Geological disaster early warning method and system based on edge computing Internet of Things gateway equipment

Abstract

The invention provides a geological disaster early warning method and system based on edge computing Internet of Things gateway equipment, and relates to the technical field of geological disaster monitoring, and the method specifically comprises the steps: firstly, deploying a plurality of geological and meteorological sensors in an easy-to-occur area, and collecting related data in real time; secondly, processing the collected data by utilizing edge computing equipment, calculating historical and current geological parameter change rates and a change quantity of meteorological data, and determining a geological risk index based on historical statistical analysis; thirdly, constructing a deep learning model, taking the historical geological parameters as a training set, and obtaining a current risk index; then, generating an environmental influence index and carrying out correlation analysis to obtain a comprehensive risk index; and finally, comparing the comprehensive risk index with a preset threshold value, predicting the geological disaster risk level of the Three Gorges Reservoir Region, and sending out a corresponding early warning signal. According to the invention, the accuracy of early warning of geological disasters is improved, the early warning result can be obtained more quickly, and the early warning information can be issued in time.

Description

Technical Field

[0001] The present invention relates to the field of geological disaster monitoring technology, and specifically to a geological disaster early warning method and system based on edge computing Internet of Things gateway devices. Background Art

[0002] At present, the utilization rate of big data for geological disaster monitoring in the Three Gorges Reservoir area is low, there is a lack of reliable and effective intelligent early warning and forecasting models, and the monitoring and early warning equipment and work processes are not standardized enough.

[0003] In the prior art, the publication number CN117809433A discloses a method and system for processing IoT gateway equipment that supports precise fusion early warning, which includes: obtaining disaster monitoring data through a gateway connected to a monitoring sensor device; receiving disaster monitoring data, and preprocessing the disaster monitoring data through a gateway using a preset preprocessing algorithm; based on the disaster monitoring data, establishing the judgment expression of each type of monitoring sensor, the combination of multi-parameter judgment expressions, and macro-phenomenon conditions; setting the triggering conditions of the early warning model; based on the triggering conditions of the early warning model, obtaining the calculation and judgment results of the early warning model, and issuing early warning information. This method can solve the technical problem in the prior art that the accuracy of IoT gateway early warning is low due to the low efficiency of edge computing and the linkage efficiency of monitoring data, and achieve the goal of improving the efficiency of edge computing and the linkage efficiency of monitoring data, and achieve the technical effect of improving the accuracy of IoT gateway early warning.

[0004] However, there are still the following shortcomings: From the above statements, it can be seen that in the existing technology, due to the limited edge computing capabilities, the processing speed of IoT gateway devices is slow, resulting in a low response speed of the early warning results; in addition, the monitoring data lacks linkage, resulting in insufficient correlation analysis between various types of monitoring data, thereby affecting the accuracy of the early warning.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a geological disaster early warning method and system based on edge computing Internet of Things gateway devices to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A geological disaster early warning method based on edge computing Internet of Things gateway devices, the specific steps include:

[0009] S1. Deploy multiple geological sensors and meteorological sensors in areas prone to geological disasters to collect geological parameters and meteorological data in real time, and select geological parameters and meteorological data within several T time periods in history, as well as geological parameters and meteorological data within T time periods before the current moment. The geological parameters include horizontal displacement of the surface, displacement of the slope surface, height of the groundwater level, slope inclination angle and deep displacement. The meteorological data include temperature, humidity and rainfall.

[0010] S2. Set up edge computing IoT gateway equipment, process the collected geological parameters, obtain the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate and deep displacement change rate within the same T time period, process the collected meteorological data, and obtain the absolute values ​​of temperature change, humidity change and rainfall change within the T time period before the current moment;

[0011] S3. Construct a deep learning network model, use the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in historical geological parameters as training sets, and the corresponding geological risk index as a label, input them into the deep learning network for training, and input the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in current geological parameters into the trained deep learning network model to obtain the current geological risk index;

[0012] S4. Process the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment to generate an environmental impact index for characterizing meteorological characteristics, and process and analyze the correlation between the environmental impact index and the current geological risk index to generate a comprehensive risk index for characterizing the geological state;

[0013] S5. Compare the comprehensive risk index with the preset threshold value, predict the risk level of geological disasters in the Three Gorges Reservoir area based on the comparison result, and issue corresponding early warning signals.

