Intelligent fill deformation sensing system and method based on hydraulic characteristics of collapsible loess

Abstract

The invention relates to the technical field of online monitoring, in particular to an intelligent fill deformation sensing system and method based on hydraulic characteristics of collapsible loess, and the method comprises the steps: evaluating the brittleness of a loess structure based on characteristic data of collapsible loess, and obtaining a brittleness index of the loess structure; constructing a collapsibility risk assessment model, and importing the loess structure brittleness index, hydraulic characteristic data in the fill body and soil dynamic response data in the deformation process of the fill body into the collapsibility risk assessment model to obtain a collapsibility risk index; judging whether to position a water source intrusion point according to the collapse risk index, constructing a water source intrusion positioning model, and tracing the water source intrusion point; and visualizing the collapse risk index and the positioned coordinates of the water source invasion point to a fill early warning platform in real time. The problems that in the prior art, only the deformation consequence can be passively dealt with, an early predictive intervention strategy is lacked, and early quantitative early warning and deformation intervention of the collapse risk cannot be achieved are solved.

Description

Technical Field

[0001] This invention relates to the field of online monitoring technology, specifically to an intelligent sensing system and method for fill deformation based on the hydraulic characteristics of collapsible loess. Background Technology

[0002] In collapsible loess areas, embankment projects are prone to sudden deformation under waterlogging conditions. Existing monitoring technologies have the following limitations: current methods mainly rely on surface displacement measurements (such as total stations and InSAR) and point-based pore water pressure monitoring, making it difficult to capture the dynamic processes of hydraulic-mechanical coupling within the embankment. The fundamental problems include: collapsible loess contains closed air cavities formed by sedimentary history, which are caused by air trapped between soil aggregates by cementing materials. When water invades, the cementing materials dissolve, exposing the air cavities, which then migrate under seepage drive; simultaneously, sudden changes in pore water pressure trigger the collapse of these air cavities, producing localized cavitation effects and accelerating the disintegration of the soil structure. Existing technologies lack effective monitoring of cavitation dynamics (collapse frequency, sound pressure amplitude) and moisture migration trajectories, and cannot quantify cavitation damage energy (such as the cavitation power index in the patent), resulting in an inability to predict the sudden risk of structural damage. In addition, existing deformation monitoring only focuses on macroscopic displacement or single pore water pressure values, ignoring dynamic parameters such as abrupt changes in soil matrix suction and pore water pressure gradients. These parameters directly reflect the instantaneous impact intensity of water intrusion on cemented structures and are key precursor signals for inducing collapse. When surface displacement of collapsible loess occurs, internal damage is already irreversible. At the same time, existing monitoring methods cannot trace the water intrusion point in reverse, resulting in an inability to specifically block seepage paths. They can only passively respond to deformation consequences, lacking early predictive intervention strategies, and cannot achieve early quantitative warning and deformation intervention for collapse risks. Summary of the Invention

[0003] The technical problem to be solved by this invention is that existing technologies can only passively respond to deformation consequences, lack early predictive intervention strategies, and cannot achieve early quantitative warning and deformation intervention of collapsibility risk. This invention proposes an intelligent sensing system and method for fill deformation based on the hydraulic characteristics of collapsible loess.

[0004] To achieve the above objectives, the technical solution of the intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess of the present invention includes the following steps: S1: Obtain characteristic data of collapsible loess, hydraulic characteristic data of the interior of the fill, and soil dynamic response data during the deformation process of the fill; S2: Based on the collapsible loess characteristic data obtained in S1, the structural brittleness of loess is assessed, and the structural brittleness index of loess is obtained. S3: Construct a collapsibility risk assessment model, and import the loess structural brittleness index, hydraulic characteristic data inside the fill body, and soil dynamic response data during the deformation process of the fill body output by S2 into the collapsibility risk assessment model to conduct fill deformation risk assessment and obtain the collapsibility risk index. S4: Determine whether to locate the water intrusion point based on the subsidence risk index. If the determination is yes, proceed to S5; if the determination is no, end the process. S5: Construct a water intrusion location model, and import the hydraulic characteristic data and soil dynamic response data obtained in S1 into the water intrusion location model to trace the source of water intrusion. S6: Visualize the collapse risk index and the coordinates of the located water intrusion point output in step S3 to the filling early warning platform in real time.

