Early warning identification method for immersed roadbed under action of repeated seepage and load

Abstract

The invention relates to the technical field of road engineering, and particularly provides an early warning identification method for an immersed roadbed under the action of repeated seepage and load, which comprehensively considers the influence of the action of repeated seepage and load on the immersed roadbed, and can more accurately simulate the actual working condition. The seepage, stress, displacement and water content change of the immersed roadbed are monitored in all directions, and more comprehensive data support is provided for early warning; an early warning index system is established, and accuracy and reliability of early warning are improved by considering a plurality of indexes; the method comprises: establishing a roadbed mechanical model; monitoring sensor groups are arranged at the typical section of the immersed roadbed along the depth direction in a layered manner; collecting monitoring data in real time according to a preset frequency; establishing an early warning index system according to the roadbed mechanical model and the monitoring data; establishing an early warning model based on the early warning index system; and the early warning model calculates an early warning index comprehensive value according to the monitoring data, and compares the early warning index comprehensive value with an early warning threshold value for early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of road engineering, and in particular to a method for early warning identification of a submerged roadbed under repeated seepage and load effects. Background Art

[0002] The roadbed is a crucial component of road construction, and its stability is directly related to the safe use of the road. In practical engineering, the roadbed is often subjected to the dual effects of repeated seepage and loads. This is especially true in flooded environments, where the stability of the roadbed is more vulnerable. Repeated seepage can cause changes in the water content of the roadbed soil, which in turn affects the mechanical properties of the soil; while loads can cause stress and deformation in the roadbed. When these two factors act together, the roadbed may suffer from conditions such as settlement and slippage, and may even lead to serious safety accidents. Therefore, developing a method that can accurately warn of flooded roadbeds under repeated seepage and loads is of great practical significance.

[0003] While various methods for monitoring and early warning of flooded roadbeds exist, most focus on a single factor, such as seepage or load. Limited research exists on early warning of flooded roadbeds under the combined effects of repeated seepage and load. Some existing methods assess the stability of flooded roadbeds by monitoring displacement or settlement solely on the surface. However, this approach fails to reflect changes in seepage and stress within the submerged roadbed, resulting in insufficient accuracy and timeliness in early warning. Other methods, while accounting for seepage and load, lack consideration of repeated effects and fail to accurately simulate actual operating conditions. Therefore, existing technologies are insufficient in addressing early warning of flooded roadbeds under repeated seepage and load. Summary of the Invention

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] The present invention provides a method for early warning identification of a submerged roadbed under repeated seepage and load, comprising:

[0006] A roadbed mechanical model is established to simulate the seepage, stress and deformation changes of the submerged roadbed under different working conditions.

[0007] A monitoring sensor group is arranged in layers along the depth direction at a typical section of the submerged roadbed; the monitoring sensor group includes but is not limited to seepage monitoring sensors, stress monitoring sensors, displacement monitoring sensors and water content monitoring sensors.

[0008] The monitoring data of each monitoring sensor is collected in real time according to a preset frequency.

[0009] An early warning indicator system is established based on the roadbed mechanical model and the monitoring data; the early warning indicator system includes but is not limited to a seepage velocity indicator, a stress indicator, a displacement indicator, and a water content indicator.

[0010] An early warning model is established based on the early warning indicator system.

[0011] The early warning model calculates a comprehensive value of early warning indicators based on the monitoring data, and compares the comprehensive value of early warning indicators with the early warning threshold:

[0012] When the comprehensive value of the early warning indicators is less than the early warning threshold, there is no need to issue an early warning signal.

[0013] When the comprehensive value of the early warning indicators is greater than or equal to the early warning threshold, an early warning signal is issued.

[0014] Furthermore, the method for early warning identification of a submerged roadbed under repeated seepage and load, after the early warning model calculates a comprehensive value of early warning indicators based on the monitoring data and compares the comprehensive value of early warning indicators with an early warning threshold, further includes:

[0015] Calculate the difference between the comprehensive value of the early warning indicator and the early warning threshold.

[0016] A graded warning is performed based on the difference.

[0017] Furthermore, the method for early warning identification of submerged roadbed under repeated seepage and load, performing graded early warning according to the difference, includes:

[0018] When the difference is within the first-level warning threshold, a first-level warning is triggered.

[0019] When the difference is within the second-level warning threshold, a second-level warning is triggered.

[0020] When the difference is within the third-level warning threshold, a third-level warning is triggered.

[0021] Furthermore, the method for early warning identification of submerged roadbed under repeated seepage and load, after performing graded early warning according to the difference, further includes:

[0022] The early warning result is fed back to the monitoring sensor group and the early warning model, so as to optimize and adjust the monitoring sensor group and the early warning model using the early warning result.