[0014] Furthermore, the collected meteorological data is processed to obtain the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment. The specific process is as follows:

[0015] The absolute value of the temperature change = (the absolute value of the temperature change in the T time period before the current moment, that is, the absolute value of the final temperature minus the initial temperature);

[0016] The absolute value of humidity change = (the absolute value of humidity change in the T time period before the current moment, that is, the absolute value of the final humidity minus the initial humidity);

[0017] The absolute value of the change in rainfall = (the absolute value of the change in rainfall in the T time period before the current moment, that is, the absolute value of the final rainfall minus the absolute value of the initial rainfall).

[0018] Furthermore, the deep learning network model is a convolutional neural network model, which is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

[0019] Furthermore, the absolute values ​​of the temperature change, humidity change, and rainfall change in the T time period before the current moment are processed to generate an environmental impact index for characterizing meteorological characteristics. The specific process is as follows:

[0020] C=wS·ΔS+wH·ΔH+wR·ΔR

[0021] Where C is the environmental impact index, ΔS is the absolute value of temperature change, ΔH is the absolute value of humidity change, ΔR is the absolute value of rainfall change, wS is the weight coefficient of the absolute value of temperature change, wH is the weight coefficient of the absolute value of humidity change, wR is the weight coefficient of the absolute value of rainfall change, 0 <wR<wH<wS<1,wS+wH+wR=1。

[0022] Furthermore, the environmental impact index and the current geological risk index are processed and correlated to generate a comprehensive risk index for characterizing the geological status. The specific process is as follows:

[0023] ZS=wC·C+wG·G

[0024] Among them, ZS is the comprehensive risk index, G is the current geological risk index, wC is the weight coefficient of the environmental impact index, wG is the weight coefficient of the current geological risk index, and 0 <wC<wG<1,wC+wG=1。

[0025] Furthermore, the comprehensive risk index is compared with the preset threshold value, and the risk level of geological disasters in the Three Gorges Reservoir area is predicted based on the comparison results. The specific process is as follows:

[0026] When ZS≤YZ, that is, the comprehensive risk index is less than or equal to its threshold, the risk level of geological disasters in the Three Gorges Reservoir area is low and no warning signal is issued;

[0027] When ZS>YZ, that is, the comprehensive risk index is greater than its threshold, the risk level of geological disasters in the Three Gorges Reservoir area is high and an early warning signal is issued.

[0028] To achieve the above object, the present invention provides the following technical solutions:

[0029] A geological disaster early warning system based on edge computing Internet of Things gateway devices, the system is used to execute any of the geological disaster early warning methods based on edge computing Internet of Things gateway devices as described above, including:

[0030] The equipment layout and acquisition module is used to deploy multiple geological sensors and meteorological sensors in areas prone to geological disasters, collect geological parameters and meteorological data in real time, and select geological parameters and meteorological data within several T time periods in history, as well as geological parameters and meteorological data within T time periods before the current moment. The geological parameters include horizontal displacement of the surface, displacement of the slope surface, height of the groundwater level, slope inclination angle and deep displacement. The meteorological data include temperature, humidity and rainfall.

[0031] The data processing module is used to set the edge computing IoT gateway device, process the collected geological parameters, obtain the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate and deep displacement change rate within the same T time period, and process the collected meteorological data to obtain the absolute values ​​of temperature change, humidity change and rainfall change within the T time period before the current moment;

[0032] The deep learning network module is used to construct a deep learning network model. The surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in the historical geological parameters are used as training sets, and the corresponding geological risk index is used as a label. The data are input into the deep learning network for training. The surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in the current geological parameters are input into the trained deep learning network model to obtain the current geological risk index.

