Geological disaster section driving guidance method, device and equipment and storage medium

Abstract

This application discloses a driving guidance method, device, equipment, and storage medium for geological disaster-prone road sections, relating to the field of geological disaster prevention and control technology. The method utilizes the visual and analytical capabilities of small baseline integrated interferometric synthetic aperture radar, combined with an extreme learning machine that has good vector compatibility to further analyze potential geological disasters that have not yet occurred, thus preventing them before they happen. After predicting potential geological risks, the method reminds vehicles to change routes in a timely manner and notifies monitoring roles to take timely preventive measures. This achieves a double insurance of early warning and prevention, preventing natural disasters caused by adverse geological bodies from causing losses to life and property, and ensuring personal and property safety.

Description

Technical Field

[0001] This application relates to the field of road traffic technology, and in particular to a method, device, equipment and storage medium for guiding traffic in geological disaster-prone road sections. Background Technology

[0002] Transportation is a key driver of economic and social development and an important means of connecting the whole country and even the world.

[0003] Currently, the main mode of transportation is road travel. Roads are linear engineering projects, laid out in a strip, characterized by their wide range and high density. Road construction inevitably involves crossing unfavorable geological formations, posing some safety hazards. Currently, for sections of road crossing unfavorable geological formations, the primary method is to set up warning signs on the roadside to remind passing vehicles and pedestrians to observe and slow down. This method mainly serves as a reminder. However, in sections of road crossing unfavorable geological formations that are prone to natural disasters, traffic accidents caused by natural disasters still frequently occur, resulting in losses to the lives and property of passing vehicles. Summary of the Invention

[0004] The main purpose of this application is to provide a driving guidance method, device, equipment, and storage medium for road sections with geological hazards, in order to solve the problem that in the prior art, when a road passes through a section with poor geological conditions, the main method is to set up warning signs on the roadside to remind passing vehicles and pedestrians to observe and slow down. This method mainly serves as a reminder, but it is inevitable that traffic accidents caused by natural disasters will still frequently occur when passing through sections with poor geological conditions, resulting in losses to the lives and property of passing vehicles.

[0005] To achieve the above objectives, this application provides the following technical solution: A method for guiding traffic on roads affected by geological hazards, wherein the geological hazard road section is located on at least one of several interconnected roads within a preset area, and at least one vehicle is traveling on all roads, the method comprising: Step S1: The radar image of the preset area is acquired by small baseline integrated interferometric synthetic aperture radar based on several preset time periods. Step S2: Analyze the deformation displacement vector of all radar images based on the time series of all radar images; Step S3: Integrate all deformation displacement vectors of the same preset time period into a single vector dataset; Step S4: Learn and train all vector datasets using an extreme learning machine, and obtain several prediction vector datasets based on a number of preset prediction steps; Step S5: Based on the time series of all predicted vector datasets, the geological changes of the preset area are simulated by dynamic simulation, and a simulated image is obtained based on a preset number of prediction steps; Step S6: Sequentially determine whether each simulated image intersects with any road along the time series of all predicted vector datasets. If so, proceed to step S7. Step S7: Obtain the planned route of the current vehicle and determine whether the planned route passes through the intersection point. If it does, proceed to step S8. Step S8: Obtain the road topology of all roads in the preset area, and delete the roads with the intersection points from the road topology to form a candidate road topology; Step S9: In the candidate road topology, with the current vehicle as the path start point and the planned route end point as the path end point, obtain the shortest path and send it to the current vehicle.

[0006] As a further improvement to this application, step S9 involves obtaining the shortest path in the candidate road topology, with the current vehicle as the path start point and the planned route's end point as the path end point, and sending it to the current vehicle. Following this, the process includes: Step S10: Obtain the earliest future timestamp of whether each simulated image intersects with any road; Step S20: Obtain the map coordinates of the intersection point corresponding to the earliest future timestamp, and define them as disaster occurrence risk coordinates; Step S30: Send the disaster risk coordinates and the earliest future timestamp to the external monitoring terminal.

[0007] As a further improvement to this application, step S9 involves obtaining the shortest path in the candidate road topology, with the current vehicle as the path start point and the planned route's end point as the path end point, and sending it to the current vehicle. Following this, the process includes: Step S100: Obtain the ratio of the length of the congested section to the total length of the shortest path based on external navigation software; Step S200: Determine whether the length ratio is greater than or equal to a preset ratio threshold. If so, proceed to step S300. Step S300: Remove the shortest path from the candidate road topology to obtain the filtered candidate road topology; Step S400: In the filtered candidate road topology, the second shortest path is obtained with the current vehicle as the path start point and the planned route end point as the path end point. Step S500: Repeat steps S100 to S400 with the second shortest path as the execution subject until the length ratio of the second shortest path after iteration is less than the preset ratio threshold. Step S600: Send the next shortest path after the iteration to the current vehicle.