[0023] Furthermore, the method for early warning identification of submerged roadbed under repeated seepage and load, after collecting monitoring data from each monitoring sensor in real time at a preset frequency, further includes:

[0024] The monitoring data is preprocessed; the preprocessing includes but is not limited to data filtering, data denoising and data normalization.

[0025] Furthermore, in the method for early warning identification of submerged roadbed under repeated seepage and load, the monitoring data includes:

[0026] The monitoring data includes but is not limited to the seepage data, stress data, displacement data and water content data of the submerged roadbed.

[0027] Furthermore, the method for early warning identification of submerged roadbed under repeated seepage and load, and establishing a roadbed mechanical model, include:

[0028] The subgrade mechanical model is established based on the finite element analysis method, that is, the submerged subgrade is divided into multiple units, and the seepage, stress and deformation changes of the submerged subgrade under different working conditions are simulated.

[0029] Furthermore, in the method for early warning identification of submerged roadbed under repeated seepage and load, the comprehensive value of the early warning index includes:

[0030] The early warning model uses a weighted average method to calculate the comprehensive value of the early warning indicators.

[0031] Furthermore, in the method for early warning identification of submerged roadbed under repeated seepage and load, the early warning threshold value includes:

[0032] The warning threshold is set based on historical data and empirical formulas.

[0033] Furthermore, in the method for early warning identification of submerged roadbed under repeated seepage and load, the early warning signal includes:

[0034] The warning signals include but are not limited to sound warnings, light warnings, text message notifications and system prompts.

[0035] The present invention provides an early warning identification method for a submerged roadbed under repeated seepage and load. The method comprehensively considers the effects of repeated seepage and load on the submerged roadbed, establishes a mechanical model, and can more accurately simulate actual working conditions. The method comprehensively monitors the seepage, stress, displacement, and water content changes of the submerged roadbed to provide more comprehensive data support for early warning. The method establishes an early warning indicator system to improve the accuracy and reliability of early warning by comprehensively considering multiple indicators. The method feeds back the early warning results to a monitoring sensor group and an early warning model, and uses the early warning results to optimize and adjust the monitoring sensor group and the early warning model so that they can better adapt to actual engineering needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0037] Figure 1This is a schematic flow chart of a method for early warning identification of a submerged roadbed under repeated seepage and load provided in Example 1 of the present invention;

[0038] Figure 2 This is a schematic flow chart of a method for early warning identification of a submerged roadbed under repeated seepage and load provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0040] In the following, the terms "first," "second," etc., are used for descriptive convenience only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified with "first," "second," etc., may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0041] In the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed mechanical connection, a detachable mechanical connection, or an integrated one; or, "connection" can be a direct connection or an indirect connection through an intermediate medium. In addition, unless otherwise clearly specified and limited, the term "coupling" should be understood in a broad sense. For example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components, or it can be understood as the electrical connection between different components in a circuit structure through a physical line that can transmit electrical signals, such as printed circuit board (PCB) copper foil or wire, so as to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in an airless / non-contact manner, such as electrical connection between two components using capacitive coupling to transmit electrical signals.

[0042] In an embodiment of the present invention, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to changes in the orientation of the components in the drawings.

[0043] The embodiments of the present invention can be used for monitoring and early warning of highway and railway roadbeds, especially in areas with complex geological conditions or high groundwater levels, to ensure road safety.

[0044] Example 1: like Figure 1 As shown, an embodiment of the present invention provides a method for early warning identification of a submerged roadbed under repeated seepage and load, comprising the following steps:

[0045] S101. Establish a roadbed mechanical model to simulate the seepage, stress and deformation changes of the submerged roadbed under different working conditions.

[0046] The subgrade mechanics model is a mathematical model used to describe the mechanical behavior of a submerged subgrade under various external conditions, such as seepage and loads. It establishes relationships between physical quantities (such as seepage, stress, strain, and displacement) to predict the submerged subgrade's response under different operating conditions. The subgrade mechanics model not only simulates seepage within the submerged subgrade, including changes in groundwater levels and the distribution of seepage velocities, but is also crucial for understanding the stability of the subgrade under submerged conditions, as seepage alters the mechanical properties of the soil. It also calculates the stress distribution within the submerged subgrade under various loads. For example, vehicle loads and static loads can exert varying stresses on the submerged subgrade, and the model can predict the magnitude and distribution of these stresses. Furthermore, the subgrade mechanics model predicts the deformation of the submerged subgrade under seepage and loads, including settlement and displacement. These deformations are important indicators for assessing subgrade stability; excessive deformation can lead to submerged failure.