[0033] The data analysis module is used to process the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment, generate an environmental impact index for characterizing meteorological characteristics, and process and perform correlation analysis on the environmental impact index and the current geological risk index to generate a comprehensive risk index for characterizing the geological state;

[0034] The prediction module is used to compare the comprehensive risk index with the pre-set threshold value, predict the risk level of geological disasters in the Three Gorges Reservoir area based on the comparison results, and issue corresponding early warning signals.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention utilizes edge computing IoT gateway devices to pre-process the collected disaster monitoring data through a preset pre-processing algorithm, thereby improving the efficiency of edge computing, obtaining early warning results more quickly and issuing early warning information in a timely manner; by constructing a deep learning network model, historical geological parameters are used as training sets, and the corresponding geological risk index is used as a label, which is input into the deep learning network for training, and the current geological parameters are input into the trained deep learning network model to obtain the current geological risk index, thereby performing correlation analysis on various types of monitoring data and improving the accuracy of early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0038] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0039] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0040] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0041] Example:

[0042] See also Figure 1 , the present invention provides a technical solution:

[0043] A geological disaster early warning method based on edge computing Internet of Things gateway devices, the specific steps include:

[0044] S1. Deploy multiple geological sensors and meteorological sensors in areas prone to geological disasters to collect geological parameters and meteorological data in real time, and select geological parameters and meteorological data within several T time periods in history, as well as geological parameters and meteorological data within T time periods before the current moment. The geological parameters include horizontal displacement of the surface, displacement of the slope surface, height of the groundwater level, slope inclination angle and deep displacement. The meteorological data include temperature, humidity and rainfall.

[0045] S2. Set up edge computing IoT gateway devices, process the collected geological parameters, obtain the surface horizontal displacement change rate in several historical T time periods and the T time period before the current moment, the displacement change rate of the slope surface, the change rate of the groundwater level, the slope inclination angle change rate and the deep displacement change rate, and process the collected meteorological data to obtain the temperature change, humidity change and rainfall change in the T time period before the current moment;

[0046] S3. Construct a deep learning network model, use the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in historical geological parameters as training sets, and the corresponding geological risk index as a label, input them into the deep learning network for training, and input the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in current geological parameters into the trained deep learning network model to obtain the current geological risk index;

[0047] S4. Process the temperature change, humidity change and rainfall change in the T time period before the current moment to generate an environmental impact index for characterizing meteorological characteristics, process the environmental impact index and the current geological risk index and perform correlation analysis to generate a comprehensive risk index for characterizing geological conditions;

[0048] S5. Compare the comprehensive risk index with the preset threshold value, predict the risk level of geological disasters in the Three Gorges Reservoir area based on the comparison result, and issue corresponding early warning signals.

[0049] Among them, areas prone to geological disasters have the following characteristics: slopes with a gradient exceeding 15 degrees, active faults or unstable geological structures, and a historical record of geological disasters such as landslides and mud-rock flows in the area.

[0050] On the basis of the above embodiment, multiple geological sensors and meteorological sensors are deployed in areas prone to geological disasters to collect geological parameters and meteorological data in real time. The specific steps are as follows:

[0051] Displacement sensors, water level sensors and tilt sensors are used to monitor the horizontal displacement of the ground surface, the displacement of the slope surface, the deep displacement, the height of the groundwater level and the slope inclination angle respectively. Temperature sensors, humidity sensors and rain gauges are used to monitor the temperature, humidity and rainfall respectively. Data are filtered according to timestamps, and geological parameters and meteorological data within a historical T time period and geological parameters and meteorological data within a T time period before the current moment are filtered out from the real-time collected data.