[0008] As a further improvement to this application, step S600 involves sending the iteratively shortest path to the current vehicle, followed by: Step S1000: Send the iteratively shortest path to the external security monitoring terminal; Step S2000: Continuously acquire the real-time map location of the current vehicle; Step S3000: Determine whether the real-time map location has reached the end of the path. If so, proceed to step S4000. Step S4000: Remove the iteratively shortest path from the external security monitoring terminal.

[0009] As a further improvement to this application, step S9, obtaining the shortest path in the candidate road topology with the current vehicle as the path starting point and the planned route ending point as the path ending point, and sending it to the current vehicle, includes: Step S91: Extract the road boundaries of the candidate road topology using a boundary extraction algorithm; Step S92: Divide the digital elevation model using square grids of a preset density; Step S93: Obtain all square grids within all road boundaries and define them as candidate grid sets; Step S94: Define each square grid cell in the candidate grid set as a node; Step S95: Calculate the minimum number of grid cells required to reach the end point of the path from the starting point using the A_star algorithm; Step S96: Obtain the grid corresponding to the minimum number of grids, and connect them sequentially to form the shortest path.

[0010] To achieve the above objectives, this application also provides the following technical solutions: A traffic guidance device for road sections prone to geological disasters, wherein the traffic guidance device is applied to the traffic guidance method described above, and the traffic guidance device comprises: A preset area radar image acquisition module is used to acquire radar images of the preset area based on several preset time periods using a small baseline integrated interferometric synthetic aperture radar. The deformation displacement vector analysis module is used to analyze the deformation displacement vector of all radar images based on the time series of all radar images. The vector dataset integration module is used to integrate all deformation displacement vectors within the same preset time period into a single vector dataset. The prediction vector dataset acquisition module is used to learn and train all vector datasets through extreme learning machine, and obtain several prediction vector datasets based on several preset prediction steps; The prediction vector dataset simulation module is used to dynamically simulate the geological changes of the preset area based on the time series of all prediction vector datasets, and obtain a simulated image based on a preset number of prediction steps. The simulated image motion determination module is used to sequentially determine whether each simulated image intersects with any road along the time series of all predicted vector datasets; The planned route acquisition and judgment module is used to acquire the planned route of the current vehicle and determine whether the planned route passes through the intersection point if the condition is met. The alternative road topology acquisition module is used to acquire the road topology of all roads in the preset area if the area is traversed, and to delete the roads with the intersection points from the road topology to form alternative road topologies. The shortest path acquisition and transmission module is used to acquire the shortest path in the candidate road topology with the current vehicle as the path start point and the planned route as the path end point, and then send it to the current vehicle.

[0011] To achieve the above objectives, this application also provides the following technical solutions: An electronic device includes a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the driving guidance method as described above.

[0012] To achieve the above objectives, this application also provides the following technical solutions: A storage medium storing program instructions that, when executed by a processor, can implement the vehicle guidance method described above.

[0013] This application acquires radar images of a preset area using a small baseline integrated interferometric synthetic aperture radar (SAIL) over several preset time periods. It then analyzes the deformation displacement vectors of all radar images based on their time series. All deformation displacement vectors from the same preset time period are integrated into a single vector dataset. The application uses an extreme learning machine to learn and train all vector datasets, obtaining several predicted vector datasets based on several preset prediction steps. Based on the time series of all predicted vector datasets, it dynamically simulates geological changes in the preset area, obtaining a simulated image based on one preset prediction step. It sequentially determines whether each simulated image intersects with any road along the time series of all predicted vector datasets. If so, it obtains the planned route of the current vehicle and determines whether the planned route passes through the intersection point. If it does, it obtains the road topology of all roads in the preset area and removes roads with intersection points from the road topology, forming a candidate road topology. Finally, it obtains the shortest path from the candidate road topology, using the current vehicle as the path start point and the planned route's end point as the path endpoint, and sends this path to the current vehicle. This application leverages the visual and analytical capabilities of small baseline integrated interferometric synthetic aperture radar (SAMR), combined with an extreme learning machine (ELM) that has good vector compatibility, to further analyze potential, yet-to-occur, geological hazards. This allows for proactive prevention, and upon predicting potential geological risks, it alerts vehicles to change routes in a timely manner while simultaneously notifying monitoring roles to implement preventative measures. This achieves a dual guarantee of early warning and prevention, preventing natural disasters caused by adverse geological formations from causing loss of life and property, and ensuring personal and property safety. Attached Figure Description

[0014] Figure 1 This is a schematic flowchart illustrating one embodiment of the traffic guidance method for geological disaster-prone road sections according to this application; Figure 2 This is a schematic diagram of the functional modules of a driving guidance device for geological disaster-prone road sections according to one embodiment of this application; Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of this application; Figure 4 This is a schematic diagram of the structure of one embodiment of the storage medium of this application. Detailed Implementation

[0015] 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 a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0016] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0017] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0018] like Figure 1 As shown, this embodiment provides an example of a driving guidance method for geological disaster road sections. In this embodiment, the geological disaster road section is located on at least one of several interconnected roads within a preset area, and at least one vehicle is traveling on all roads.