[0047] The method for establishing a roadbed mechanical model is to build a mathematical model based on theories such as soil mechanics, seepage theory, and structural mechanics. For example, Darcy's law is used to describe seepage, and elasticity or plasticity theory is used to describe stress and deformation. Finite element analysis (FEA) is typically used to solve the model. The submerged roadbed is divided into multiple units, and the seepage, stress, and deformation of each unit are calculated through numerical calculations. The model parameters are determined based on the soil properties (such as permeability, elastic modulus, Poisson's ratio), load characteristics (such as vehicle load size and frequency), and boundary conditions (such as groundwater level and boundary constraints) used in actual projects.

[0048] Specifically, Darcy's law is a basic equation that describes the seepage of fluid through porous media (such as roadbed soil). Its expression is:

[0049] ,

[0050] Where, represents the seepage rate, represents the permeability coefficient of the soil, represents the seepage cross-sectional area, It represents the pressure gradient per unit length.

[0051] In elastic mechanics, the relationship between stress and deformation can be described by the constitutive equation. For linear elastic materials, the constitutive equation can be expressed as:

[0052] ,

[0053] Where, represents the strain component, represents the elastic modulus, is Poisson's ratio, represents the stress component, represents the stress locus, Represents the Kronecker symbol.

[0054] By establishing a roadbed mechanical model, the behavior of a submerged roadbed under different working conditions can be predicted in advance, providing theoretical support for the early warning indicator system; it can help identify potential unstable factors and provide a basis for the layout of monitoring sensor groups and the setting of early warning thresholds, thereby improving the accuracy and reliability of early warnings.

[0055] S102. Deploy monitoring sensor groups in layers along the depth direction at typical sections of the submerged roadbed; the monitoring sensor groups include but are not limited to seepage monitoring sensors, stress monitoring sensors, displacement monitoring sensors, and water content monitoring sensors.

[0056] A typical section is a cross-section that represents the characteristics of the entire submerged roadbed. This section is typically selected in areas where the submerged roadbed is subject to complex stresses, highly variable geological conditions, or prone to disease. Examples include the centerline section of the submerged roadbed, slope sections, or sections with groundwater seepage paths. By deploying monitoring sensor groups at these typical sections, the overall condition of the submerged roadbed can be more comprehensively reflected, avoiding the omission of critical information due to localized monitoring.

[0057] The depth direction refers to the vertical direction from the surface of the submerged roadbed to the bottom of the submerged roadbed. Since the seepage, stress, and deformation inside the submerged roadbed vary with depth, monitoring at different depths is required.

[0058] Layered deployment involves placing monitoring sensors at different depths within the submerged roadbed. For example, sensors can be placed on the surface, in the middle layer, and at the bottom of the submerged roadbed to obtain monitoring data at different depths.

[0059] A sensor group is a set of different types of sensors used to monitor various physical quantities of a flooded roadbed. A sensor group typically includes:

[0060] (1) Seepage monitoring sensors: such as water level gauges and flow rate sensors, used to monitor groundwater levels and seepage rates.

[0061] (2) Stress monitoring sensors: such as strain gauges and pressure sensors, used to monitor the stress distribution inside the submerged roadbed.

[0062] (3) Displacement monitoring sensors: such as total stations, GPS positioning systems, and displacement meters, used to monitor the deformation of submerged roadbeds.

[0063] (4) Moisture content monitoring sensors: such as soil moisture sensors and humidity sensors, used to monitor the moisture content of submerged roadbed soil.

[0064] During specific implementation, the specific placement of each sensor in the sensor group is determined based on the geological conditions, seepage path, and stress characteristics of the submerged roadbed. For example, displacement sensors and water content sensors are placed on the surface of the submerged roadbed, stress sensors and seepage sensors are placed in the middle layer of the submerged roadbed, and water level gauges are placed at the bottom of the submerged roadbed. The depth interval of the sensors can be determined based on the actual needs of the submerged roadbed and the monitoring accuracy requirements. For example: for a shallower submerged roadbed, the interval can be 0.5 meters or 1 meter; for a deeper submerged roadbed, the interval can be 1 meter or 2 meters. The sensors can be installed inside the submerged roadbed by drilling, burying, etc. During the installation process, it is necessary to ensure the stability and reliability of the sensors to avoid affecting the accuracy of the monitoring data due to improper installation.

[0065] S103: Collect monitoring data from each monitoring sensor in real time according to a preset frequency.

