Roadbed service condition evaluation method and device, computer device and storage medium

Abstract

The application provides a roadbed service condition evaluation method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring roadbed data of each mileage section in a roadbed section to be monitored; determining a corresponding deviation threshold according to single-day monitoring data of each roadbed disease type; and removing error data in the roadbed data of each mileage section according to the deviation threshold. The roadbed data of each mileage section from which the error data is removed is corrected to obtain roadbed correction data of each mileage section. Disease degree evaluation is performed on the roadbed correction data of each mileage section to obtain the service state of the roadbed section to be monitored. The application improves the quality and accuracy of the monitoring data by acquiring various disease data and performing correction processing on the data, ensures that the subsequent evaluation index can more accurately reflect the roadbed health condition, and guarantees the accuracy and reliability of the evaluation.

Description

Technical Field

[0001] This invention relates to the field of road or building structure safety testing technology, and in particular to a method, apparatus, computer equipment and storage medium for assessing the service condition of roadbeds. Background Technology

[0002] Railway subgrade is a crucial component of railway operations, and its safety and reliability significantly impact railway operations. However, over long-term use, due to factors such as the natural environment, operational load, and geological structure, the condition of railway subgrade gradually changes, potentially leading to problems such as settlement, deformation, and damage. In severe cases, these issues can threaten the safety and normal operation of the railway.

[0003] Traditional methods for monitoring and assessing the condition of railway subgrade typically involve manual inspections and periodic testing, which suffer from drawbacks such as low monitoring frequency, incomplete data collection, and low efficiency in data analysis and processing. With the continuous development and maturation of Internet of Things (IoT) technology, utilizing wireless sensor networks, cloud computing, and other technologies to achieve real-time monitoring and assessment of railway subgrade condition has become a research hotspot.

[0004] Current research has proposed methods for monitoring and evaluating the condition of railway subgrade based on the Internet of Things (IoT). For example, patent publication number CN108197374A discloses an automatic monitoring method and system for potential structural hazards in railway subgrade, which includes the following steps: Presetting structural modal safety range values ​​and structural morphological safety range values ​​for the railway subgrade in a cloud platform, and establishing structural modal damage alarm models and structural morphological damage alarm models respectively; using the changes in the railway subgrade when a vehicle passes by as a dynamic stimulus, and utilizing several field terminals installed on the railway subgrade to detect the structural modal and structural morphological characteristics of the railway subgrade; when a vehicle passes by a field terminal, the field terminal transmits the structural modal and structural morphological information to the vehicle; the vehicle transmits the structural modal and structural morphological information to the cloud platform.

[0005] However, the aforementioned technologies do not disclose how to process and analyze monitoring data, so some problems still exist, such as data defects and inaccurate evaluation indicators, which affect the monitoring effect and evaluation accuracy. Summary of the Invention

[0006] Therefore, it is necessary to provide a method, apparatus, computer equipment, and storage medium for assessing the service condition of roadbeds to address the aforementioned technical problems.

[0007] Firstly, a method for assessing the service condition of roadbeds is provided, as follows:

[0008] A method for assessing the service condition of roadbeds includes:

[0009] Obtain roadbed data for each mileage segment in the roadbed section to be monitored, wherein the roadbed data includes monitoring data for at least two types of roadbed defects;

[0010] Based on the daily monitoring data of each type of roadbed defect, the corresponding deviation threshold is determined, and based on the deviation threshold, the error data in the roadbed data of each mileage segment is removed.

[0011] The roadbed data of each mileage segment after removing the error data is corrected to obtain the corrected roadbed data for each mileage segment;

[0012] The damage level of the subgrade correction data for each mileage segment is assessed to obtain the service status of the subgrade segment to be monitored.

[0013] In one embodiment, determining the corresponding deviation threshold based on the daily monitoring data of each of the roadbed defect types, and removing error data from the roadbed data of each mileage segment based on the deviation threshold, includes:

[0014] Calculate the average value of at least the first N sets of data in the daily monitoring data, where N is greater than or equal to 2;

[0015] The standard deviation of the daily monitoring data is calculated based on the average value, and the standard deviation of a preset multiple is used as the deviation threshold.

[0016] Calculate the offset distance between each group of data after the Nth group of data in the daily monitoring data and the average value, and determine the monitoring data whose offset distance is greater than the deviation threshold as the error data;

[0017] Remove the aforementioned error data.

[0018] In one embodiment, correcting the roadbed data for each mileage segment after removing the error data to obtain corrected roadbed data for each mileage segment includes:

[0019] Mark null values ​​at the positions where the error data was not removed;

[0020] The missing values ​​are interpolated and corrected using an interpolation method to obtain the roadbed correction data for each mileage segment.

[0021] In one embodiment, the roadbed data includes subgrade data, embankment data, and cut data. The subgrade data includes monitoring data for at least two types of subgrade-related defects, the embankment data includes monitoring data for at least two types of embankment-related defects, and the cut data includes monitoring data for at least two types of cut-related defects.

[0022] In one embodiment, the assessment of the severity of damage to the subgrade correction data for each of the mileage segments includes at least one of the following:

[0023] The monitoring data of at least two types of diseases related to the substrate are evaluated using a preset disease assessment model to obtain a substrate disease score matrix. A preset severity level membership function is then used to obtain a substrate fuzzy comprehensive judgment matrix based on the substrate disease score matrix. Finally, the substrate status level is obtained based on the substrate disease score matrix and the substrate fuzzy comprehensive judgment matrix.

