Soil roadbed deformation monitoring method and monitoring system based on distributed optical fibers

Abstract

The invention provides a distributed optical fiber-based soil roadbed deformation monitoring method and monitoring system, and the method comprises the steps: obtaining a distributed optical fiber sensing data set of a target soil roadbed, dividing the target soil roadbed into a plurality of monitoring regions with different deformation characteristics according to the deformation intensity distribution of an optical fiber strain data sequence, and carrying out the monitoring of the deformation of the target soil roadbed. And performing coupling analysis processing on the optical fiber strain data sequence and the temperature compensation data sequence of each monitoring area to generate a multi-dimensional deformation feature set of the monitoring area, and generating deformation early warning information of the target soil roadbed according to a space-time matching result of the multi-dimensional deformation feature set and a preset deformation threshold condition. And generating a soil roadbed deformation optimization strategy based on the deformation early warning information, and feeding back the soil roadbed deformation optimization strategy to the roadbed maintenance system to trigger reinforcement response operation. The method can effectively improve the active control capability of the health state maintenance of the soil roadbed.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a soil roadbed deformation monitoring method and monitoring system based on distributed optical fiber. Background Art

[0002] In the field of civil engineering health monitoring, soil roadbed deformation monitoring technology evaluates the structural stability of roadbed structures by real-time collection and analysis of physical deformation data of roadbed structures. Existing technologies usually use optical fiber strain sensor networks to collect deformation data, and divide the roadbed into fixed-length monitoring areas based on preset spatial segmentation rules. By extracting the deformation displacement indicators of each area, static comparison is performed with the uniformly set deformation threshold, and an early warning signal is triggered when the threshold is exceeded. However, this method does not consider the strain measurement drift effect caused by ambient temperature fluctuations, resulting in systematic errors in the identification of deformation intensity distribution. The fixed-length regional division method cannot accurately capture the natural boundaries of actual deformation gradient changes, resulting in a monitoring blind spot for key deformation conduction paths. The simple deformation displacement judgment mode makes it difficult to distinguish the mechanism of internal stress accumulation from external environmental disturbances, resulting in insufficient early warning sensitivity. At the same time, static threshold setting is prone to false alarms and missed alarms when facing complex geological conditions, and there is a lack of automated connection between early warning information and engineering reinforcement strategies, resulting in a lag in maintenance response. How to achieve accurate and reliable monitoring and active control of soil roadbed deformation has become a technical problem that needs to be solved urgently in the field of infrastructure safety operation and maintenance. Summary of the invention

[0003] The invention provides a soil roadbed deformation monitoring method and monitoring system based on distributed optical fiber.

[0004] In a first aspect, an embodiment of the present invention provides a method for monitoring soil roadbed deformation based on distributed optical fiber, comprising: obtaining a distributed optical fiber sensing data set of a target soil roadbed, the distributed optical fiber sensing data set comprising a plurality of spatially and temporally continuous optical fiber strain data sequences and temperature compensation data sequences; dividing the target soil roadbed into a plurality of monitoring areas with different deformation characteristics according to the deformation intensity distribution of the optical fiber strain data sequence; performing coupling analysis processing on the optical fiber strain data sequence and the temperature compensation data sequence of each monitoring area to generate a multi-dimensional deformation feature set of the monitoring area; the multi-dimensional deformation feature set comprises a deformation rate feature, a stress accumulation correlation feature and an environmental disturbance response feature; generating deformation warning information of the target soil roadbed according to a spatial and temporal matching result of the multi-dimensional deformation feature set and a preset deformation threshold condition; generating a soil roadbed deformation optimization strategy based on the deformation warning information, and feeding back the soil roadbed deformation optimization strategy to a roadbed maintenance system to trigger a reinforcement response operation.

[0005] In a second aspect, an embodiment of the present invention provides a monitoring system, including: a memory in which a computer program is stored; and a processor configured to load the computer program to implement the method for monitoring the deformation of the soil subgrade based on distributed optical fiber as described above.

[0006] The method for monitoring the deformation of the soil subgrade based on distributed optical fiber provided by the present invention breaks through the limitations of single-parameter static threshold determination in traditional monitoring means by obtaining the spatio-temporally continuous optical fiber strain data sequence and temperature compensation data sequence of the target soil subgrade and performing dynamic coupling analysis. By correcting the physical correlation between the optical fiber strain data and the temperature compensation data, the problem of strain measurement distortion caused by environmental temperature fluctuations is effectively eliminated, and the accuracy of identifying the deformation intensity distribution is significantly improved. Based on the dynamic division of the monitoring area with different deformation characteristics according to the deformation intensity distribution, the true boundary of the internal mechanical transmission path of the soil subgrade can be adaptively captured, and the accurate mapping between the monitoring area division and the physical deformation characteristics can be realized. By constructing a multi-dimensional deformation feature set including deformation rate characteristics, stress accumulation correlation characteristics, and environmental disturbance response characteristics, the coupling relationship between the deformation evolution mechanism and external environmental disturbances is revealed under the time-frequency domain joint analysis framework, and a comprehensive evaluation index with early warning ability is formed. By adopting the spatio-temporal matching rule with a preset deformation threshold condition and dynamically adjusting the determination threshold according to the geological characteristics and evolution stages of different monitoring areas, the false alarm rate under complex geological conditions is significantly reduced while the early warning timeliness is improved. Finally, through the automatic mapping mechanism between the deformation warning information and the reinforcement strategy, the analysis results of multi-dimensional deformation characteristics are directly converted into executable engineering optimization schemes, realizing the full-link response from deformation monitoring to engineering intervention, and effectively improving the active control ability of maintaining the health state of the soil subgrade. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a flowchart of a method for monitoring the deformation of the soil subgrade based on distributed optical fiber provided by an embodiment of the present invention.

[0008] Figure 2 is a schematic diagram of the composition of a monitoring system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0009] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for monitoring the deformation of the soil subgrade based on distributed optical fiber provided by an embodiment of the present invention. This method can be executed by a monitoring system and includes the following steps: Step S100: Obtain a set of distributed optical fiber sensing data of the target soil subgrade, where the set of distributed optical fiber sensing data includes a plurality of spatio-temporally continuous optical fiber strain data sequences and temperature compensation data sequences.

[0010] The distributed optical fiber sensing data set is a set of relevant data about the target soil roadbed obtained using distributed optical fiber sensing technology. The optical fiber strain data sequence is a sequence of strain data generated by the deformation of the optical fiber due to the soil roadbed at different time and space positions, arranged in chronological order, reflecting the deformation of the soil roadbed under different time and space conditions. The temperature compensation data sequence is a temperature data sequence collected to eliminate the influence of temperature changes on optical fiber strain measurement. Since temperature changes can cause thermal expansion and contraction of the optical fiber, thereby generating false strain signals, temperature compensation is required.

[0011] The process of obtaining a distributed optical fiber sensing data set of a target soil roadbed can be achieved by pre-laying distributed optical fiber sensors in the target soil roadbed. For example, in the soil roadbed of a highway, a distributed optical fiber sensor is laid at a preset distance, and the sensor can adopt a distributed optical fiber sensing technology based on Raman scattering or Brillouin scattering. In the data acquisition process, the scattered light in the optical fiber is detected and demodulated by an optical fiber sensor demodulator to obtain optical fiber strain data and temperature data. For optical fiber strain data, it is arranged in the order of acquisition time to form an optical fiber strain data sequence; for temperature data, it is also arranged in the order of acquisition time to form a temperature compensation data sequence.

[0012] Step S200: According to the deformation intensity distribution of the optical fiber strain data sequence, the target soil roadbed is divided into a plurality of monitoring areas with different deformation characteristics.

[0013] The deformation intensity distribution of the optical fiber strain data sequence is the distribution of the deformation intensity of the soil roadbed reflected by the optical fiber strain data at different locations and at different times of the target soil roadbed. The deformation characteristics are the various characteristics of the soil roadbed during the deformation process, such as the deformation rate, amplitude, and stress accumulation. The monitoring area with different deformation characteristics is the soil roadbed in different areas of the target soil roadbed. Due to different geological conditions, load conditions and other factors, the deformation characteristics are different. These areas with different deformation characteristics are divided out to form monitoring areas.

[0014] The process of dividing the monitoring area according to the deformation intensity distribution of the optical fiber strain data sequence requires in-depth analysis of the optical fiber strain data sequence. For example, by statistically analyzing the collected optical fiber strain data sequence, the deformation intensity values at different positions are calculated, and then the target soil roadbed is divided into different areas according to the size and distribution of the deformation intensity values. For areas with large deformation intensity and more drastic changes, they can be divided into high deformation monitoring areas; for areas with small deformation intensity and relatively stable, they can be divided into low deformation monitoring areas.

[0015] As an implementation manner, step S200 may specifically include the following steps S210 to S240: Step S210: Perform segmented gradient calculation on the optical fiber strain data sequence, and extract the maximum deformation gradient value and the average deformation fluctuation amplitude of each optical fiber segment.

[0016] Segmented gradient calculation is to segment the optical fiber strain data sequence according to a preset length or time interval, and then calculate the gradient of each segment of data. The gradient represents the rate of change of a function at a certain point. In the optical fiber strain data sequence, the gradient reflects the rate of deformation change of the soil subgrade in the area corresponding to this segment of the optical fiber. The maximum deformation gradient value is the maximum value of the gradient in each segment of the optical fiber strain data sequence, which reflects the most intense degree of deformation change in the soil subgrade area corresponding to this optical fiber segment. The average deformation fluctuation amplitude is the average value of the fluctuation amplitude of the strain data relative to its average value in each segment of the optical fiber strain data sequence, which reflects the stability degree of the deformation in the soil subgrade area corresponding to this optical fiber segment. The process of performing segmented gradient calculation on the optical fiber strain data sequence can adopt the method of numerical differentiation. For example, the optical fiber strain data sequence is divided into segments of 10 meters each. For each segment of data, the central difference method is used to calculate its gradient. By calculating the gradient of each segment of data and finding the maximum value among them, it is the maximum deformation gradient value of this optical fiber segment. At the same time, calculate the fluctuation amplitude of the strain value relative to its average value in each segment of data, and then find the average value to obtain the average deformation fluctuation amplitude of this optical fiber segment.

[0017] Step S220: Assign a deformation intensity level to each optical fiber segment based on the ratio of the maximum deformation gradient value to the average deformation fluctuation amplitude.

[0018] The deformation intensity level is a classification of the optical fiber segment according to the deformation intensity of the soil subgrade, and is used to represent the deformation degree of the soil subgrade area corresponding to different optical fiber segments. The ratio of the maximum deformation gradient value to the average deformation fluctuation amplitude reflects the comprehensive situation of the intensity and stability of the deformation of the soil subgrade in the area corresponding to this optical fiber segment.

[0019] The process of assigning a deformation intensity level to each optical fiber segment based on the ratio of the maximum deformation gradient value to the average deformation fluctuation amplitude can adopt the method of threshold division. For example, several thresholds are preset, such as a ratio less than 1 is a low deformation intensity level, a ratio between 1 and 3 is a medium deformation intensity level, and a ratio greater than 3 is a high deformation intensity level. For each optical fiber segment, calculate the ratio of its maximum deformation gradient value to the average deformation fluctuation amplitude, and then according to the comparison result of this ratio with the preset threshold, assign the corresponding deformation intensity level to this optical fiber segment. In this way, the optical fiber segments in the target soil subgrade can be classified according to the deformation intensity, which is convenient for subsequent analysis and processing.

[0020] Step S230: Cluster the fiber optic segments with continuous distribution and the same or adjacent deformation intensity levels into initial candidate monitoring regions, and adjust the regional boundaries of the initial candidate monitoring regions according to the fluctuation range of the deformation intensity levels of the initial candidate monitoring regions.

[0021] Continuous distribution means that the fiber optic segments are adjacent in space without intervals. Clustering is a process of grouping objects with similar characteristics. Here, it is to group the fiber optic segments with continuous distribution and the same or adjacent deformation intensity levels into one category to form initial candidate monitoring regions. The fluctuation range of the deformation intensity level is the change range of the deformation intensity levels of each fiber optic segment within the initial candidate monitoring region. Adjusting the regional boundary is to correct the boundary of the initial candidate monitoring region according to the fluctuation range of the deformation intensity level to make it more accurately reflect the actual deformation of the soil subgrade.

[0022] The process of clustering the fiber optic segments with continuous distribution and the same or adjacent deformation intensity levels into initial candidate monitoring regions can adopt a clustering algorithm based on adjacency relationships. For example, starting from a certain fiber optic segment, check the deformation intensity levels of its adjacent fiber optic segments. If the deformation intensity levels of the adjacent fiber optic segments are the same or adjacent, add them to the current cluster until there are no eligible adjacent fiber optic segments, thus forming an initial candidate monitoring region. Then, calculate the fluctuation range of the deformation intensity levels of each fiber optic segment within the initial candidate monitoring region. If the fluctuation range is large, it indicates that the deformation situation within this region is relatively complex and the regional boundary needs to be adjusted. The adjustment method can be to divide out the fiber optic segments in the boundary part with large fluctuations, or merge in adjacent regions with similar deformation situations to improve the accuracy of the monitoring region.