[0066] The preset frequency refers to the data collection interval pre-set during the design of the monitoring sensor group. This frequency can be determined based on actual monitoring needs and the stability requirements of the submerged roadbed. The preset frequency determines the timeliness and density of the monitoring data. A higher collection frequency can provide more timely and detailed data, but it also increases the data processing burden and energy consumption. A lower collection frequency can save resources but may miss some critical transient changes. For example, for a submerged roadbed requiring high-precision monitoring, the preset frequency can be set to collect data once a minute; for a relatively stable submerged roadbed, the preset frequency can be set to collect data once an hour.

[0067] Real-time data collection involves continuously collecting sensor output signals at a preset frequency and converting them into analyzable data. This collection method ensures data continuity and timeliness. Real-time data collection can promptly capture changes in the condition of a flooded roadbed, particularly in unexpected situations (such as sudden changes in seepage caused by heavy rain or sudden changes in stress caused by overloaded vehicles), enabling rapid problem resolution and triggering early warning mechanisms. Specifically, real-time data collection typically relies on automated monitoring equipment and data transmission systems, such as wireless sensor networks (WSNs) and wired data transmission systems, to ensure rapid and accurate data transmission to data processing centers.

[0068] Monitoring data refers to the numerical values ​​of various physical quantities collected by sensors, such as seepage velocity, stress, displacement, and water content. This data is crucial for assessing the stability of submerged roadbeds. Analysis of this data can determine whether the submerged roadbed is safe and whether maintenance or repair measures are necessary. Generally, collected monitoring data requires preprocessing, such as filtering, denoising, and normalization, to improve data quality and usability.

[0069] S104. Establish an early warning indicator system based on the roadbed mechanical model and the monitoring data; the early warning indicator system includes but is not limited to a seepage velocity indicator, a stress indicator, a displacement indicator, and a water content indicator.

[0070] The early warning indicator system is a set of quantitative metrics used to assess the stability of flooded roadbeds. These metrics, based on roadbed mechanics models and monitoring data, reflect changes in various aspects of the flooded roadbed's condition. This system is used to assess the stability of flooded roadbeds and, through its establishment, enables real-time monitoring and early warning of flooded roadbed conditions.

[0071] The seepage velocity index reflects the magnitude of seepage velocity within a submerged roadbed. Changes in seepage velocity can affect the mechanical properties of the soil. Excessively high seepage velocity can cause scour or softening of the submerged soil, thereby affecting its stability. The seepage velocity index is typically calculated from data collected by seepage monitoring sensors, for example, by measuring the ratio of the seepage velocity to the design allowable seepage velocity.

[0072] The stress index reflects the stress level within the submerged roadbed soil. Excessive stress can damage or deform the submerged roadbed soil, affecting its bearing capacity. The stress index is calculated from data collected by stress monitoring sensors, for example, the ratio of the maximum stress in the submerged roadbed soil to its compressive strength.

[0073] The displacement index reflects deformation on or within the submerged roadbed. Excessive displacement may indicate subsidence, slippage, or other instability. The displacement index is calculated from data collected by displacement monitoring sensors, such as the ratio of the maximum displacement of the submerged roadbed surface to the design allowable displacement.

[0074] The moisture content index reflects the changes in the moisture content of the submerged roadbed soil. This change in moisture content affects the mechanical properties of the soil. Excessively high or low moisture content can lead to stability issues in the submerged roadbed. The moisture content index is calculated using data collected by moisture monitoring sensors, such as the ratio of the submerged roadbed soil moisture content to the saturated moisture content.

[0075] The establishment of an early warning indicator system requires a combination of a roadbed mechanics model and monitoring data. The roadbed mechanics model provides theoretical guidance, while monitoring data provides practical verification. The early warning indicator system not only includes the four indicators mentioned above, but can also include other relevant indicators, such as temperature and vibration, based on actual needs, to more comprehensively assess the stability of flooded roadbeds. The early warning indicator system can be dynamically adjusted based on monitoring data and verification results of the roadbed mechanics model to improve the accuracy and reliability of early warnings.

[0076] S105: Establishing an early warning model based on the early warning indicator system.

[0077] The early warning model is a comprehensive analytical tool used to assess the stability of flooded roadbeds based on various indicators within the early warning indicator system. The early warning model integrates multiple indicators and uses algorithms or rules to determine the overall state of the flooded roadbed, enabling early identification and early warning of potential risks.

[0078] Specifically, the early warning model's input data comes from various indicators within the early warning indicator system. These indicators reflect the state of the flooded roadbed in terms of seepage, stress, displacement, and moisture content. Simple algorithms such as weighted averages and linear combinations can be used to combine these multiple indicators into a single composite value. For example, a composite value can be calculated by assigning weights to each indicator based on its impact on the stability of the flooded roadbed. Alternatively, machine learning algorithms (such as support vector machines and neural networks) or data mining techniques can be used to learn from and analyze historical data to develop more complex early warning models, improving the accuracy and reliability of early warnings.