[0024] and / or

[0025] The monitoring data of at least two types of embankment-related defects are evaluated using the pre-defined defect assessment model to obtain an embankment defect score matrix. A fuzzy comprehensive judgment matrix is ​​then obtained based on the embankment defect score matrix using a pre-defined severity level membership function. Finally, the embankment condition level is determined based on both the embankment defect score matrix and the fuzzy comprehensive judgment matrix.

[0026] and / or

[0027] The monitoring data of at least two types of road cut-related defects are evaluated using the preset defect assessment model to obtain a road cut defect score matrix. A road cut fuzzy comprehensive judgment matrix is ​​obtained based on the road cut defect score matrix using a preset severity level membership function. The road cut status level is obtained based on the road cut defect score matrix and the road cut fuzzy comprehensive judgment matrix.

[0028] Based on the preset mileage-to-location judgment matrix, the degree of damage of each mileage segment is obtained according to the subgrade condition level and / or embankment condition level and / or cutting condition level of each mileage segment.

[0029] In one embodiment, the step of assessing the severity of roadbed damage based on the roadbed correction data for each of the mileage segments further includes:

[0030] Obtain the severity level corresponding to each of the aforementioned disease types, and obtain the corresponding weight based on each severity level;

[0031] Determine the number of different severity levels of defects within the subgrade correction data for each mileage segment.

[0032] The calculation formula for the preset disease assessment model is as follows:

[0033]

[0034] Among them, S j This indicates the score for disease type j; C i This indicates the number of type j diseases with a severity level of i; Wi This represents the weight of the severity level of a disease of type j as type i.

[0035] In one embodiment, the preset severity level membership function is as follows:

[0036] A-level membership function:

[0037]

[0038] B-level membership function:

[0039]

[0040] C-level membership function:

[0041]

[0042] D-level membership function:

[0043]

[0044] E-level membership function:

[0045]

[0046] Where a1, a2, a3, a4, and a5 are preset membership function parameters, and the membership functions from level A to level E represent the severity levels from high to low.

[0047] Secondly, a method for assessing the service condition of roadbeds is provided, as follows:

[0048] A roadbed service condition assessment device includes:

[0049] The acquisition module is used to acquire roadbed data for each mileage segment in the roadbed section to be monitored, wherein the roadbed data includes monitoring data for at least two types of roadbed defects;

[0050] The elimination module is used to determine the corresponding deviation threshold based on the daily monitoring data of each type of roadbed defect, and to eliminate the error data in the roadbed data of each mileage segment based on the deviation threshold.

[0051] The correction module is used to correct the roadbed data of each mileage segment after the error data has been removed, so as to obtain the roadbed correction data of each mileage segment.

[0052] The evaluation module is used to evaluate the damage degree of the subgrade correction data of each mileage segment to obtain the service status of the subgrade segment to be monitored.

[0053] Thirdly, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the roadbed service condition assessment method described in any of the preceding claims.

[0054] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the roadbed service condition assessment method described in any of the preceding claims.

[0055] The aforementioned methods, devices, computer equipment, and storage media for assessing the service condition of roadbeds acquire relevant roadbed information, such as temperature, strain, and vibration. The collected data is processed, including preprocessing steps such as data filtering, noise reduction, and normalization, to improve data quality and accuracy. The preprocessed data is then fed into an assessment index system unit for further processing. This unit comprehensively considers multiple factors, such as temperature, strain, and vibration, to calculate a comprehensive evaluation index reflecting the health condition of the roadbed, ensuring the accuracy and reliability of the evaluation indicators. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating a method for assessing the service condition of a roadbed in one embodiment;

[0057] Figure 2 This is a schematic diagram of the membership parameters for railway subgrade evaluation in one embodiment;

[0058] Figure 3 This is an internal structural diagram of a computer device in one embodiment;

[0059] Figure 4 This is a statistical table of the number of diseases in one embodiment;

[0060] Figure 5 This is a table of subgrade disease level weights, embankment disease level weights, and cut disease level weights in one embodiment;

[0061] Figure 6 This is a severity level score matrix for each mileage segment in one embodiment;

[0062] Figure 7 This is a schematic diagram of a roadbed service condition assessment device in one embodiment;

[0063] Figure 8 This is a framework diagram of a comprehensive evaluation system for the service status of roadbeds in one embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] Example 1

[0066] In this embodiment, as Figure 1 As shown, a method for assessing the service condition of a roadbed includes:

[0067] Step 110: Obtain roadbed data for each mileage segment in the roadbed section to be monitored, wherein the roadbed data includes monitoring data for at least two types of roadbed defects.

[0068] In this embodiment, roadbed data for each mileage segment in each roadbed section to be monitored is obtained through a variety of monitoring devices, including inclinometers, moisture meters, guy wire displacement gauges, ultrasonic water level gauges, etc.

[0069] The selection of monitoring equipment is determined based on actual monitoring needs. Different roadbeds require different defect data for monitoring. For example, railway roadbeds and road roadbeds require different defect data when assessing their service status, and the corresponding monitoring equipment is also different. No restrictions are imposed here.

