Slope collapse early warning method, device and equipment based on distributed optical fiber sensing

Abstract

This application discloses a method, device, and equipment for slope collapse early warning based on distributed optical fiber sensing, relating to the field of natural disaster monitoring technology, and aiming to solve the problem of low accuracy and timeliness in slope collapse early warning. The method includes: deploying a hybrid communication network in the slope monitoring area, the hybrid communication network consisting of distributed optical fiber sensors, relay gateways, and a cloud-based early warning platform; collecting slope deformation data in real time through the distributed optical fiber sensors and compressing the slope deformation data to obtain compressed data packets; dynamically selecting the communication mode based on the real-time signal strength, and transmitting the compressed data packets to the cloud-based early warning platform through multi-hop routing via the relay gateway; and performing multi-source fusion analysis on the compressed data packets on the cloud-based early warning platform to generate and output graded early warning signals.

Description

Technical Field

[0001] This application relates to the field of natural disaster monitoring technology, and in particular to a method, device and equipment for early warning of slope collapse based on distributed optical fiber sensing. Background Technology

[0002] With continued rainfall and resource extraction, the probability of geological disasters is gradually increasing, especially slope collapses, which are becoming more and more frequent. If early warnings can be issued, the losses will be greatly reduced.

[0003] Currently, traditional slope collapse early warning systems typically collect data using conventional sensors such as displacement gauges, stress gauges, and rain gauges, transmit the data via wired communication, and then analyze the data to obtain the final warning result. However, this traditional early warning system faces challenges when dealing with complex terrain where mountains obstruct the view. Wired communication cabling is costly and easily damaged, potentially leading to the loss of crucial data and affecting the accuracy of the warning. Furthermore, the inconsistent data formats require conversion, impacting the timeliness of the warning.

[0004] Therefore, traditional early warning schemes suffer from low accuracy and timeliness in predicting slope collapses. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, and equipment for early warning of slope collapse based on distributed optical fiber sensing, which aims to solve the problem of low accuracy and timeliness in early warning of slope collapse.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] This application provides a slope collapse early warning method based on distributed optical fiber sensing. The method includes: deploying a hybrid communication network in the slope monitoring area, the hybrid communication network consisting of distributed optical fiber sensors, relay gateways, and a cloud-based early warning platform; collecting slope deformation data in real time through distributed optical fiber sensors and compressing the slope deformation data to obtain compressed data packets; dynamically selecting the communication mode according to the real-time signal strength and transmitting the compressed data packets to the cloud-based early warning platform through multi-hop routing of the relay gateways; and performing multi-source fusion analysis on the compressed data packets on the cloud-based early warning platform to generate and output graded early warning signals.

[0008] The slope collapse early warning method based on distributed optical fiber sensing provided in this application achieves end-to-end optimization of slope monitoring data acquisition, transmission, and analysis by constructing a hybrid communication network that coordinates distributed optical fiber sensors, relay gateways, and a cloud-based early warning platform. First, the method leverages the omnidirectional sensing capabilities of optical fiber sensors combined with the multi-hop routing mechanism of relay gateways to enhance communication redundancy while ensuring monitoring coverage. Second, the method effectively reduces transmission load through data compression during acquisition, and the dynamic signal strength adaptive communication mode selection mechanism ensures the stability and real-time performance of data transmission in complex environments. Finally, the method employs multi-source data fusion analysis technology in the cloud to intelligently judge based on spatiotemporal deformation characteristics. This avoids the environmental adaptability limitations of single communication modes and improves system response efficiency through a hierarchical data processing architecture, thereby enhancing the accuracy and timeliness of slope collapse early warning.

[0009] In some embodiments, the above-mentioned deployment of a hybrid communication network in the slope monitoring area includes: deploying distributed optical fiber sensors with integrated dual-mode communication modules on the slope surface and in the deep geological structure; deploying relay gateways with integrated BeiDou short message modules at the highest point of the slope; and establishing a cloud-based early warning platform that supports multi-protocol parsing.

[0010] Based on this, this application constructs a three-dimensional monitoring network by deploying dual-mode fiber optic sensors on the surface and deep layers of the slope, and deploying a BeiDou relay gateway at a high point, thereby enhancing the monitoring range and communication redundancy.

[0011] In some embodiments, the above-mentioned real-time acquisition of slope deformation data by distributed optical fiber sensors includes: acquiring slope deformation data at a first sampling frequency when the displacement rate of the slope monitoring area is detected to be less than a preset rate; or acquiring slope deformation data at a second sampling frequency when the displacement rate of the slope monitoring area is detected to be greater than or equal to a preset rate, wherein the first sampling frequency is less than the second sampling frequency.

[0012] Based on this, this application adopts a dynamic sampling mechanism, which automatically adjusts the sampling frequency according to the slope displacement rate, balancing data accuracy and transmission load, and reducing energy consumption while ensuring monitoring continuity.

[0013] In some embodiments, the above-mentioned method of dynamically selecting the communication mode based on real-time signal strength and transmitting compressed data packets to the cloud-based early warning platform via multi-hop routing through the relay gateway includes: determining a target communication module that matches the real-time signal strength from the dual-mode communication modules, and using the target communication module to transmit the compressed data packets to the relay gateway; automatically selecting a target transmission path according to the multi-hop routing algorithm of the relay gateway, and transmitting the compressed data packets to the cloud-based early warning platform through the target transmission path.

[0014] Based on this, this application combines a dual-mode communication module with a multi-hop routing algorithm to automatically select the optimal communication path according to the real-time signal strength, thereby avoiding the environmental limitations of a single communication mode and ensuring the stability and real-time performance of data transmission.

