sends the current geological hazard level to the cloud platform and user terminal. Thus, the edge computing device only wakes up all monitoring devices when it detects that the current geological hazard risk meets preset risk conditions through the signal generator and signal acquisition device. This allows each monitoring device to remain in a dormant state most of the time, significantly reducing power consumption and thus lowering the cost of geological hazard monitoring. Furthermore, when the current geological hazard risk meets preset risk conditions, the edge computing device wakes up all monitoring devices used to monitor the target area and controls the signal generator and signal acquisition device to shut down. This avoids interference from the signal generator and signal acquisition device to other monitoring devices and reduces their power consumption. In addition, by first conducting a preliminary assessment of the geological hazard risk and then accurately assessing the geological hazard level, the accuracy of geological hazard monitoring can be improved, and the computing load on the edge computing device can be reduced.

[0039] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring geological disasters using the Internet of Things (IoT) based on edge computing, characterized in that, Includes the following steps: S1: Activate the signal generating device to radiate an electromagnetic field toward the target monitoring area; S2: Activate the signal acquisition device to acquire the electromagnetic response signal of the target monitoring area under the electromagnetic field radiation, and send the electromagnetic response signal to the edge computing device; S3: The edge computing device, based on the electromagnetic response signal, makes a preliminary assessment of the current geological hazard risk in the target monitoring area, including the following steps: The edge computing device acquires various historical electromagnetic response signals collected within a preset time range prior to the current moment, and obtains a comparison set containing multiple historical electromagnetic response signals. The edge computing device compares the electromagnetic response signal with each historical electromagnetic response signal in the comparison set; When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is greater than a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be high risk. When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is less than or equal to a preset deviation range, the current geological disaster risk status of the target monitoring area is preliminarily determined to be low risk. S4: When the current geological disaster risk situation meets the preset risk conditions, the edge computing device wakes up all monitoring devices used to monitor the target monitoring area and controls the signal generating device and the signal acquisition device to shut down; the preset risk conditions are that the current geological disaster risk situation of the target monitoring area is initially determined to be high risk. S5: The edge computing device receives monitoring data collected by all the monitoring devices and assesses the current geological hazard level based on the monitoring data; Step S6: When the current geological disaster level meets the alarm conditions, the edge computing device sends the current geological disaster level to the cloud platform and the user terminal.

2. The IoT-based geological disaster monitoring method based on edge computing according to claim 1, characterized in that, The monitoring equipment includes at least one of the following: displacement sensor, soil pressure sensor, pore water pressure gauge, rain gauge, inclinometer, crack gauge, mud level sensor, soil temperature and humidity sensor, ground acoustic sensor, secondary sensor, vibration sensor, and monitoring camera.

3. The IoT-based geological disaster monitoring method based on edge computing according to claim 1, characterized in that, S5 specifically includes the following steps: The edge computing device receives monitoring data collected by all the monitoring devices; The edge computing device inputs the monitoring data into a pre-trained geological hazard assessment model to obtain the current geological hazard level.

4. The IoT-based geological disaster monitoring method based on edge computing according to claim 3, characterized in that, S6 further includes the following steps: The cloud platform divides the area that is within a preset distance from the target monitoring area into risk areas; The cloud platform sends a wake-up command to the edge computing device corresponding to the risk area, so that the edge computing device wakes up all monitoring devices in the risk area according to the wake-up command.

5. An IoT-based geological disaster monitoring system based on edge computing, characterized in that, This includes signal generating devices, signal acquisition devices, edge computing devices, monitoring devices, cloud platforms, and user terminals; The signal generating device is used to radiate an electromagnetic field to the target monitoring area; The signal acquisition device is used to acquire the electromagnetic response signal of the target monitoring area under electromagnetic field radiation, and send the electromagnetic response signal to the edge computing device; The edge computing device is used for: Based on the electromagnetic response signal, the current geological disaster risk of the target monitoring area is preliminarily assessed. The edge computing device acquires various historical electromagnetic response signals collected within a preset time range prior to the current moment, and obtains a comparison set containing multiple historical electromagnetic response signals. The edge computing device compares the electromagnetic response signal with each historical electromagnetic response signal in the comparison set; When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is greater than a preset deviation range, the current geological disaster risk of the target monitoring area is preliminarily determined to be high risk. When the deviation between the electromagnetic response signal and each historical electromagnetic response signal in the comparison set is less than or equal to a preset deviation range, the current geological disaster risk status of the target monitoring area is preliminarily determined to be low risk. When the current geological hazard risk situation meets the preset risk conditions, all monitoring equipment used to monitor the target monitoring area is activated, and the signal generating device and the signal acquisition device are shut down; the preset risk conditions are that the current geological hazard risk situation of the target monitoring area is initially determined to be high risk. Receive monitoring data collected by all the monitoring devices, and assess the current geological hazard level based on the monitoring data; When the current geological hazard level meets the alarm conditions, the current geological hazard level is sent to the cloud platform and user terminal.

6. The IoT geological disaster monitoring system based on edge computing according to claim 5, characterized in that, The preset risk condition is that the current geological disaster risk situation in the target monitoring area is initially determined to be high risk.

7. The IoT geological disaster monitoring system based on edge computing according to claim 6, characterized in that, The monitoring equipment includes at least one of the following: displacement sensor, soil pressure sensor, pore water pressure gauge, rain gauge, inclinometer, crack gauge, mud level sensor, soil temperature and humidity sensor, ground acoustic sensor, secondary sensor, vibration sensor, and monitoring camera.

Images