[0079] S106. The early warning model calculates a comprehensive value of early warning indicators based on the monitoring data, and compares the comprehensive value of early warning indicators with an early warning threshold:

[0080] When the comprehensive value of the early warning indicators is less than the early warning threshold, there is no need to issue an early warning signal.

[0081] When the comprehensive value of the early warning indicators is greater than or equal to the early warning threshold, an early warning signal is issued.

[0082] The comprehensive value of the early warning indicators is a numerical value that comprehensively considers multiple early warning indicators and is used to assess the overall stability of the flooded roadbed. Specifically, the calculation method for the comprehensive value of the early warning indicators can use the weighted average method, or more complex algorithms such as machine learning algorithms (support vector machines, neural networks, etc.) can automatically calculate the comprehensive value of the early warning indicators by learning and analyzing historical data. The following is a detailed introduction to the weighted average method:

[0083] Comprehensive value of early warning indicators = Seepage velocity index+ Stress Index+ Displacement Index+ Moisture content index

[0084] Where, 、 、 、 are the weights of the corresponding indicators respectively.

[0085] The warning threshold is a preset critical value used to determine whether the flooded roadbed is in a safe state. Specifically, the warning threshold can be set based on historical data and engineering experience, or it can be set based on relevant design specifications and safety standards.

[0086] Specifically, the early warning model compares the calculated comprehensive value of the early warning indicators with the preset early warning threshold:

[0087] When the comprehensive value of the early warning indicators is less than the early warning threshold, it indicates that the submerged roadbed is in a safe state and there is no need to issue an early warning signal.

[0088] When the comprehensive value of the early warning indicators is greater than or equal to the early warning threshold, it indicates that there may be a safety hazard in the submerged roadbed and an early warning signal needs to be issued.

[0089] An embodiment of the present invention provides a method for early warning and identification of a submerged roadbed under repeated seepage and load. The method comprehensively considers the effects of repeated seepage and load on the submerged roadbed, establishes a mechanical model, and can more accurately simulate actual working conditions. The method also comprehensively monitors changes in seepage, stress, displacement, and water content of the submerged roadbed to provide more comprehensive data support for early warning. Furthermore, the method establishes an early warning indicator system to improve the accuracy and reliability of early warnings by comprehensively considering multiple indicators.

[0090] Example 2: like Figure 2 As shown, an embodiment of the present invention provides a method for early warning identification of a submerged roadbed under repeated seepage and load, comprising the following steps:

[0091] S201. Establish a roadbed mechanical model to simulate the seepage, stress and deformation changes of the submerged roadbed under different working conditions.

[0092] Specifically, a subgrade mechanics model is established based on the finite element analysis method. This involves dividing the submerged subgrade into multiple units to simulate changes in seepage, stress, and deformation under different operating conditions. Finite element analysis is a numerical analysis method used to solve complex systems in engineering and physics problems. It divides a continuous domain into a finite number of small units (elements), approximating the unknown function within each unit with a simple function, and then combining the approximate solutions of all units to obtain an approximate solution for the entire system. Within the subgrade mechanics model, finite element analysis can be used to simulate changes in seepage, stress, and deformation under different operating conditions, providing a numerical solution for the stability analysis of the submerged subgrade.

[0093] S202. Deploy monitoring sensor groups in layers along the depth direction at typical sections of the submerged roadbed; the monitoring sensor groups include but are not limited to seepage monitoring sensors, stress monitoring sensors, displacement monitoring sensors, and water content monitoring sensors.

[0094] S203: Collect monitoring data from each monitoring sensor in real time according to a preset frequency.

[0095] Monitoring data refers to the numerical values ​​of various physical quantities collected by various sensors and monitoring equipment that reflect the actual operating status of the submerged roadbed. This data is an important basis for assessing the stability of the submerged roadbed, conducting early warning analysis, and implementing maintenance measures. Specifically, monitoring data includes but is not limited to seepage data, stress data, displacement data, and water content data of the submerged roadbed. The following is a detailed introduction to each type of monitoring data:

[0096] Seepage data refers to data reflecting seepage conditions within a submerged roadbed, including groundwater level, seepage velocity, and seepage direction. Seepage is a key factor affecting the stability of a submerged roadbed. Excessively high seepage velocities can cause scouring, softening, or liquefaction of the submerged soil, thereby impacting the submerged roadbed's bearing capacity and stability. Typically, water level gauges are used to monitor groundwater level changes within the submerged roadbed; flow velocity sensors are used to monitor seepage velocity; and numerical simulations and monitoring data are combined to analyze seepage paths.