[0023] Step S240: According to the preset regional division density requirement, perform regional merging or splitting processing on the adjusted initial candidate monitoring regions to generate a final regional division result containing multiple monitoring regions.

[0024] The preset regional division density requirement is the requirement for the number, size, and distribution of monitoring regions preset according to the actual monitoring needs and the characteristics of the soil subgrade. Region merging means merging adjacent monitoring regions with similar deformation characteristics into a larger monitoring region to reduce the number of monitoring regions and improve the monitoring efficiency. Region splitting means splitting a larger monitoring region into multiple smaller monitoring regions according to preset rules to meet the regional division density requirement and improve the monitoring accuracy. The process of performing region merging or splitting on the adjusted initial candidate monitoring regions according to the preset regional division density requirement can adopt a rule-based method. The splitting method can be to select a suitable splitting line according to the deformation intensity distribution within the region and split it into two monitoring regions with an area not exceeding 100 square meters. If the preset regional division density requirement is that the number of monitoring regions does not exceed 10, and there are 15 adjusted initial candidate monitoring regions, then it is necessary to merge adjacent regions with similar deformation characteristics. The merging method can be to fuse the boundaries of adjacent regions to form a larger monitoring region. Through region merging or splitting processing, a final regional division result containing multiple monitoring regions is finally generated, and this result can meet the preset regional division density requirement and more accurately reflect the deformation of the soil subgrade. Among them, the differential deformation characteristics are jointly characterized by the median and standard deviation of the deformation intensity levels of each monitoring region.

[0025] The median of the deformation intensity level is the value located in the middle position after arranging the deformation intensity levels of each optical fiber segment within the monitoring region in ascending order. It reflects the intermediate level of the deformation intensity level within the monitoring region. The standard deviation is a measure of the degree to which a set of data deviates from its average value. Here, it is the degree of deviation of the deformation intensity levels of each optical fiber segment within the monitoring region from its median. The median and standard deviation jointly characterize the differential deformation characteristics because the median can reflect the overall deformation intensity level of the monitoring region, while the standard deviation can reflect the dispersion degree of the deformation intensity within the monitoring region.

[0026] Step S300: Perform coupled analysis processing on the optical fiber strain data sequence and temperature compensation data sequence of each monitoring region to generate a multi-dimensional deformation feature set of the monitoring region; the multi-dimensional deformation feature set includes deformation rate features, stress accumulation correlation features, and environmental disturbance response features.

[0027] Coupling analysis is a process of comprehensively considering the mutual relationship between the optical fiber strain data sequence and the temperature compensation data sequence and conducting a joint analysis on them. Since temperature changes will affect the measurement of optical fiber strain, it is necessary to conduct a coupling analysis on the temperature compensation data sequence and the optical fiber strain data sequence to eliminate the interference of temperature and obtain more accurate deformation information of the soil subgrade. The multi-dimensional deformation feature set is a feature set that describes the deformation of the soil subgrade in the monitoring area from different perspectives, including the deformation rate feature, the stress accumulation correlation feature, and the environmental disturbance response feature. The deformation rate feature is the rate of change of the deformation of the soil subgrade in the monitoring area over time, reflecting the speed of the deformation of the soil subgrade. The stress accumulation correlation feature is the correlation between the stress accumulation situation and the deformation of the soil subgrade in the monitoring area, reflecting the influence of the stress accumulation during the long-term loading process on the deformation of the soil subgrade. The environmental disturbance response feature is the response of the soil subgrade in the monitoring area to changes in environmental factors (such as temperature, humidity, rainfall, etc.), reflecting the influence of environmental factors on the deformation of the soil subgrade.

[0028] As an implementation manner, step S300 may specifically include the following steps S310 to S350: Step S310: Perform noise filtering and baseline calibration processing on the optical fiber strain data sequence to obtain a denoised and standardized strain data sequence.

[0029] Noise filtering is a process of removing the noise signals contained in the optical fiber strain data sequence. The noise signals may be caused by factors such as measurement errors of optical fiber sensors and external interference, which will affect the accurate judgment of the deformation situation of the soil subgrade. Baseline calibration is to adjust the baseline of the optical fiber strain data sequence to a suitable level to eliminate the deviation caused by factors such as the initial state of the sensor and installation errors. The denoised and standardized strain data sequence is the optical fiber strain data sequence that has been processed by noise filtering and baseline calibration, removing the noise signals and adjusting the baseline, and this sequence can more accurately reflect the actual deformation situation of the soil subgrade.

[0030] The process of noise filtering and baseline calibration for the optical fiber strain data sequence is as follows: For noise filtering, digital filtering algorithms can be used, such as the moving average filtering algorithm, median filtering algorithm, etc. Taking the moving average filtering algorithm as an example, the basic idea of this algorithm is to take the average value of a set number of data points before and after each data point in the optical fiber strain data sequence as the filtered value of this point. For example, for an optical fiber strain data sequence with a length of N, using a sliding window with a length of M, for the i-th data point, its filtered value is the average value of this point and (M - 1) / 2 data points before and after it. For baseline calibration, the method of linear regression can be used. By linearly fitting the optical fiber strain data over a period of time, the slope and intercept of the baseline are obtained, and then the data sequence is subtracted by this baseline to obtain the calibrated strain data sequence. Through noise filtering and baseline calibration processing, a denoised and standardized strain data sequence is obtained.

[0031] Step S320: According to the temperature change trend of the temperature compensation data sequence, construct a temperature-strain compensation coefficient matrix, and use the temperature-strain compensation coefficient matrix to correct the temperature drift of the standardized strain data sequence to generate a corrected target strain data sequence.

[0032] The temperature change trend is the change of temperature over time in the temperature compensation data sequence, including trends such as temperature rising, falling, fluctuating, etc. The temperature-strain compensation coefficient matrix is a matrix used to describe the influence of temperature change on optical fiber strain measurement. The elements of the matrix represent the compensation coefficients that need to be applied to the optical fiber strain data under different temperature change conditions. Temperature drift correction is to use the temperature-strain compensation coefficient matrix to adjust the standardized strain data sequence to eliminate the strain measurement error caused by temperature change. The corrected target strain data sequence is the optical fiber strain data sequence after temperature drift correction, which eliminates the influence of temperature and can more accurately reflect the actual deformation of the soil subgrade. The process of constructing the temperature-strain compensation coefficient matrix is as follows: Analyze the temperature compensation data sequence, divide the temperature change into different intervals, such as the temperature rising interval, temperature falling interval, temperature stable interval, etc. Then, within each temperature interval, determine the relationship between temperature change and optical fiber strain change through experiments or theoretical analysis to obtain the temperature-strain compensation coefficient within this interval. Arrange these compensation coefficients in the order of temperature intervals to form the temperature-strain compensation coefficient matrix.

[0033] Step S330: Conduct a joint time-frequency domain analysis on the target strain data sequence to extract the time-domain deformation cumulative amount and frequency-domain perturbation response intensity of the monitoring area.

[0034] The joint time-frequency domain analysis is a process of analyzing the target strain data sequence in both the time domain and the frequency domain. The time domain analysis mainly focuses on the variation of data over time, while the frequency domain analysis mainly focuses on the distribution of different frequency components in the data. The cumulative deformation amount in the time domain is the cumulative degree of deformation of the soil subgrade in the monitoring area within a set time, reflecting the overall deformation situation of the soil subgrade over a period of time. The disturbance response intensity in the frequency domain is the response intensity of the soil subgrade in the monitoring area to disturbance signals of different frequencies, reflecting the dynamic characteristics of the soil subgrade at different frequencies.

[0035] The process of performing joint time-frequency domain analysis on the target strain data sequence and extracting the cumulative deformation amount in the time domain and the disturbance response intensity in the frequency domain of the monitoring area is as follows: For time domain analysis, an integration operation can be performed on the target strain data sequence to obtain the cumulative deformation amount in the time domain. For frequency domain analysis, the fast Fourier transform (FFT) algorithm can be used to transform the target strain data sequence from the time domain to the frequency domain to obtain its frequency spectrum diagram. Then, the amplitudes of different frequency components in the frequency spectrum diagram are analyzed to determine the disturbance response intensity in the frequency domain.

[0036] Step S340: Calculate the stress cumulative correlation eigenvalue of the monitoring area according to the non-linear correlation relationship between the cumulative deformation amount in the time domain and the disturbance response intensity in the frequency domain.

[0037] Specifically, first, a non-linear function model between the cumulative deformation amount in the time domain and the disturbance response intensity in the frequency domain is established through experiments or theoretical analysis. For example, a polynomial regression model, a neural network model, etc. can be used. Taking the polynomial regression model as an example, let the cumulative deformation amount in the time domain be C, the disturbance response intensity in the frequency domain be F, and the stress cumulative correlation eigenvalue be S. Then, the following polynomial regression model can be established: S = a0 + a1C + a2F + a3C 2 + a4F 2 + a5CF, where a0, a1, a2, a3, a4, and a5 are the coefficients of the model and can be obtained by fitting experimental data. Then, the calculated cumulative deformation amount in the time domain and the disturbance response intensity in the frequency domain are substituted into this model to calculate the stress cumulative correlation eigenvalue of the monitoring area.

[0038] Step S350: Integrate the cumulative deformation amount in the time domain, the disturbance response intensity in the frequency domain, and the stress cumulative correlation eigenvalue to generate a multi-dimensional deformation feature set of the monitoring area.

[0039] Specifically, first, normalize the time-domain deformation accumulation amount, the frequency-domain perturbation response intensity, and the stress accumulation correlation eigenvalue, and unify their numerical ranges to a suitable interval, such as [0, 1]. The normalization process can adopt a linear normalization method, such as the maximum-minimum normalization method. Then, combine the normalized time-domain deformation accumulation amount, the frequency-domain perturbation response intensity, and the stress accumulation correlation eigenvalue to form a vector, which is the multi-dimensional deformation feature set of the monitoring area.

[0040] Step S400: Generate deformation warning information for the target soil subgrade according to the spatio-temporal matching result between the multi-dimensional deformation feature set and the preset deformation threshold condition.

[0041] The multi-dimensional deformation feature set is a feature set that describes the deformation of the soil subgrade in the monitoring area from different perspectives, including deformation rate characteristics, stress accumulation correlation characteristics, environmental perturbation response characteristics, etc. The preset deformation threshold condition is the threshold condition for the deformation of the soil subgrade preset according to factors such as the design requirements and safety standards of the soil subgrade, including thresholds for the size, rate, and accumulation amount of deformation. The spatio-temporal matching result is the result of comparing and matching the multi-dimensional deformation feature set with the preset deformation threshold condition in time and space, reflecting whether the deformation situation in the monitoring area exceeds the preset threshold condition. The deformation warning information is the warning information about the deformation situation of the target soil subgrade generated according to the spatio-temporal matching result, including warning trigger conditions, risk area positioning marks, and recommended response time limits.

[0042] As an implementation method, step S400 can specifically include the following steps S410 to S450: Step S410: Obtain the historical deformation feature library of the monitoring area, and the historical deformation feature library contains multi-dimensional deformation feature data of multiple historical deformation cases and the corresponding deformation evolution results.

[0043] The historical deformation feature library of the monitoring area is a database that stores the relevant information of the deformation cases that occurred in the past in the monitoring area. The historical deformation case is a soil subgrade deformation event that has occurred in the monitoring area. The multi-dimensional deformation feature data is the feature data that describes the deformation of the soil subgrade in the historical deformation case from different perspectives, including deformation rate characteristics, stress accumulation correlation characteristics, and environmental perturbation response characteristics. The deformation evolution result is the development process and final result of the deformation of the soil subgrade in the historical deformation case, such as whether serious situations such as collapse and settlement have occurred.

[0044] The process of obtaining the historical deformation feature library of the monitoring area can be achieved through the following methods. First, collect and organize the historical monitoring data of the monitoring area. These historical monitoring data can be the soil subgrade deformation data collected by devices such as distributed optical fiber sensors in the past few years or even decades. Then, analyze and process these historical monitoring data to extract multi-dimensional deformation feature data. For example, using the methods introduced in the previous steps, perform coupled analysis and processing on the historical optical fiber strain data sequence and temperature compensation data sequence to extract deformation rate features, stress accumulation correlation features, environmental disturbance response features, etc. At the same time, record the deformation evolution results of each historical deformation case, such as whether reinforcement measures have been taken and the effect after reinforcement. Finally, store these multi-dimensional deformation feature data and the corresponding deformation evolution results in a database to form the historical deformation feature library of the monitoring area. By obtaining the historical deformation feature library, it can provide a reference and comparison basis for subsequent early warning analysis.

[0045] Step S420: Perform similarity matching between the multi-dimensional deformation feature set and the feature data in the historical deformation feature library to determine the target matching case of the current deformation mode of the monitoring area and the historical deformation case.

