A tunnel construction stability prediction method and system

Abstract

The application relates to the technical field of tunnel construction, in particular to a tunnel construction stability prediction method and system. In tunnel construction, the supporting parameters of a supporting structure in a preset analysis period are acquired in real time. If the supporting parameter state is abnormal, the abnormal period corresponding to the abnormal supporting parameter is acquired, the supporting parameters of the abnormal period are statistically analyzed, the abnormal parameter judgment value is calculated, the abnormal degree of the supporting parameters is judged based on the abnormal parameter judgment value, the risk assessment value is obtained by trend analysis of the supporting parameters of the abnormal period, the construction risk degree is identified, if the construction risk is low, the length of the analysis period is adjusted, and the supporting parameter stability prediction analysis is completed through analysis periods with different lengths. Thus, the supporting parameters can be monitored in real time during construction, the abnormal stress condition of the supporting structure can be found in time, and strong support can be provided for safety management and decision-making in the construction process.

Description

Technical Field

[0001] This invention relates to the field of tunnel construction technology, and specifically to a method and system for predicting the stability of tunnel construction. Background Technology

[0002] Tunnel construction is the core of tunnel engineering, and its key lies in selecting scientific and reasonable construction methods and support measures based on the characteristics of tunnel construction to ensure the safety and stability of the tunnel structure. During construction, the principles of "advanced detection, dynamic design, and timely support" must be followed.

[0003] Therefore, tunnel construction generally requires advanced support measures. In order to ensure project safety, the design of advanced support is often conservative, which can easily lead to a decrease in construction efficiency and an increase in construction costs. At the same time, in the process of monitoring and analyzing the support structure, the in-depth analysis and risk assessment of abnormal support parameters are relatively simple.

[0004] In view of this, we propose a method and system for predicting the stability of tunnel construction. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for predicting the stability of tunnel construction, so as to solve the technical problems mentioned above.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] In a first aspect, the present invention provides a method for predicting the stability of tunnel construction, which specifically includes the following steps: during tunnel construction, the support parameters of the support structure are acquired in real time within a preset analysis period, and the state of the support parameters is identified.

[0008] If the support parameters are abnormal, the abnormal time period corresponding to the abnormal support parameters is obtained, and the support parameters during the abnormal time period are statistically analyzed to calculate the abnormal parameter judgment value.

[0009] The degree of abnormality of support parameters is judged based on the abnormal parameter judgment value. If the degree of abnormality is low, the trend analysis of support parameters during the abnormal period is carried out, and the risk assessment value is calculated based on the change analysis results.

[0010] The degree of construction risk is identified based on the risk assessment value. If the construction risk is low, the duration of the analysis period is adjusted, and the stability prediction analysis of the support parameters is completed through analysis periods of different durations.

[0011] Secondly, the present invention provides a tunnel construction stability prediction system, the system comprising:

[0012] Support parameter analysis module: During tunnel construction, the support parameters of the support structure are acquired in real time within a preset analysis period, and the status of the support parameters is identified.

[0013] If the support parameters are abnormal, the abnormal time period corresponding to the abnormal support parameters is obtained, and the support parameters during the abnormal time period are statistically analyzed to calculate the abnormal parameter judgment value.

[0014] Risk Analysis Module: Based on the abnormal parameter judgment value, the degree of abnormality of the support parameters is judged. If the degree of abnormality is low, the trend analysis of the support parameters during the abnormal period is performed, and the risk assessment value is calculated based on the change analysis results.

[0015] Adjustment and optimization module: Based on the risk assessment value, the degree of construction risk is identified. If the construction risk is low, the duration of the analysis period is adjusted. The stability prediction analysis of the support parameters is completed through analysis periods of different durations.

[0016] The beneficial effects of this invention are:

[0017] (1) This invention uses finite element numerical calculation method and intelligent optimization method to compare and select multiple schemes of tunnel construction advance support scheme and optimize support parameters, thereby increasing the safety and stability of tunnel construction and reducing project costs;

[0018] (2) This invention monitors the support parameters of tunnel construction in real time and judges the support parameters. When generating the support parameter analysis signal, it further analyzes the support parameters during the analysis period of the signal generation, obtains the abnormal period of the support parameters during the analysis period, analyzes the support parameters during the abnormal period of the support parameters, calculates the abnormal parameter degree value, calculates the abnormal parameter characterization value based on the obtained abnormal parameter degree value and the time value of the abnormal period of the support parameters, and sums all the abnormal parameter characterization values ​​within the analysis period to obtain the abnormal parameter judgment value. Thus, the support parameters can be monitored in real time during the construction process, and the abnormal stress of the support structure can be detected in time, providing strong support for safety management and decision-making during the construction process. This not only improves the safety and stability of tunnel construction, but also reduces construction risks.