[0019] Preferably, geological hazards include landslides, debris flows, rockfalls, and other hazards with significant geological changes.

[0020] Specifically, this driving guidance method includes the following steps: Step S1: The radar image of the preset area is acquired by the small baseline integrated interferometric synthetic aperture radar based on several preset time periods.

[0021] Preferably, the small baseline integrated interferometric synthetic aperture radar is a detection device based on differential interferometry short baseline set temporal deformation and damage analysis technology. This device is usually monitored directly by satellite and does not require manual on-site placement of monitoring equipment.

[0022] Step S2: Analyze the deformation displacement vector of all radar images based on the time series of all radar images.

[0023] Preferably, the time series can proceed synchronously according to a preset time period or a preset number of prediction steps as described below.

[0024] Step S3: Integrate all deformation displacement vectors of the same preset time period into a single vector dataset.

[0025] Preferably, since the deformation process of geological disasters is relatively slow, the preset time period and the preset prediction steps in this embodiment can both be set to any natural duration between one natural hour and one natural day.

[0026] Step S4: Learn and train all vector datasets using an extreme learning machine, and obtain several prediction vector datasets based on a number of preset prediction steps.

[0027] Preferably, the Extreme Learning Model (ELM) is a type of feedforward neural network that can be used to train a single hidden layer. Unlike traditional single-hidden-layer feedforward neural network training algorithms, the ELM randomly selects input layer weights and hidden layer biases. The output layer weights are analytically calculated using the Moore-Penrose (MP) generalized inverse matrix theory, by minimizing a loss function consisting of the training error term and the regularization term of the output layer weight norm. Furthermore, even with randomly generated hidden layer nodes, the ELM maintains the general approximation capability of a single-hidden-layer feedforward neural network.

[0028] Step S5: Based on the time series of all predicted vector datasets, the geological changes of the preset area are simulated by dynamic simulation, and a simulated image is obtained based on a preset number of prediction steps.

[0029] Preferably, the dynamic simulation software capable of implementing step S5 is as follows: ①Abaqus.

[0030] Features: Supports fluid-structure interaction and complex nonlinear deformation modeling, suitable for dynamic response analysis of geotechnical engineering structures.

[0031] Applications: Stress changes during foundation pit excavation, deformation simulation during tunnel construction, etc.

[0032] ② PLAXIS series (2D / 3D).

[0033] Features: Provides 2D / 3D geotechnical engineering finite element analysis, covering deformation, consolidation, seepage and dynamic load simulation, and has built-in multiple constitutive models (such as Mohr-Coulomb and hardened soil models).

[0034] Applications: Slope stability analysis, deformation prediction during the excavation stage of underground engineering, etc.

[0035] ③ GeoStudio.

[0036] Features: Integrates modules such as SIGMA / W (stress-deformation analysis) and QUAKE / W (seismic dynamic analysis), and supports multiphysics coupling calculations.

[0037] Applications: Soil settlement simulation, dynamic assessment of geological hazards (such as landslides).

[0038] ④ FLAC3D.

[0039] Features: Based on the explicit finite difference method, it excels at handling large deformations and nonlinear behavior of geotechnical materials, and is suitable for transient and steady-state analysis.

[0040] Applications: Prediction of surrounding rock deformation and long-term foundation settlement in mining engineering.

[0041] ⑤ MIDAS.

[0042] Features: Combining finite element method and limit equilibrium method, it provides high-precision dynamic simulation function for geotechnical engineering.

[0043] Applications: Analysis of the interaction between bridge foundations and soil, simulation of slope reinforcement effects.

[0044] Step S6: Sequentially determine whether each simulated image intersects with any road along the time series of all predicted vector datasets. If so, proceed to step S7.

[0045] Step S7: Obtain the planned route of the current vehicle and determine whether the planned route passes through an intersection point. If it does, proceed to step S8.

[0046] Step S8: Obtain the road topology of all roads in the preset area, and delete roads with intersection points from the road topology to form a candidate road topology.

[0047] Step S9: In the candidate road topology, take the current vehicle as the path start point and the planned route end point as the path end point, obtain the shortest path and send it to the current vehicle.

[0048] Further, in step S9, the shortest path is obtained from the candidate road topology, with the current vehicle as the path start point and the planned route end point as the path end point, and then sent to the current vehicle. This is followed by the following steps: Step S10: Obtain the earliest future timestamp of whether each simulated image intersects with any road.