[0097] Stress data reflects the internal stress distribution within a submerged roadbed, including normal and shear stresses in the soil. Stress is a key indicator for assessing the bearing capacity and stability of a submerged roadbed. Excessive stress can damage or deform the soil, compromising its proper function. Typically, normal stress in the submerged roadbed is monitored using strain gauges or pressure sensors, while shear stress is monitored using shear sensors. Stress distribution is analyzed through a combination of finite element analysis and monitored data.

[0098] Displacement data refers to data reflecting the deformation of the surface or interior of a flooded roadbed, including horizontal and vertical displacements. Displacement is a key indicator for assessing the deformation and stability of a flooded roadbed. Excessive displacement may indicate settlement, slippage, or other instability. Typically, horizontal displacement of the flooded roadbed surface is monitored using a total station or GPS positioning system; vertical displacement within the flooded roadbed is monitored using displacement meters; and overall deformation of the flooded roadbed is analyzed through a combination of numerical simulation and monitoring data.

[0099] Moisture content data refers to data reflecting changes in the moisture content of submerged roadbed soil, including volumetric moisture content and relative humidity. Changes in moisture content can affect the mechanical properties of the soil; excessively high or low moisture content can lead to stability issues in the submerged roadbed. Typically, soil moisture sensors are used to monitor the volumetric moisture content of submerged roadbed soil, while humidity sensors monitor the relative humidity. Numerical simulations are then combined with the monitored data to analyze moisture content trends.

[0100] S204: Preprocess the monitoring data; the preprocessing includes but is not limited to data filtering, data denoising and data normalization.

[0101] Preprocessing refers to a series of preliminary steps performed on monitoring data before analysis. These steps aim to improve data quality and usability so that subsequent analysis can more accurately reflect the actual situation. Preprocessing removes noise and outliers from the data and unifies the data format and dimension, thereby providing a more reliable data foundation for subsequent data analysis and model calculations.

[0102] Specifically, preprocessing includes but is not limited to data filtering, data denoising, and data normalization, which are described in detail below:

[0103] Data filtering uses mathematical algorithms to remove high-frequency noise or irregular fluctuations from data. The goal of filtering is to preserve the data's key features while removing unnecessary interference. Data filtering can smooth data curves, reduce short-term fluctuations caused by sensor accuracy limitations or environmental interference, and make the data easier to analyze. For example, a moving average filter can be used to smooth monitoring data.

[0104] Data filtering usually uses methods such as moving average filters or low-pass filters. For example, the formula for a moving average filter is:

[0105]

[0106] Where, represents the filtered data point, represents the original data points, Indicates the window size of the moving average.

[0107] Data denoising involves removing random noise or interfering signals from data using specific algorithms or techniques. The goal is to improve the signal-to-noise ratio (SNR) and bring the data closer to the true value. Denoising can reduce random errors in data, improving its accuracy and reliability. For example, wavelet transforms can be used to decompose and reconstruct data to remove high-frequency noise, or dynamic estimation can be used to remove noise from data, which is applicable to time series data.

[0108] Data denoising can be done using methods such as wavelet transform and Kalman filtering. For example, the formula for wavelet transform is:

[0109]

[0110] Where, represents the wavelet coefficients, Represents the original data, represents the wavelet function, represents the scale parameter, Represents the translation parameter.

[0111] Data normalization involves converting data to a uniform range (typically [0, 1] or [-1, 1]) to facilitate comparison and analysis. The goal of normalization is to eliminate dimensional differences between data and make them comparable. Normalization can avoid analytical bias caused by dimensional differences and improve data processing efficiency and accuracy. Examples include min-max normalization and Z-score normalization.

[0112] Data normalization usually uses methods such as minimum-maximum normalization or Z-score normalization. For example, the formula for minimum-maximum normalization is:

[0113]

[0114] Where, represents the normalized data point, represents the original data points, Indicates the minimum value of the data. Indicates the maximum value of the data.

[0115] The formula for Z-score standardization is:

[0116]

[0117] Where, represents the normalized data points, represents the original data points, represents the mean of the data, Represents the standard deviation of the data.

[0118] S205. Establish an early warning indicator system based on the roadbed mechanical model and the monitoring data; the early warning indicator system includes but is not limited to a seepage velocity indicator, a stress indicator, a displacement indicator, and a water content indicator.

[0119] S206: Establishing an early warning model based on the early warning indicator system.

[0120] S207: The early warning model calculates a comprehensive value of early warning indicators based on the monitoring data, and compares the comprehensive value of early warning indicators with an early warning threshold:

[0121] When the comprehensive value of the early warning indicators is less than the early warning threshold, there is no need to issue an early warning signal.