[0019] (3) In the case of generating a low degree of anomaly signal, the present invention analyzes the support parameters during the abnormal period of the support parameters, establishes a two-dimensional model, draws the support parameter change curve, analyzes the support parameter change curve, calculates the proportion value of the growth sub-curve segment and the average value of the growth amplitude ratio, performs data processing based on the proportion value of the growth sub-curve segment and the average value of the growth amplitude ratio, calculates the risk assessment value, compares it with the risk assessment threshold, and analyzes the degree of construction risk of the corresponding monitoring point. Thus, by analyzing the support parameters with a low degree of anomaly signal, the monitoring points with many growth trends and large growth amplitudes can be inspected and maintained in advance, thereby preventing construction risks, increasing construction safety, and reducing the accident rate.

[0020] (4) This invention obtains the corresponding abnormal support parameter time period, as well as the corresponding abnormal parameter difference and abnormal parameter mean, and performs analysis and processing to calculate the control ratio. Based on the control ratio and the analysis time period time value, the time control value is calculated. The difference between the analysis time period time value and the time control value is calculated to obtain the target time period value. Thus, the obtained target time period value is used as the new analysis time period time value, increasing the analysis frequency, timely understanding of construction risks, and reducing potential safety hazards during construction. Attached Figure Description

[0021] The invention will now be further described with reference to the accompanying drawings.

[0022] Figure 1 This is a flowchart of a method for predicting the stability of tunnel construction according to the present invention;

[0023] Figure 2 This is a flowchart of step three in the tunnel construction stability prediction method of the present invention.

[0024] Figure 3 This is a block diagram of a tunnel construction stability prediction system according to the present invention. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Example 1:

[0027] Please see Figure 1 As shown in the figure, the method for predicting the stability of tunnel construction according to an embodiment of the present invention specifically includes the following steps:

[0028] Step 1: During tunnel construction, based on geological survey data, various advanced support schemes are obtained, and the optimal advanced support scheme is extracted using the finite element numerical calculation method.

[0029] In some embodiments, geological exploration data is acquired, including but not limited to: geological conditions, rock strata distribution, groundwater conditions, faults, and weak interlayers;

[0030] Based on geological survey data and actual engineering conditions, a preliminary advanced support scheme was determined, which includes, but is not limited to: advanced anchor bolts, advanced small guide pipes, and advanced pipe roof method.

[0031] Based on the tunnel cross-sectional dimensions, support structure type, and geological conditions, a finite element numerical calculation model is established. The calculation model includes, but is not limited to, the tunnel excavation process, support structure installation, and stress conditions.

[0032] Using the finite element method, the stress process of tunnel excavation and support structure is simulated, and the stress state and deformation of each support scheme during construction are analyzed.

[0033] Based on the numerical calculation results, the construction period and project cost of each support scheme are evaluated.

[0034] It should be noted that the factors to be considered in the construction period include, but are not limited to: the installation speed of the support structure and its impact on subsequent construction; and the costs to be considered in the project cost include, but are not limited to: the procurement, transportation, installation and maintenance of support materials.

[0035] Compare the construction period, project cost, and support effect of each support scheme, and extract the optimal advanced support scheme;

[0036] Step 2: Optimize the support parameters corresponding to the advanced support scheme using the finite element numerical calculation method, and select the optimal support parameters;

[0037] In some embodiments, the optimization objectives are support effectiveness and engineering cost. Support effectiveness includes the stability and safety of the support structure, and engineering cost includes the procurement, transportation, installation and maintenance costs of support materials.

[0038] Based on the finite element numerical calculation model, an optimization model for the support parameters is established;

[0039] Intelligent optimization methods are used to perform numerical calculations and optimizations within the parameter range. These intelligent optimization methods include, but are not limited to, genetic algorithms, particle swarm optimization, and ant colony optimization.