[0049] Step S20: Obtain the map coordinates of the intersection point corresponding to the earliest future timestamp and define them as disaster risk coordinates.

[0050] Step S30: Send the disaster risk coordinates and the earliest future timestamp to the external monitoring terminal.

[0051] Preferably, the external monitoring terminals include road administration departments, transportation departments, etc.

[0052] Further, step S2, which involves analyzing the deformation displacement vectors of all radar images based on their time series, specifically includes the following steps: Step S21: Perform atmospheric delay removal and orbital error removal on all radar images to obtain accurate SAR data based on a single radar image.

[0053] Step S22: Based on two adjacent preset time period differences, two precise SAR data are obtained to obtain an interferometric image.

[0054] Step S23: Obtain the digital elevation model of the preset area, assign the digital elevation model to all interferometric images, and obtain an interferometric coordinate set based on an interferometric image.

[0055] Step S24: Generate several differential interferograms based on all interferometric coordinate sets along the time series of all radar images.

[0056] Step S25: Unwrap the phase information of each differential interferogram to obtain all surface deformation phase data of the preset area.

[0057] Step S26: Convert all surface deformation phase data into map coordinates and fuse them with the digital elevation model to obtain surface deformation coordinate data.

[0058] Step S27: Analyze all surface deformation coordinate data to obtain all deformation displacement vectors.

[0059] For example, in practical applications of step S2 and its sub-steps, the following operations can be performed: ① Data preprocessing and selection of interferential pairs: Data import and registration: Import all radar images (such as Sentinel-1A data) into processing software (such as SARscape), select common master images for registration, and ensure spatial consistency between images.

[0060] Multi-master image grouping: Based on spatiotemporal baseline thresholds (e.g., temporal baseline ≤ 120 days, spatial baseline ≤ 10% of the maximum baseline), the image is divided into multiple interferometric subsets to reduce the impact of decoherence.

[0061] Terrain phase removal: The terrain phase is simulated using an external DEM, and the terrain contribution is subtracted from the original interferometric phase to generate a differential interferogram.

[0062] ② Interference processing and phase unwrapping: Generate differential interferometric atlases: Perform differential interferometry processing on each subset of interferometry to form a time-series differential interferometric atlas, which includes deformation, atmospheric delay, and noise phase.

[0063] Multi-view processing: Reduces phase noise and improves signal-to-noise ratio through multi-view operation.

[0064] Phase unwrapping: Using the minimum cost flow or SVD (singular value decomposition) method, the differential interference phase is unwrapped to separate the continuous deformation phase information.

[0065] ③ Error correction and deformation modeling: Atmospheric delay correction: Removes atmospheric phase effects through spatiotemporal filtering or meteorological data modeling.

[0066] Track error correction: Eliminate residual track errors using polynomial models or precise track data.

[0067] Deformation rate inversion: Based on the linear deformation assumption, a time series deformation equation is constructed, and the average deformation rate of each pixel is solved by the least squares method.

[0068] Time series deformation extraction: Combine the SVD method to jointly solve multiple interference subsets to obtain high-resolution time series deformation displacement vectors.

[0069] ④ Results Validation and Optimization: Cross-validation: Compare results from different interferometric subsets or PS-InSAR to verify the consistency of deformation.

[0070] Parameter optimization: Adjust parameters such as spatiotemporal baseline threshold and multi-view coefficient to optimize deformation monitoring accuracy.

[0071] ⑤ Technical implementation tools and data requirements: Software support: Commonly used tools include SARscape, GMTSAR, etc., which support automated processing workflows.

[0072] Data requirements: SAR images with continuous coverage (such as Sentinel-1A data) are required. The longer the time span and the more images (≥15 scenes recommended), the more reliable the results will be.

[0073] Hardware requirements: High-performance computing resources are required, and parallel computing support is needed when processing massive amounts of data.

[0074] Key points to note: Spatiotemporal baseline balancing: An excessively large baseline can lead to incoherence, so a reasonable threshold needs to be set to balance data utilization and quality.

[0075] Deformation model adaptability: For different settlement mechanisms (such as embankment consolidation, tectonic activity), it is necessary to select an appropriate time function (such as an exponential decay model).

[0076] Error control: Atmospheric and orbital errors are the main sources of interference and need to be combined with multi-source data (such as GNSS) for joint correction.

[0077] Further, in step S9, the shortest path is obtained from the candidate road topology, with the current vehicle as the path start point and the planned route end point as the path end point, and then sent to the current vehicle. This is followed by the following steps: Step S100: Obtain the ratio of the length of the congested section to the total length of the shortest path based on external navigation software.