[0046] Similarity matching is the process of comparing the multi-dimensional deformation feature set with the feature data in the historical deformation feature library to find the feature data with a relatively high degree of similarity. The current deformation mode is the current soil subgrade deformation situation of the monitoring area, which is described by the multi-dimensional deformation feature set. The target matching case is the historical deformation case in the historical deformation feature library that is most similar to the current deformation mode of the monitoring area.

[0047] The process of performing similarity matching between the multi-dimensional deformation feature set and the feature data in the historical deformation feature library to determine the target matching case of the current deformation mode of the monitoring area and the historical deformation case is, for example: First, select a similarity measurement method, such as Euclidean distance, cosine similarity, etc. Then, compare the multi-dimensional deformation feature set with the feature data of each historical deformation case in the historical deformation feature library and calculate the similarity measurement value between them. Finally, select the historical deformation case with the smallest similarity measurement value as the target matching case. By performing similarity matching and determining the target matching case, it can provide a reference for predicting the subsequent deformation development trend.

[0048] Step S430: Predict the deformation development trend of the monitoring area based on the deformation evolution result of the target matching case, and generate a preliminary early warning level based on the deviation degree between the deformation development trend and the preset deformation threshold condition.

[0049] The deformation development trend is the change trend of the subgrade deformation in the monitoring area in the future for a period of time, including changes in aspects such as the magnitude, rate, and cumulative amount of deformation. The deviation degree is the degree of difference between the deformation development trend and the preset deformation threshold condition, reflecting whether the deformation situation in the monitoring area exceeds the safe range. The preliminary warning level is the warning level initially determined for the deformation situation in the monitoring area according to the deviation degree between the deformation development trend and the preset deformation threshold condition, such as the three levels of low, medium, and high.

[0050] The process of predicting the deformation development trend of the monitoring area based on the deformation evolution result of the target matching case and generating the preliminary warning level based on the deviation degree between the deformation development trend and the preset deformation threshold condition is as follows: First, analyze the deformation evolution result of the target matching case to understand the development process and law of the subgrade deformation in this case. For example, observe the change of the deformation rate with time and the growth trend of the stress cumulative amount in this case. Then, based on the similarity between the current deformation mode of the monitoring area and the target matching case, assume that the deformation development trend of the monitoring area is similar to that of the target matching case, so as to predict the deformation development trend of the monitoring area. Next, compare the predicted deformation development trend with the preset deformation threshold condition and calculate the deviation degree between them. For example, for the deformation rate, calculate the difference between the predicted deformation rate and the preset deformation rate threshold; for the stress cumulative amount, calculate the difference between the predicted stress cumulative amount and the preset stress cumulative threshold. Finally, determine the preliminary warning level according to the size of the deviation degree. For example, if the deviation degree is small, the preliminary warning level is low; if the deviation degree is medium, the preliminary warning level is medium; if the deviation degree is large, the preliminary warning level is high.

[0051] Step S440: Combine the spatial distribution correlation of the preliminary warning levels of adjacent monitoring areas to perform spatio-temporal correction processing on the preliminary warning levels to generate the final warning level of the monitoring area.

[0052] The spatial distribution correlation is the correlation relationship between the preliminary warning levels of adjacent monitoring areas. Since the deformation situation of the subgrade is continuous in space, the deformation situations of adjacent monitoring areas often affect each other, so their preliminary warning levels may also be correlated. The spatio-temporal correction processing is the process of comprehensively considering time and space factors to adjust and correct the preliminary warning levels. The final warning level is the final warning level of the monitoring area determined after spatio-temporal correction processing, which more accurately reflects the actual deformation risk situation of the monitoring area.

[0053] The process of generating the final warning level of the monitoring area by performing spatio-temporal correction on the preliminary warning level in combination with the spatial distribution correlation of the preliminary warning levels of adjacent monitoring areas is as follows: First, establish the spatial topological relationship of adjacent monitoring areas to determine the adjacent monitoring areas of each monitoring area. For example, for the distribution of monitoring areas on a two-dimensional plane, the four-neighborhood or eight-neighborhood method can be used to determine adjacent monitoring areas. Then, analyze the spatial distribution of the preliminary warning levels of adjacent monitoring areas and calculate the correlation between them. For example, methods such as the Pearson correlation coefficient can be used to calculate the correlation between the preliminary warning levels of adjacent monitoring areas. If the correlation of the preliminary warning levels of adjacent monitoring areas is relatively high, it indicates that their deformation conditions may have a greater mutual influence, and it is necessary to adjust the preliminary warning level of the current monitoring area. The adjustment method can be to correct it according to the average value, weighted average value, etc. of the preliminary warning levels of adjacent monitoring areas. For example, if the preliminary warning levels of adjacent monitoring areas are all relatively high, while the preliminary warning level of the current monitoring area is relatively low, the preliminary warning level of the current monitoring area can be appropriately increased. Finally, after spatio-temporal correction, the final warning level of the monitoring area is obtained. Through spatio-temporal correction, the accuracy of the warning level can be improved, and the situations of false alarms and missed alarms can be reduced.

[0054] Step S450: Generate the overall deformation warning information of the target soil subgrade based on the spatial superposition result of the final warning levels of all monitoring areas; the deformation warning information includes the warning trigger condition, the risk area positioning identifier, and the recommended response time limit.

[0055] The spatial superposition result is the result of spatially superposing and comprehensively analyzing the final warning levels of all monitoring areas, reflecting the overall deformation risk distribution of the target soil subgrade. The overall deformation warning information is the warning information about the overall deformation of the target soil subgrade generated according to the spatial superposition result, including the warning trigger condition, the risk area positioning identifier, the recommended response time limit, etc. The warning trigger condition is the condition for triggering the deformation warning, such as the deformation rate exceeding the set threshold, the stress accumulation reaching a certain level, etc. The risk area positioning identifier is the identification information that clearly indicates which areas in the target soil subgrade have deformation risks, such as the location and scope of the area. The recommended response time limit is the time range for recommending measures to be taken against the deformation risk.

[0056] The process of generating the overall deformation warning information of the target soil subgrade is as follows: Superimpose the final warning levels of all monitoring areas spatially to form a warning level distribution map. In this distribution map, different warning levels can be represented by different colors or symbols to visually display the distribution of the deformation risk of the overall target soil subgrade. According to the warning level distribution map, determine the warning trigger conditions. For example, if the warning level of a certain area reaches a high level, it is considered that the warning is triggered in this area, and the warning trigger condition can be that the deformation rate of this area exceeds a preset high threshold. Then, generate a risk area positioning identifier according to the warning level distribution map. Technologies such as Geographic Information System (GIS) can be used to mark the location and scope of the risk area on the map to form a clear risk area positioning identifier. Finally, determine the recommended response time limit according to the warning level and the situation of the risk area.

[0057] Step S500: Generate a soil subgrade deformation optimization strategy based on the deformation warning information, and feedback the soil subgrade deformation optimization strategy to the subgrade maintenance system to trigger the reinforcement response operation.

[0058] The soil subgrade deformation optimization strategy is a strategy formulated according to the deformation warning information for optimizing the deformation situation of the soil subgrade and reducing the deformation risk, including reinforcement material configuration parameters, construction time sequence planning, resource allocation ratio, etc. The subgrade maintenance system is a system for maintaining and managing the soil subgrade. This system can receive the soil subgrade deformation optimization strategy and trigger the corresponding reinforcement response operation according to the strategy. The reinforcement response operation is a reinforcement measure taken for the deformation risk of the soil subgrade, such as laying reinforcement materials and conducting soil improvement.

[0059] As an implementation method, in step S500, generating a soil subgrade deformation optimization strategy based on the deformation warning information can specifically include the following steps S510 to S540: Step S510: Determine at least one high-risk monitoring area in the target soil subgrade that needs to be processed preferentially according to the risk area positioning identifier.

[0060] The risk area positioning identifier is identification information that clearly indicates which areas in the target soil subgrade have deformation risks, such as the location and scope of the area. The high-risk monitoring area is a monitoring area in the target soil subgrade with a relatively high warning level and a relatively large deformation risk. These areas need to be processed preferentially to avoid serious deformation accidents.

[0061] The process of determining at least one high-risk monitoring area that needs to be preferentially treated in the target soil subgrade based on the risk area positioning identifier is as follows: First, based on the risk area positioning identifier, obtain the location and scope information of each monitoring area in the target soil subgrade. Then, in combination with the warning level in the deformation warning information, screen out the monitoring areas with a high warning level. For example, if the deformation warning information clearly indicates that the warning level of a certain area is high, then determine this area as a high-risk monitoring area. If there are multiple monitoring areas with a high warning level, the order of preferential treatment can be further determined according to factors such as the importance of these areas and the urgency of the deformation risk. For example, for a high-risk monitoring area located under a traffic artery, since its deformation may have a serious impact on traffic once it occurs, it needs to be preferentially treated. Through the above steps, determine at least one high-risk monitoring area that needs to be preferentially treated in the target soil subgrade, providing a clear goal for subsequent treatment.

[0062] Step S520: Obtain the geological structure data and historical maintenance records of the high-risk monitoring area, and construct a deformation response model for the high-risk monitoring area.

[0063] The geological structure data are relevant data describing the underground geological structure and geotechnical properties of the high-risk monitoring area, including soil layer stratification data, geotechnical mechanical parameters, etc. The historical maintenance records are relevant records of past maintenance and reinforcement of the high-risk monitoring area, including maintenance time, maintenance measures, maintenance effects, etc. The deformation response model is a model used to describe the deformation response of the high-risk monitoring area under different load actions. This model can predict the deformation of the high-risk monitoring area based on the input load data.

[0064] The process of obtaining the geological structure data and historical maintenance records of the high-risk monitoring area and constructing a deformation response model for the high-risk monitoring area is as follows: First, through means such as geological exploration and geotechnical testing, obtain the geological structure data of the high-risk monitoring area. For example, use drilling, geophysical exploration and other methods to obtain soil layer stratification data, and obtain geotechnical mechanical parameters through indoor geotechnical tests. At the same time, consult relevant archival materials to obtain the historical maintenance records of the high-risk monitoring area. Then, according to the geological structure data and historical maintenance records, select appropriate model structures and parameters to construct a deformation response model. For example, a finite element model, a discrete element model, etc. can be used. Taking the finite element model as an example, this model divides the high-risk monitoring area into multiple finite elements, and solves the deformation of the entire area by establishing the mechanical equilibrium equations of each element. During the process of constructing the model, the boundary conditions, material parameters, etc. of the model need to be determined according to the geological structure data and historical maintenance records. Finally, verify and calibrate the constructed deformation response model to ensure the accuracy and reliability of the model. Through the above steps, construct a deformation response model for the high-risk monitoring area, providing a basis for subsequent simulation of the reinforcement plan.

[0065] As an implementation manner, the construction process of the above deformation response model includes the following steps S521 to S524: Step S521: Collect the soil layer stratification data, water content distribution data, and load history data of the high-risk monitoring area.

[0066] The soil layer stratification data are relevant data describing the stratification of the underground soil layer in the high-risk monitoring area, including the thickness of the soil layer, the type of rock and soil, etc. The water content distribution data are relevant data describing the distribution of water content in the underground soil layer in the high-risk monitoring area. The water content has an important impact on the mechanical properties of rock and soil. The load history data are relevant data on the load conditions that the high-risk monitoring area has endured in the past, including the magnitude of the load, the acting time, the acting frequency, etc.

[0067] The process of collecting the soil layer stratification data, water content distribution data, and load history data of the high-risk monitoring area is, for example: For the soil layer stratification data, methods such as drilling and geophysical prospecting can be used for collection. The drilling method is to obtain samples of the underground soil layer through drilling, and then analyze the samples to determine information such as the thickness of the soil layer and the type of rock and soil. The geophysical prospecting method is to use geophysical principles to infer the stratification of the underground soil layer by measuring the changes in the underground physical field. For example, the resistivity method, the seismic wave method, etc. can be used. For the water content distribution data, methods such as the drying method and the capacitance method can be used for collection.

[0068] Step S522: Build a layered geomechanical model based on the soil layer stratification data, and correct the interlayer shear strength parameters of the layered geomechanical model through the water content distribution data.

[0069] The layered geomechanical model is a model built according to the soil layer stratification data for describing the mechanical properties of the underground soil layer in the high-risk monitoring area. This model divides the underground soil layer into multiple layers, and each layer has different mechanical properties. The interlayer shear strength parameter is a parameter describing the shear strength between adjacent soil layers and has an important impact on the stability of the soil layer. The water content has an important impact on the mechanical properties of rock and soil, especially on the interlayer shear strength parameter. Therefore, it is necessary to correct the interlayer shear strength parameters of the layered geomechanical model through the water content distribution data.