[0052] On the basis of the above embodiment, an edge computing IoT gateway device is set to process the collected geological parameters to obtain the surface horizontal displacement change rate, the slope surface displacement change rate, the groundwater level change rate, the slope inclination angle change rate and the deep displacement change rate within the T time period. The specific process is as follows:

[0053] Surface horizontal displacement change rate = (final surface horizontal displacement in the same T time period - initial surface horizontal displacement) / T;

[0054] The displacement change rate of the slope surface = (the final slope surface displacement in the same T time period - the initial slope surface displacement) / T;

[0055] The rate of change of groundwater level = (final groundwater level within the same time period T - initial groundwater level) / T;

[0056] Slope inclination angle change rate = (final slope inclination angle in the same T time period - initial slope inclination angle) / T;

[0057] Deep displacement change rate = (final deep displacement in the same T time period - initial deep displacement) / T;

[0058] Where T is the duration of the time period;

[0059] Setting up edge computing IoT gateways has the following advantages over the cloud:

[0060] Edge computing pushes data processing and analysis to the edge of the network, reducing the delay of data during network transmission and achieving faster response;

[0061] Edge computing can pre-process and compress data locally, reducing the amount of data transmitted and lowering the requirements for cloud bandwidth;

[0062] Edge computing can process and analyze data locally, reducing the risk of sensitive data being transmitted over the network and enhancing data privacy and security.

[0063] Edge computing devices can work independently in offline environments and can perform data processing and analysis even when the network is unavailable or bandwidth is limited.

[0064] On the basis of the above embodiment, the collected meteorological data is processed to obtain the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment. The specific process is as follows:

[0065] The absolute value of the temperature change = (the absolute value of the temperature change in the T time period before the current moment, that is, the absolute value of the final temperature minus the initial temperature);

[0066] Humidity change = (the absolute value of the humidity change in the T time period before the current moment, that is, the absolute value of the final humidity minus the initial humidity);

[0067] The absolute value of the change in rainfall = (the absolute value of the change in rainfall in the T time period before the current moment, that is, the absolute value of the final rainfall minus the absolute value of the initial rainfall).

[0068] Determining the geological risk index corresponding to historical data based on historical statistical analysis is a common method. This method conducts statistical analysis on historical geological disaster events and related data through expert group review, and associates the historical data of different geological disaster risk factors with the frequency and severity of geological disaster events to determine the geological risk index. The value of the geological risk index is between 0 and 1. The greater the surface horizontal displacement change rate, the slope surface displacement change rate, the groundwater level change rate, the slope inclination angle change rate, and the deep displacement change rate, the greater the value of the geological risk index.

[0069] Based on the above embodiment, the deep learning network model is a convolutional neural network model, which is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

[0070] In this embodiment, the input features of the deep neural network of the multilayer perceptron include five features: the rate of change of horizontal displacement of the surface, the rate of change of displacement of the slope surface, the rate of change of the groundwater level, the rate of change of the slope inclination angle, and the rate of change of deep displacement.

[0071] The structure of a deep neural network with a multilayer perceptron is:

[0072] Input layer**: receives input of 5 features;

[0073] The first hidden layer has 64 neurons and uses ReLU as the activation function.

[0074] The second hidden layer has 128 neurons and also uses the ReLU activation function.

[0075] The third hidden layer has 64 neurons and uses the ReLU activation function.

[0076] Output layer: has a single neuron, the current geological risk index.

[0077] On the basis of the above embodiment, the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment are processed to generate an environmental impact index for characterizing meteorological characteristics. The specific process is as follows:

[0078] C=wS·ΔS+wH·ΔH+wR·ΔR

[0079] Wherein, C is the environmental impact index, ΔS is the absolute value of temperature change, ΔH is the absolute value of humidity change, ΔR is the absolute value of rainfall change, wS is the weight coefficient of the absolute value of temperature change, wH is the weight coefficient of the absolute value of humidity change, and wR is the weight coefficient of the absolute value of rainfall change.

[0080] Since temperature directly affects the growth, reproduction and survival of organisms, rising temperature is the main driving factor of global climate change, directly affecting climate patterns, sea level rise and the frequency of extreme weather. Temperature changes can affect chemical reaction rates and physical states (such as evaporation and condensation of water). Therefore, in many environmental models, temperature changes are often the most important factor.