[0040] It should be explained that genetic algorithms, particle swarm optimization, and ant colony optimization can automatically search for the optimal combination of support parameters within a given parameter range.

[0041] The impact of different support parameter combinations on support effect and engineering cost is analyzed, the optimal support parameters are determined, and the support parameter combination with the best support effect and the lowest engineering cost is selected based on the numerical calculation results.

[0042] Verify the feasibility and stability of the optimal support parameters in actual engineering, and formulate a construction plan based on the optimal support parameters. The construction plan includes, but is not limited to, the installation sequence of the support structure, construction methods, and quality control measures.

[0043] The main technical solution of this invention is: by using finite element numerical calculation method and intelligent optimization method, multiple schemes of tunnel construction advance support scheme are compared and the support parameters are optimized, thereby increasing the safety and stability of tunnel construction and reducing project costs;

[0044] Example 2:

[0045] Based on Example 1, please refer to Figure 1 and Figure 2 As shown in the figure, the method for predicting the stability of tunnel construction according to an embodiment of the present invention specifically includes the following steps:

[0046] Step 3: Considering the difficulty in accurately determining the creep parameters of soft rock, monitoring and analysis of the tunnel support structure are conducted.

[0047] The process of monitoring and analyzing the support structure during tunnel construction includes:

[0048] A1: Obtain the real-time support parameters of the support structure and compare them with the support parameter threshold to determine whether the support parameters are normal. If they are not normal, obtain the abnormal period of the support parameters, analyze and process the support parameters during the abnormal period, and calculate the abnormal parameter judgment value.

[0049] In some embodiments, several monitoring points are set on each support structure to obtain the real-time support parameters of each monitoring point;

[0050] Among them, the support parameters include, but are not limited to: support stress and support displacement;

[0051] A preset analysis period is defined by a person skilled in the art based on experience, and is used to analyze abnormal support parameters of the support structure.

[0052] The support parameters are compared with the support parameter thresholds, where the support parameter thresholds are set by those skilled in the art based on historical experimental data and experience.

[0053] If the support parameter is less than or equal to the support parameter threshold, it indicates that the support parameter of the monitoring point is in a normal state during the analysis period, and a normal support parameter signal is generated.

[0054] If the support parameter is greater than the support parameter threshold, it indicates that the support parameter of the monitoring point is in an abnormal state during the analysis period, and a support parameter analysis signal is generated.

[0055] It should be explained that if any support parameters are in an abnormal state during the analysis period, further analysis is required for the period in which the abnormal state occurs.

[0056] Obtain the analysis period corresponding to the generated support parameter analysis signal, obtain the time period within the analysis period where the support parameter is greater than the support parameter threshold, mark it as the support parameter abnormal period, and obtain the time value of the support parameter abnormal period;

[0057] For each period of abnormal support parameters, the support parameters are substituted into the variance formula to calculate the variance value of the abnormal parameters;

[0058] The support parameters are summed and averaged to obtain the mean of abnormal parameters. The difference between the mean of abnormal parameters and the support parameter threshold is calculated to obtain the difference of abnormal parameters. The ratio of the difference of support parameters to the support parameter threshold is processed to obtain the deviation ratio of abnormal parameters.

[0059] Based on the variance of outliers and the deviation ratio of outliers, a pre-built model of the severity of outliers is input, and the severity value of outliers is output.

[0060] The outlier parameter severity model is constructed based on a multilayer perceptron model. The input layer of this model can have two nodes to input the outlier parameter variance and outlier parameter bias ratio. To improve the model's expressive power and generalization ability, and reduce the computational complexity of the parameters, the hidden layer can be divided into multiple hidden layer groups. Each hidden layer group can share a portion of the data, which helps reduce the computational burden on the model and improves the efficiency of training and prediction. Simultaneously, multiple hidden layer groups can help the model better generalize to unseen data. Each group can focus on learning different types of data features and processing different regions of data, more effectively capturing local patterns and characteristics in the dataset, thereby improving the model's adaptability to different data distributions and reducing the risk of overfitting. Preferably, three hidden layer groups can be selected to process the outlier parameter variance and outlier parameter bias ratio input from the input layer nodes. Throughout the model training process, an attention mechanism is used to fuse the outputs of multiple hidden layer groups to obtain the outlier parameter severity value.