[0078] Preferably, slow traffic can be considered as no congestion, and the color-coding function of external navigation software to distinguish the degree of congestion can be incorporated into this embodiment, where a red marker on a road segment is considered congested.

[0079] Step S200: Determine whether the length ratio is greater than or equal to the preset ratio threshold. If so, proceed to step S300.

[0080] Preferably, the preset ratio threshold is set to 0.5, meaning that when the length of the congested road segment reaches half of the total length, this road is no longer recommended.

[0081] Step S300: Remove the shortest path from the candidate road topology to obtain the filtered candidate road topology.

[0082] Step S400: In the filtered candidate road topology, the second shortest path is obtained with the current vehicle as the path start point and the planned route end point as the path end point.

[0083] In step S500, the second shortest path is used as the execution subject, and steps S100 to S400 are repeated until the length ratio of the second shortest path after iteration is less than the preset ratio threshold.

[0084] Step S600: Send the next shortest path after the iteration to the current vehicle.

[0085] Preferably, since the degree of road topology is uncontrollable, this embodiment selects a better second shortest path through iteration.

[0086] Further, in step S600, the next shortest path after the iteration is sent to the current vehicle, followed by the following steps: Step S1000: Send the next shortest path after iteration to the external security monitoring terminal.

[0087] Step S2000: Continuously acquire the real-time map location of the current vehicle.

[0088] Step S3000: Determine whether the real-time map location has reached the end of the path. If so, proceed to step S4000.

[0089] Step S4000: Remove the next shortest path after the iteration from the external security monitoring terminal.

[0090] Preferably, steps S1000 to S4000 are designed to prevent additional geological hazards from affecting safety.

[0091] Further, in step S9, the shortest path is obtained from the candidate road topology, with the current vehicle as the starting point and the planned route's ending point as the ending point, and then sent to the current vehicle. This specifically includes the following steps: Step S91: Extract the road boundaries of the candidate road topology using a boundary extraction algorithm.

[0092] Step S92: Divide the digital elevation model using square grids of preset density.

[0093] Step S93: Obtain all square grids within all road boundaries and define them as candidate grid sets.

[0094] Step S94: Define each square grid cell in the candidate grid set as a node.

[0095] Step S95: Calculate the minimum number of grid cells required to reach the end point of the path from the starting point using the A_star algorithm.

[0096] Preferably, the path search algorithm in this embodiment can be selected from depth-first search, breadth-first search, Dijstra's shortest path algorithm, Floyd's shortest path algorithm, greedy algorithm, A* algorithm, etc. One of the algorithms.

[0097] Step S96: Obtain the grid corresponding to the minimum number of grid cells, and connect them sequentially to form the shortest path.

[0098] This embodiment acquires radar images of a preset area using a small baseline integrated interferometric synthetic aperture radar (SAIL) over several preset time periods. It then analyzes the deformation displacement vectors of all radar images based on their time series. All deformation displacement vectors from the same preset time period are integrated into a single vector dataset. An extreme learning machine is used to learn and train all vector datasets, resulting in several predicted vector datasets based on several preset prediction steps. Based on the time series of all predicted vector datasets, dynamic simulation is used to model the geological changes in the preset area, generating a simulated image based on one preset prediction step. The time series of all predicted vector datasets is used to sequentially determine whether each simulated image intersects with any road. If so, the planned route of the current vehicle is obtained, and it is determined whether the planned route passes through an intersection point. If it does, the road topology of all roads in the preset area is obtained, and roads with intersection points are removed from the road topology to form a candidate road topology. In the candidate road topology, the shortest path is obtained with the current vehicle as the starting point and the planned route's ending point as the ending point, and this path is sent to the current vehicle. This embodiment leverages the visual and analytical capabilities of a small baseline integrated interferometric synthetic aperture radar (SAMR), combined with an extreme learning machine (ELM) that has good vector compatibility, to further analyze potential geological hazards that have not yet occurred. This allows for proactive prevention, and once a potential geological risk is predicted, it alerts vehicles to change routes in a timely manner while simultaneously notifying monitoring personnel to take preventative measures. This achieves a double insurance of early warning and prevention, preventing natural disasters caused by adverse geological formations from causing losses to life and property, and ensuring personal and property safety.

[0099] like Figure 2 As shown, this embodiment provides an example of a traffic guidance device for road sections prone to geological disasters. In this embodiment, the traffic guidance device is applied to the traffic guidance method described in the above embodiment.

[0100] Specifically, the driving guidance device includes a preset area radar image acquisition module 1, a deformation displacement vector analysis module 2, a vector dataset integration module 3, a prediction vector dataset acquisition module 4, a prediction vector dataset simulation module 5, a simulated image motion judgment module 6, a planned route acquisition and judgment module 7, an alternative road topology acquisition module 8, and a shortest path acquisition and transmission module 9, which are connected in sequence.