[0081] Humidity has an important impact on plant transpiration and animal water retention. Appropriate humidity helps plant growth, while too high or too low humidity will have a negative impact. Humidity changes are closely related to weather phenomena such as precipitation, haze, and tropical cyclones. Therefore, humidity changes also play an important role in climate models. Humidity has an indirect impact on the environment by affecting the perception of temperature (such as "felt temperature").

[0082] The impact of rainfall is often temporal and spatial. It may have an impact in the short term, but in the long term, changes in rainfall are greatly affected by seasonality and climate patterns. Although rainfall has a direct impact on water resources, agriculture and ecosystems, its changes are generally considered to be a comprehensive response to temperature and humidity, and extreme changes in rainfall are often associated with temperature changes (such as tropical storms). The impact of rainfall is relatively complex and may be very important in some areas, but the impact in other areas may be relatively small.

[0083] After comprehensively considering the ecology, climate change and their direct impacts on the environment, it is generally considered that temperature has the greatest impact on the environment, followed by humidity, while the impact of rainfall is relatively small. Therefore, set 0 < wR < wH < wS < 1, and in the absence of other parameters, set wS + wH + wR = 1.

[0084] Based on the above embodiments, the environmental impact index and the current geological risk index are processed and analyzed for correlation to generate a comprehensive risk index for characterizing the geological state. The specific process is as follows:

[0085] ZS = wC·C + wG·G

[0086] Where ZS is the comprehensive risk index, G is the current geological risk index, wC is the weight coefficient of the environmental impact index, and wG is the weight coefficient of the current geological risk index.

[0087] Since the geological risk index directly reflects the current situation of the geological state, such as the risks of geological disasters like earthquakes, landslides, and debris flows, the assessment of geological risks is crucial for disaster prevention and emergency response.

[0088] Although the environmental impact index is used to characterize the environmental impact, it is itself calculated from the change rates of temperature, humidity, and rainfall factors. Therefore, its impact on the geological state is relatively indirect. Changes in environmental factors may have a long-term impact on the geological state, but these impacts usually require time accumulation and may not have a significant impact on geological risks in the short term.

[0089] Taking the above factors into comprehensive consideration, the weight of the current geological risk index is greater than the weight of the environmental impact index. Therefore, set 0 < wC < wG < 1, and in the absence of other parameters, set wC + wG = 1.

[0090] Based on the above embodiments, the comprehensive risk index is compared with a pre-set threshold, and according to the comparison result, the risk level of geological disasters in the Three Gorges Reservoir Area is predicted. The specific process is as follows:

[0091] When ZS ≤ YZ, that is, the comprehensive risk index is less than or equal to its threshold, the risk level of geological disasters in the Three Gorges Reservoir Area is low, and no warning signal is issued;

[0092] When ZS > YZ, that is, the comprehensive risk index is greater than its threshold, the risk level of geological disasters in the Three Gorges Reservoir Area is high, and a warning signal is issued.

[0093] The specific values ​​of wT, wH, wR, wC and wG in the formula are generally determined by technical personnel in this field according to actual conditions. The essence of this formula is a comprehensive analysis based on weighted summation. Technical personnel in this field collect multiple groups of sample data, and set corresponding proportional factors or weight coefficients for each group of sample data. The set proportional factors or weight coefficients and the collected sample data are substituted into the formula. Through repeated experiments and parameter adjustments, the accuracy of the model output and the rationality of the results are observed, and these proportional factors or weight coefficients are gradually adjusted. The performance and effect of the model under different parameter settings are compared to find the optimal coefficient combination. The calculated proportional factors or weight coefficients are screened and averaged to obtain the values ​​of wS, wH, wR, wC and wG.