[0005] Furthermore, S1 includes: S11: Obtain characteristic data of collapsible loess, wherein the characteristic data of collapsible loess includes: cement erosion rate data; S12: Obtain hydraulic characteristic data inside the fill body, including seepage parameters of the fill body including: collapse data of closed air cavities of several layered monitoring units and water migration trajectory data of the fill body, including collapse data of closed air cavities including: collapse frequency and sound pressure amplitude data, and water migration trajectory data including: air cavity migration rate and three-dimensional spatial coordinate data. S13: Obtain soil dynamic response data during the deformation process of the fill body, including: soil matrix suction abrupt change value, pore water pressure gradient and soil microseismic acceleration data; S14: Store the data obtained in steps S11, S12 and S13 in a distributed data network.

[0006] Furthermore, in S2, the structural brittleness of loess is assessed, including: Based on the cementitious erosion rate data obtained in step S11, the loess structural brittleness index, which characterizes the sensitivity of the internal structure of the collapsible loess fill to water intrusion, is calculated. Specifically: ; Where p is the number of monitoring layers, and k represents the kth layer monitoring unit; in, The measured dissolution rate of the kth layer of cementitious material reflects the chemical erosion capability of water. The average rate of cementitious erosion across all monitored layers; These represent the maximum and minimum cementitious erosion rates among all monitored layers.

[0007] Furthermore, in S3, a risk assessment of fill deformation is conducted to obtain a collapse risk index, including: S31: Extract the closed air cavity collapse data of several layered monitoring units collected in step S12, and simultaneously extract the water migration trajectory data of the fill body collected in step S12 and import it into the air cavity cavitation power index calculation strategy to calculate the air cavity cavitation power index. S32: Obtain soil dynamic response data, import the soil dynamic response data into the cementation failure index calculation strategy, and calculate the cementation failure index. S33: Cavitation power index calculated based on step S31 Calculate the cavitation damage strain rate of collapsible loess ; The cementation failure index calculated in step S32 Calculate the cementation damage strain rate of collapsible loess ; S34: Extract the loess structural brittleness index calculated in step S2. The cavitation damage strain rate of loess calculated in step S33 and cementation damage strain rate The extracted data is input into the collapse risk assessment model to assess the risk of fill deformation and obtain the collapse risk index. The output strategy of the collapse risk assessment model is as follows: ; in, This is the collapse risk index output by the collapse risk assessment model.

[0008] Furthermore, in S4, the determination of whether to locate the water intrusion point is based on the subsidence risk index includes: The obtained subsidence risk index is compared with the set subsidence risk threshold. If the obtained subsidence risk index is greater than or equal to the set subsidence risk threshold, the water intrusion point needs to be located and step S5 is continued. If the obtained subsidence risk index is less than the set subsidence risk threshold, the water intrusion point does not need to be located and monitoring continues.

[0009] Furthermore, S5 includes: S51: Map the spatial location of each data acquisition point to a dynamic grid node. For the same batch of air cavity collapse events monitored, extract the sound pressure energy value of each grid node. Calculate the energy decay gradient vector of target node i relative to its spatially neighboring nodes j, k, m. ; S52: For each grid node, trace back along the opposite direction of its energy decay gradient vector. On the tracing path, calculate in real time the rate of energy change between adjacent points as a function of distance. When a certain point is detected The rate of energy change exceeded the threshold for the first time. They were marked as candidate air cavity collapse sources; Synchronous check If the rate of change of energy at a point is greater than or equal to twice the average value of its neighboring region, then ignore the candidate point and continue tracing along the path until a point that meets the conditions is found or the boundary is reached. S53: Candidate collapse sources located in step S52 Starting from this point, trace back the grid nodes in the direction of their energy source. • Calculate the energy decay gradient vectors pointed to by these upstream nodes, and determine the values ​​pointed to by these upstream nodes. The average direction of the energy decay gradient vector.

[0010] Adjusting along the vector average direction, we continue to search for the peak point of the rate of change of the energy field distribution, which is then identified as the final source of gas cavity collapse. ; Calculate the final air cavity collapse source The ratio of the energy change rate to the energy change threshold is used as the final gas cavity collapse source. The confidence level.

[0011] Furthermore, S54: as the final air cavity collapse source Centered on the soil dynamic response data acquired in real time, the infiltration front of the region was simulated, and the curvature distribution of the infiltration front in space was analyzed by the spatial difference method. Determine the direction in which the radius of curvature of the wetting front decreases most rapidly. , as the direction of water intrusion; S55: Along the water intrusion direction determined in step S54 From the source of the final air cavity collapse The extension process begins, with the extension length set to 1.2 times the length of the maximum migration trajectory observed in this batch of air cavity collapse events; The obtained extension endpoint is used as the predicted water intrusion point. ; S56: Verify predicted water intrusion points Whether it is located at the edge of a dynamic mesh or in a known risk area, specifically including: If water source intrusion point If the point is within the effective monitoring area and nearby sensor data supports the existence of abnormal seepage, then the verification is successful and the location is confirmed.