[0070] To facilitate the acquisition of roadbed data, all selected monitoring equipment is equipped with wireless sensor network hardware to support real-time data acquisition and transmission. Corresponding monitoring equipment is installed at each mileage section to acquire monitoring data for different types of roadbed defects, ensuring a more comprehensive understanding of the roadbed's condition.

[0071] Step 120: Based on the daily monitoring data of each type of roadbed defect, determine the corresponding deviation threshold, and based on the deviation threshold, remove the error data from the roadbed data of each mileage segment.

[0072] In this embodiment, the service status of the railway subgrade is monitored in real time, and daily monitoring data of defect A and defect B are obtained through monitoring equipment.

[0073] In actual monitoring, abnormal monitoring conditions or equipment failures often lead to error values ​​in the monitoring data, affecting subsequent data analysis and processing results. Therefore, it is necessary to remove these error values.

[0074] Correspondingly, based on the daily monitoring data of disease A, a deviation threshold for the monitoring data of disease A is determined, and then erroneous data in the daily monitoring data of disease A is removed based on the deviation threshold. Similarly, based on the daily monitoring data of disease B, a deviation threshold for the monitoring data of disease B is determined, and then erroneous data in the daily monitoring data of disease B is removed based on the deviation threshold, thus completing the removal of erroneous data from the roadbed data for the corresponding mileage section.

[0075] In actual monitoring data, there may be more than dozens of disease types. By removing the error values ​​from the monitoring data of each disease according to the above method, more reliable mileage monitoring data can be obtained.

[0076] The deviation threshold is set based on the specific type of roadbed defects and data characteristics, and is determined through statistical analysis or expert experience.

[0077] Step 130: Correct the roadbed data of each mileage segment after removing the error data to obtain the corrected roadbed data for each mileage segment.

[0078] Removing erroneous data reduces the amount of monitoring data, which may affect subsequent data analysis and result interpretation. Therefore, it is necessary to correct the roadbed data for each mileage segment after removing the erroneous data.

[0079] In one embodiment, correction is performed using interpolation, where the value of the unknown point is extrapolated from the known data points in the daily monitoring data to fill in the missing parts of the data.

[0080] In one embodiment, an average substitution method is used for correction, replacing the discarded error value with the average value of the daily monitoring data. This method is more suitable for situations where the proportion of missing data is small.

[0081] In another embodiment, correction is performed using a locally weighted smoothing method. This method corrects for missing data points by applying a weighted average to the data surrounding them. This approach avoids the bias introduced by a global average and better preserves the overall trend of the data.

[0082] When correcting data, it is necessary to comprehensively consider factors such as data quality, data type, and data distribution, select an appropriate correction method, and conduct appropriate comparisons and evaluations. No restrictions are imposed here.

[0083] Step 140: Assess the damage level of the subgrade correction data for each mileage segment to obtain the service status of the subgrade segment to be monitored.

[0084] In this embodiment, the degree of damage to the corresponding mileage section is determined by first comprehensively evaluating the monitoring data of roadbed defects, and then the service status of the entire roadbed section to be monitored is determined by comprehensively judging the degree of damage to each mileage section.

[0085] Data on defects at a single mileage segment may be affected by local factors and cannot fully reflect the condition of the entire roadbed. By combining data from multiple mileage segments, the impact of individual local factors can be reduced, and the accuracy of defect assessment can be improved.

[0086] Simultaneously, by integrating damage data from multiple mileage sections, areas with more severe damage within the entire roadbed can be identified, enabling the development of targeted maintenance plans. Based on the damage assessment results, it can be determined which sections require priority repair or reinforcement to ensure the safety and reliability of the entire roadbed.

[0087] Furthermore, by analyzing damage data from multiple mileage sections, the distribution trends and evolution patterns of damage can be observed. This allows for better prediction of the types and severity of damage that may occur in a future section, enabling timely maintenance preparations and extending the service life of the roadbed.

[0088] The steps for assessing the severity of roadbed damage based on the roadbed correction data for each of the aforementioned mileage sections include the following:

[0089] A: Determine the disease assessment indicators.

[0090] Evaluation indicators include the severity of disease, the rate of disease expansion, and the degree of impact of disease on the overall performance of the roadbed. The specific indicators can be selected based on the actual situation and professional knowledge, and there are no restrictions here.

[0091] B: Calculate the disease severity assessment index.

[0092] Based on the roadbed correction data and the determined evaluation indicators, the average value, maximum value, standard deviation, etc. of each indicator are calculated to reflect the overall condition of the disease.

[0093] C: Define the service status boundaries.

[0094] After the disease severity assessment is completed, different service status boundaries are defined based on the assessment results. For example, the disease severity is divided into three levels: slight, moderate, and severe, and the specific index range for each level is determined.

[0095] D: Determine the service status of the roadbed section to be monitored.

[0096] Based on the damage assessment results of the subgrade correction data and the defined service condition limits, the service condition of the subgrade section to be monitored is determined.

[0097] For example, if the damage assessment value of a certain section is within the minor range, it can be determined that the section is in normal service condition; if the assessment value is within the moderate or severe range, it means that the section needs attention and corresponding maintenance measures.