[0101] The system comprises the following modules: a preset area radar image acquisition module 1, which acquires radar images of a preset area using a small baseline integrated interferometric synthetic aperture radar (IASAR) over several preset time periods; a deformation displacement vector analysis module 2, which analyzes the deformation displacement vectors of all radar images based on their time series; a vector dataset integration module 3, which integrates all deformation displacement vectors from the same preset time period into a single vector dataset; a prediction vector dataset acquisition module 4, which learns and trains all vector datasets using an extreme learning machine (ELM) to obtain several prediction vector datasets based on several preset prediction steps; and a prediction vector dataset simulation module 5, which simulates the geological changes of the preset area using dynamic simulation based on the time series of all prediction vector datasets. The system generates a simulated image based on a preset number of prediction steps. The simulated image motion judgment module 6 is used to sequentially determine whether each simulated image intersects with any road along the time series of all prediction vector datasets. The planned route acquisition and judgment module 7 is used to acquire the planned route of the current vehicle and determine whether the planned route passes through an intersection point if so. The alternative road topology acquisition module 8 is used to acquire the road topology of all roads in the preset area if so, and delete the roads with intersection points from the road topology to form alternative road topologies. The shortest path acquisition and sending module 9 is used to acquire the shortest path in the alternative road topology with the current vehicle as the path start point and the planned route end point as the path end point, and send it to the current vehicle.

[0102] Furthermore, the driving guidance device also includes an earliest future timestamp acquisition module, a disaster risk coordinate definition module, and a disaster risk coordinate and earliest future timestamp transmission module that are electrically connected in sequence; the earliest future timestamp acquisition module is electrically connected to the shortest path acquisition and transmission module 9.

[0103] The earliest future timestamp acquisition module is used to obtain the earliest future timestamp of whether each simulated image intersects with any road; the disaster risk coordinate definition module is used to obtain the map coordinates of the intersection point corresponding to the earliest future timestamp and define them as disaster risk coordinates; the disaster risk coordinate and earliest future timestamp sending module is used to send the disaster risk coordinate and the earliest future timestamp to the external monitoring terminal.

[0104] Furthermore, the prediction vector dataset acquisition module 4 specifically includes a first prediction vector dataset acquisition submodule, a second prediction vector dataset acquisition submodule, a third prediction vector dataset acquisition submodule, a fourth prediction vector dataset acquisition submodule, a fifth prediction vector dataset acquisition submodule, and a sixth prediction vector dataset acquisition submodule that are electrically connected in sequence; the first prediction vector dataset acquisition submodule is electrically connected to the vector dataset integration module 3, and the sixth prediction vector dataset acquisition submodule is electrically connected to the prediction vector dataset simulation module 5.

[0105] The module comprises six submodules: a first submodule for obtaining a predicted vector dataset, a second submodule for obtaining a predicted vector dataset, a third submodule for obtaining a predicted vector dataset, a fourth submodule for obtaining a predicted vector dataset, a fifth submodule for obtaining a predicted vector dataset, a sixth submodule for obtaining a predicted vector dataset, and a seventh submodule for obtaining a predicted vector dataset. The sixth submodule is used to reconstruct a predicted vector dataset from each predicted vector dataset using the inverse vector normalization operation.

[0106] Furthermore, the driving guidance device also includes a congestion section percentage acquisition module, a congestion section percentage judgment module, a candidate road topology screening module, a second shortest path acquisition module, a second shortest path iteration module, and an iterated second shortest path sending module, which are connected in sequence; the congestion section percentage acquisition module is electrically connected to the shortest path acquisition and sending module 9.

[0107] The system comprises the following modules: a congestion segment percentage acquisition module, which uses external navigation software to obtain the ratio of the length of the congested segment to the total length of the shortest path; a congestion segment percentage judgment module, which determines whether the ratio is greater than or equal to a preset threshold; a candidate road topology filtering module, which removes the shortest path from the candidate road topology if the ratio is greater than or equal to a preset threshold; a second shortest path acquisition module, which obtains the second shortest path from the filtered candidate road topology, using the current vehicle as the starting point and the planned route's ending point as the ending point; a second shortest path iteration module, which repeatedly executes the congestion segment percentage acquisition module and the second shortest path acquisition module using the second shortest path as the execution subject, until the ratio of the length of the second shortest path after iteration is less than a preset threshold; and a second shortest path sending module, which sends the second shortest path after iteration to the current vehicle.

[0108] Furthermore, the driving guidance device also includes an iterative second shortest path safety monitoring module, a vehicle real-time map location acquisition module, a vehicle real-time trip judgment module, and an iterative second shortest path removal module, which are connected in sequence and electrically. The iterative second shortest path safety monitoring module is electrically connected to the iterative second shortest path sending module.