[0015] In some embodiments, the above-mentioned multi-source fusion analysis of compressed data packets on the cloud-based early warning platform to generate and output graded early warning signals includes: performing spatiotemporal grid interpolation on the compressed data packets on the cloud-based early warning platform to generate a slope deformation cloud map; extracting the temporal correlation features of multiple parameters in the slope deformation cloud map through a long short-term memory network, the multiple parameters including displacement, stress, and rainfall; inputting the temporal correlation features into a machine learning early warning model for risk assessment, and generating and outputting graded early warning signals.

[0016] Based on this, this application uses spatiotemporal grid interpolation and long short-term memory networks in the cloud to transform discrete monitoring data into continuous deformable cloud maps and extract multi-parameter time-series features, providing more refined feature inputs for multi-source fusion analysis and improving the accuracy of early warning.

[0017] In some embodiments, the aforementioned graded early warning signals include: a primary trend warning corresponding to a situation where the rate of change of multiple parameters is greater than the historical average; an intermediate spatial correlation warning corresponding to a situation where data synchronization between distributed fiber optic sensors is abnormal; and a high-level critical warning corresponding to a situation where the early warning probability output by the machine learning early warning model is greater than the critical early warning probability.

[0018] Based on this, this application refines the risk level classification by setting three levels of early warning thresholds (trend early warning, spatial correlation early warning, and critical early warning), making the early warning output more operational and the response more targeted, and improving the practicality of the early warning system.

[0019] In some embodiments, the slope collapse early warning method based on distributed optical fiber sensing provided in this application further includes: in the event of abnormal public network communication in a hybrid communication network, outputting graded early warning signals through the Beidou short message module of the relay gateway.

[0020] Based on this, this application ensures communication reliability in extreme scenarios by outputting early warning signals via BeiDou short messages when the public network is abnormal, provides redundancy protection for early warning signal output, and enhances the system's disaster recovery capability.

[0021] This application provides a slope collapse early warning device based on distributed optical fiber sensing. The device includes: a deployment unit for deploying a hybrid communication network in the slope monitoring area, the hybrid communication network consisting of distributed optical fiber sensors, relay gateways, and a cloud-based early warning platform; a data acquisition unit for acquiring slope deformation data in real time through distributed optical fiber sensors and compressing the slope deformation data to obtain compressed data packets; a transmission unit for dynamically selecting the communication mode according to the real-time signal strength and transmitting the compressed data packets to the cloud-based early warning platform through multi-hop routing of the relay gateway; and a generation unit for performing multi-source fusion analysis on the compressed data packets on the cloud-based early warning platform to generate and output graded early warning signals.

[0022] In some embodiments, the above-mentioned deployment unit is specifically used for: deploying distributed optical fiber sensors with integrated dual-mode communication modules on the slope surface and in deep geological structures; deploying relay gateways with integrated BeiDou short message modules at the highest point of the slope; and establishing a cloud-based early warning platform that supports multi-protocol parsing.

[0023] In some embodiments, the above-mentioned acquisition unit is specifically used to: acquire slope deformation data at a first sampling frequency when the displacement rate of the slope monitoring area is detected to be less than a preset rate; or, acquire slope deformation data at a second sampling frequency when the displacement rate of the slope monitoring area is detected to be greater than or equal to a preset rate, wherein the first sampling frequency is less than the second sampling frequency.

[0024] In some embodiments, the above-mentioned transmission unit is specifically used to: determine a target communication module that matches the real-time signal strength from the dual-mode communication modules, and use the target communication module to transmit the compressed data packet to the relay gateway; automatically select a target transmission path according to the multi-hop routing algorithm of the relay gateway, and transmit the compressed data packet to the cloud early warning platform through the target transmission path.

[0025] In some embodiments, the above-mentioned generation unit is specifically used to: perform spatiotemporal grid interpolation on the compressed data packet on the cloud-based early warning platform to generate a slope deformation cloud map; extract the temporal correlation features of multiple parameters in the slope deformation cloud map through a long short-term memory network, the multiple parameters including displacement, stress, and rainfall; input the temporal correlation features into a machine learning early warning model for risk assessment, and generate and output a graded early warning signal.

[0026] In some embodiments, the aforementioned graded early warning signals include: a primary trend warning corresponding to a situation where the rate of change of multiple parameters is greater than the historical average; an intermediate spatial correlation warning corresponding to a situation where data synchronization between distributed fiber optic sensors is abnormal; and a high-level critical warning corresponding to a situation where the early warning probability output by the machine learning early warning model is greater than the critical early warning probability.

[0027] In some embodiments, the aforementioned transmission unit is further configured to output a graded early warning signal through the BeiDou short message module of the relay gateway in the event of abnormal public network communication in a hybrid communication network.

[0028] This application provides an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the slope collapse early warning method based on distributed optical fiber sensing described above.

[0029] This application provides a computer-readable storage medium storing instructions that, when executed on a terminal, cause the terminal to perform the slope collapse early warning method based on distributed optical fiber sensing described above.

[0030] This application provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the slope collapse early warning method based on distributed optical fiber sensing described above.

[0031] This application provides a chip including a processor and a communication interface, the communication interface and the processor being coupled together. The processor is used to run computer programs or instructions to implement the slope collapse early warning method based on distributed optical fiber sensing described above.

[0032] Specifically, the chip provided in this application embodiment also includes a memory for storing computer programs or instructions. Attached Figure Description

[0033] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 A flowchart illustrating a slope collapse early warning method based on distributed optical fiber sensing, provided in an embodiment of this application;

[0035] Figure 2 A structural diagram of a slope collapse early warning device based on distributed optical fiber sensing provided in an embodiment of this application;

[0036] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "rear," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or relative positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and for simplification, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned orientational descriptions can be flexibly set in practical applications, provided that the relative positional relationships shown in the accompanying drawings are satisfied.