[0012] If the predicted water intrusion point If the data is outside the grid range or there is no supporting data nearby, the verification fails and a secondary traceback is initiated, including: tracing back to step S53, attempting to relocate the collapse source with the second highest confidence, and repeatedly executing steps S54 and S55 until the output verification is successful, at which point the loop stops.

[0013] In addition, the intelligent sensing system for fill deformation based on the hydraulic properties of collapsible loess of this invention includes the following modules: The system includes modules for data acquisition, loess brittleness assessment, collapsibility risk assessment, location determination, water intrusion point tracing, and visualization. The data acquisition module is used to acquire characteristic data of collapsible loess, hydraulic characteristic data of the interior of the fill body, and soil dynamic response data during the deformation process of the fill body. The loess brittleness assessment module assesses the structural brittleness of loess based on the characteristic data of collapsible loess, and obtains the loess structural brittleness index; The collapse risk assessment module is used to construct a collapse risk assessment model and import the loess structural brittleness index, hydraulic characteristic data of the fill body, and soil dynamic response data during the deformation process of the fill body into the collapse risk assessment model to conduct fill deformation risk assessment and obtain the collapse risk index. The positioning judgment module determines whether to locate the water intrusion point based on the sinkhole risk index. If the judgment is yes, the water intrusion point tracing module is run; if the judgment is no, the process ends. The water intrusion point tracing module is used to construct a water intrusion location model and import hydraulic characteristic data and soil dynamic response data into the water intrusion location model to trace the water intrusion point. The visualization module is used to visualize the collapse risk index and the coordinates of the located water intrusion points to the reclamation early warning platform in real time.

[0014] A storage medium storing instructions, which, when read by a computer, cause the computer to execute the intelligent sensing method for fill deformation based on the hydraulic characteristics of collapsible loess.

[0015] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess.

[0016] Compared with the prior art, the technical effects of the present invention are as follows: 1. This invention integrates the inherent cement erosion rate of collapsible loess, the collapse data of closed air cavities in the hydraulic process inside the fill body, the water migration trajectory data, and the soil dynamic response data induced by deformation; it overcomes the limitations of single-index monitoring, and can more comprehensively and sensitively capture the early induction mechanism and dynamic evolution process of collapsible deformation, significantly improving the accuracy and timeliness of collapsible risk identification, and buying valuable time for engineering intervention.

[0017] 2. This invention visualizes the calculated collapse risk index, the three-dimensional coordinates of the located water intrusion points, and their key source parameters in real time on the backfill early warning platform. This enables engineering managers to intuitively grasp the overall risk situation, quickly identify high-risk areas and water intrusion sources, and provides strong data support and decision-making basis for taking targeted and differentiated prevention and control measures (such as local drainage and seepage prevention reinforcement), greatly improving the intelligence and precision of engineering safety management. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a flowchart illustrating the intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess according to the present invention. Figure 2 This is a flowchart illustrating step S3 of the present invention; Figure 3 This is a flowchart illustrating step S5 of the present invention; Figure 4 This is a schematic diagram of the intelligent sensing system for fill deformation based on the hydraulic properties of collapsible loess according to the present invention. Detailed Implementation

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1:

[0023] like Figure 1 As shown in the figure, the intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess in this invention embodiment is as follows: Figure 1 As shown, the specific steps include the following: S1: Obtain characteristic data of collapsible loess, hydraulic characteristic data of the interior of the fill, and soil dynamic response data during the deformation process of the fill; S11: Obtain characteristic data of collapsible loess, wherein the characteristic data of collapsible loess includes: cement erosion rate data; S12: Obtain hydraulic characteristic data inside the fill body, including seepage parameters of the fill body including: collapse data of closed air cavities of several layered monitoring units and water migration trajectory data of the fill body, including collapse data of closed air cavities including: collapse frequency and sound pressure amplitude data, and water migration trajectory data including: air cavity migration rate and three-dimensional spatial coordinate data. S13: Obtain soil dynamic response data during the deformation process of the fill body, including: soil matrix suction abrupt change value, pore water pressure gradient and soil microseismic acceleration data; S14: Store the data obtained in steps S11, S12 and S13 in a distributed data network.