[0109] Among them, the iteration-based second shortest path safety monitoring module is used to send the iteration-based second shortest path to the external safety monitoring terminal; the vehicle real-time map location acquisition module is used to continuously acquire the current vehicle's real-time map location.

[0110] The vehicle real-time route determination module is used to determine whether the real-time map location has reached the end of the path; if so, the iteration-after-shortest-path removal module will remove the iteration-after-shortest-path from the external safety monitoring terminal.

[0111] Furthermore, the shortest path acquisition and transmission module 9 specifically includes a first shortest path acquisition and transmission submodule, a second shortest path acquisition and transmission submodule, a third shortest path acquisition and transmission submodule, a fourth shortest path acquisition and transmission submodule, a fifth shortest path acquisition and transmission submodule, and a sixth shortest path acquisition and transmission submodule, which are electrically connected in sequence; the first shortest path acquisition and transmission submodule is electrically connected to the alternative road topology acquisition module 8.

[0112] The first shortest path acquisition and transmission submodule is used to extract the road boundaries of the candidate road topology using a boundary extraction algorithm; the second shortest path acquisition and transmission submodule is used to divide the digital elevation model using square grids of a preset density; the third shortest path acquisition and transmission submodule is used to acquire all square grids within all road boundaries and define them as a candidate grid set; the fourth shortest path acquisition and transmission submodule is used to define each square grid in the candidate grid set as a node; the fifth shortest path acquisition and transmission submodule is used to calculate the minimum number of grids required to reach the end point of the path from the starting point using the A_star algorithm; and the sixth shortest path acquisition and transmission submodule is used to acquire the grids corresponding to the minimum number of grids and connect them sequentially to form the shortest path.

[0113] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. For the preferred, extended, limited, exemplified and principle explanation parts of this embodiment, please refer to the above embodiment. This embodiment will not repeat them.

[0114] This embodiment acquires radar images of a preset area using a small baseline integrated interferometric synthetic aperture radar (SAIL) over several preset time periods. It then analyzes the deformation displacement vectors of all radar images based on their time series. All deformation displacement vectors from the same preset time period are integrated into a single vector dataset. An extreme learning machine is used to learn and train all vector datasets, resulting in several predicted vector datasets based on several preset prediction steps. Based on the time series of all predicted vector datasets, dynamic simulation is used to model the geological changes in the preset area, generating a simulated image based on one preset prediction step. The time series of all predicted vector datasets is used to sequentially determine whether each simulated image intersects with any road. If so, the planned route of the current vehicle is obtained, and it is determined whether the planned route passes through an intersection point. If it does, the road topology of all roads in the preset area is obtained, and roads with intersection points are removed from the road topology to form a candidate road topology. In the candidate road topology, the shortest path is obtained with the current vehicle as the starting point and the planned route's ending point as the ending point, and this path is sent to the current vehicle. This embodiment leverages the visual and analytical capabilities of a small baseline integrated interferometric synthetic aperture radar (SAMR), combined with an extreme learning machine (ELM) that has good vector compatibility, to further analyze potential geological hazards that have not yet occurred. This allows for proactive prevention, and once a potential geological risk is predicted, it alerts vehicles to change routes in a timely manner while simultaneously notifying monitoring personnel to take preventative measures. This achieves a double insurance of early warning and prevention, preventing natural disasters caused by adverse geological formations from causing losses to life and property, and ensuring personal and property safety.

[0115] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0116] The memory 102 stores program instructions for implementing a fault detection method for an oil-immersed transformer according to any of the above embodiments.

[0117] The processor 101 is used to execute program instructions stored in the memory 102 to perform fault detection of the oil-immersed transformer.

[0118] The processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with signal processing capabilities. The processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0119] Furthermore, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of this application. In this embodiment, the storage medium 11 stores program instructions 111 capable of implementing all the above-described methods. These program instructions 111 can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in 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, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of 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 system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0121] 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 units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the protection scope of this application.

Claims

1. A method for guiding traffic on a geological disaster-prone road section, wherein the geological disaster-prone road section is located on at least one of several interconnected roads within a preset area, and at least one vehicle is traveling on all roads, characterized in that, The driving guidance method includes: Step S1: The radar image of the preset area is acquired by small baseline integrated interferometric synthetic aperture radar based on several preset time periods. Step S2: Analyze the deformation displacement vector of all radar images based on the time series of all radar images; Step S3: Integrate all deformation displacement vectors of the same preset time period into a single vector dataset; Step S4: Learn and train all vector datasets using an extreme learning machine, and obtain several prediction vector datasets based on a number of preset prediction steps; Step S5: Based on the time series of all predicted vector datasets, the geological changes of the preset area are simulated by dynamic simulation, and a simulated image is obtained based on a preset number of prediction steps; Step S6: Sequentially determine whether each simulated image intersects with any road along the time series of all predicted vector datasets. If so, proceed to step S7. Step S7: Obtain the planned route of the current vehicle and determine whether the planned route passes through the intersection point. If it does, proceed to step S8. Step S8: Obtain the road topology of all roads in the preset area, and delete the roads with the intersection points from the road topology to form a candidate road topology; Step S9: In the candidate road topology, with the current vehicle as the path start point and the planned route end point as the path end point, obtain the shortest path and send it to the current vehicle.