[0098] In one embodiment, determining the corresponding deviation threshold based on the daily monitoring data of each of the roadbed defect types, and removing error data from the roadbed data of each mileage segment based on the deviation threshold, includes:

[0099] Calculate the average value of at least the first N sets of data in the daily monitoring data, where N is greater than or equal to 2;

[0100] The standard deviation of the daily monitoring data is calculated based on the average value, and the standard deviation of a preset multiple is used as the deviation threshold.

[0101] Calculate the offset distance between each group of data after the Nth group of data in the daily monitoring data and the average value, and determine the monitoring data whose offset distance is greater than the deviation threshold as the error data;

[0102] Remove the aforementioned error data.

[0103] In this embodiment, the monitoring data at the target time is compared with the monitoring data over a standard time period. This method is applicable to different types of monitoring equipment, such as level gauges, hydrostatic levels, transverse settlement tubes, and fixed inclinometers.

[0104] Taking a level gauge as an example, the following is a detailed explanation:

[0105] A: Calculate the mean

[0106] For the imported daily level gauge deformation data, collect the first n (n≥15) sets of data and calculate the average of the first n sets of data, i.e.:

[0107]

[0108] B: Calculate the standard deviation

[0109] The standard deviation of the daily deformation of the level gauge based on these n sets of data is used to measure the dispersion of the data. The calculation method is as follows:

[0110]

[0111] C: Calculate offset distance

[0112] The formula for calculating the offset distance between each data set after the nth set in the daily monitoring data and the average value is as follows:

[0113]

[0114] D: Determine the deviation threshold and error data

[0115] In this implementation, the preset multiplier is 3, and the deviation threshold is 3σ. The offset distance between the (n+1)th group of data and the average value is compared with the deviation threshold 3σ.

[0116]

[0117] If the data is found to be abnormally disturbed and is considered error data, it will be deleted and marked as null; otherwise, it will be retained as normal data.

[0118] In other possible embodiments, the preset multiple can be 2 or 5, or any natural number, and there is no specific limitation here.

[0119] In one embodiment, the monitoring data is screened for missing values ​​based on the monitoring time sequence. For missing data screening, the monitoring data values ​​in the database are checked recursively according to a preset monitoring sampling frequency. If no missing values ​​are found, they are marked as missing data and recorded as null values.

[0120] The following is an example of the monitoring data from level gauges and automatic inclinometers commonly used in railway subgrade monitoring:

[0121] (1) Screening of level gauge error data

[0122] For the data collected by the level gauge, the system screens the data collected twice. When the data collected in the second time is 0, it indicates that the level gauge is abnormal. The data collected in the second time is confirmed to be invalid and marked as null.

[0123] (2) Screening of error data from automatic inclinometer

[0124] For the monitoring data of the automatic inclinometer, the system will screen whether all three included angles are 0°. When all three included angles are 0°, it indicates that the inclinometer is damaged, the corresponding monitoring data is confirmed to be invalid and marked as null value.

[0125] In one embodiment, correcting the roadbed data for each mileage segment after removing the error data to obtain corrected roadbed data for each mileage segment includes:

[0126] Mark null values ​​at the positions where the error data was not removed;

[0127] The missing values ​​are interpolated and corrected using an interpolation method to obtain the roadbed correction data for each mileage segment.

[0128] There are various interpolation methods, such as nearest neighbor interpolation, linear interpolation, Lagrange interpolation, and spline interpolation. In this embodiment, Lagrange interpolation is used to interpolate and correct for missing values.

[0129] Lagrange interpolation is a method based on interpolation polynomials for known discrete data points, which can be used to interpolate missing data. The implementation will be illustrated using monitoring data from a level gauge as an example.

[0130] Specifically, for n+1 known discrete data points (x_i, y_i), i = 0, 1, the following Lagrange interpolation polynomial can be constructed:

[0131] Suppose there are three different time points t. i (i = 1, 2, 3), where the single deformation amounts corresponding to times t1 and t3 are f1 and f3, respectively. At time t2, due to the omission of data from the level gauge or its identification as error data, the current single deformation amount f2 is a null value. Now, it is necessary to use the Lagrange polynomial to interpolate and calculate f2.

[0132] In the null value processing of level gauges, for given data points (x_0,y_0), (x_2,y_2), and (x_3,y_3), a Lagrange interpolation polynomial can be constructed, and the value of x_1 can be substituted into it for interpolation to obtain the estimated value of y_1.

[0133] The Lagrange interpolation polynomial is shown below:

[0134]

[0135] Substituting t = t2 into equation (4), we obtain p(t2), which can be considered as f2.

[0136] In one embodiment, the roadbed data includes subgrade data, embankment data, and cut data. The subgrade data includes monitoring data for at least two types of subgrade-related defects, the embankment data includes monitoring data for at least two types of embankment-related defects, and the cut data includes monitoring data for at least two types of cut-related defects.

[0137] like Figure 2 As shown, in this embodiment, the railway subgrade is evaluated, wherein:

[0138] The types of diseases in the subgrade data are subsidence and outward extrusion, frost heave and mud sluice, frost damage, sinkholes and other diseases;

[0139] The types of damage in the embankment data are slope collapse, embankment settlement, slope erosion, landslide, frost damage, and waterlogged embankment;

[0140] The types of damage in the road cut data are landslides, slope collapses, slope erosion, unstable rocks and falling rocks, and frost damage.