[0024] S2: Based on the collapsible loess characteristic data obtained in S1, the structural brittleness of loess is assessed, and the structural brittleness index of loess is obtained. Based on the cementitious erosion rate data obtained in step S11, the loess structural brittleness index, which characterizes the sensitivity of the internal structure of the collapsible loess fill to water intrusion, is calculated. Specifically: ; Where p is the number of monitoring layers, and k represents the kth layer monitoring unit; in, The measured dissolution rate of the kth layer of cementitious material reflects the chemical erosion capability of water. The average rate of cementitious erosion across all monitored layers; These represent the maximum and minimum cementitious erosion rates among all monitored layers.

[0025] S3: Construct a collapsibility risk assessment model, and import the loess structural brittleness index, hydraulic characteristic data inside the fill body, and soil dynamic response data during the deformation process of the fill body output by S2 into the collapsibility risk assessment model to conduct fill deformation risk assessment and obtain the collapsibility risk index. like Figure 3 As shown, S31: Extract the closed air cavity collapse data of several layered monitoring units collected in step S12, and simultaneously extract the water migration trajectory data of the fill body collected in step S12 and import it into the air cavity cavitation power index calculation strategy to calculate the air cavity cavitation power index. For example, in this embodiment, a calculation strategy for the cavitation power index is provided, specifically as follows: ; in, It is the cavitation power index, which characterizes the damage caused by wet collapse; p represents the number of monitoring layers, and q represents the number of sensors per layer; The distance from the l-th sensor in the k-th layer to the center of curvature of the wetting front is [missing information]. This is the sound pressure amplitude weighting coefficient; Let l be the sound pressure amplitude of the l-th sensor in the k-th layer. ρ is the soil density of collapsible loess, c is the speed of sound; S is the nominal receiving area of ​​the sensor. Let be the air cavity collapse frequency of the l-th sensor in the k-th layer; Energy released by the collapse of a single air cavity in collapsible loess (obtained through laboratory data calibration). It should be noted that, regarding acoustic items , among them Sound energy flux density (sound intensity) is the sound power per unit area; the nominal receiving area S of the sensor is intended to convert the power per unit area into total power. It should also be noted that, for energy terms... This represents the total power released by all collapsing gas chambers per unit time; for the spatial weighting factor... The distance from the sensor to the center of curvature of the immersion front is used as the weight. The smaller the distance, the greater the weight, reflecting the near-field effect. The 0.1 in the denominator is a regularization constant to avoid the weight being infinite when the distance is zero.

[0026] S32: Obtain soil dynamic response data, import the soil dynamic response data into the cementation failure index calculation strategy, and calculate the cementation failure index. For example, in this embodiment, a strategy for obtaining the cementation failure index is provided, specifically as follows: ; in, The cementation failure index; This represents the abrupt change in suction force of the k-th matrix layer, reflecting the intensity of hydraulic impact. Let be the pore water pressure gradient of the k-th layer, which drives water infiltration; The cementation strength of the k-th layer of loess characterizes the ability of the fill to resist structural failure. It should be noted that the molecular part of the strategy for obtaining the cementation failure index is quantified by the product of the matrix suction abrupt change value and the pore water pressure gradient, which together constitute the hydraulic erosion force. S33: Cavitation power index calculated based on step S31 Calculate the cavitation damage strain rate of collapsible loess ; For example, in this embodiment, a cavitation damage strain rate of collapsible loess is provided. The acquisition strategy is as follows: ; The volume of soil in the fill is [the volume of soil in the fill]. The elastic modulus of collapsible loess; The cementation failure index calculated in step S32 Calculate the cementation damage strain rate of collapsible loess ; For example, in this embodiment, a cementation damage strain rate for collapsible loess is provided. The acquisition strategy is as follows: ; This represents the average loess cementation strength across all monitored layers. The average rate of cementitious erosion across all monitored layers; This refers to the vertical height of the fill body; It should be noted that, for Acquisition strategy The physical meaning of is the cavitation power absorbed by a unit volume of soil. The elastic modulus of collapsible loess characterizes the soil's ability to resist deformation. Therefore, the cavitation damage strain rate of collapsible loess aims to characterize the deformation rate caused by mechanical cavitation.

[0027] It should be noted that, for The acquisition strategy aims to characterize the deformation rate driven by chemical damage dissolution rate.

[0028] It should also be noted that the deformation of the fill includes both the structural damage caused by the energy absorbed by the soil per unit volume during mechanical cavitation (i.e., cavitation damage strain rate) and the soil strength reduction caused by hydraulic erosion during cementation failure (i.e., cementation damage strain rate).