[0094] In addition, the size of the proportional factor or weight coefficient is a specific numerical value obtained by quantizing each parameter. In order to facilitate subsequent comparison, the size of the proportional factor or weight coefficient depends on the amount of sample data and the technical personnel in this field preliminarily set the corresponding proportional factor or weight coefficient for each set of sample data. It is not unique as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0095] See also Figure 2 , the present invention also provides a technical solution:

[0096] A geological disaster early warning system based on edge computing Internet of Things gateway devices, the system is used to execute any of the geological disaster early warning methods based on edge computing Internet of Things gateway devices as described above, including:

[0097] The equipment layout and acquisition module is used to deploy multiple geological sensors and meteorological sensors in areas prone to geological disasters, collect geological parameters and meteorological data in real time, and select geological parameters and meteorological data within several T time periods in history, as well as geological parameters and meteorological data within T time periods before the current moment. The geological parameters include horizontal displacement of the surface, displacement of the slope surface, height of the groundwater level, slope inclination angle and deep displacement. The meteorological data include temperature, humidity and rainfall.

[0098] The data processing module is used to set the edge computing IoT gateway device, process the collected geological parameters, obtain the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate and deep displacement change rate within the same T time period, and process the collected meteorological data to obtain the absolute values ​​of temperature change, humidity change and rainfall change within the T time period before the current moment;

[0099] The deep learning network module is used to construct a deep learning network model. The surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in the historical geological parameters are used as training sets, and the corresponding geological risk index is used as a label. The data are input into the deep learning network for training. The surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in the current geological parameters are input into the trained deep learning network model to obtain the current geological risk index.

[0100] The data analysis module is used to process the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment, generate an environmental impact index for characterizing meteorological characteristics, and process and perform correlation analysis on the environmental impact index and the current geological risk index to generate a comprehensive risk index for characterizing the geological state;

[0101] The prediction module is used to compare the comprehensive risk index with the pre-set threshold value, predict the risk level of geological disasters in the Three Gorges Reservoir area based on the comparison results, and issue corresponding early warning signals.

[0102] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0103] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A geological disaster early warning method based on edge computing Internet of Things devices, characterized in that: The specific steps include: S1. Deploy multiple geological sensors and meteorological sensors in areas prone to geological disasters to collect geological parameters and meteorological data in real time, and select geological parameters and meteorological data within several T time periods in history, as well as geological parameters and meteorological data within T time periods before the current moment. The geological parameters include horizontal displacement of the surface, displacement of the slope surface, height of the groundwater level, slope inclination angle and deep displacement. The meteorological data include temperature, humidity and rainfall. S2. Set up edge computing IoT gateway equipment, process the collected geological parameters, obtain the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate and deep displacement change rate within the same T time period, process the collected meteorological data, and obtain the absolute values ​​of temperature change, humidity change and rainfall change within the T time period before the current moment; S3. Construct a deep learning network model, use the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in historical geological parameters as training sets, and the corresponding geological risk index as a label, input them into the deep learning network for training, and input the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in current geological parameters into the trained deep learning network model to obtain the current geological risk index; S4. Process the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment to generate an environmental impact index for characterizing meteorological characteristics, and process and analyze the correlation between the environmental impact index and the current geological risk index to generate a comprehensive risk index for characterizing the geological state; S5. Compare the comprehensive risk index with the preset threshold value, predict the risk level of geological disasters in the Three Gorges Reservoir area based on the comparison result, and issue corresponding early warning signals.

2. The geological disaster early warning method based on edge computing Internet of Things gateway equipment according to claim 1 is characterized in that: The collected meteorological data is processed to obtain the absolute values ​​of the temperature change, humidity change, and rainfall change in the T time period before the current moment. The specific process is as follows: The absolute value of the temperature change = (the absolute value of the temperature change in the T time period before the current moment, that is, the absolute value of the final temperature minus the initial temperature); The absolute value of humidity change = (the absolute value of humidity change in the T time period before the current moment, that is, the absolute value of the final humidity minus the initial humidity); The absolute value of the change in rainfall = (the absolute value of the change in rainfall in the T time period before the current moment, that is, the absolute value of the final rainfall minus the absolute value of the initial rainfall).