[0070] The process of constructing a layered geomechanical model based on soil layer stratification data and correcting the interlayer shear strength parameters of the layered geomechanical model through water content distribution data is as follows: First, according to the soil layer stratification data, the underground soil layer in the high-risk monitoring area is divided into multiple layers, and each layer has different geotechnical types and thicknesses. Then, a suitable mechanical model and parameters are selected for each layer to construct a layered geomechanical model. For example, the Mohr-Coulomb model, Duncan-Chang model, etc. can be used. Taking the Mohr-Coulomb model as an example, this model describes the mechanical properties of geotechnical materials through the internal friction angle and cohesion. Next, according to the water content distribution data, the influence of water content on the interlayer shear strength parameters is analyzed. The relationship between water content and interlayer shear strength parameters can be established through experiments or empirical formulas. For example, for a certain type of geotechnical material, the interlayer shear strength at different water contents can be measured through indoor direct shear tests, and then the relationship curve between water content and interlayer shear strength parameters can be fitted. Finally, according to the water content distribution data and the established relationship curve, the interlayer shear strength parameters of the layered geomechanical model are corrected. Through the above steps, a more accurate layered geomechanical model is constructed, providing a basis for subsequent calculations.

[0071] Step S523: Input the load history data into the corrected layered geomechanical model to calculate the theoretical deformation response curve of the high-risk monitoring area under different load scenarios.

[0072] The load history data are the relevant data of the load conditions borne by the high-risk monitoring area in the past, including the magnitude, action time, action frequency, etc. of the load. The theoretical deformation response curve is the curve of the theoretical deformation of the high-risk monitoring area changing with time under different load scenarios, reflecting the deformation response of the high-risk monitoring area under different load actions.

[0073] The process of inputting the load history data into the modified layered geomechanical model to calculate the theoretical deformation response curves of the high-risk monitoring area under different load scenarios is as follows: First, different load scenarios are determined according to the load history data. For example, the load history data can be classified according to factors such as the magnitude of the load and the acting time to obtain different load scenarios. Then, the load data under each load scenario is input into the modified layered geomechanical model. In the model, according to the mechanical properties of the rock and soil and the boundary conditions, the mechanical equilibrium equations at each time step are solved to obtain the deformation of the high-risk monitoring area at that time step. By calculating each time step, the deformation of the high-risk monitoring area during the entire load application process is obtained. Finally, the calculated deformation conditions are arranged in chronological order to plot the theoretical deformation response curves. For example, for a load application process with a duration of T, the deformation values at each time step are used as the ordinate and the time as the abscissa to plot the theoretical deformation response curves. Through the above steps, the theoretical deformation response curves of the high-risk monitoring area under different load scenarios are calculated, providing a reference for subsequent model calibration.

[0074] Step S524: By comparing the theoretical deformation response curves with the actual deformation monitoring data of the high-risk monitoring area, calibrate the parameter errors of the layered geomechanical model to obtain a calibrated deformation response model; among them, the calibration process of the parameter errors adopts an iterative feedback mechanism until the matching degree between the theoretical deformation response curves and the actual deformation monitoring data reaches a preset threshold.

[0075] The actual deformation monitoring data are the actual deformation data of the high-risk monitoring area collected by devices such as distributed optical fiber sensors, reflecting the true deformation of the high-risk monitoring area under actual loads. The parameter error is the difference between the actual value and the theoretical value of the parameters in the layered geomechanical model, and this difference will cause a deviation between the theoretical deformation response curves and the actual deformation monitoring data. The iterative feedback mechanism is a process of continuously adjusting the parameters of the layered geomechanical model to gradually improve the matching degree between the theoretical deformation response curves and the actual deformation monitoring data. The preset threshold is a threshold preset for the matching degree between the theoretical deformation response curves and the actual deformation monitoring data. When the matching degree reaches this threshold, it is considered that the parameter errors of the model have been effectively calibrated.

[0076] The process of calibrating the parameter error of the layered geomechanics model by comparing the theoretical deformation response curve with the actual deformation monitoring data in the high-risk monitoring area to obtain the calibrated deformation response model is as follows: First, compare the calculated theoretical deformation response curve with the actual deformation monitoring data and calculate the matching degree between them. The matching degree can be measured by indicators such as the correlation coefficient and the mean square error. For example, when using the correlation coefficient to measure the matching degree, the closer the correlation coefficient is to 1, the higher the matching degree between the theoretical deformation response curve and the actual deformation monitoring data. Then, based on the calculation result of the matching degree, determine whether it is necessary to adjust the parameters of the layered geomechanics model. If the matching degree does not reach the preset threshold, the parameters of the model need to be adjusted. The adjustment method can adopt the trial-and-error method, optimization algorithm, etc. Taking the trial-and-error method as an example, according to experience or theoretical analysis, adjust the parameters of the model, then recalculate the theoretical deformation response curve, compare it with the actual deformation monitoring data again, and calculate the matching degree. Continuously repeat this process until the matching degree reaches the preset threshold. Finally, when the matching degree reaches the preset threshold, it is considered that the parameter error of the model has been effectively calibrated, and the layered geomechanics model obtained at this time is the calibrated deformation response model.

[0077] Step S530: Based on the deformation response model, simulate the deformation suppression effects of different reinforcement schemes on the high-risk monitoring area, and screen the optimal reinforcement scheme according to the simulation effects.

[0078] The reinforcement scheme is a scheme for reinforcing the high-risk monitoring area, including the type of reinforcement material, the layout density, the structural form, etc. The deformation suppression effect is the degree to which the deformation in the high-risk monitoring area is suppressed after adopting different reinforcement schemes, reflecting the effectiveness of the reinforcement scheme. The optimal reinforcement scheme is the scheme with the best deformation suppression effect among all the simulated reinforcement schemes.

[0079] As an implementation method, step S530, simulating the deformation suppression effects of different reinforcement schemes on the high-risk monitoring area, may specifically include the following steps S531 to S534: Step S531: Obtain a set of candidate reinforcement schemes, which includes various combinations of reinforcement material types, layout densities, and structural forms.

[0080] The set of candidate reinforcement schemes is a set containing multiple different reinforcement schemes, which are composed of different combinations of reinforcement material types, layout densities, and structural forms. The type of reinforcement material is the type of material used to reinforce the high-risk monitoring area, such as geogrid, cement mixing pile, reinforced concrete pile, etc. The layout density is the distribution density of the reinforcement material in the high-risk monitoring area, such as the spacing of the geogrid, the number of cement mixing piles, etc. The structural form is the arrangement method and connection method of the reinforcement material, such as the laying direction of the geogrid, the arrangement form of the cement mixing piles, etc.

[0081] The process of obtaining the set of candidate reinforcement solutions is as follows: First, based on factors such as the geological structure data, deformation conditions, and load conditions of the high-risk monitoring area, determine the types of reinforcement materials that may be applicable. For example, if the soil layer in the high-risk monitoring area is relatively soft, rigid reinforcement materials such as cement mixing piles and reinforced concrete piles can be selected; if the soil layer has good stability but needs to improve its tensile strength, flexible reinforcement materials such as geogrids can be selected. Then, for each type of reinforcement material, consider different layout densities and structural forms to combine and form a variety of different reinforcement solutions. For example, for geogrids, different spacings (such as 0.5 m, 1 m, 1.5 m, etc.) and laying directions (such as horizontal, vertical, diagonal, etc.) can be considered to combine and form a variety of reinforcement solutions. Finally, summarize all these reinforcement solutions to form a set of candidate reinforcement solutions. By obtaining the set of candidate reinforcement solutions, multiple options can be provided for subsequent simulation and screening.

[0082] Step S532: Input the parameters of each candidate reinforcement solution into the deformation response model, and calculate the predicted deformation amount and stress distribution uniformity index of the high-risk monitoring area after the reinforcement is applied.

[0083] The parameters of the candidate reinforcement solution are the specific parameters such as the type, layout density, and structural form of the reinforcement material in each candidate reinforcement solution. The predicted deformation amount is the predicted deformation situation of the high-risk monitoring area under different load scenarios after a certain candidate reinforcement solution is applied, which reflects the inhibitory effect of the reinforcement solution on the deformation of the high-risk monitoring area. The stress distribution uniformity index is the degree of uniformity of the stress distribution within the high-risk monitoring area after a certain candidate reinforcement solution is applied, which reflects the improvement effect of the reinforcement solution on the stress distribution of the high-risk monitoring area.

[0084] The process of inputting the parameters of each candidate reinforcement solution into the deformation response model and calculating the predicted deformation amount and stress distribution uniformity index of the high-risk monitoring area after the reinforcement is applied is as follows: First, input the parameters of each candidate reinforcement solution into the calibrated deformation response model. In the model, according to the mechanical properties and layout method of the reinforcement material, the boundary conditions and material parameters of the model are adjusted accordingly. Then, input different load scenarios, solve the mechanical equilibrium equation of the model, and obtain the deformation situation and stress distribution situation of the high-risk monitoring area at each time step after the reinforcement is applied. For the predicted deformation amount, indicators such as the maximum deformation amount and average deformation amount of the high-risk monitoring area after the reinforcement is applied can be calculated. For the stress distribution uniformity index, indicators such as the standard deviation and coefficient of variation can be used to measure. For example, calculate the standard deviation of the stress values at different positions within the high-risk monitoring area. The smaller the standard deviation, the more uniform the stress distribution. Through the above steps, the predicted deformation amount and stress distribution uniformity index of the high-risk monitoring area after the reinforcement is applied are calculated, providing a basis for subsequent scoring and screening.

[0085] Step S533: Assign a comprehensive suppression score to each candidate reinforcement scheme according to the difference between the predicted deformation amount and the preset safety deformation threshold, and the deviation degree of the stress distribution uniformity index from the ideal distribution.

[0086] The preset safety deformation threshold is a safety threshold for the deformation of the high-risk monitoring area preset according to factors such as the design requirements and safety standards of the high-risk monitoring area. When the predicted deformation amount exceeds this threshold, it is considered that there are potential safety hazards in the high-risk monitoring area. The ideal distribution is an ideal state of the stress distribution, such as a state of uniform stress distribution. The deviation degree is the degree of difference between the stress distribution uniformity index and the ideal distribution, reflecting the non-uniformity degree of the stress distribution. The comprehensive suppression score is a comprehensive score assigned to each candidate reinforcement scheme according to the difference between the predicted deformation amount and the preset safety deformation threshold, and the deviation degree of the stress distribution uniformity index from the ideal distribution, reflecting the comprehensive suppression effect of the reinforcement scheme on the deformation and stress distribution of the high-risk monitoring area.

[0087] The process of assigning a comprehensive suppression score to each candidate reinforcement scheme according to the difference between the predicted deformation amount and the preset safety deformation threshold, and the deviation degree of the stress distribution uniformity index from the ideal distribution is as follows: First, calculate the difference between the predicted deformation amount and the preset safety deformation threshold. If the predicted deformation amount is less than the preset safety deformation threshold, the difference is positive, indicating that the reinforcement scheme has an inhibitory effect on the deformation; if the predicted deformation amount is greater than the preset safety deformation threshold, the difference is negative, indicating that the reinforcement scheme may not meet the safety requirements. Then, calculate the deviation degree of the stress distribution uniformity index from the ideal distribution. For example, in the case where the standard deviation is used to measure the stress distribution uniformity index, the difference between the standard deviation and the ideal standard deviation (such as a standard deviation of 0) can be calculated as the deviation degree. Next, normalize the difference and the deviation degree to unify their numerical ranges into a suitable interval, such as [0, 1]. The normalization process can adopt the linear normalization method. Finally, according to the normalized values of the difference and the deviation degree, use the weighted fusion method to assign a comprehensive suppression score to each candidate reinforcement scheme.

[0088] Step S534: Sort all candidate reinforcement schemes based on the comprehensive suppression score, and select the candidate reinforcement scheme with the highest score as the optimal reinforcement scheme; among them, the comprehensive suppression score is obtained by weighted fusion of the normalized values of the difference and the deviation degree, and the weight coefficient is configured according to the warning level of the high-risk monitoring area.

[0089] Sorting is the process of arranging all candidate reinforcement solutions in descending order of the comprehensive suppression score. The optimal reinforcement solution is the one with the highest comprehensive suppression score among all candidate reinforcement solutions, and this solution has the best comprehensive suppression effect on the deformation and stress distribution in high-risk monitoring areas. Weighted fusion is the process of multiplying the normalized values of the difference and the deviation by their respective weight coefficients and then adding them together to obtain the comprehensive suppression score. The weight coefficient is a coefficient used to adjust the proportion of the difference and the deviation in the comprehensive suppression score, and it is configured according to the warning level of the high-risk monitoring area.

[0090] The process of sorting all candidate reinforcement solutions based on the comprehensive suppression score and selecting the candidate reinforcement solution with the highest score as the optimal reinforcement solution is as follows: First, according to the warning level of the high-risk monitoring area, configure the weight coefficients of the difference and the deviation. For example, for a high-risk monitoring area with a higher warning level, more attention is paid to the difference between the predicted deformation amount and the preset safety deformation threshold, so the weight coefficient of the difference can be set larger; for a high-risk monitoring area with a lower warning level, the weight coefficient of the difference can be appropriately reduced and the weight coefficient of the deviation can be increased. Then, according to the configured weight coefficients, use the weighted fusion method to calculate the comprehensive suppression score of each candidate reinforcement solution. Next, sort all candidate reinforcement solutions in descending order of the comprehensive suppression score. Sorting algorithms such as bubble sort and quick sort can be used to achieve this. Taking bubble sort as an example, compare the comprehensive suppression scores of two adjacent candidate reinforcement solutions, and swap them if the order is incorrect. Repeat this step until the entire sequence is ordered. Finally, select the candidate reinforcement solution with the highest score after sorting as the optimal reinforcement solution. This optimal reinforcement solution can maximize the suppression of deformation and improve the stress distribution considering the warning level of the high-risk monitoring area.