[0029] S34: Extract the loess structural brittleness index calculated in step S2. The cavitation damage strain rate of loess calculated in step S33 and cementation damage strain rate The extracted data is input into the collapse risk assessment model to assess the risk of fill deformation and obtain the collapse risk index. The output strategy of the collapse risk assessment model is as follows: ; in, This is the collapse risk index output by the collapse risk assessment model.

[0030] S4: Determine whether to locate the water intrusion point based on the subsidence risk index. If the determination is yes, proceed to S5; if the determination is no, end the process. Specifically, this includes: The obtained subsidence risk index is compared with the set subsidence risk threshold. If the obtained subsidence risk index is greater than or equal to the set subsidence risk threshold, the water intrusion point needs to be located and step S5 is continued. If the obtained subsidence risk index is less than the set subsidence risk threshold, the water intrusion point does not need to be located and monitoring continues.

[0031] S5: Construct a water intrusion location model, and import the hydraulic characteristic data and soil dynamic response data obtained in S1 into the water intrusion location model to trace the source of water intrusion. like Figure 3 As shown, S51: Map the spatial location of each data acquisition point to a dynamic grid node. For the same batch of air cavity collapse events monitored, extract the sound pressure energy value of each grid node. Calculate the energy decay gradient vector of target node i relative to its spatially neighboring nodes j, k, m. ; For example, in this embodiment, a strategy for obtaining the energy decay gradient vector is provided, specifically as follows: ; in, Let i be the energy decay gradient vector of the target node i relative to its spatially neighboring nodes j, k, m; Let i be the sound pressure energy value of the target node i; , respectively, are the sound pressure energy values ​​of neighboring nodes j, k, and m; Let be the node distance (i.e., Euclidean distance) between the target node i and its neighboring nodes j, k, and m. The characteristic distance is the reference wavelength scale that characterizes the sound wave in the medium. In this embodiment, for collapsible loess, ; It should be noted that when sound waves propagate in collapsible loess, energy attenuation includes: geometric attenuation (inversely proportional to distance, exhibiting spherical wave diffusion) and medium absorption (exponential attenuation, i.e., viscoelastic energy dissipation of the soil). By introducing a logarithmic term, when the numerator of the logarithmic term is smaller than the denominator, the fraction as a whole is less than 1, and the logarithmic term has a negative value, indicating that geometric attenuation dominates and enhances the gradient; while when the numerator of the logarithmic term is larger than the denominator, the fraction as a whole is greater than 1, and the logarithmic term has a positive value, indicating that medium absorption dominates and suppresses the gradient.

[0032] By introducing a logarithmic term into the strategy for obtaining the energy attenuation gradient vector, the non-geometric attenuation of sound waves in soil (i.e., medium absorption effect) can be corrected, which can effectively improve the accuracy of the gradient direction. It should be noted that the technical purpose of step S51 is to transform the data collected from discrete data acquisition points into a continuous spatial field, while quantifying the energy decay direction. S52: For each grid node, trace back along the opposite direction of its energy decay gradient vector. On the tracing path, calculate in real time the rate of energy change between adjacent points as a function of distance (i.e., the ratio of the energy change difference to the distance difference). When a certain point is detected The rate of energy change exceeded the threshold for the first time. They were marked as candidate air cavity collapse sources; Synchronous check If the rate of change of energy at a point is greater than or equal to twice the average value of its neighboring region, then ignore the candidate point and continue tracing along the path until a point that meets the conditions is found or the boundary is reached. It should be noted that the technical purpose of step S52 is to filter out local outliers by using absolute threshold to filter out minor fluctuations and relative thresholds of twice the average value. This can eliminate noise interference, locate the core point of energy mutation, and effectively avoid misjudging sensor failures or local foreign objects in the soil as the source of collapse.

[0033] S53: Candidate collapse sources located in step S52 Starting from this point, we trace back the direction of its energy source (i.e.) Grid nodes in the opposite direction; • Calculate the points these upstream nodes point to The energy decay gradient vector is calculated, and the direction of these upstream nodes is determined. The average direction of the energy decay gradient vector.

[0034] Adjusting along the vector average direction, we continue to search for the peak point of the rate of change of the energy field distribution, which is then identified as the final source of gas cavity collapse. ; Calculate the final air cavity collapse source The ratio of the energy change rate to the energy change threshold is used as the final gas cavity collapse source. The confidence level.

[0035] It should be noted that the technical purpose of step S53 is to solve the randomness of single-point positioning and improve the reliability of the collapse source coordinates by quantifying confidence and using multi-node information to correct single-point errors.