2. The driving guidance method according to claim 1, characterized in that, Step S9: In the candidate road topology, using the current vehicle as the path start point and the planned route's end point as the path end point, obtain the shortest path and send it to the current vehicle. Then, the process includes: Step S10: Obtain the earliest future timestamp of whether each simulated image intersects with any road; Step S20: Obtain the map coordinates of the intersection point corresponding to the earliest future timestamp, and define them as disaster occurrence risk coordinates; Step S30: Send the disaster risk coordinates and the earliest future timestamp to the external monitoring terminal.

3. The driving guidance method according to claim 1, characterized in that, Step S9: In the candidate road topology, using the current vehicle as the path start point and the planned route's end point as the path end point, obtain the shortest path and send it to the current vehicle. Then, the process includes: Step S100: Obtain the ratio of the length of the congested section to the total length of the shortest path based on external navigation software; Step S200: Determine whether the length ratio is greater than or equal to a preset ratio threshold. If so, proceed to step S300. Step S300: Remove the shortest path from the candidate road topology to obtain the filtered candidate road topology; Step S400: In the filtered candidate road topology, the second shortest path is obtained with the current vehicle as the path start point and the planned route end point as the path end point. Step S500: Repeat steps S100 to S400 with the second shortest path as the execution subject until the length ratio of the second shortest path after iteration is less than the preset ratio threshold. Step S600: Send the next shortest path after the iteration to the current vehicle.

4. The driving guidance method according to claim 3, characterized in that, Step S600: Send the iteratively shortest path to the current vehicle, followed by: Step S1000: Send the iteratively shortest path to the external security monitoring terminal; Step S2000: Continuously acquire the real-time map location of the current vehicle; Step S3000: Determine whether the real-time map location has reached the end of the path. If so, proceed to step S4000. Step S4000: Remove the iteratively shortest path from the external security monitoring terminal.

5. The driving guidance method according to claim 1, characterized in that, Step S9, in the candidate road topology, using the current vehicle as the path start point and the planned route's end point as the path end point, obtain the shortest path and send it to the current vehicle, including: Step S91: Extract the road boundaries of the candidate road topology using a boundary extraction algorithm; Step S92: Divide the digital elevation model using square grids of preset density; Step S93: Obtain all square grids within all road boundaries and define them as candidate grid sets; Step S94: Define each square grid cell in the candidate grid set as a node; Step S95: Calculate the minimum number of grid cells required to reach the end point of the path from the starting point using the A_star algorithm; Step S96: Obtain the grid corresponding to the minimum number of grids, and connect them sequentially to form the shortest path.

6. A traffic guidance device for road sections prone to geological disasters, wherein the traffic guidance device is applied to the traffic guidance method as described in any one of claims 1 to 5, characterized in that, The driving guidance device includes: A preset area radar image acquisition module is used to acquire radar images of the preset area based on several preset time periods using a small baseline integrated interferometric synthetic aperture radar. The deformation displacement vector analysis module is used to analyze the deformation displacement vector of all radar images based on the time series of all radar images. The vector dataset integration module is used to integrate all deformation displacement vectors within the same preset time period into a single vector dataset. The prediction vector dataset acquisition module is used to learn and train all vector datasets through extreme learning machine, and obtain several prediction vector datasets based on several preset prediction steps; The prediction vector dataset simulation module is used to dynamically simulate the geological changes of the preset area based on the time series of all prediction vector datasets, and obtain a simulated image based on a preset number of prediction steps. The simulated image motion determination module is used to sequentially determine whether each simulated image intersects with any road along the time series of all predicted vector datasets; The planned route acquisition and judgment module is used to acquire the planned route of the current vehicle and determine whether the planned route passes through the intersection point if the condition is met. The alternative road topology acquisition module is used to acquire the road topology of all roads in the preset area if the area is traversed, and to delete the roads with the intersection points from the road topology to form alternative road topologies. The shortest path acquisition and transmission module is used to acquire the shortest path in the candidate road topology with the current vehicle as the path start point and the planned route as the path end point, and then send it to the current vehicle.

7. An electronic device, characterized in that, The method includes a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the vehicle guidance method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores program instructions, which, when executed by a processor, can implement the vehicle guidance method as described in any one of claims 1 to 5.

Images