[0091] Step S540: Generate a soil subgrade deformation optimization strategy including reinforcement material configuration parameters, construction time sequence planning, and resource allocation ratio based on the recommended response time limit and the optimal reinforcement solution.

[0092] The recommended response time limit is the time range for taking measures against deformation risks as recommended in the deformation warning information. The reinforcement material configuration parameters are the specific setting information about the reinforcement materials, including the preferred sequence of material types, the unit area usage gradient, and the interlayer layout rules, etc. The construction time sequence planning is the time arrangement and sequence planning for the reinforcement construction process, including the division of construction sub-areas, the determination of construction time windows, the parallel execution strategy, and the emergency adjustment mechanism, etc. The resource allocation ratio is the ratio of allocating resources such as manpower, material resources, and financial resources according to the deformation warning level of the high-risk monitoring area and the resource requirements of the remaining monitoring areas.

[0093] As an implementation manner, the generation process of the above construction time sequence plan may include the following steps S54A1 to S54A5: Step S54A1: Determine the supply cycle and transportation route of the required materials and equipment according to the reinforcement material configuration parameters.

[0094] The reinforcement material configuration parameters clarify information such as the types and quantities of materials required for reinforcement. The supply cycle is the time required from purchasing materials and equipment to their arrival at the construction site, which is affected by factors such as the production capacity of suppliers, transportation distance, and transportation method. The transportation route is the transportation route of materials and equipment from the supplier to the construction site.

[0095] The process of determining the supply cycle and transportation route of the required materials and equipment according to the reinforcement material configuration parameters is as follows. First, determine the list of specific materials and equipment to be purchased according to the material types and quantities in the reinforcement material configuration parameters. For example, if geogrids and cement mixing piles are determined to be used in the reinforcement material configuration parameters, then the specifications and quantities of the required geogrids and the list of equipment required for cement mixing pile construction need to be listed. Then, contact multiple suppliers to understand their production capacity and delivery time. For some commonly used reinforcement materials and equipment, there may be multiple suppliers available in the market. By communicating with them, the supply cycle information of different suppliers can be obtained. At the same time, consider the impact of transportation distance and transportation method on the supply cycle. If the supplier is far from the construction site, it may be necessary to select a suitable transportation method, such as road transportation or railway transportation, to ensure that the materials and equipment can arrive on time. For the determination of the transportation route, factors such as road conditions, traffic flow, and transportation cost need to be comprehensively considered. Tools such as geographic information system (GIS) can be used to analyze the advantages and disadvantages of different transportation routes and select the optimal transportation route. For example, select a route with better road conditions and less traffic flow to reduce transportation time and transportation cost.

[0096] Step S54A2: Divide multiple construction sub-regions and assign construction priorities based on the distribution density and traffic accessibility of high-risk monitoring areas.

[0097] The distribution density of high-risk monitoring areas is the degree of concentration of high-risk monitoring areas in the target soil subgrade. The traffic accessibility is the degree of difficulty for construction vehicles and equipment to reach high-risk monitoring areas, which is affected by factors such as road conditions and topography. Construction sub-regions are multiple smaller regions divided from high-risk monitoring areas for convenient construction management. Construction priorities are the construction sequence assigned to each construction sub-region.

[0098] Based on the distribution density and traffic accessibility of high-risk monitoring areas, the process of dividing multiple construction sub-areas and assigning construction priorities is as follows. First, use tools such as Geographic Information System (GIS) to analyze the distribution of high-risk monitoring areas, and combine traffic maps and terrain data to understand the traffic accessibility of each area. Then, according to the distribution density and traffic accessibility, use methods such as cluster analysis to divide the high-risk monitoring areas into multiple construction sub-areas. For example, if the high-risk monitoring areas are relatively concentrated and the traffic is convenient, they can be divided into one or several larger construction sub-areas; if the distribution is relatively scattered and the traffic conditions vary greatly, they need to be divided into multiple smaller construction sub-areas. When dividing the construction sub-areas, the convenience and efficiency of construction should be considered, and the construction tasks within each construction sub-area should be made relatively independent as much as possible. Next, according to factors such as the importance of each construction sub-area, the degree of deformation risk, and traffic accessibility, assign construction priorities. For construction sub-areas located under traffic arteries, with a relatively high deformation risk and good traffic accessibility, construction should be arranged first; for construction sub-areas with a relatively low deformation risk and inconvenient traffic, construction can be postponed appropriately.

[0099] Step S54A3: Configure the construction time window and human resource scheduling plan for each construction sub-area in combination with the resource allocation ratio and supply cycle.

[0100] The resource allocation ratio determines the quantity of resources such as manpower, material resources, and financial resources that each construction sub-area can obtain. The supply cycle determines the time when materials and equipment arrive at the construction site. The construction time window is the time range for each construction sub-area to carry out construction, and factors such as weather and the surrounding environment need to be considered. The human resource scheduling plan is the arrangement of construction personnel in different construction sub-areas and different construction times.

[0101] The process of configuring the construction time window and human resource scheduling plan for each construction sub - area in combination with the resource allocation ratio and supply cycle is as follows. First, according to the resource allocation ratio, determine the allocable human, material, and financial resources for each construction sub - area. For example, according to the resource allocation ratio, allocate construction personnel, reinforcement materials, and construction equipment to a certain construction sub - area. Then, considering the supply cycle, determine the time when materials and equipment arrive at the construction site. Based on this time, combined with factors such as weather and the surrounding environment, determine the construction time window for each construction sub - area. For example, if materials and equipment are expected to arrive during a certain period, and the weather is suitable for construction and the surrounding environment also permits construction during this period, then this period can be determined as the construction time window. Next, according to the construction time window and the workload of the construction tasks, formulate a human resource scheduling plan. For construction sub - areas with a large workload and a short construction time window, reasonably increase the number of construction personnel and arrange them to work in different construction stages to ensure that the construction tasks can be completed on time. At the same time, consider the skill levels and work experience of the construction personnel and reasonably allocate them to different construction positions.

[0102] Step S54A4: Optimize the parallel execution strategy of the human resource scheduling plan according to the overlap of the construction time windows and the equipment reuse requirements.

[0103] The overlap of the construction time windows refers to whether there is an overlap in the construction time windows of different construction sub - areas. The equipment reuse requirement refers to the usage requirements for some common equipment during the construction process in different construction sub - areas. The parallel execution strategy refers to how to arrange construction personnel to work in parallel in different construction sub - areas in the human resource scheduling plan to improve construction efficiency.

[0104] The process of optimizing the parallel execution strategy of the human resource scheduling plan according to the overlap of the construction time windows and the equipment reuse requirements is as follows. First, analyze the overlap of the construction time windows. If there is an overlap in the construction time windows of multiple construction sub - areas, it indicates that parallel construction can be considered. Then, consider the equipment reuse requirements. For some common equipment, such as cranes and mixers, reasonably arrange their usage order in different construction sub - areas to avoid equipment idleness and conflicts. For example, if two construction sub - areas both need to use a crane during the same period, according to the urgency and workload of the construction tasks, reasonably arrange which construction sub - area the crane will serve first. Next, according to the overlap of the construction time windows and the equipment reuse requirements, adjust the human resource scheduling plan. For the construction sub - areas with parallel construction, reasonably allocate construction personnel to ensure that each construction sub - area has sufficient manpower for construction. At the same time, establish an effective communication mechanism to ensure that construction personnel can communicate and cooperate in a timely manner. For example, set up on - site dispatching personnel to be responsible for coordinating the construction progress and equipment usage in different construction sub - areas.

[0105] Step S54A5: Generate a construction time sequence plan including construction sub - areas, construction time windows, parallel execution strategies, and emergency adjustment mechanisms.

[0106] The construction sub - areas define the specific scope of construction. The construction time windows specify the construction time for each construction sub - area. The parallel execution strategies improve construction efficiency, and the emergency adjustment mechanisms provide guarantees for dealing with unexpected situations during construction.

[0107] The process of generating a construction time sequence plan including construction sub - areas, construction time windows, parallel execution strategies, and emergency adjustment mechanisms is as follows. First, integrate the divided construction sub - areas, determined construction time windows, and optimized parallel execution strategies to form a preliminary construction time sequence plan. Then, formulate an emergency adjustment mechanism. The emergency adjustment mechanism should consider various possible unexpected situations, such as bad weather, equipment failures, and casualties. For each unexpected situation, corresponding countermeasures should be formulated. For example, if bad weather is encountered, construction should be suspended, and measures should be taken to protect the completed construction parts and construction equipment; if equipment fails, maintenance personnel should be arranged for repair in a timely manner, or spare equipment should be allocated. At the same time, an emergency response process should be established to ensure that emergency measures can be quickly initiated when unexpected situations occur. Finally, review and improve the construction time sequence plan to ensure its rationality and feasibility. During the review process, factors such as construction safety, construction quality, and construction cost should be considered. Through the above steps, a construction time sequence plan including construction sub - areas, construction time windows, parallel execution strategies, and emergency adjustment mechanisms is generated.

[0108] As an implementation method, the process of generating the above - mentioned parameters for the configuration of reinforcement materials may include the following steps S54B1 - S54B6: Step S54B1: Determine a set of candidate reinforcement material types according to the material type requirements of the optimal reinforcement plan.

[0109] The optimal reinforcement plan clarifies the type requirements of the required reinforcement materials. The set of candidate reinforcement material types is the set of all possible reinforcement material types that meet these requirements.

[0110] According to the material type requirements of the optimal reinforcement plan, the process of determining the set of candidate reinforcement material types is as follows. First, carefully analyze the specific requirements for the reinforcement material type in the optimal reinforcement plan, including requirements in aspects such as the mechanical properties, chemical properties, and durability of the material. For example, if the optimal reinforcement plan requires the reinforcement material to have high tensile strength and good flexibility, then materials that meet these requirements can be screened out from common reinforcement materials. Common reinforcement materials include geogrids, geotextiles, cement mixing piles, reinforced concrete piles, etc. Then, through methods such as consulting relevant materials, consulting experts, and market research, collect reinforcement materials that meet the material type requirements of the optimal reinforcement plan. For each reinforcement material, understand its performance characteristics, application scope, price, and other information. Finally, summarize all the collected reinforcement material types that meet the requirements to form a set of candidate reinforcement material types.

[0111] Step S54B2: Perform historical performance parameter analysis and processing on each material in the set of candidate reinforcement material types, and extract a set of key performance parameters associated with the stress distribution uniformity index of the high-risk monitoring area.

[0112] Historical performance parameter analysis and processing is a process of collecting, organizing, and analyzing the performance data of each material in the set of candidate reinforcement material types in previous engineering applications. The stress distribution uniformity index is an index that measures the degree of stress distribution uniformity in the high-risk monitoring area. The set of key performance parameters is a set of performance parameters of the reinforcement material that is closely related to the stress distribution uniformity index.

[0113] The process of performing historical performance parameter analysis and processing on each material in the set of candidate reinforcement material types and extracting the set of key performance parameters is as follows. First, collect the performance data of each candidate reinforcement material in previous engineering applications, including parameters such as the strength, elastic modulus, Poisson's ratio, and durability of the material. These data can be obtained from channels such as engineering reports, academic papers, and laboratory test reports. Then, organize and analyze the collected performance data to establish a performance database for each material. Next, analyze the influencing factors of the stress distribution uniformity index of the high-risk monitoring area, and determine the performance parameters of the reinforcement material associated with this index. For example, the elastic modulus and Poisson's ratio of the material will affect the deformation of the material when stressed, and thus affect the stress distribution uniformity in the high-risk monitoring area. Therefore, the elastic modulus and Poisson's ratio can be used as key performance parameters. Finally, extract the key performance parameters associated with the stress distribution uniformity index from the performance database of each material to form a set of key performance parameters.

[0114] Step S54B3: Based on the mapping relationship between the set of key performance parameters and the predicted deformation amount of the deformation response model, perform dynamic load simulation processing on each candidate reinforcement material to generate simulation performance data of different materials in the high-risk monitoring area.

[0115] The mapping relationship is a functional relationship or statistical relationship between the set of key performance parameters and the predicted deformation amount of the deformation response model. The dynamic load simulation processing is to simulate the performance of each candidate reinforcement material when subjected to dynamic loads in the high-risk monitoring area on a computer. The simulation performance data is the performance data of each candidate reinforcement material in the high-risk monitoring area obtained through dynamic load simulation processing, such as deformation amount, stress distribution, etc.