[0141] In one embodiment, the step of assessing the severity of roadbed damage based on the roadbed correction data for each of the mileage segments further includes:

[0142] Obtain the severity level corresponding to each of the aforementioned disease types, and obtain the corresponding weight based on each severity level;

[0143] Determine the number of different severity levels of defects within the subgrade correction data for each mileage segment.

[0144] The calculation formula for the preset disease assessment model is as follows:

[0145]

[0146] Among them, S j This indicates the score for disease type j; C i This indicates the number of type j diseases with a severity level of i; W i This represents the weight of the severity level of a disease of type j as type i.

[0147] In this embodiment, as Figure 2 As shown, the severity level of each disease type is divided into 5 levels: A, B, C, D and E, with the severity level gradually decreasing from A to E.

[0148] In one embodiment, the preset severity level membership function is as follows:

[0149] A-level membership function:

[0150]

[0151] B-level membership function:

[0152]

[0153] C-level membership function:

[0154]

[0155] D-level membership function:

[0156]

[0157] E-level membership function:

[0158]

[0159] Where a1, a2, a3, a4, and a5 are preset membership function parameters, and their specific values ​​are as follows: Figure 4 As shown.

[0160] In the step of obtaining the corresponding weight based on each severity level, the weights are determined according to the Analytic Hierarchy Process (AHP). The AHP method is a method of organizing a problem according to certain principles to form a complete structural model, and then performing qualitative and quantitative analysis on this basis.

[0161] The specific steps for determining the weights are as follows:

[0162] (1) Establish a hierarchical analysis model to divide the decision problem into the target layer, the criterion layer and the alternative layer.

[0163] (2) Construct the judgment matrix by comparing factors pairwise.

[0164] (3) Hierarchical single sorting and consistency test: The consistency test of the judgment matrix requires the calculation of consistency indices (CI, RI) and consistency ratio (CR). When CR < 0.1, the consistency of the judgment matrix is ​​considered to be passed. The calculation formula is as follows:

[0165]

[0166] In the formula λ max To determine the largest eigenvalue of the matrix, where n is the number of factors and λ' is the eigenvalue. max The average value of the largest eigenvalue is obtained by randomly constructing 500 judgment matrices.

[0167] In this embodiment, the preset disease judgment matrix of the substrate bed is [0.1429 0.2439 0.4714 0.0959 0.0459], and its CR = 0.0580 < 0.1, so the consistency of the matrix is ​​passed.

[0168] The embankment defect judgment matrix = [0.1043 0.0353 0.0648 0.2374 0.3999 0.1583] has a CR of 0.0709 < 0.1, so the matrix consistency is passed.

[0169] The road cut defect judgment matrix = [0.2406 0.0705 0.0512 0.1598 0.4779] has a CR of 0.0506 < 0.1, so the matrix consistency is passed.

[0170] (4) Hierarchical overall ranking and consistency test to obtain the ranking weight of each factor to the overall goal.

[0171] The assessment of the severity of damage to the subgrade correction data for each of the aforementioned mileage sections includes at least one of the following:

[0172] In one embodiment, a preset disease assessment model is used to evaluate monitoring data of at least two types of diseases related to the substrate, resulting in a substrate disease score matrix. A preset severity level membership function is then used to obtain a substrate fuzzy comprehensive judgment matrix based on the substrate disease score matrix. Finally, the substrate status level is determined based on the substrate disease score matrix and the substrate fuzzy comprehensive judgment matrix.

[0173] and / or

[0174] The monitoring data of at least two types of embankment-related defects are evaluated using the pre-defined defect assessment model to obtain an embankment defect score matrix. A fuzzy comprehensive judgment matrix is ​​then obtained based on the embankment defect score matrix using a pre-defined severity level membership function. Finally, the embankment condition level is determined based on both the embankment defect score matrix and the fuzzy comprehensive judgment matrix.

[0175] and / or

[0176] The monitoring data of at least two types of road cut-related defects are evaluated using the preset defect assessment model to obtain a road cut defect score matrix. A road cut fuzzy comprehensive judgment matrix is ​​obtained based on the road cut defect score matrix using a preset severity level membership function. The road cut status level is obtained based on the road cut defect score matrix and the road cut fuzzy comprehensive judgment matrix.

[0177] Based on the preset mileage-to-location judgment matrix, the degree of damage of each mileage segment is obtained according to the subgrade condition level and / or embankment condition level and / or cutting condition level of each mileage segment.

[0178] In this embodiment, the evaluation calculation method is explained in detail using the corrected data for the mileage segment K45+000-K46+000 as an example:

[0179] like Figure 4 As shown, after statistical analysis, the number of diseases corresponding to each disease type at different severity levels was obtained.

[0180] like Figure 5 The figures show the weights for subgrade disease levels, embankment disease levels, and cutting disease levels, respectively.

[0181] Calculation step 1: Based on the calculation formula of the above-mentioned preset disease assessment model, obtain the assessment score of each disease related to the subgrade, each disease related to the embankment, and each disease related to the cutting, and finally form the corresponding score matrix, as follows:

[0182] Subgrade disease score matrix = [4.1 4.4 4.6 2.8 3.2];

[0183] Embankment defect score matrix = [4.6 9.65 2.3 0.7 2.4 2.8];

[0184] Cutting defects score matrix = [1.05 0.75 6.25 0.9 2.6].