[0039] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0040] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "communication" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. They can refer to a direct connection or an indirect connection through an intermediate medium, or a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0041] In some embodiments, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, article, or apparatus that includes that element.

[0042] In some embodiments, the words "exemplary" or "for example" are used to indicate that something is an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0043] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0044] In the field of slope safety monitoring, traditional monitoring technologies are limited by complex terrain environments and the challenges of fusing multi-source heterogeneous data, making it difficult to achieve efficient and accurate collapse early warning. Existing technical solutions typically rely on wired communication (such as recommended standard 485, RS485) or conventional wireless communication (such as wireless fidelity, WiFi), but these face the following drawbacks in mountainous slope scenarios:

[0045] (a) Communication coverage defects: Complex terrain leads to severe mountain obstruction, resulting in a high probability of interruption of conventional wireless communication signals. Wired communication cabling is costly and easily damaged, causing the loss of critical data.

[0046] (ii) Data silo problem: The protocols of sensors such as displacement gauges, stress gauges, and rain gauges are fragmented, the data formats are not uniform, cross-device linkage analysis is difficult, and the accuracy of early warning is low.

[0047] (iii) The contradiction between energy efficiency and model lag: Existing early warning systems mostly adopt threshold triggering mechanisms, lack the ability to model spatiotemporal correlation characteristics, cannot capture nonlinear precursors of slope deformation, and have insufficient timeliness of early warning response.

[0048] Therefore, existing solutions suffer from low accuracy and timeliness in warning scenarios with complex terrain.

[0049] Against this backdrop, to address the issues of low accuracy and timeliness in early warning of slope collapse in related technologies, this application provides a slope collapse early warning method, device, and equipment based on distributed optical fiber sensing. By deploying a hybrid communication network to overcome terrain limitations and combining edge-cloud collaborative computing to improve data processing efficiency, and finally by employing a multi-level intelligent early warning model to enhance early warning accuracy, the overall accuracy and timeliness of early warning for slope collapse are improved.

[0050] The following is a reference. Figure 1 The slope collapse early warning method based on distributed optical fiber sensing provided in the embodiments of this application is described.

[0051] Figure 1 The flowchart of the slope collapse early warning method based on distributed optical fiber sensing provided in the embodiments of this application is shown. The main body executing the method can be an electronic device or various devices / modules in the electronic device, such as integrated circuits or chips. The embodiments of this application do not specifically limit this.

[0052] For example, such as Figure 1 As shown, the slope collapse early warning method based on distributed optical fiber sensing provided in this application embodiment may include the following steps S101 to S104:

[0053] S101. Deploy a hybrid communication network in the slope monitoring area.

[0054] In this embodiment, the hybrid communication network consists of distributed fiber optic sensors, relay gateways, and a cloud-based early warning platform.

[0055] For example, the distributed optical fiber sensor can use sensing optical fiber based on Brillouin optical time domain reflectometer (BOTDR) technology, which has both temperature and strain dual parameter sensing capabilities; and deploy a dual-mode communication module that supports narrow band Internet of Things (NB-IoT) and long range radio (LoRa).

[0056] For example, the relay gateway integrates the short message unit of the BeiDou satellite radio determination satellite service (RDSS), and the relay gateway has data caching and preprocessing capabilities.

[0057] For example, the cloud-based early warning platform is a multi-protocol parsing middleware built on a microservice architecture, compatible with Transmission Control Protocol (TCP) / Internet Protocol (IP) and custom sensing protocols.

[0058] In some embodiments, distributed fiber optic sensors with integrated dual-mode communication modules can be deployed on the slope surface and in deep geological structures.

[0059] For example, the optical fiber in the slope surface can adopt an armored tight-fitting structure with a tensile strength ≥2000N and a bending radius ≤10 times the diameter of the optical fiber.

[0060] For example, optical fibers in deep geological formations can be encapsulated in polyvinyl chloride (PVC) inclinometer tubes with 2mm diameter permeable holes in the tube wall and 10cm spacing between the holes.

[0061] Specifically, in a hydropower station high slope project, optical fibers on the slope surface can be laid in an S-shape along the walkway, and optical fibers in the deep geology can form a composite monitoring profile with the inclinometer gauge.

[0062] In other embodiments, a relay gateway integrating a BeiDou short message module can be deployed at the highest point of a slope.

[0063] For example, the relay gateway can adopt a dual power supply redundancy design, with the main power supply being a 24V solar power system and the backup power supply being a supercapacitor energy storage module, which can maintain normal operation even under continuous rainy weather for 7 days.

[0064] Among them, the BeiDou short message module supports BeiDou-3 regional short message service.

[0065] In some other embodiments, a cloud-based early warning platform that supports multi-protocol parsing can be established.

[0066] For example, the cloud-based early warning platform can use an edge computing gateway for protocol conversion, with a built-in deep learning-driven semantic parsing model that can convert TCP, custom binary protocols, etc., into standard message queueing telemetry transport (MQTT) messages.

[0067] Specifically, in the scenario of a highway slope, the system simultaneously accesses fiber optic sensor data, rain gauge RS485 data, and meteorological station Hypertext Transfer Protocol (HTTP) push data. The cloud-based early warning platform can convert these three types of data into a unified protocol.

[0068] Thus, this application constructs a three-dimensional monitoring network by deploying dual-mode fiber optic sensors on the surface and deep layers of the slope, and deploying a BeiDou relay gateway at a high point, thereby enhancing the monitoring range and communication redundancy.