[0116] Based on the mapping relationship between the set of key performance parameters and the predicted deformation amount of the deformation response model, the process of generating simulation performance data by performing dynamic load simulation processing on each candidate reinforcement material is as follows. First, establish the mapping relationship between the set of key performance parameters and the predicted deformation amount of the deformation response model. This mapping relationship can be established by methods such as experimental data fitting and machine learning algorithms. For example, using the multiple linear regression algorithm, with the key performance parameters as independent variables and the predicted deformation amount of the deformation response model as the dependent variable, establish a regression equation. Then, use tools such as finite element analysis software to perform dynamic load simulation processing on each candidate reinforcement material. During the simulation, use the key performance parameters as input parameters, apply dynamic loads similar to the actual situation in the high-risk monitoring area, solve the mechanical equilibrium equation of the model, and obtain simulation performance data such as the deformation amount and stress distribution of each material in the high-risk monitoring area. Finally, organize and analyze the simulation performance data to provide a basis for subsequent material screening.

[0117] Step S54B4: According to the coupling correlation between the material compressive strength decay rate and the environmental adaptation coefficient in the simulation performance data, screen out a subset of candidate materials that meet the preset durability conditions.

[0118] The material compressive strength decay rate is the decay speed of the compressive strength of the material during long-term loading, reflecting the durability of the material. The environmental adaptation coefficient is the performance change coefficient of the material under different environmental conditions (such as temperature, humidity, pH value, etc.), reflecting the environmental adaptability of the material. The coupling correlation is the mutual relationship between the material compressive strength decay rate and the environmental adaptation coefficient. The preset durability conditions are the conditions regarding the durability of the material preset according to the actual situation of the high-risk monitoring area and engineering requirements. The subset of candidate materials is the set of material types that meet the preset durability conditions selected from the set of candidate reinforcement material types.

[0119] According to the coupling correlation between the material compressive decay rate and the environmental adaptability coefficient in the simulated performance data, the process of screening a subset of candidate materials that meet the preset durability conditions is as follows. First, the compressive decay rate and environmental adaptability coefficient of each candidate reinforcement material are extracted from the simulated performance data. Then, the coupling correlation between the material compressive decay rate and the environmental adaptability coefficient is analyzed. This correlation can be analyzed by establishing a mathematical model, drawing a scatter plot, and other methods. For example, by establishing a regression model, the linear relationship between the compressive decay rate and the environmental adaptability coefficient is analyzed. Then, according to the preset durability conditions, the screening criteria are determined. The preset durability conditions may include an upper limit of the compressive decay rate, a lower limit of the environmental adaptability coefficient, and the like. Finally, according to the screening criteria, a subset of candidate materials that meet the preset durability conditions are screened out from the set of candidate reinforcement material types. Materials that do not meet the conditions are excluded.

[0120] Step S54B5: Perform long-term stability prediction processing on each material in the candidate material subset, combine the soil stratification data and moisture content distribution data of the high-risk monitoring area, and calculate the matching degree between the material penetration resistance and the interlayer shear strength.

[0121] The long-term stability prediction process is the process of predicting the performance changes of each material in the candidate material subset during long-term use. The material penetration resistance is the ability of the material to resist the penetration of liquid or gas. The interlayer shear strength is the shear strength between adjacent soil layers. The matching degree is the degree of fit between the material penetration resistance and the interlayer shear strength, which reflects the applicability of the material in the soil layer of the high-risk monitoring area.

[0122] For each material in the candidate material subset, a long-term stability prediction process is carried out, and the process of calculating the matching degree between the material's penetration resistance and the interlayer shear strength is as follows. First, a long-term stability prediction process is carried out for each material in the candidate material subset by means of accelerated aging tests, numerical simulations, etc. The accelerated aging test simulates the environmental conditions during the long-term use of the material, such as high temperature, high humidity, ultraviolet radiation, etc., to accelerate the aging process of the material, so as to predict the long-term performance changes of the material. Numerical simulation uses computer software to establish an aging model of the material, and by inputting relevant parameters, predicts the performance changes of the material during long-term use. Then, combining the soil layer stratification data and the moisture content distribution data in the high-risk monitoring area, the relationship between the material's penetration resistance and the interlayer shear strength is analyzed. For example, the moisture content of the soil layer will affect the material's penetration resistance and interlayer shear strength, and a higher moisture content may reduce the material's penetration resistance and interlayer shear strength. Next, the matching degree between the material's penetration resistance and the interlayer shear strength is calculated. Methods such as normalization processing and weighted average can be used to calculate the matching degree. For example, the material's penetration resistance and interlayer shear strength are respectively normalized, and then different weights are assigned according to their influence degrees on the material's performance in the soil layer, and the weighted average is calculated as the matching degree.

[0123] Step S54B6: Generate reinforcement material configuration parameters including the preferred sequence of material types, the gradient of the dosage per unit area, and the interlayer layout rules according to the constraint conditions of the matching degree and the resource allocation ratio.

[0124] The matching degree reflects the applicability of the material in the soil layer of the high-risk monitoring area, and the resource allocation ratio stipulates the amount of resources available for each material. The preferred sequence of material types is the sequence obtained by sorting the materials in the candidate material subset according to the matching degree, and the materials ranked higher are given priority. The gradient of the dosage per unit area is the change in the dosage of the reinforcement material per unit area at different positions in the high-risk monitoring area. The interlayer layout rule is the laying method and sequence of the reinforcement material between different soil layers.

[0125] According to the constraints of matching degree and resource allocation ratio, the process of generating reinforcement material configuration parameters is as follows. First, the materials in the candidate material subset are sorted according to the matching degree to form a material type optimization sequence. The higher the matching degree of the material, the higher the position in the sequence. Then, the unit area usage gradient is determined in combination with the resource allocation ratio and the actual situation of the high-risk monitoring area. For materials with higher matching degree, the unit area usage can be appropriately increased if resources permit; for materials with lower matching degree, the usage can be reduced. At the same time, considering the deformation degree and stress distribution at different locations in the high-risk monitoring area, the unit area usage of reinforcement materials is increased in areas with larger deformation and concentrated stress; and the usage is reduced in areas with smaller deformation and relatively uniform stress. Then, according to the performance characteristics of the material and the soil layer stratification data of the high-risk monitoring area, the interlayer layout rules are formulated. For example, for geogrids with better flexibility, they can be laid on the upper part of the soil layer to improve the tensile strength of the soil layer; for cement mixing piles with stronger rigidity, they can be laid deep into the deeper soil layer to improve the bearing capacity of the soil layer. Finally, the preferred sequence of material types, unit area usage gradient and interlayer layout rules are sorted out to form the reinforcement material configuration parameters.

[0126] As an implementation manner, the above process of generating the reinforcement material configuration parameters includes the following steps S54C1-S54C5: Step S54C1: Determine a set of candidate reinforcement material types according to the material type requirements of the optimal reinforcement solution.

[0127] The principle and implementation process of this step are the same as those of step S54B1. According to the specific requirements of the optimal reinforcement scheme for the type of reinforcement material, reinforcement materials that meet the requirements are collected by consulting materials, consulting experts and conducting market research to form a set of candidate reinforcement material types.

[0128] Step S54C2: Perform historical performance parameter analysis on each material in the candidate reinforcement material type set, and extract a set of key performance parameters associated with the stress distribution uniformity index of the high-risk monitoring area.

[0129] This step has the same principle and implementation process as step S54B2. The historical performance data of each material in the candidate reinforcement material type set is collected, sorted and analyzed to establish a performance database, and then the key performance parameters associated with the stress distribution uniformity index in the high-risk monitoring area are extracted according to the influencing factors of the index to form a key performance parameter set.

[0130] Step S54C3: Based on the mapping relationship between the key performance parameter set and the predicted deformation variable of the deformation response model, dynamic load simulation processing is performed on each candidate reinforcement material to generate simulated performance data of different materials in the high-risk monitoring area.

[0131] This step is the same as step S54B3 in terms of principle and implementation process. Establish the mapping relationship between the set of key performance parameters and the predicted deformation amount of the deformation response model, and use tools such as finite element analysis software to perform dynamic load simulation processing on each candidate reinforcement material, so as to obtain the simulated performance data of different materials in the high-risk monitoring area, such as deformation amount, stress distribution, etc.

[0132] Step S54C4: According to the coupling correlation between the material compressive attenuation rate and the environmental adaptation coefficient in the simulated performance data, screen out the subset of candidate materials that meet the preset durability conditions.

[0133] This step is the same as step S54B4 in terms of principle and implementation process. Extract the compressive attenuation rate and environmental adaptation coefficient of each candidate reinforcement material from the simulated performance data, analyze their coupling correlation, determine the screening criteria according to the preset durability conditions, and screen out the subset of candidate materials that meet the conditions from the set of candidate reinforcement material types.

[0134] Step S54C5: Perform long-term stability prediction processing on each material in the subset of candidate materials, and combine the soil layer stratification data and water content distribution data of the high-risk monitoring area to calculate the matching degree between the material penetration resistance and the interlayer shear strength.

[0135] This step is the same as step S54B5 in terms of principle and implementation process. Use methods such as accelerated aging tests and numerical simulations to perform long-term stability prediction processing on each material in the subset of candidate materials, combine the soil layer stratification data and water content distribution data of the high-risk monitoring area, analyze the relationship between the material penetration resistance and the interlayer shear strength, and calculate their matching degree.

[0136] Step S54C6: According to the constraint conditions of the matching degree and the resource allocation ratio, generate the reinforcement material configuration parameters including the preferred sequence of material types, the gradient of the dosage per unit area, and the interlayer layout rules.

[0137] This step is the same as step S54B6 in terms of principle and implementation process. Sort the materials in the subset of candidate materials according to the matching degree to form the preferred sequence of material types, combine the resource allocation ratio and the actual situation of the high-risk monitoring area to determine the gradient of the dosage per unit area, and formulate the interlayer layout rules according to the material performance characteristics and the soil layer stratification data, and finally generate the reinforcement material configuration parameters.

[0138] As an implementation manner, the method provided by the embodiment of the present invention may further include the following steps S600~S1000: Step S600: Periodically obtain the updated distributed optical fiber sensing data set of the target soil subgrade.

[0139] Periodic acquisition means collecting the distributed optical fiber sensing data of the target soil subgrade at time intervals. The updated distributed optical fiber sensing data set is the set of distributed optical fiber sensing data of the target soil subgrade collected at the current time point, including the latest optical fiber strain data sequence and temperature compensation data sequence.

[0140] The process of periodically acquiring the updated distributed optical fiber sensing data set of the target soil subgrade can be achieved in the following way. First, determine the data acquisition period according to the actual situation and monitoring requirements of the target soil subgrade. For example, for a soil subgrade with rapid deformation changes, a shorter acquisition period can be set, such as once a day; for a soil subgrade with relatively stable deformation, a longer acquisition period can be set, such as once a week. Then, use the distributed optical fiber sensors and optical fiber sensing demodulators pre-laid in the target soil subgrade to collect data according to the set acquisition period. During the acquisition process, ensure the accuracy and integrity of the data. For example, perform real-time verification on the collected data to promptly detect and correct errors in the data acquisition process. Finally, store and manage the collected updated distributed optical fiber sensing data set for subsequent analysis and processing.

[0141] Step S700: Regenerate the multi-dimensional deformation feature set of the monitoring area according to the updated distributed optical fiber sensing data set.

[0142] The principle and implementation process of this step are similar to those of step S300. According to the optical fiber strain data sequence and temperature compensation data sequence in the updated distributed optical fiber sensing data set, perform coupled analysis and processing on them to generate the multi-dimensional deformation feature set of the monitoring area. The specific process includes performing noise filtering and baseline calibration processing on the optical fiber strain data sequence to obtain the denoised and standardized strain data sequence; constructing a temperature-strain compensation coefficient matrix according to the temperature change trend of the temperature compensation data sequence, and performing temperature drift correction on the standardized strain data sequence to generate the corrected target strain data sequence; performing joint time-frequency domain analysis on the target strain data sequence to extract the time-domain deformation cumulative amount and frequency-domain perturbation response intensity of the monitoring area; calculating the stress cumulative correlation eigenvalue of the monitoring area according to the non-linear correlation relationship between the time-domain deformation cumulative amount and the frequency-domain perturbation response intensity; and fusing the time-domain deformation cumulative amount, frequency-domain perturbation response intensity, and stress cumulative correlation eigenvalue to generate the multi-dimensional deformation feature set of the monitoring area.

[0143] Step S800: Compare the difference between the regenerated multi-dimensional deformation feature set and the historical multi-dimensional deformation feature set, and extract the spatio-temporal propagation path characteristics of the difference.

[0144] The historical multi-dimensional deformation feature set is the multi-dimensional deformation feature set of the monitored area generated during previous monitoring processes. The difference quantity is the difference between the newly generated multi-dimensional deformation feature set and the historical multi-dimensional deformation feature set, reflecting the changes in the deformation situation of the monitored area at different time points. The spatio-temporal propagation path feature is the propagation law and feature of the difference quantity in time and space.