[0185] In step 2, each value in the disease score matrix of the bed base is substituted into the five membership functions of the AE level mentioned above to obtain the fuzzy comprehensive judgment matrix R1 of the bed base.

[0186] In step 3, the severity level score matrix of the base bed is obtained by multiplying the fuzzy comprehensive judgment matrix R1 of the base bed with the disease judgment matrix of the base bed.

[0187] For example, the severity level score matrix of the bed base is [0.4717 0 0.1132 0.4062 0.0092], where 0.4717 is the score belonging to severity level A, 0 is the score belonging to severity level B, and 0.0092 is the score belonging to severity level E.

[0188] Following the principle of maximum membership, the severity level of the substrate is A.

[0189] Similarly, following the same calculation steps, the severity level score matrix of the embankment is obtained to determine the severity level of the embankment, and the severity level score matrix of the cutting is obtained to determine the severity level of the cutting.

[0190] At this point, the severity levels of three different monitoring locations (subgrade, embankment, and cutting) in the mileage section are obtained.

[0191] Step 4: Calculate the severity level of the mileage segment based on the severity level of different monitoring locations.

[0192] Specifically, the preset mileage-to-location judgment matrix = [0.6250 0.2385 0.1365] has a CR of 0.0158 < 0.1, and the matrix consistency is passed.

[0193] The scores of the subgrade severity level, embankment severity level, and cut severity level are combined to form a 3*5 location score matrix. The location score matrix is ​​multiplied by the preset mileage location judgment matrix to obtain the mileage severity level score matrix.

[0194] For example, the mileage severity level score matrix for the K45+000-K46+000 mileage segment is [0.5026 0.0609 0.1078 0.2880 0.0408], and the severity level is determined to be A.

[0195] Similarly, following steps 1-4, the severity level score matrix for each mileage segment is obtained, as follows: Figure 6 The figure shows the severity level score matrix for the three mileage segments.

[0196] Step 5: Based on the severity level of each mileage segment, obtain the severity level score matrix of the monitored segment.

[0197] Specifically, the preset segment mileage judgment matrix = [0.2970 0.5396 0.1634] has a CR of 0.0079 < 0.1, and the consistency test is passed.

[0198] The severity score matrices for the K45+000-K46+000 mileage segment, the K46+000-K47+000 mileage segment, and the K47+000-K48+000 mileage segment are combined to form a 3*5 mileage score matrix. The mileage score matrix is ​​then multiplied by the preset segment mileage judgment matrix to obtain the segment severity score matrix.

[0199] For example, the severity level score matrix of the section = [0.3077 0.1053 0.2110 0.1342 0.2419] corresponds to a severity level of A, which means that the severity of the disease in this section is very serious and relevant measures need to be taken immediately.

[0200] In summary, as Figure 8 The diagram shown is a framework diagram of the comprehensive evaluation system for the service status of the roadbed mentioned above.

[0201] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0202] Example 2

[0203] In this embodiment, as Figure 7 As shown, a roadbed service condition assessment device is provided, comprising:

[0204] The acquisition module 710 is used to acquire roadbed data for each mileage segment in the roadbed section to be monitored, wherein the roadbed data includes monitoring data for at least two types of roadbed defects.

[0205] The elimination module 720 is used to determine the corresponding deviation threshold based on the daily monitoring data of each type of roadbed defect, and to eliminate the error data in the roadbed data of each mileage segment based on the deviation threshold.

[0206] The correction module 730 is used to correct the roadbed data of each mileage segment after the error data has been removed, so as to obtain the roadbed correction data of each mileage segment.

[0207] The evaluation module 740 is used to evaluate the damage degree of the subgrade correction data of each mileage segment to obtain the service status of the subgrade segment to be monitored.

[0208] Specific limitations regarding the subgrade service condition assessment device can be found in the limitations of the subgrade service condition assessment method described above, and will not be repeated here. Each unit in the aforementioned subgrade service condition assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These units can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each unit.

[0209] Example 3

[0210] In this embodiment, a computer device is provided. Its internal structure diagram can be shown as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs, and also contains a database for storing monitoring data from various monitoring devices. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with other computer devices that have deployed application software. When the computer program is executed by the processor, it implements a method for assessing the service condition of a roadbed. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0211] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0212] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to perform the following steps:

[0213] Obtain roadbed data for each mileage segment in the roadbed section to be monitored, wherein the roadbed data includes monitoring data for at least two types of roadbed defects;

[0214] Based on the daily monitoring data of each type of roadbed defect, the corresponding deviation threshold is determined, and based on the deviation threshold, the error data in the roadbed data of each mileage segment is removed.

[0215] The roadbed data of each mileage segment after removing the error data is corrected to obtain the corrected roadbed data for each mileage segment;

[0216] The damage level of the subgrade correction data for each mileage segment is assessed to obtain the service status of the subgrade segment to be monitored.

[0217] In one embodiment, when the processor executes a computer program, it also performs the following steps:

[0218] Calculate the average value of at least the first N sets of data in the daily monitoring data, where N is greater than or equal to 2;

[0219] The standard deviation of the daily monitoring data is calculated based on the average value, and the standard deviation of a preset multiple is used as the deviation threshold.