[0069] S102. Real-time acquisition of slope deformation data is achieved through distributed fiber optic sensors, and the slope deformation data is compressed to obtain a compressed data packet.

[0070] In one possible implementation, when the displacement rate of the slope monitoring area is detected to be less than a preset rate, slope deformation data is collected at a first sampling frequency.

[0071] In one example, the preset rate and the first sampling frequency can be manually set values ​​that can be flexibly adjusted according to the actual scenario. For example, the preset rate can be 0.5 mm / h; the first sampling frequency range can be 0.1 Hz to 1 Hz.

[0072] In another example, the preset rate can be determined based on historical data analysis; the first sampling frequency can be adjusted according to the fiber length. For example, a 500m long optical cable can use 0.5Hz sampling.

[0073] For example, taking a preset rate of 0.5 mm / h and a first sampling frequency of 0.5 Hz as an example, a sliding window algorithm can be used to calculate the displacement change within 30 seconds. When the rate of change is less than 0.5 mm / h, low-frequency sampling is triggered, and slope deformation data is collected at a sampling frequency of 0.5 Hz.

[0074] In another possible implementation, when the displacement rate of the slope monitoring area is detected to be greater than or equal to a preset rate, slope deformation data is collected at a second sampling frequency.

[0075] The first sampling frequency is less than the second sampling frequency.

[0076] In some embodiments, the second sampling frequency can be a manually set value, which can be flexibly adjusted according to the actual scenario. For example, the range of the second sampling frequency can be 10Hz-100Hz.

[0077] For example, taking a preset rate of 0.5 mm / h and a second sampling frequency of 20 Hz as an example, a sliding window algorithm can be used to calculate the displacement change within 1 minute. When the rate of change is greater than or equal to 0.5 mm / h, high-frequency sampling is triggered, and slope deformation data is collected at a sampling frequency of 20 Hz.

[0078] Thus, this application adopts a dynamic sampling mechanism, which automatically adjusts the sampling frequency according to the slope displacement rate, balancing data accuracy and transmission load, and reducing energy consumption while ensuring monitoring continuity.

[0079] Optionally, the above data compression can employ a two-stage compression mechanism.

[0080] In some embodiments, primary compression can use an improved wavelet threshold denoising algorithm to achieve a 3:1 compression ratio in the 0.1Hz-10Hz frequency band; secondary compression can use run-length coding combined with differential pulse code modulation (DPCM) to encode the difference between adjacent sampling points with variable length.

[0081] For example, under continuous rainfall conditions, the system automatically increases the sampling frequency of the slope toe area from 1Hz to 10Hz, while compressing the collected data.

[0082] S103. Dynamically select the communication mode based on the real-time signal strength, and transmit the compressed data packet to the cloud early warning platform through the multi-hop routing of the relay gateway.

[0083] In this embodiment, the communication mode selection can be based on the received signal strength indication (RSSI) value. When the NB-IoT signal strength is greater than -90dBm, the NB-IoT protocol is used preferentially; otherwise, the LoRa protocol is switched. Multi-hop routing adopts the ad hoc on-demand distance vector (AODV) routing protocol, combined with the link quality estimation (LQE) mechanism to select the optimal path.

[0084] For example, in the scenario of canyon terrain monitoring, when there is obstructing terrain in the slope that causes direct communication to be interrupted, compressed data packets can be transmitted indirectly through three relay gateways.

[0085] Optionally, the compressed data packets collected by the distributed fiber optic sensors can be sent to the relay gateway first, and then forwarded to the cloud-based early warning platform through the relay gateway.

[0086] In one alternative implementation, a target communication module matching the real-time signal strength can be determined from the dual-mode communication modules, and the target communication module can be used to transmit the compressed data packet to the relay gateway.

[0087] In one example, the protocol can be dynamically switched using the RSSI value. When the RSSI is greater than -90dBm, the NB-IoT protocol is selected, and compressed data packets are transmitted to the relay gateway through the NB-IoT protocol.

[0088] In another example, the protocol can be dynamically switched using the RSSI value. When the RSSI is less than or equal to -90dBm, the LoRa protocol is selected, and compressed data packets are transmitted to the relay gateway through the LoRa protocol.

[0089] Furthermore, the target transmission path is automatically selected based on the multi-hop routing algorithm of the relay gateway, and the compressed data packet is transmitted to the cloud-based early warning platform through the target transmission path.

[0090] In some embodiments, the multi-hop routing algorithm may employ a dynamic weighted path selection mechanism, which first evaluates the path, then calculates the path weight, and finally selects the path.

[0091] For example, path assessment can be performed based on beacon frames periodically broadcast by each relay gateway. These beacon frames include a gateway identifier (ID), RSSI value, remaining battery power, and load status.

[0092] For example, path weight calculation can be performed using formula (i).

[0093] Formula (1)

[0094] Where W is the path weight, α, β, and γ are configurable weight coefficients, Hops is the number of path hops, and Battery is the percentage of remaining battery power at the node.

[0095] For example, after calculating the weight of each path, the path with the smallest weight can be used as the target transmission path, and then the compressed data packet can be transmitted to the cloud early warning platform through the target transmission path.

[0096] Thus, this application combines a dual-mode communication module with a multi-hop routing algorithm to automatically select the optimal communication path based on real-time signal strength, avoiding the environmental limitations of a single communication mode and ensuring the stability and real-time performance of data transmission.

[0097] Furthermore, when multiple equivalent paths exist, load balancing can be achieved by randomly distributing traffic using a hash algorithm.

[0098] In another alternative implementation, the target communication module can be determined based on data priority and remaining power, and the target communication module can be used to transmit compressed data packets to the relay gateway.