[0145] The process of extracting the spatio-temporal propagation path feature of the difference quantity by comparing the difference quantity between the newly generated multi-dimensional deformation feature set and the historical multi-dimensional deformation feature set is as follows. First, subtract the historical multi-dimensional deformation feature set from the newly generated multi-dimensional deformation feature set element by element to obtain the difference quantity. For example, for deformation rate features, stress accumulation correlation features, and environmental perturbation response features in the multi-dimensional deformation feature set, calculate their differences between the newly generated set and the historical set respectively. Then, use spatial analysis techniques and time series analysis methods to analyze the difference quantity and extract its spatio-temporal propagation path feature. For example, use Geographic Information System (GIS) technology to visually display the difference quantity in space and observe its propagation between different monitored areas; use time series clustering analysis methods to analyze the change law of the difference quantity in time and determine features such as the starting time and propagation speed of its propagation.

[0146] Step S900: Determine the deformation source area and the affected area chain according to the spatio-temporal propagation path feature, and update the dynamic matching rule of the preset deformation threshold condition based on the coupling attenuation coefficient between the deformation rate feature of the deformation source area and the stress accumulation correlation feature of the affected area chain.

[0147] The deformation source area is the area where deformation starts to occur in the soil subgrade and is the starting point of soil subgrade deformation. The affected area chain is a set of a series of monitored areas affected by the deformation propagation of the deformation source area, and these monitored areas are arranged in the order of deformation propagation. The coupling attenuation coefficient is the attenuation relationship coefficient between the deformation rate feature of the deformation source area and the stress accumulation correlation feature of the affected area chain, reflecting the attenuation degree of deformation during the propagation process. The dynamic matching rule of the preset deformation threshold condition is a rule for judging whether the deformation situation of the monitored area exceeds the preset threshold, and this rule will be dynamically updated according to the actual deformation situation of the soil subgrade.

[0148] The process of determining the deformation source area and the affected area chain based on the spatio-temporal propagation path characteristics and updating the dynamic matching rule of the preset deformation threshold condition is as follows. First, based on the spatio-temporal propagation path characteristics, the deformation source area is determined by retrospective analysis. For example, in the propagation path of the difference quantity, the monitoring area where the obvious difference first appears is found and determined as the deformation source area. Then, along the propagation path of the difference quantity, the affected area chain is determined. The affected monitoring areas can be determined in turn according to the spatial adjacency relationship between the monitoring areas and the propagation direction of the difference quantity, and they are arranged in the propagation order to form the affected area chain. Next, the relationship between the deformation rate characteristics of the deformation source area and the stress accumulation correlation characteristics of the affected area chain is analyzed, and the coupling attenuation coefficient is calculated. Methods such as regression analysis can be used to establish a regression model between the deformation rate characteristics and the stress accumulation correlation characteristics, and the coupling attenuation coefficient is determined through the model parameters. Finally, according to the coupling attenuation coefficient and the actual situations of the deformation source area and the affected area chain, the dynamic matching rule of the preset deformation threshold condition is updated. For example, for the monitoring areas in the affected area chain that are relatively close to the deformation source area, the preset deformation threshold condition is appropriately reduced; for the monitoring areas that are relatively far away, the preset deformation threshold condition is appropriately increased according to the coupling attenuation coefficient.

[0149] As an implementation manner, in step S900, determining the deformation source area and the affected area chain according to the spatio-temporal propagation path characteristics may specifically include the following steps S910 to S960: Step S910: Perform time series clustering analysis on the difference quantity to identify the set of monitoring areas with continuous deformation conduction characteristics.

[0150] Time series clustering analysis is to group the difference quantity according to the time series, so that the difference quantities within the same group have similar change trends and characteristics. The continuous deformation conduction characteristic means that there is a continuous propagation and influence relationship between the deformations of the monitoring areas. The set of monitoring areas is a set of a group of monitoring areas with continuous deformation conduction characteristics.

[0151] The process of performing time series clustering analysis on the amount of difference to identify the set of monitoring regions with continuous deformation conduction characteristics is as follows. First, arrange the amount of difference according to the monitoring regions and time to form multiple time series data. Each time series data represents the change of the amount of difference in a monitoring region over time. Then, select a suitable clustering algorithm, such as the K-means clustering algorithm, hierarchical clustering algorithm, etc., to perform clustering analysis on these time series data. Taking the K-means clustering algorithm as an example, first determine the number of clusters K, then randomly select K initial cluster centers, assign each time series data to the cluster where the nearest cluster center is located, and then update the cluster centers. Repeat the assignment and update process until the cluster centers no longer change. Finally, according to the clustering results, identify the set of monitoring regions with continuous deformation conduction characteristics. For monitoring regions that belong to the same cluster and are adjacent in space, it can be considered that they have continuous deformation conduction characteristics and they are grouped into a set of monitoring regions.

[0152] Step S920: Construct a deformation conduction topological network according to the change direction of the deformation rate and the transfer polarity of the stress accumulation correlation characteristics of the set of monitoring regions.

[0153] The change direction of the deformation rate is the change trend of the deformation rate of the monitoring region over time, such as whether the deformation rate is increasing or decreasing. The transfer polarity of the stress accumulation correlation characteristics is the direction and positive and negative nature of the transfer of the stress accumulation correlation characteristics between the monitoring regions. The deformation conduction topological network is a network used to describe the deformation conduction relationship between the monitoring regions. The nodes in the network represent the monitoring regions, and the edges represent the deformation conduction relationship between the monitoring regions.

[0154] The process of constructing a deformation conduction topological network according to the change direction of the deformation rate and the transfer polarity of the stress accumulation correlation characteristics of the set of monitoring regions is as follows. First, analyze the change direction of the deformation rate and the transfer polarity of the stress accumulation correlation characteristics of the monitoring regions in each set of monitoring regions. The change direction of the deformation rate can be determined by calculating the first derivative of the deformation rate, and the transfer polarity can be determined by analyzing the difference of the stress accumulation correlation characteristics between adjacent monitoring regions. Then, according to the change direction of the deformation rate and the transfer polarity, determine the deformation conduction relationship between the monitoring regions. If the deformation rate of a monitoring region increases and its stress accumulation correlation characteristics are transferred to the adjacent monitoring region, then it can be considered that there is a deformation conduction relationship from this monitoring region to the adjacent monitoring region. Finally, use the monitoring regions as nodes and the deformation conduction relationship as edges to construct a deformation conduction topological network. In the network, the direction of deformation conduction can be represented by a directed edge, and the strength of conduction can be represented by the weight of the edge.

[0155] Step S930: Backtrack to determine the initial conduction nodes of the deformation source region through the node connection strength and directional weight in the deformation conduction topological network.

[0156] The node connection strength is the tightness of the connection between nodes in the deformation conduction topology network, reflecting the strength of deformation conduction between monitoring regions. The directional weight is the weight of the directed edge in the deformation conduction topology network, indicating the direction and strength of deformation conduction. The initial conduction node is the starting node of the deformation source region in the deformation conduction topology network, which is the node where the deformation begins to spread.

[0157] The process of backtracking to determine the initial conduction node of the deformation source region through the node connection strength and directional weight in the deformation conduction topology network is as follows. First, select one or more nodes with a larger in-degree (i.e., more edges pointing to the node) in the deformation conduction topology network as candidate nodes. Nodes with a larger in-degree may be the source nodes of the deformation. Then, based on the node connection strength and directional weight, start backtracking analysis from the candidate nodes. Along the reverse direction of the directed edge, gradually trace the connection relationship between nodes and calculate the backtracking score of each node. The backtracking score can be calculated according to the node connection strength and directional weight. For example, the product of the node connection strength and directional weight is used as the backtracking score. Finally, select the node with the largest backtracking score as the initial conduction node of the deformation source region. This node is the node where the deformation begins to spread.

[0158] Step S940: Generate a conduction path map containing the chain of affected regions based on the spatial distribution relationship between the initial conduction node and the set of monitoring regions.

[0159] The spatial distribution relationship is the positional relationship in space between the initial conduction node and other monitoring regions in the set of monitoring regions. The conduction path map is a map used to display the path of deformation spreading from the initial conduction node to the chain of affected regions, which can intuitively show the direction of deformation propagation and the affected regions.

[0160] The process of generating a conduction path map containing the chain of affected regions based on the spatial distribution relationship between the initial conduction node and the set of monitoring regions is as follows. First, determine its corresponding monitoring region in space according to the position of the initial conduction node in the deformation conduction topology network. Then, starting from this monitoring region, along the directed edge in the deformation conduction topology network, sequentially determine the affected monitoring regions to form a chain of affected regions. Next, use tools such as Geographic Information System (GIS) to mark the initial conduction node and the chain of affected regions on the map, and connect these monitoring regions with lines according to the direction of deformation conduction to generate a conduction path map. In the map, different colors or line styles can be used to represent different intensities of deformation conduction to more intuitively display the propagation of deformation.

[0161] Step S950: Divide the deformation source region and the chains of affected regions at different levels according to the node attenuation gradient and the inter-region coupling strength in the conduction path map.

[0162] The node attenuation gradient is the degree of attenuation of the relevant characteristics of a node (such as the deformation rate, stress accumulation correlation characteristics, etc.) as the deformation propagates from the initial conduction node to the affected area chain in the conduction path map. The inter-region coupling strength is the degree of mutual influence between monitoring regions, reflecting the ease or difficulty of deformation propagation between regions.

[0163] The process of dividing the deformation source region and different levels of affected area chains according to the node attenuation gradient and inter-region coupling strength in the conduction path map is as follows. First, analyze the variation of the relevant characteristics of the nodes in the conduction path map with the propagation distance, and calculate the node attenuation gradient. For example, calculate the attenuation ratio of the deformation rate and stress accumulation correlation characteristics between adjacent nodes. Then, according to the inter-region coupling strength, determine the difficulty of deformation propagation between different monitoring regions. The inter-region coupling strength can be determined by analyzing factors such as the geological conditions and topographic features between the monitoring regions. Next, formulate a division criterion according to the node attenuation gradient and inter-region coupling strength. For example, when the node attenuation gradient reaches a set threshold or the inter-region coupling strength is weak, divide the region where the node is located into different levels of affected area chains. Finally, according to the division criterion, label and divide the deformation source region and different levels of affected area chains in the conduction path map.

[0164] Step S960: The division result is used to configure the blocking and reinforcement sequence for the conduction path and the cross-region resource scheduling path in the construction time sequence planning.

[0165] The division result clarifies the deformation source region and different levels of affected area chains, which has important guiding significance for the configuration of the blocking and reinforcement sequence and the cross-region resource scheduling path in the construction time sequence planning. The blocking and reinforcement sequence is to reinforce the monitoring regions on the conduction path in sequence during the reinforcement construction of the soil subgrade to block the propagation of deformation. The cross-region resource scheduling path is the path for allocating resources such as manpower, material resources, and financial resources between different monitoring regions.

[0166] The process of configuring the blocking and reinforcement sequence for the conduction path and the cross-regional resource scheduling path in the construction time sequence planning is as follows. First, according to the division results, determine the reinforcement priorities of the deformation source area and the affected area chains at different levels. The deformation source area is the starting point of the deformation and needs to be reinforced first to prevent the further spread of the deformation. For the affected area chains at different levels, determine the reinforcement sequence according to their distance from the deformation source area and the degree of influence. The areas closer to the deformation source area and more affected are reinforced first. Then, according to the reinforcement sequence, formulate a blocking and reinforcement plan for the conduction path. For example, set reinforcement measures at key nodes on the conduction path, such as reinforcing walls and strengthening supports, to block the spread of the deformation. Next, consider the cross-regional resource scheduling path. According to the resource requirements and distribution in different monitoring areas, rationally allocate resources such as manpower, material resources, and financial resources. For example, for the affected area chains with resource shortages, resources can be allocated from other areas with rich resources. When allocating resources, factors such as transportation costs and transportation times should be considered to select the optimal cross-regional resource scheduling path. Finally, incorporate the blocking and reinforcement sequence and the cross-regional resource scheduling path into the construction time sequence planning to ensure that the construction process can effectively block the spread of the deformation and improve the stability of the soil subgrade.

[0167] Step S1000: Regenerate the deformation warning information of the target soil subgrade according to the updated dynamic matching rules, and adjust the resource allocation ratio and construction time sequence planning in the soil subgrade deformation optimization strategy based on the priority of the deformation source area.

[0168] The updated dynamic matching rules are the rules for judging whether the deformation situation in the monitoring area exceeds the preset threshold updated according to factors such as the coupling attenuation coefficient of the deformation rate characteristics of the deformation source area and the stress accumulation correlation characteristics of the affected area chain. The deformation warning information is the warning information about the deformation situation of the target soil subgrade, including warning trigger conditions, risk area positioning marks, and recommended response time limits, etc. The resource allocation ratio is the allocation ratio of resources such as manpower, material resources, and financial resources among different monitoring areas in the soil subgrade deformation optimization strategy. The construction time sequence planning is the time arrangement and sequence planning for the reinforcement construction process.