[0122] When the comprehensive value of the early warning indicators is greater than or equal to the early warning threshold, an early warning signal is issued.

[0123] A warning signal is a notification or alarm issued by the system when monitoring data reaches or exceeds a preset warning threshold. It alerts personnel to potential safety hazards posed by flooded roadbeds. The purpose of the warning signal is to promptly notify personnel to take necessary measures to prevent accidents or minimize losses.

[0124] Specifically, warning signals include but are not limited to sound warnings, light warnings, SMS notifications, and system prompts. The following is a detailed introduction to each warning signal:

[0125] Audio warnings alert personnel by emitting specific sound signals (such as sirens and buzzers). They can quickly draw the attention of on-site personnel and are suitable for scenarios requiring immediate response. For example, an audio alarm can be installed at a construction site or monitoring center to sound an alarm when monitoring data is abnormal, or voice prompts can be issued through a loudspeaker or intercom to alert on-site personnel.

[0126] Light warnings alert personnel through light signals (such as flashing red or yellow lights). These warnings are visually conspicuous and can attract attention from a distance or in noisy environments. For example, flashing red lights could be installed at flooded roadbed monitoring points, flashing when monitoring data is abnormal, or using different colors of lights to indicate different warning levels.

[0127] SMS notifications are sent to relevant personnel's mobile phones, informing them of abnormalities in flooded roadbed monitoring data. These notifications can promptly convey warning signals to off-site management or maintenance personnel, ensuring they can take prompt action. For example, when the combined value of a warning indicator exceeds or equals the warning threshold, an SMS message is automatically sent to a preset mobile phone number.

[0128] System alerts are warning messages or pop-up notifications displayed through monitoring system interfaces (such as computer software and mobile applications). They display real-time monitoring data and warning signals, allowing monitoring personnel to review and respond at any time. For example, system alerts can include detailed information such as charts and data trend analysis, helping monitoring personnel quickly determine the severity of an issue.

[0129] S208: Calculate the difference between the comprehensive value of the early warning indicator and the early warning threshold.

[0130] Calculate the difference between the comprehensive value of the early warning indicator and the early warning threshold, that is:

[0131] Difference = comprehensive value of warning indicators - warning threshold

[0132] The difference reflects the gap between the stability of the submerged roadbed and the safety standard. The size of the difference can be used to judge the stability of the submerged roadbed and the urgency of taking corresponding measures.

[0133] S209: Perform graded warning according to the difference.

[0134] When the difference is within the first-level warning threshold, a first-level warning is triggered.

[0135] When the difference is within the second-level warning threshold, a second-level warning is triggered.

[0136] When the difference is within the third-level warning threshold, a third-level warning is triggered.

[0137] A graded early warning system categorizes early warning signals into different levels, with warnings divided into Level 1, Level 2, and Level 3 based on the magnitude of the difference. Different levels of early warning signals correspond to varying degrees of safety risk, enabling appropriate measures to be taken. This system provides a more detailed picture of the stability of flooded roadbeds, helping personnel take appropriate measures based on risk levels and improving the practicality and effectiveness of the early warning system.

[0138] S210 : Feedback the early warning result to the monitoring sensor group and the early warning model, so as to optimize and adjust the monitoring sensor group and the early warning model using the early warning result.

[0139] The warning result refers to the model's final decision, including whether to issue a warning signal, the warning level (e.g., Level 1, Level 2, or Level 3), and recommended measures. The warning result is a key output for assessing flooded roadbed stability and forms the basis of the feedback mechanism.

[0140] Based on the early warning results, the monitoring sensor array is optimized and adjusted, including sensor placement, quantity, type, and sampling frequency. This optimization improves the quality and representativeness of monitoring data, ensuring that the monitoring system more accurately reflects the actual condition of the flooded roadbed. For example, if early warning results indicate insufficient or abnormal monitoring data in certain areas, sensors can be added or relocated. Based on the frequency and importance of early warning results, the sampling frequency of sensors can be adjusted to improve the timeliness and accuracy of the data. If certain sensor types perform poorly under specific conditions, consideration can be given to replacing them with more suitable sensor types.

[0141] Optimize and adjust the early warning model based on the early warning results, including adjusting the model's parameters, algorithms, and thresholds. Optimizing the early warning model can improve the accuracy and reliability of early warnings, reduce false positives and missed alerts, and ensure the early warning system can more effectively identify potential safety hazards. For example, based on the early warning results, the early warning threshold can be dynamically adjusted to better adapt to different operating conditions and environmental conditions; the early warning model algorithm can be adjusted based on the accuracy and response speed of the early warning results; and based on the effectiveness of the early warning results, indicators in the early warning indicator system can be added or subtracted to improve the model's comprehensive assessment capabilities.