[0099] In one example, the NB-IoT protocol is forced to be used when the data priority is higher than the first priority and the remaining battery power is greater than the first priority (such as in the case of a sudden event).

[0100] In another example, the LoRa protocol is used when the data priority is lower than the first priority and the remaining battery power is less than or equal to the first priority (such as normal data).

[0101] S104. Perform multi-source fusion analysis on the compressed data packet on the cloud-based early warning platform to generate and output graded early warning signals.

[0102] In some embodiments, spatiotemporal grid interpolation can be performed on compressed data packets on a cloud-based early warning platform to generate slope deformation cloud maps.

[0103] In this embodiment, the spatiotemporal grid can adopt a non-uniform partitioning strategy, setting a high-density grid (e.g., spacing ≤ 1m) in regions with large deformation gradients and a low-density grid (e.g., spacing 10m) in stable regions.

[0104] For example, the received compressed data packets can be decompressed and parsed to remove outliers caused by communication interference. The spatiotemporal synchronization of multi-sensor data can be ensured by timestamp alignment. Then, an adaptive non-uniform grid strategy can be adopted to identify potential sliding surfaces, faults and other deformation-sensitive areas based on the slope geological survey report. High-density grids can be deployed in sensitive areas and low-density grids can be used in stable areas.

[0105] In the embodiments of this application, the interpolation algorithm can introduce a terrain correction factor to eliminate the influence of elevation on deformation calculation.

[0106] For example, an improved Kriging interpolation algorithm can be used to introduce a terrain correction factor to compensate for the measurement deviation caused by elevation, as shown in Formula (II) below.

[0107] Formula (II)

[0108] in, This is the corrected deformation amount. This is the original interpolation result. The topographic influence coefficient (calculated using a digital elevation model, DEM). This represents the elevation gradient.

[0109] In this embodiment of the application, after obtaining the corrected deformation amount, the deformation amount can be mapped to a three-dimensional coordinate system, and the deformation level can be represented by a rainbow color scale (red represents positive deformation and blue represents negative deformation), and contour lines and geological profile maps can be superimposed to assist in the analysis.

[0110] Furthermore, the temporal correlation features of multiple parameters in the slope deformation cloud map are extracted by long short-term memory network, and the temporal correlation features are input into the machine learning early warning model for risk assessment, generating and outputting graded early warning signals.

[0111] Several parameters are included, such as displacement, stress, and rainfall.

[0112] For example, displacement can be calculated using fiber optic Brillouin frequency shift; stress can be calculated using a strain-stress conversion model obtained from birefringent optical fibers; and rainfall can be calculated by fusing meteorological station data with fiber optic temperature gradient inversion data. The fiber optic Brillouin frequency shift refers to the frequency shift caused by the interaction between the acoustic field and the light wave as light propagates in the optical fiber.

[0113] In this embodiment, the long short-term memory network can be a two-layer long short-term memory (LSTM) network, with each layer containing 128 hidden units. The input parameters include three types of features: displacement, stress, and rainfall.

[0114] For example, displacement, stress, and rainfall can be extracted from the slope deformation cloud map. Four types of features, namely displacement rate v, acceleration a, temperature T, and rainfall R, can be selected to construct a four-dimensional time series tensor (T×N×F, where T=240 is the time window, N=16 is the number of spatial grids, and F=4 is the feature dimension).

[0115] Furthermore, a spatiotemporal attention module is introduced between LSTM layers to assign higher weights to key time steps (such as the peak rainfall time) and spatial locations (such as the maximum displacement region) through formula (III).

[0116] Formula (3)

[0117] in, This represents the attention score at time t and spatial location (x, y); The sigmoid function is used to map the attention score to the (0, 1) interval; These are learnable weight parameters, corresponding to time, X-axis spatial position, and Y-axis spatial position, respectively; is the hidden state at time t, which contains historical information up to time t; b is the bias term, used to adjust the baseline value of the attention score.

[0118] In this embodiment, the machine learning early warning model can be constructed using the extreme gradient boosting (XGBoost) algorithm, and the contribution of each feature can be explained by the Shapley (SHAP) value.

[0119] For example, statistical features, frequency domain features, and correlation features can be extracted from the temporal correlation features output by LSTM. Then, the marginal contribution (SHAP value) of each feature to the warning probability can be calculated using formula (iv). Finally, the warning level can be determined based on the magnitude and sign of the SHAP value and the warning probability output by the machine learning warning model.

[0120] Formula (IV)

[0121] in, SHAP value represents the marginal contribution of the i-th feature to the model output; S is the feature subset, representing the combination of features other than the i-th feature; F is the feature set, containing all features used for model training. Represents a feature subset containing the i-th feature. The corresponding model output; This represents the model output corresponding to the feature subset S that does not contain the i-th feature.

[0122] In this embodiment of the application, the difference in model output with and without the i-th feature can be calculated using formula (iv), and all possible combinations of feature subsets can be considered to evaluate the average marginal contribution of the i-th feature to the model output.

[0123] It should be noted that the SHAP value quantifies the marginal contribution of each feature to the model's warning probability output. A positive SHAP value indicates that the feature contributes positively to the warning probability, i.e., increases the risk of landslides; a negative SHAP value indicates that the feature contributes negatively to the warning probability, i.e., reduces the risk of landslides.

[0124] Specifically, if the SHAP value of the rainfall feature is positive and the model outputs a high probability of warning, an advanced warning may be triggered.

[0125] Thus, this application transforms discrete monitoring data into continuous deformable cloud maps by employing spatiotemporal grid interpolation and long short-term memory networks in the cloud, and extracts multi-parameter time-series features, providing more refined feature inputs for multi-source fusion analysis and improving the accuracy of early warning.