[0220] Calculate the offset distance between each group of data after the Nth group of data in the daily monitoring data and the average value, and determine the monitoring data whose offset distance is greater than the deviation threshold as the error data;

[0221] Remove the aforementioned error data.

[0222] In one embodiment, when the processor executes a computer program, it also performs the following steps:

[0223] Mark null values ​​at the positions where the error data was not removed;

[0224] The missing values ​​are interpolated and corrected using an interpolation method to obtain the roadbed correction data for each mileage segment.

[0225] In one embodiment, when the processor executes a computer program, it also performs the following steps:

[0226] The monitoring data of at least two types of diseases related to the substrate are evaluated using a preset disease assessment model to obtain a substrate disease score matrix. A preset severity level membership function is then used to obtain a substrate fuzzy comprehensive judgment matrix based on the substrate disease score matrix. Finally, the substrate status level is obtained based on the substrate disease score matrix and the substrate fuzzy comprehensive judgment matrix.

[0227] and / or

[0228] The monitoring data of at least two types of embankment-related defects are evaluated using the pre-defined defect assessment model to obtain an embankment defect score matrix. A fuzzy comprehensive judgment matrix is ​​then obtained based on the embankment defect score matrix using a pre-defined severity level membership function. Finally, the embankment condition level is determined based on both the embankment defect score matrix and the fuzzy comprehensive judgment matrix.

[0229] and / or

[0230] The monitoring data of at least two types of road cut-related defects are evaluated using the preset defect assessment model to obtain a road cut defect score matrix. A road cut fuzzy comprehensive judgment matrix is ​​obtained based on the road cut defect score matrix using a preset severity level membership function. The road cut status level is obtained based on the road cut defect score matrix and the road cut fuzzy comprehensive judgment matrix.

[0231] Based on the preset mileage-to-location judgment matrix, the degree of damage of each mileage segment is obtained according to the subgrade condition level and / or embankment condition level and / or cutting condition level of each mileage segment.

[0232] In one embodiment, when the processor executes a computer program, it also performs the following steps:

[0233] Obtain the severity level corresponding to each of the aforementioned disease types, and obtain the corresponding weight based on each severity level;

[0234] Determine the number of different severity levels of defects within the subgrade correction data for each mileage segment.

[0235] The calculation formula for the preset disease assessment model is as follows:

[0236]

[0237] Among them, S j This indicates the score for disease type j; C i This indicates the number of type j diseases with a severity level of i; W iThis represents the weight of the severity level of a disease of type j as type i.

[0238] Example 4

[0239] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, it performs the following steps:

[0240] Obtain roadbed data for each mileage segment in the roadbed section to be monitored, wherein the roadbed data includes monitoring data for at least two types of roadbed defects;

[0241] Based on the daily monitoring data of each type of roadbed defect, the corresponding deviation threshold is determined, and based on the deviation threshold, the error data in the roadbed data of each mileage segment is removed.

[0242] The roadbed data of each mileage segment after removing the error data is corrected to obtain the corrected roadbed data for each mileage segment;

[0243] The damage level of the subgrade correction data for each mileage segment is assessed to obtain the service status of the subgrade segment to be monitored.

[0244] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0245] Calculate the average value of at least the first N sets of data in the daily monitoring data, where N is greater than or equal to 2;

[0246] The standard deviation of the daily monitoring data is calculated based on the average value, and the standard deviation of a preset multiple is used as the deviation threshold.

[0247] Calculate the offset distance between each group of data after the Nth group of data in the daily monitoring data and the average value, and determine the monitoring data whose offset distance is greater than the deviation threshold as the error data;

[0248] Remove the aforementioned error data.

[0249] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0250] Mark null values ​​at the positions where the error data was not removed;

[0251] The missing values ​​are interpolated and corrected using an interpolation method to obtain the roadbed correction data for each mileage segment.

[0252] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0253] The monitoring data of at least two types of diseases related to the substrate are evaluated using a preset disease assessment model to obtain a substrate disease score matrix. A preset severity level membership function is then used to obtain a substrate fuzzy comprehensive judgment matrix based on the substrate disease score matrix. Finally, the substrate status level is obtained based on the substrate disease score matrix and the substrate fuzzy comprehensive judgment matrix.

[0254] and / or

[0255] The monitoring data of at least two types of embankment-related defects are evaluated using the pre-defined defect assessment model to obtain an embankment defect score matrix. A fuzzy comprehensive judgment matrix is ​​then obtained based on the embankment defect score matrix using a pre-defined severity level membership function. Finally, the embankment condition level is determined based on both the embankment defect score matrix and the fuzzy comprehensive judgment matrix.

[0256] and / or

[0257] The monitoring data of at least two types of road cut-related defects are evaluated using the preset defect assessment model to obtain a road cut defect score matrix. A road cut fuzzy comprehensive judgment matrix is ​​obtained based on the road cut defect score matrix using a preset severity level membership function. The road cut status level is obtained based on the road cut defect score matrix and the road cut fuzzy comprehensive judgment matrix.

[0258] Based on the preset mileage-to-location judgment matrix, the degree of damage of each mileage segment is obtained according to the subgrade condition level and / or embankment condition level and / or cutting condition level of each mileage segment.