[0142] An embodiment of the present invention provides a method for early warning identification of a submerged roadbed under repeated seepage and load. The method comprehensively considers the effects of repeated seepage and load on the submerged roadbed, establishes a mechanical model, and can more accurately simulate actual working conditions. The method also comprehensively monitors the seepage, stress, displacement, and water content changes of the submerged roadbed to provide more comprehensive data support for early warning. An early warning indicator system is established to improve the accuracy and reliability of early warning by comprehensively considering multiple indicators. The early warning results are fed back to a monitoring sensor group and an early warning model, and the monitoring sensor group and the early warning model are optimized and adjusted using the early warning results to enable them to better adapt to actual engineering needs.

[0143] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0144] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0145] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0146] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the various embodiments of the method of the present invention via a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0147] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for early warning identification of submerged roadbed under repeated seepage and load, characterized in that: include: Establish a roadbed mechanical model to simulate the seepage, stress and deformation changes of submerged roadbed under different working conditions; A monitoring sensor group is arranged in layers along the depth direction at a typical section of the submerged roadbed; the monitoring sensor group includes but is not limited to a seepage monitoring sensor, a stress monitoring sensor, a displacement monitoring sensor, and a water content monitoring sensor; Collecting monitoring data from each monitoring sensor in real time according to a preset frequency; Establishing an early warning indicator system based on the roadbed mechanical model and the monitoring data; the early warning indicator system includes but is not limited to a seepage velocity indicator, a stress indicator, a displacement indicator, and a water content indicator; Establishing an early warning model based on the early warning indicator system; The early warning model calculates a comprehensive value of early warning indicators based on the monitoring data, and compares the comprehensive value of early warning indicators with the early warning threshold: When the comprehensive value of the warning indicators is less than the warning threshold, there is no need to issue a warning signal; When the comprehensive value of the early warning indicators is greater than or equal to the early warning threshold, an early warning signal is issued.

2. The early warning identification method for submerged roadbed under repeated seepage and load according to claim 1 is characterized in that: After the early warning model calculates a comprehensive value of early warning indicators based on the monitoring data and compares the comprehensive value of early warning indicators with an early warning threshold, the method further includes: Calculating the difference between the comprehensive value of the early warning indicator and the early warning threshold; A graded warning is performed based on the difference.

3. The early warning identification method for submerged roadbed under repeated seepage and load according to claim 2 is characterized in that: A graded warning is issued based on the difference, including: When the difference is within the first-level warning threshold, a first-level warning is triggered; When the difference is within the second-level warning threshold, a second-level warning is triggered; When the difference is within the third-level warning threshold, a third-level warning is triggered.

4. The early warning identification method for submerged roadbed under repeated seepage and load according to claim 2 is characterized in that: After issuing a graded warning based on the difference, the following steps are also included: The early warning result is fed back to the monitoring sensor group and the early warning model, so as to optimize and adjust the monitoring sensor group and the early warning model using the early warning result.

5. The early warning identification method for submerged roadbed under repeated seepage and load according to claim 1 is characterized in that: After collecting the monitoring data of each monitoring sensor in real time according to a preset frequency, the method further includes: The monitoring data is preprocessed; the preprocessing includes but is not limited to data filtering, data denoising and data normalization.

6. The method for early warning identification of submerged roadbed under repeated seepage and load according to claim 1, characterized in that: The monitoring data includes: The monitoring data includes but is not limited to the seepage data, stress data, displacement data and water content data of the submerged roadbed.

7. The method for early warning identification of submerged roadbed under repeated seepage and load according to claim 1, characterized in that: Establishing the roadbed mechanical model includes: The subgrade mechanical model is established based on the finite element analysis method, that is, the submerged subgrade is divided into multiple units, and the seepage, stress and deformation changes of the submerged subgrade under different working conditions are simulated.

8. The method for early warning identification of submerged roadbed under repeated seepage and load according to claim 1, characterized in that: The comprehensive value of the early warning indicators includes: The early warning model uses a weighted average method to calculate the comprehensive value of the early warning indicators.

9. The method for early warning identification of submerged roadbed under repeated seepage and load according to claim 1, characterized in that: The warning thresholds include: The warning threshold is set based on historical data and empirical formulas.

10. The early warning identification method for submerged roadbed under repeated seepage and load according to claim 1, characterized in that: The early warning signals include: The warning signals include but are not limited to sound warnings, light warnings, text message notifications and system prompts.

Images