[0036] S54: Source of final air cavity collapse Centered on the soil dynamic response data acquired in real time, the infiltration front of the region is simulated, and the curvature distribution of the infiltration front in space is analyzed by the spatial difference method (such as the three-point curvature strategy). Determine the direction in which the radius of curvature of the wetting front decreases most rapidly. , as the direction of water intrusion; It should be noted that the direction of decreasing radius of curvature directly reflects the variation in soil permeability (which can form a preferential channel). The direction in which the radius of curvature of the wetting front decreases the fastest indicates the path of preferential water migration and more vulnerable soil structure, which is the most likely direction of water intrusion.

[0037] S55: Along the water intrusion direction determined in step S54 From the source of the final air cavity collapse The extension process begins, with the extension length set to 1.2 times the length of the maximum migration trajectory observed in this batch of air cavity collapse events; The obtained extension endpoint is used as the predicted water intrusion point. ; For example, in this embodiment, it should be noted that the extension path shape is not a simple straight line extension. After the direction of the infiltration front is determined (i.e., the vector direction has been shown in step S54), the extension needs to be corrected in combination with the soil anisotropy parameters. For example, when the soil permeability coefficient ratio is... When the value is greater than 1.5, the actual path will deviate towards the direction of high permeability. The streamline deflection angle can be calculated using Darcy's law. , ,in, , respectively, represent the permeability coefficients of collapsible loess in the x and y directions. The standard orientation angle; based on the streamline deflection angle calculated in real time. Correct and fit the shape of the extended path.

[0038] In this embodiment, it should also be noted that, according to historical data on water intrusion, after the air cavity collapses, 80% of the water intrusion points are located in the range of 1.0-1.3 times the migration length. In this embodiment, taking 1.2 times is a balance value that takes into account both safety margin and economy.

[0039] S56: Verify predicted water intrusion points Whether it is located at the edge of a dynamic mesh or in a known risk area (such as a crack zone or pipe joint), specifically including: If water source intrusion point If the point is within the effective monitoring area and nearby sensor data supports the presence of abnormal seepage (such as a slow increase in pore water pressure), then the verification is successful and the location is confirmed.

[0040] If the predicted water intrusion point If the data is outside the grid range or there is no supporting data nearby, the verification fails and a secondary traceback is initiated, including: tracing back to step S53, attempting to relocate the collapse source with the second highest confidence, and repeatedly executing steps S54 and S55 until the output verification is successful, at which point the loop stops.

[0041] S6: Visualize the collapse risk index and the coordinates of the located water intrusion points output in step S3 to the fill early warning platform in real time, specifically including: Extract the collapsibility risk index output from step S3 and verify the predicted water intrusion points. 3D coordinates; Simultaneously, extract the key parameters of the localization process in step S5, including: the final air cavity collapse source. Confidence level, direction of water intrusion and extension length; On the dynamic grid visualization framework, the collapse risk index output in step S3 is updated in real time, and the final air cavity collapse source is highlighted. Water intrusion direction and water source intrusion points And add confidence information.

[0042] Example 2:

[0043] like Figure 4 As shown in the figure, the intelligent sensing system for fill deformation based on the hydraulic properties of collapsible loess in this embodiment of the invention is as follows: Figure 4 As shown, it includes the following modules: The system includes modules for data acquisition, loess brittleness assessment, collapsibility risk assessment, location determination, water intrusion point tracing, and visualization. The data acquisition module is used to acquire characteristic data of collapsible loess, hydraulic characteristic data of the interior of the fill body, and soil dynamic response data during the deformation process of the fill body. The loess brittleness assessment module assesses the structural brittleness of loess based on the characteristic data of collapsible loess, and obtains the loess structural brittleness index; The collapse risk assessment module is used to construct a collapse risk assessment model and import the loess structural brittleness index, hydraulic characteristic data of the fill body, and soil dynamic response data during the deformation process of the fill body into the collapse risk assessment model to conduct fill deformation risk assessment and obtain the collapse risk index. The positioning judgment module determines whether to locate the water intrusion point based on the sinkhole risk index. If the judgment is yes, the water intrusion point tracing module is run; if the judgment is no, the process ends. The water intrusion point tracing module is used to construct a water intrusion location model and import hydraulic characteristic data and soil dynamic response data into the water intrusion location model to trace the water intrusion point. The visualization module is used to visualize the collapse risk index and the coordinates of the located water intrusion points to the reclamation early warning platform in real time.