[0126] Optionally, the tiered early warning signals may include: primary trend warning, intermediate spatial correlation warning, and advanced critical warning.

[0127] In some embodiments, the primary trend warning is a warning corresponding to the situation where the rate of change of multiple parameters is greater than the historical average. The primary trend warning is used to indicate early anomalies in the slope condition.

[0128] The historical average change can be obtained by calculating the average of the monitoring data from the most recent 30 days using a sliding window. For example, the historical average change could be 0.35 mm / day.

[0129] For example, taking a historical average change of 0.35 mm / day as an example, the rate of change of displacement can be calculated using the exponentially weighted moving average (EWMA) method. When the rate of change for three consecutive sampling periods exceeds 0.35 mm / day, a primary trend warning is triggered.

[0130] In some embodiments, the intermediate spatial correlation warning is a warning corresponding to the abnormal data synchronization between distributed fiber optic sensors, and the intermediate spatial correlation warning is used to indicate the spatial integrity of the monitoring network.

[0131] For example, synchronization anomalies can be determined by the correlation coefficient matrix. When the correlation between adjacent fiber optic sensor data is lower than a preset threshold and the duration is longer than a preset duration, it is determined to be a spatial correlation anomaly.

[0132] The preset threshold and preset duration are both manually set values ​​that can be flexibly adjusted according to the actual scenario. For example, the preset threshold can be 0.7; the preset duration can be 1 hour.

[0133] Specifically, taking a preset threshold of 0.7 and a preset duration of 1 hour as an example, in a certain local landslide, if the data correlation between fiber optic sensor No. 3 and fiber optic sensor No. 4 drops sharply from 0.85 to 0.3 and lasts for 3 hours, it is determined that spatial decoupling has occurred in the area, triggering a medium-level spatial correlation warning.

[0134] In some embodiments, advanced critical warning is the warning corresponding to the case where the warning probability output by the machine learning warning model is greater than the critical warning probability. Advanced critical warning is used to characterize the high-risk state of a slope that is about to become unstable.

[0135] The critical warning probability can be determined by inverting historical landslide events. For example, the critical warning probability is usually set to 0.8.

[0136] For example, taking a critical warning probability of 0.8 as an example, the Monte Carlo method can be used to quantify the uncertainty of the model output to obtain the warning probability. If, during a severe rainstorm, the landslide probability predicted by the model rapidly increases from 0.65 to 0.92, then the highest level emergency plan is activated, triggering a high-level critical warning.

[0137] Thus, by setting three levels of early warning thresholds (trend early warning, spatial correlation early warning, and critical early warning), this application refines the risk level classification, making the early warning output more operational and the response more targeted, thereby improving the practicality of the early warning system.

[0138] Optionally, in the event of abnormal public network communication in a hybrid communication network, a graded early warning signal can be output through the BeiDou short message module of the relay gateway.

[0139] For example, when the public network is interrupted, the relay gateway automatically switches to the short message module to send early warning signals, and the sending frequency is dynamically adjusted according to the early warning level (e.g., 1 time / hour for primary trend early warning, 1 time / 15 minutes for advanced critical early warning).

[0140] In the slope collapse early warning method based on distributed optical fiber sensing provided in this application embodiment, a hybrid communication network integrating distributed optical fiber sensors, relay gateways, and a cloud-based early warning platform is constructed to achieve end-to-end optimization of slope monitoring data acquisition, transmission, and analysis. First, the omnidirectional sensing characteristics of optical fiber sensors combined with the multi-hop routing mechanism of the relay gateway enhance communication redundancy while ensuring the monitoring range. Second, the data processing method of simultaneous acquisition and compression effectively reduces the transmission load, and the dynamic signal strength adaptive communication mode selection mechanism ensures the stability and real-time performance of data transmission in complex environments. Finally, multi-source data fusion analysis technology is used in the cloud to intelligently judge based on spatiotemporal deformation characteristics. This avoids the environmental adaptability defects of a single communication mode and improves system response efficiency through a hierarchical data processing architecture, thereby enhancing the accuracy and timeliness of slope collapse early warning.

[0141] The above primarily describes the solutions provided in the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, the slope collapse early warning device or electronic device based on distributed optical fiber sensing includes corresponding hardware structures and / or software modules for performing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0142] This application embodiment can, according to the above method, exemplarily divide the slope collapse early warning device or electronic device based on distributed optical fiber sensing into functional modules. For example, the slope collapse early warning device or electronic device based on distributed optical fiber sensing may include functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0143] Figure 2 This is a structural diagram of a slope collapse early warning device based on distributed optical fiber sensing, provided in an embodiment of this application. The slope collapse early warning device 200 based on distributed optical fiber sensing includes: a deployment unit 201, a data acquisition unit 202, a transmission unit 203, and a generation unit 204.

[0144] The system comprises: a deployment unit 201, used to deploy a hybrid communication network in the slope monitoring area, the hybrid communication network consisting of distributed fiber optic sensors, relay gateways, and a cloud-based early warning platform; an acquisition unit 202, used to acquire slope deformation data in real time through distributed fiber optic sensors and compress the slope deformation data to obtain compressed data packets; a transmission unit 203, used to dynamically select the communication mode according to the real-time signal strength and transmit the compressed data packets to the cloud-based early warning platform through multi-hop routing of the relay gateway; and a generation unit 204, used to perform multi-source fusion analysis on the compressed data packets on the cloud-based early warning platform to generate and output graded early warning signals.

[0145] In some embodiments, the deployment unit 201 is specifically used for: deploying distributed optical fiber sensors with integrated dual-mode communication modules on the slope surface and in deep geological structures; deploying relay gateways with integrated BeiDou short message modules at the highest point of the slope; and establishing a cloud-based early warning platform that supports multi-protocol parsing.