3. The geological disaster early warning method based on edge computing Internet of Things gateway equipment according to claim 2 is characterized in that: The deep learning network model is a convolutional neural network model, which is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

4. The geological disaster early warning method based on edge computing Internet of Things gateway equipment according to claim 3 is characterized in that: The absolute values ​​of the temperature change, humidity change, and rainfall change in the T time period before the current moment are processed to generate an environmental impact index for characterizing meteorological characteristics. The specific process is as follows: C=wS·|ΔS|+wH·|ΔH|+wR·|ΔR| Where C is the environmental impact index, ΔS is the absolute value of temperature change, ΔH is the absolute value of humidity change, ΔR is the absolute value of rainfall change, wS is the weight coefficient of the absolute value of temperature change, wH is the weight coefficient of the absolute value of humidity change, wR is the weight coefficient of the absolute value of rainfall change, 0 <wR<wH<wS<1,wS+wH+wR=1。 5. The geological disaster early warning method based on edge computing Internet of Things gateway equipment according to claim 4 is characterized in that: The environmental impact index and the current geological risk index are processed and correlated to generate a comprehensive risk index for characterizing the geological status. The specific process is as follows: ZS=wC·C+wG·G Among them, ZS is the comprehensive risk index, G is the current geological risk index, wC is the weight coefficient of the environmental impact index, wG is the weight coefficient of the current geological risk index, and 0 <wC<wG<1,wC+wG=1。 6. The geological disaster early warning method based on edge computing Internet of Things gateway equipment according to claim 5 is characterized in that: The comprehensive risk index is compared with the preset threshold value, and the risk level of geological disasters in the Three Gorges Reservoir area is predicted based on the comparison results. The specific process is as follows: When ZS≤YZ, that is, the comprehensive risk index is less than or equal to its threshold, the risk level of geological disasters in the Three Gorges Reservoir area is low and no warning signal is issued; When ZS>YZ, that is, the comprehensive risk index is greater than its threshold, the risk level of geological disasters in the Three Gorges Reservoir area is high and an early warning signal is issued.

7. A geological disaster early warning system based on edge computing Internet of Things gateway devices, the system is used to execute the geological disaster early warning method based on edge computing Internet of Things gateway devices as described in any one of claims 1-6, characterized in that: include: The equipment layout and acquisition module is used to deploy multiple geological sensors and meteorological sensors in areas prone to geological disasters, collect geological parameters and meteorological data in real time, and select geological parameters and meteorological data within several T time periods in history, as well as geological parameters and meteorological data within T time periods before the current moment. The geological parameters include horizontal displacement of the surface, displacement of the slope surface, height of the groundwater level, slope inclination angle and deep displacement. The meteorological data include temperature, humidity and rainfall. The data processing module is used to set the edge computing IoT gateway device, process the collected geological parameters, obtain the surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate and deep displacement change rate within the same T time period, and process the collected meteorological data to obtain the absolute values ​​of temperature change, humidity change and rainfall change within the T time period before the current moment; The deep learning network module is used to construct a deep learning network model. The surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in the historical geological parameters are used as training sets, and the corresponding geological risk index is used as a label. The data are input into the deep learning network for training. The surface horizontal displacement change rate, slope surface displacement change rate, groundwater level change rate, slope inclination angle change rate, and deep displacement change rate in the current geological parameters are input into the trained deep learning network model to obtain the current geological risk index. The data analysis module is used to process the absolute values ​​of the temperature change, humidity change and rainfall change in the T time period before the current moment, generate an environmental impact index for characterizing meteorological characteristics, and process and perform correlation analysis on the environmental impact index and the current geological risk index to generate a comprehensive risk index for characterizing the geological state; The prediction module is used to compare the comprehensive risk index with the pre-set threshold value, predict the risk level of geological disasters in the Three Gorges Reservoir area based on the comparison results, and issue corresponding early warning signals.

Images