[0044] Example 3:

[0045] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the aforementioned intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess by calling the computer program stored in the memory.

[0046] The electronic device can vary considerably depending on its configuration and performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Details will not be elaborated upon in this embodiment.

[0047] Example 4:

[0048] This embodiment proposes a computer-readable storage medium on which an erasable and rewritable computer program is stored. When the computer program runs on the computer device, it causes the computer device to execute the above-mentioned intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess.

[0049] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices.

[0050] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0051] It should be understood that determining B based on A does not mean determining B solely based on A; it also means determining B based on A and / or other information.

[0052] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives (SSDs).

[0053] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software 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 implementations should not be considered beyond the scope of this invention.

[0054] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0055] In addition, the functional units in the various embodiments of the present invention 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.

[0056] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0057] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A smart sensing method for fill deformation based on the hydraulic properties of collapsible loess, characterized in that, The method includes: S1: Obtain characteristic data of collapsible loess, hydraulic characteristic data of the interior of the fill, and soil dynamic response data during the deformation process of the fill; S2: Based on the collapsible loess characteristic data obtained in S1, the structural brittleness of loess is assessed, and the structural brittleness index of loess is obtained. S3: Construct a collapsibility risk assessment model, and import the loess structural brittleness index, hydraulic characteristic data inside the fill body, and soil dynamic response data during the deformation process of the fill body output by S2 into the collapsibility risk assessment model to conduct fill deformation risk assessment and obtain the collapsibility risk index. S4: Determine whether to locate the water intrusion point based on the subsidence risk index. If the determination is yes, proceed to S5; if the determination is no, end the process. S5: Construct a water intrusion location model, and import the hydraulic characteristic data and soil dynamic response data obtained in S1 into the water intrusion location model to trace the source of water intrusion. S6: Visualize the collapse risk index and the coordinates of the located water intrusion point output in step S3 to the filling early warning platform in real time.

2. The intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess according to claim 1, characterized in that, S1 includes: S11: Obtain characteristic data of collapsible loess, wherein the characteristic data of collapsible loess includes: cement erosion rate data; S12: Obtain hydraulic characteristic data inside the fill body, including seepage parameters of the fill body including: collapse data of closed air cavities of several layered monitoring units and water migration trajectory data of the fill body, including collapse data of closed air cavities including: collapse frequency and sound pressure amplitude data, and water migration trajectory data including: air cavity migration rate and three-dimensional spatial coordinate data. S13: Obtain soil dynamic response data during the deformation process of the fill body, including: soil matrix suction abrupt change value, pore water pressure gradient and soil microseismic acceleration data; S14: Store the data obtained in steps S11, S12 and S13 in a distributed data network.

3. The intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess according to claim 2, characterized in that, In S2, the structural brittleness of loess is assessed, including: Based on the cementitious erosion rate data obtained in step S11, the loess structural brittleness index, which characterizes the sensitivity of the internal structure of the collapsible loess fill to water intrusion, is calculated. Specifically: ； Where p is the number of monitoring layers, and k represents the kth layer monitoring unit; in, The measured dissolution rate of the kth layer of cementitious material reflects the chemical erosion capability of water. The average rate of cementitious erosion across all monitored layers; These represent the maximum and minimum cementitious erosion rates among all monitored layers.

4. The intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess according to claim 3, characterized in that, In S3, a risk assessment of fill deformation is conducted to obtain a collapse risk index, including: S31: Extract the closed air cavity collapse data of several layered monitoring units collected in step S12, and simultaneously extract the water migration trajectory data of the fill body collected in step S12 and import it into the air cavity cavitation power index calculation strategy to calculate the air cavity cavitation power index. S32: Obtain soil dynamic response data, import the soil dynamic response data into the cementation failure index calculation strategy, and calculate the cementation failure index. S33: Cavitation power index calculated based on step S31 Calculate the cavitation damage strain rate of collapsible loess ; The cementation failure index calculated in step S32 Calculate the cementation damage strain rate of collapsible loess ; S34: Extract the loess structural brittleness index calculated in step S2. The cavitation damage strain rate of loess calculated in step S33 and cementation damage strain rate The extracted data is input into the collapse risk assessment model to assess the risk of fill deformation and obtain the collapse risk index. The output strategy of the collapse risk assessment model is as follows: ； in, The collapse risk index is the output of the collapse risk assessment model.