[0146] In some embodiments, the acquisition unit 202 is specifically used to: acquire slope deformation data at a first sampling frequency when the displacement rate of the slope monitoring area is detected to be less than a preset rate; or, acquire slope deformation data at a second sampling frequency when the displacement rate of the slope monitoring area is detected to be greater than or equal to a preset rate, wherein the first sampling frequency is less than the second sampling frequency.

[0147] In some embodiments, the transmission unit 203 is specifically used to: determine a target communication module that matches the real-time signal strength from the dual-mode communication modules, and use the target communication module to transmit the compressed data packet to the relay gateway; automatically select a target transmission path according to the multi-hop routing algorithm of the relay gateway, and transmit the compressed data packet to the cloud early warning platform through the target transmission path.

[0148] In some embodiments, the generation unit 204 is specifically used to: perform spatiotemporal grid interpolation on the compressed data packet on the cloud-based early warning platform to generate a slope deformation cloud map; extract the temporal correlation features of multiple parameters in the slope deformation cloud map through a long short-term memory network, the multiple parameters including displacement, stress, and rainfall; input the temporal correlation features into a machine learning early warning model for risk assessment, and generate and output a graded early warning signal.

[0149] In some embodiments, the aforementioned graded early warning signals include: a primary trend warning corresponding to a situation where the rate of change of multiple parameters is greater than the historical average; an intermediate spatial correlation warning corresponding to a situation where data synchronization between distributed fiber optic sensors is abnormal; and a high-level critical warning corresponding to a situation where the early warning probability output by the machine learning early warning model is greater than the critical early warning probability.

[0150] In some embodiments, the transmission unit 203 is further configured to output a graded early warning signal through the BeiDou short message module of the relay gateway in the event of abnormal public network communication in a hybrid communication network.

[0151] In the slope collapse early warning device based on distributed optical fiber sensing provided in this application embodiment, a hybrid communication network integrating distributed optical fiber sensors, relay gateways, and a cloud-based early warning platform is constructed to achieve end-to-end optimization of slope monitoring data acquisition, transmission, and analysis. First, the omnidirectional sensing characteristics of optical fiber sensors combined with the multi-hop routing mechanism of the relay gateway enhance communication redundancy while ensuring the monitoring range. Second, the data processing method of simultaneous acquisition and compression effectively reduces the transmission load, and the dynamic signal strength adaptive communication mode selection mechanism ensures the stability and real-time performance of data transmission in complex environments. Finally, multi-source data fusion analysis technology is used in the cloud to intelligently judge based on spatiotemporal deformation characteristics. This avoids the environmental adaptability defects of a single communication mode and improves system response efficiency through a hierarchical data processing architecture, thereby enhancing the accuracy and timeliness of slope collapse early warning.

[0152] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0153] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 300 includes, but is not limited to, a processor 301 and a memory 302.

[0154] The aforementioned memory 302 is used to store the executable instructions of the aforementioned processor 301. It is understood that the processor 301 is configured to execute instructions to implement the slope collapse early warning method based on distributed optical fiber sensing in the above embodiments.

[0155] It should be noted that those skilled in the art will understand that Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices. Figure 3 This may indicate more or fewer components, or combinations of certain components, or different component arrangements.

[0156] Processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 302, and by calling data stored in memory 302, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Processor 301 may include one or more processing units. Optionally, processor 301 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 301.

[0157] The memory 302 can be used to store software programs and various data. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0158] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 302 including instructions, which can be executed by a processor 301 of an electronic device 300 to implement the slope collapse early warning method based on distributed optical fiber sensing in the above embodiments.

[0159] In actual implementation, Figure 2 The steps performed by the deployment unit 201, acquisition unit 202, transmission unit 203, and generation unit 204 can all be performed by... Figure 3 The processor 301 calls the computer program stored in the memory 302 to implement the process. The specific execution process can be found in the method section of the previous embodiment, and will not be repeated here.

[0160] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0161] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by the processor 301 of an electronic device to complete the slope collapse early warning method based on distributed optical fiber sensing in the above embodiments.

[0162] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of the electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.

[0163] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0164] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0165] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the classified units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0166] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0167] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0168] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A slope collapse early warning method based on distributed optical fiber sensing, characterized in that, The method includes: deploying a hybrid communication network in the slope monitoring area, the hybrid communication network consisting of distributed fiber optic sensors, relay gateways, and a cloud-based early warning platform; collecting slope deformation data in real time through the distributed fiber optic sensors and compressing the slope deformation data to obtain compressed data packets; dynamically selecting the communication mode based on the real-time signal strength and transmitting the compressed data packets to the cloud-based early warning platform through multi-hop routing of the relay gateways; and performing multi-source fusion analysis on the compressed data packets on the cloud-based early warning platform to generate and output graded early warning signals. The step of performing multi-source fusion analysis on the compressed data packet on the cloud-based early warning platform to generate and output a graded early warning signal includes: performing spatiotemporal grid interpolation on the compressed data packet on the cloud-based early warning platform to generate a slope deformation cloud map; extracting the temporal correlation features of multiple parameters in the slope deformation cloud map through a long short-term memory network, the multiple parameters including displacement, stress, and rainfall; inputting the temporal correlation features into a machine learning early warning model for risk assessment, and generating and outputting the graded early warning signal. The tiered early warning signals include: a primary trend warning corresponding to the case where the rate of change of the multiple parameters is greater than the historical average; a secondary spatial correlation warning corresponding to the case where data synchronization between the distributed optical fiber sensors is abnormal; and a senior critical warning corresponding to the case where the early warning probability output by the machine learning early warning model is greater than the critical early warning probability. The primary trend warning is an early warning corresponding to the situation where the rate of change of multiple parameters is greater than the historical average. The primary trend warning is used to indicate early anomalies in the slope condition. The historical average change is obtained by statistically analyzing the monitoring data of the previous 30 days using a sliding window, and then calculating the average value. The intermediate spatial correlation early warning is an early warning corresponding to the abnormal data synchronization between distributed optical fiber sensors. The intermediate spatial correlation early warning is used to indicate the spatial integrity of the monitoring network. The synchronization anomaly is determined by the correlation coefficient matrix. When the correlation between adjacent fiber optic sensor data is lower than a preset threshold and the duration is longer than a preset duration, it is determined to be a spatial correlation anomaly. The preset threshold and preset duration are both manually set values. The advanced critical warning is the warning corresponding to the situation where the warning probability output by the machine learning warning model is greater than the critical warning probability. The advanced critical warning is used to characterize the high-risk state of the slope that is about to become unstable. The critical warning probability is determined by inversion of historical landslide events.