[0259] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0260] Obtain the severity level corresponding to each of the aforementioned disease types, and obtain the corresponding weight based on each severity level;

[0261] Determine the number of different severity levels of defects within the subgrade correction data for each mileage segment.

[0262] The calculation formula for the preset disease assessment model is as follows:

[0263]

[0264] Among them, S j This indicates the score for disease type j; C i This indicates the number of type j diseases with a severity level of i; W i This represents the weight of the severity level of a disease of type j as type i.

[0265] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0266] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0267] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for assessing the service condition of a roadbed, characterized in that, include: Acquire roadbed data for each mileage segment in the roadbed section to be monitored. The roadbed data includes subgrade data, embankment data, and cut data. The subgrade data includes monitoring data for at least two types of subgrade-related defects, the embankment data includes monitoring data for at least two types of embankment-related defects, and the cut data includes monitoring data for at least two types of cut-related defects. Based on the daily monitoring data of each type of roadbed defect, the corresponding deviation threshold is determined, and based on the deviation threshold, the error data in the roadbed data of each mileage segment is removed. The roadbed data of each mileage segment after removing the error data is corrected to obtain the corrected roadbed data for each mileage segment; The damage level of the subgrade correction data for each mileage segment is assessed to obtain the service status of the subgrade segment to be monitored. The assessment of the severity of damage to the subgrade correction data for each of the aforementioned mileage sections includes at least one of the following: The monitoring data of at least two types of diseases related to the substrate are evaluated using a preset disease assessment model to obtain a substrate disease score matrix. A preset severity level membership function is then used to obtain a substrate fuzzy comprehensive judgment matrix based on the substrate disease score matrix. Finally, the substrate status level is obtained based on the substrate disease score matrix and the substrate fuzzy comprehensive judgment matrix. and / or The monitoring data of at least two types of embankment-related defects are evaluated using a preset defect assessment model to obtain an embankment defect score matrix. A preset severity level membership function is then used to obtain an embankment fuzzy comprehensive judgment matrix based on the embankment defect score matrix. Finally, the embankment condition level is determined based on both the embankment defect score matrix and the embankment fuzzy comprehensive judgment matrix. and / or The monitoring data of at least two types of road cut-related defects are evaluated using a preset defect assessment model to obtain a road cut defect score matrix. A road cut fuzzy comprehensive judgment matrix is ​​obtained based on the road cut defect score matrix using a preset severity level membership function. The road cut status level is obtained based on the road cut defect score matrix and the road cut fuzzy comprehensive judgment matrix. Based on the preset mileage-to-location judgment matrix, the degree of damage of each mileage segment is obtained according to the subgrade condition level and / or embankment condition level and / or cut condition level of each mileage segment. Before the step of assessing the severity of damage to the subgrade correction data for each of the aforementioned mileage segments, the following steps are also included: Obtain the severity level corresponding to each of the aforementioned disease types, and obtain the corresponding weight based on each severity level; Determine the number of different severity levels of defects within the subgrade correction data for each mileage segment. The calculation formula for the preset disease assessment model is as follows: in, This represents the score for a disease of type j. This indicates the number of type j diseases with a severity level of i. This represents the weight of the severity level of a disease of type j as type i.

2. The method for assessing the service condition of a roadbed according to claim 1, characterized in that, The step of determining the corresponding deviation threshold based on the daily monitoring data of each of the aforementioned roadbed defect types, and removing erroneous data from the roadbed data of each of the aforementioned mileage sections based on the deviation threshold, includes: Calculate the average value of at least the first N sets of data in the daily monitoring data, where N is greater than or equal to 2; The standard deviation of the daily monitoring data is calculated based on the average value, and the standard deviation of a preset multiple is used as the deviation threshold. Calculate the offset distance between each group of data after the Nth group of data in the daily monitoring data and the average value, and determine the monitoring data whose offset distance is greater than the deviation threshold as the error data; Remove the aforementioned error data.

3. The method for assessing the service condition of a roadbed according to claim 1, characterized in that, The step of correcting the roadbed data for each mileage segment after removing the error data to obtain corrected roadbed data for each mileage segment includes: Mark null values ​​at the positions where the error data was not removed; The missing values ​​are interpolated and corrected using an interpolation method to obtain the roadbed correction data for each mileage segment.

4. The method for assessing the service condition of a roadbed according to claim 1, characterized in that, The preset severity level membership function is as follows: A-level membership function: B-level membership function: C-level membership function: D-level membership function: E-level membership function: in , , , and As preset membership function parameters, the membership functions from level A to level E represent the severity levels from high to low.

5. A subgrade service condition assessment device for implementing the subgrade service condition assessment method according to any one of claims 1-4, characterized in that, include: The acquisition module is used to acquire roadbed data for each mileage segment in the roadbed section to be monitored, wherein the roadbed data includes monitoring data for at least two types of roadbed defects; The elimination module is used to determine the corresponding deviation threshold based on the daily monitoring data of each type of roadbed defect, and to eliminate the error data in the roadbed data of each mileage segment based on the deviation threshold. The correction module is used to correct the roadbed data of each mileage segment after the error data has been removed, so as to obtain the roadbed correction data of each mileage segment. The evaluation module is used to evaluate the damage degree of the subgrade correction data of each mileage segment to obtain the service status of the subgrade segment to be monitored.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images