5. The intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess according to claim 4, characterized in that, In S4, the determination of whether to locate the water intrusion point is based on the collapse risk index, including: The obtained subsidence risk index is compared with the set subsidence risk threshold. If the obtained subsidence risk index is greater than or equal to the set subsidence risk threshold, the water intrusion point needs to be located and step S5 is continued. If the obtained subsidence risk index is less than the set subsidence risk threshold, the water intrusion point does not need to be located and monitoring continues.

6. The intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess according to claim 5, characterized in that, S5 include: S51: Map the spatial location of each data acquisition point to a dynamic grid node. For the same batch of air cavity collapse events monitored, extract the sound pressure energy value of each grid node. Calculate the energy decay gradient vector of target node i relative to its spatially neighboring nodes j, k, m. ; S52: For each grid node i, trace back along the opposite direction of its energy decay gradient vector. On the tracing path, calculate in real time the rate of energy change between adjacent points as a function of distance. When a certain point is detected The rate of energy change exceeded the threshold for the first time. They were marked as candidate air cavity collapse sources; Synchronous check If the rate of change of energy at a point is greater than or equal to twice the average value of its neighboring region, then ignore the candidate point and continue tracing along the path until a point that meets the conditions is found or the boundary is reached. S53: Candidate collapse sources located in step S52 Starting from this point, trace back the grid nodes in the direction of their energy source. • Calculate the energy decay gradient vectors pointed to by these upstream nodes, and find the average direction of these energy decay gradient vectors pointed to by these upstream nodes; Adjusting along the vector average direction, we continue to search for the peak point of the rate of change of the energy field distribution, which is then identified as the final source of gas cavity collapse. ; Calculate the final air cavity collapse source The ratio of the energy change rate to the energy change threshold is used as the final gas cavity collapse source. The confidence level.

7. The intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess according to claim 6, characterized in that, S5 also includes: S54: Source of final air cavity collapse Centered on the soil dynamic response data acquired in real time, the infiltration front of the region was simulated, and the curvature distribution of the infiltration front in space was analyzed by the spatial difference method. Determine the direction in which the radius of curvature of the wetting front decreases most rapidly. , as the direction of water intrusion; S55: Along the water intrusion direction determined in step S54 From the source of the final air cavity collapse The extension process begins, with the extension length set to 1.2 times the length of the maximum migration trajectory observed in this batch of air cavity collapse events; The obtained extension endpoint is used as the predicted water intrusion point. ; S56: Verify predicted water intrusion points Whether it is located at the edge of a dynamic mesh or in a known risk area, specifically including: If water source intrusion point If the point is within the effective monitoring area and the sensor data in the vicinity supports the existence of abnormal seepage, then the verification is successful and the location is confirmed. If the predicted water intrusion point If the data is outside the grid range or there is no supporting data nearby, the verification fails and a secondary traceback is initiated, including: tracing back to step S53, attempting to relocate the collapse source with the second highest confidence, and repeatedly executing steps S54 and S55 until the output verification is successful, at which point the loop stops.

8. An intelligent sensing system for fill deformation based on the hydraulic properties of collapsible loess, used to implement the intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess as described in any one of claims 1-7, characterized in that, The system includes the following modules: The system includes modules for data acquisition, loess brittleness assessment, collapsibility risk assessment, location determination, water intrusion point tracing, and visualization. The data acquisition module is used to acquire characteristic data of collapsible loess, hydraulic characteristic data of the interior of the fill body, and soil dynamic response data during the deformation process of the fill body. The loess brittleness assessment module assesses the structural brittleness of loess based on the characteristic data of collapsible loess, and obtains the loess structural brittleness index; The collapse risk assessment module is used to construct a collapse risk assessment model and import the loess structural brittleness index, hydraulic characteristic data of the fill body, and soil dynamic response data during the deformation process of the fill body into the collapse risk assessment model to conduct fill deformation risk assessment and obtain the collapse risk index. The positioning judgment module determines whether to locate the water intrusion point based on the sinkhole risk index. If the judgment is yes, the water intrusion point tracing module is run; if the judgment is no, the process ends. The water intrusion point tracing module is used to construct a water intrusion location model and import hydraulic characteristic data and soil dynamic response data into the water intrusion location model to trace the water intrusion point. The visualization module is used to visualize the collapse risk index and the coordinates of the located water intrusion points to the reclamation early warning platform in real time.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess as described in any one of claims 1-7.

10. An electronic device, characterized in that, include: Memory, used to store instructions; A processor is configured to execute the instructions, causing the device to perform operations that implement the intelligent sensing method for fill deformation based on the hydraulic properties of collapsible loess as described in any one of claims 1-7.

Images