[0169] The process of regenerating the deformation warning information of the target soil subgrade according to the updated dynamic matching rules and adjusting the resource allocation ratio and construction schedule planning in the soil subgrade deformation optimization strategy is as follows. First, perform spatio-temporal matching on the multi-dimensional deformation feature set of the regenerated monitoring area and the updated dynamic matching rules. According to the matching results, re-determine the warning situation of each monitoring area, including whether a warning is triggered, the warning level, etc. Then, generate the deformation warning information of the target soil subgrade according to the re-determined warning situation. The warning trigger condition can be determined according to the updated dynamic matching rules, the risk area positioning identifier can mark the monitoring area where the warning is triggered on the map through tools such as Geographic Information System (GIS), and the recommended response time limit can be determined according to the warning level and the actual situation of the monitoring area. Next, based on the priority of the deformation source area, adjust the resource allocation ratio in the soil subgrade deformation optimization strategy. The deformation source area is the key area of soil subgrade deformation and requires priority resource supply. Therefore, increase the resource allocation ratio for the deformation source area, such as increasing the number of construction personnel, allocating more reinforcement materials and equipment, etc. For the affected area chain, reasonably adjust the resource allocation ratio according to its degree of influence and warning level. Finally, according to the adjusted resource allocation ratio and deformation warning information, adjust the construction schedule planning. Prioritize the reinforcement construction of the deformation source area to ensure that the development of deformation can be controlled in time. For the affected area chain, reasonably arrange the construction time and sequence according to its reinforcement priority and resource supply situation. At the same time, consider the cross-regional resource scheduling path to ensure the smooth progress of the construction process. Through the above steps, the dynamic monitoring and optimization of the target soil subgrade are realized, and the stability and safety of the soil subgrade are improved.

[0170] It can be understood that in the above introductions of each embodiment of the present invention, various algorithms involved, such as filtering algorithms, difference methods, etc., can be obtained from relevant content in the prior art. For the sake of saving space, they will not be elaborated in the embodiments of the present application. In addition, those skilled in the art can make detailed supplements according to the common general knowledge in the art when implementing the solutions of the present application. For example, according to the general knowledge in the art, normalization can be used to eliminate the dimensional conflict before feature fusion, interpolation can be used to eliminate dimensional differences, the threshold can be reasonably set in combination with historical data, experience or business scenario requirements, and the model can be trained based on the general model training method, etc. The present application will no longer introduce the redundant implementation process in too much detail.

[0171] Please refer to Figure 2 , Figure 2Schematic structural diagram of a monitoring system provided by an embodiment of the present invention. The monitoring system may be a computer system in the background, such as a server, which at least includes a processor 101, a communication interface 102, and a memory 103. Among them, the processor 101, the communication interface 102, and the memory 103 can be connected through a bus or other means. Among them, the processor 101 (or Central Processing Unit, CPU) is the computing core and control core of the monitoring system, which can parse various instructions in the monitoring system and process various data of the monitoring system. The communication interface 102 can optionally include a standard wired interface, a wireless interface (such as WI-FI, a mobile communication interface, etc.), and can be used to transmit and receive data under the control of the processor 101; the communication interface 102 can also be used for the transmission and interaction of internal data in the monitoring system. The memory 103 (Memory) is a memory device in the monitoring system, used to store programs and data. It can be understood that the memory 103 here can include both the built-in memory of the monitoring system and, of course, the extended memory supported by the monitoring system. The memory 103 provides a storage space, and the storage space stores the operating system of the monitoring system, and the present invention does not limit this. In one embodiment, the processor 101 executes the soil subgrade deformation monitoring method based on distributed optical fiber provided above in the embodiments of the present invention by running the computer program in the memory 103.

Claims

1. A method for monitoring the deformation of soil subgrade based on distributed optical fiber, characterized in that, Including: Obtain a distributed optical fiber sensing data set of the target soil subgrade, where the distributed optical fiber sensing data set includes multiple spatio-temporally continuous optical fiber strain data sequences and temperature compensation data sequences; Divide the target soil subgrade into multiple monitoring areas with different deformation characteristics according to the deformation intensity distribution of the optical fiber strain data sequences; Perform coupled analysis and processing on the optical fiber strain data sequences and the temperature compensation data sequences of each monitoring area to generate a multi-dimensional deformation feature set of the monitoring area; The multi-dimensional deformation feature set includes deformation rate features, stress accumulation correlation features, and environmental disturbance response features; Generate deformation warning information for the target soil subgrade according to the spatio-temporal matching result between the multi-dimensional deformation feature set and the preset deformation threshold condition; Generate a soil subgrade deformation optimization strategy based on the deformation warning information and feedback the soil subgrade deformation optimization strategy to the subgrade maintenance system to trigger a reinforcement response operation.

2. The method according to claim 1, wherein The step of dividing the target soil subgrade into multiple monitoring areas with different deformation characteristics according to the deformation intensity distribution of the optical fiber strain data sequences includes: Perform segmented gradient calculation on the optical fiber strain data sequence to extract the maximum deformation gradient value and the average deformation fluctuation amplitude of each optical fiber segment; Assign a deformation intensity level to each optical fiber segment based on the ratio of the maximum deformation gradient value to the average deformation fluctuation amplitude; Cluster the continuously distributed optical fiber segments with the same or adjacent deformation intensity levels into initial candidate monitoring areas, and adjust the regional boundaries of the initial candidate monitoring areas according to the deformation intensity level fluctuation range of the initial candidate monitoring areas; Perform regional merging or splitting processing on the adjusted initial candidate monitoring areas according to the preset regional division density requirement to generate a final regional division result including the multiple monitoring areas; Wherein, the different deformation characteristics are jointly characterized by the median and standard deviation of the deformation intensity levels of each monitoring area.

3. The method according to claim 2, wherein The step of performing coupled analysis and processing on the optical fiber strain data sequences and the temperature compensation data sequences of each monitoring area to generate a multi-dimensional deformation feature set of the monitoring area includes: Perform noise filtering and baseline calibration processing on the optical fiber strain data sequence to obtain a denoised standardized strain data sequence; Construct a temperature strain compensation coefficient matrix according to the temperature change trend of the temperature compensation data sequence, and perform temperature drift correction on the standardized strain data sequence through the temperature strain compensation coefficient matrix to generate a corrected target strain data sequence; Perform joint time-frequency domain analysis on the target strain data sequence to extract the time-domain deformation accumulation amount and the frequency-domain disturbance response intensity of the monitoring area; Calculate the stress accumulation correlation eigenvalue of the monitoring area according to the non-linear correlation relationship between the time-domain deformation accumulation amount and the frequency-domain disturbance response intensity; Fuse the time-domain deformation accumulation amount, the frequency-domain disturbance response intensity, and the stress accumulation correlation eigenvalue to generate the multi-dimensional deformation feature set of the monitoring area.

4. The method according to claim 3, characterized in that Generating the deformation warning information of the target soil subgrade according to the spatio-temporal matching result of the multi-dimensional deformation feature set and the preset deformation threshold condition, includes: Obtaining the historical deformation feature library of the monitoring area, where the historical deformation feature library contains the multi-dimensional deformation feature data of multiple historical deformation cases and the corresponding deformation evolution results; Performing similarity matching between the multi-dimensional deformation feature set and the feature data in the historical deformation feature library to determine the current deformation mode of the monitoring area and the target matching case of the historical deformation case; Predicting the deformation development trend of the monitoring area according to the deformation evolution result of the target matching case, and generating a preliminary warning level based on the deviation degree between the deformation development trend and the preset deformation threshold condition; Combining the spatial distribution correlation of the preliminary warning levels of adjacent monitoring areas to perform spatio-temporal correction processing on the preliminary warning level to generate the final warning level of the monitoring area; Generating the overall deformation warning information of the target soil subgrade based on the spatial superposition result of the final warning levels of all monitoring areas; the deformation warning information includes warning trigger conditions, risk area positioning identifiers, and recommended response time limits.

5. The method according to claim 4, characterized in that, Generating the soil subgrade deformation optimization strategy based on the deformation warning information, includes: Determining at least one high-risk monitoring area that needs to be preferentially processed in the target soil subgrade according to the risk area positioning identifier; Obtaining the geological structure data and historical maintenance records of the high-risk monitoring area, and constructing a deformation response model for the high-risk monitoring area; Based on the deformation response model, simulating the deformation suppression effects of different reinforcement schemes on the high-risk monitoring area, and screening the optimal reinforcement scheme according to the simulation effects; Generating the soil subgrade deformation optimization strategy including reinforcement material configuration parameters, construction time sequence planning, and resource allocation ratio according to the recommended response time limit and the optimal reinforcement scheme; Wherein, the resource allocation ratio is adjusted according to the deformation warning level of the high-risk monitoring area and the resource requirements of the remaining monitoring areas.

6. The method according to claim 5, characterized in that The construction process of the deformation response model includes: Collecting the soil layer stratification data, moisture content distribution data, and load history data of the high-risk monitoring area; Constructing a layered geomechanics model based on the soil layer stratification data, and correcting the interlayer shear strength parameters of the layered geomechanics model through the moisture content distribution data; Inputting the load history data into the corrected layered geomechanics model to calculate the theoretical deformation response curve of the high-risk monitoring area under different load scenarios; Calibrating the parameter error of the layered geomechanics model by comparing the theoretical deformation response curve with the actual deformation monitoring data of the high-risk monitoring area to obtain the calibrated deformation response model; Wherein, the calibration process of the parameter error adopts an iterative feedback mechanism until the matching degree between the theoretical deformation response curve and the actual deformation monitoring data reaches a preset threshold.

7. The method according to claim 6, characterized in that Simulating the deformation suppression effects of different reinforcement schemes on the high-risk monitoring area, includes: Obtain a set of candidate reinforcement solutions, where the set of candidate reinforcement solutions includes various combinations of reinforcement material types, layout densities, and structural forms; Input the parameters of each candidate reinforcement solution into the deformation response model, and calculate the predicted deformation amount and the stress distribution uniformity index of the high-risk monitoring area after applying the reinforcement; According to the difference between the predicted deformation amount and the preset safety deformation threshold, and the deviation degree of the stress distribution uniformity index from the ideal distribution, assign a comprehensive suppression score to each candidate reinforcement solution; Sort all candidate reinforcement solutions based on the comprehensive suppression score, and select the candidate reinforcement solution with the highest score as the optimal reinforcement solution; Among them, the comprehensive suppression score is obtained by weighted fusion of the normalized values of the difference and the deviation degree, and the weight coefficient is configured according to the warning level of the high-risk monitoring area.

8. The method according to claim 7, wherein The generation process of the construction time sequence plan includes: Determine the supply cycle and transportation path of the required materials and equipment according to the reinforcement material configuration parameters; Based on the distribution density and traffic accessibility of the high-risk monitoring area, divide multiple construction sub-areas and assign construction priorities; Combine the resource allocation ratio and the supply cycle to configure the construction time window and the human resource scheduling plan for each construction sub-area; Optimize the parallel execution strategy of the human resource scheduling plan according to the overlap of the construction time windows and the equipment reuse requirements; Generate the construction time sequence plan including the construction sub-areas, construction time windows, parallel execution strategy, and emergency adjustment mechanism.

9. The method according to claim 1, wherein The method further includes: Periodically obtain the updated distributed optical fiber sensing data set of the target soil subgrade; Regenerate the multi-dimensional deformation feature set of the monitoring area according to the updated distributed optical fiber sensing data set; Compare the difference between the regenerated multi-dimensional deformation feature set and the historical multi-dimensional deformation feature set, and extract the spatio-temporal propagation path characteristics of the difference; Determine the deformation source area and the affected area chain according to the spatio-temporal propagation path characteristics, and update the dynamic matching rule of the preset deformation threshold condition based on the coupling attenuation coefficient between the deformation rate characteristics of the deformation source area and the stress accumulation correlation characteristics of the affected area chain; Regenerate the deformation warning information of the target soil subgrade according to the updated dynamic matching rule, and adjust the resource allocation ratio and the construction time sequence plan in the soil subgrade deformation optimization strategy based on the priority of the deformation source area; Among them, the determination of the deformation source area and the affected area chain according to the spatio-temporal propagation path characteristics includes: Perform time series clustering analysis on the difference to identify a set of monitoring areas with continuous deformation conduction characteristics; Construct a deformation conduction topology network according to the deformation rate change direction of the monitoring area set and the transmission polarity of the stress accumulation correlation characteristics; Backtrack and determine the initial conduction node of the deformation source area through the node connection strength and directional weight in the deformation conduction topology network; Generate a conduction path map including the affected area chain based on the spatial distribution relationship between the initial conduction node and the monitoring area set; Divide the deformation source area and different levels of affected area chains according to the node attenuation gradient and the inter-region coupling strength in the conduction path map; The division result is used to configure the blocking and strengthening sequence for the conduction path and the cross-region resource scheduling path in the construction time sequence planning.

10. A monitoring system, characterized in that, Including: A memory in which a computer program is stored; A processor for loading the computer program to implement the method for monitoring the deformation of the soil subgrade based on distributed optical fiber according to any one of claims 1-9.

Images