2. The slope collapse early warning method based on distributed optical fiber sensing according to claim 1, characterized in that, The deployment of a hybrid communication network in the slope monitoring area includes: deploying distributed optical fiber sensors with integrated dual-mode communication modules on the slope surface and in the deep geological structure; deploying relay gateways with integrated BeiDou short message modules at the highest points of the slope; and establishing a cloud-based early warning platform that supports multi-protocol parsing.

3. The slope collapse early warning method based on distributed optical fiber sensing according to claim 1, characterized in that, The real-time acquisition of slope deformation data through the distributed optical fiber sensor includes: acquiring the slope deformation data at a first sampling frequency when the displacement rate of the slope monitoring area is detected to be less than a preset rate; or acquiring the slope deformation data at a second sampling frequency when the displacement rate of the slope monitoring area is detected to be greater than or equal to the preset rate, wherein the first sampling frequency is less than the second sampling frequency.

4. The slope collapse early warning method based on distributed optical fiber sensing according to claim 2, characterized in that, The step of dynamically selecting the communication mode based on real-time signal strength and transmitting the compressed data packet to the cloud-based early warning platform via the multi-hop routing of the relay gateway includes: determining a target communication module matching the real-time signal strength from the dual-mode communication modules, and using the target communication module to transmit the compressed data packet to the relay gateway; automatically selecting a target transmission path according to the multi-hop routing algorithm of the relay gateway, and transmitting the compressed data packet to the cloud-based early warning platform via the target transmission path.

5. The slope collapse early warning method based on distributed optical fiber sensing according to claim 1, characterized in that, The method further includes: in the event of abnormal public network communication in the hybrid communication network, outputting the graded early warning signal through the Beidou short message module of the relay gateway.

6. A slope collapse early warning device based on distributed optical fiber sensing, characterized in that, The device includes: a deployment unit for deploying a hybrid communication network in the slope monitoring area, the hybrid communication network consisting of distributed fiber optic sensors, relay gateways, and a cloud-based early warning platform; a data acquisition unit for acquiring slope deformation data in real time through the distributed fiber optic sensors and compressing the slope deformation data to obtain compressed data packets; a transmission unit for dynamically selecting a communication mode based on real-time signal strength and transmitting the compressed data packets to the cloud-based early warning platform via multi-hop routing through the relay gateway; and a generation unit for performing multi-source fusion analysis on the compressed data packets on the cloud-based early warning platform to generate and output graded early warning signals. The generation unit is specifically used for: performing multi-source fusion analysis on the compressed data packet on the cloud-based early warning platform to generate and output graded early warning signals, including: performing spatiotemporal grid interpolation on the compressed data packet on the cloud-based early warning platform to generate a slope deformation cloud map; extracting the temporal correlation features of multiple parameters in the slope deformation cloud map through a long short-term memory network, the multiple parameters including displacement, stress, and rainfall; inputting the temporal correlation features into a machine learning early warning model for risk assessment, and generating and outputting the graded early warning signals; The tiered early warning signals include: a primary trend warning corresponding to the case where the rate of change of the multiple parameters is greater than the historical average; a secondary spatial correlation warning corresponding to the case where data synchronization between the distributed optical fiber sensors is abnormal; and a senior critical warning corresponding to the case where the early warning probability output by the machine learning early warning model is greater than the critical early warning probability. The primary trend warning is an early warning corresponding to the situation where the rate of change of multiple parameters is greater than the historical average. The primary trend warning is used to indicate early anomalies in the slope condition. The historical average change is obtained by statistically analyzing the monitoring data of the previous 30 days using a sliding window, and then calculating the average value. The intermediate spatial correlation early warning is an early warning corresponding to the abnormal data synchronization between distributed optical fiber sensors. The intermediate spatial correlation early warning is used to indicate the spatial integrity of the monitoring network. The synchronization anomaly is determined by the correlation coefficient matrix. When the correlation between adjacent fiber optic sensor data is lower than a preset threshold and the duration is longer than a preset duration, it is determined to be a spatial correlation anomaly. The preset threshold and preset duration are both manually set values. The advanced critical warning is the warning corresponding to the situation where the warning probability output by the machine learning warning model is greater than the critical warning probability. The advanced critical warning is used to characterize the high-risk state of the slope that is about to become unstable. The critical warning probability is determined by inversion of historical landslide events.

7. An electronic device, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the slope collapse early warning method based on distributed optical fiber sensing as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing instructions, characterized in that, When the computer executes the instruction, the computer performs the slope collapse early warning method based on distributed optical fiber sensing as described in any one of claims 1 to 5.

Images