[0061] The abnormal parameter severity value is multiplied by the abnormal period time value to obtain the abnormal parameter characterization value;

[0062] The abnormal parameter characterization values ​​of all support parameters during abnormal periods are summed to obtain the abnormal parameter judgment values.

[0063] It should be explained that the meaning reflected by the abnormal parameter judgment value is as follows: the abnormal parameter judgment value is obtained by summing all support parameters within the analysis period and the abnormal parameter characterization value corresponding to the abnormal period. The abnormal parameter characterization value is calculated by multiplying the abnormal parameter severity value and the abnormal period time value. The larger the abnormal parameter severity value and the abnormal period time value, the larger the abnormal parameter characterization value, and the higher the abnormality of the support parameters in the analysis period.

[0064] A2: Based on the abnormal parameter judgment value, compare it with the abnormal parameter judgment threshold to identify the degree of abnormality of the support parameter. If the degree of abnormality is low, perform change analysis on the support parameter during the abnormal period and calculate the risk assessment value based on the change analysis results.

[0065] In some embodiments, an abnormal parameter judgment value is obtained, and the abnormal parameter judgment value is compared with an abnormal parameter judgment threshold, wherein the abnormal parameter judgment threshold is set by those skilled in the art based on historical experimental data and experience.

[0066] If the abnormal parameter judgment value is less than the abnormal parameter judgment threshold, a low abnormality signal is generated;

[0067] If the abnormal parameter judgment value is greater than or equal to the abnormal parameter judgment threshold, a high degree of abnormality signal is generated;

[0068] Based on the generated high-level anomaly signal, construction should be stopped immediately, and those skilled in the art should be arranged to inspect, maintain and improve the monitoring points that generated high-level anomalies to reduce the possibility of construction risks and increase construction safety.

[0069] Obtain the support parameters during periods of abnormal support parameters, establish a two-dimensional model with time as the X-axis and support parameters as the Y-axis, substitute the support parameters into the two-dimensional model, and plot the support parameter change curves.

[0070] The support parameter variation curve is divided into several sub-curve segments for analysis, and the slope of each sub-curve segment is calculated.

[0071] It should be noted that the slope of the sub-curve segment is calculated from the two endpoints of the sub-curve segment.

[0072] The number of sub-curve segments with positive slopes is counted, and the ratio of the number of sub-curve segments with positive slopes to the total number of sub-curve segments is calculated to obtain the percentage of growing sub-curve segments.

[0073] Obtain the sub-curve segments with positive slopes, extract the maximum and minimum values ​​of the support parameters in each sub-curve segment, calculate the difference, and ratio the difference with the minimum value of the support parameter to obtain the growth rate ratio. Sum all the growth rate ratios and take the average to obtain the average growth rate ratio.

[0074] The risk assessment value is calculated by fusing data based on the ratio of the proportion of growth sub-curve segments to the average growth rate using principal component analysis.

[0075] The specific process for calculating the risk assessment value is as follows:

[0076] The ratio of the percentage of increasing sub-segments to the average of the growth rate is normalized. The normalization process can be min-max normalization.

[0077] A two-dimensional sample matrix is ​​constructed by comparing the normalized percentage of growth sub-segments with the average growth rate.

[0078] The mean of the proportion of the normalized growth sub-segments and the ratio of growth rate are centered to obtain a centered matrix; where centering is achieved by subtracting the mean of each variable, that is, the mean of the proportion of the growth sub-segments and the mean of the ratio of growth rate.

[0079] Construct a covariance matrix to characterize the linear correlation between the proportion of growth sub-segments and the mean of the growth rate ratio;

[0080] Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalues. and the corresponding feature vectors and ;in, and This represents the variance contribution of the corresponding principal component; This corresponds to the first principal component (the direction with the largest variance). Corresponding to the second principal component;

[0081] Since the goal is to fuse two-dimensional data into a one-dimensional risk assessment value, the first principal component is chosen, as it retains the most important variance information in the data. The expression for the first principal component, PC1, is as follows: ;in, This represents the proportion of the growth sub-curve segment after centralization. This indicates that the growth rate after centralization is higher than the average. and The weighting coefficients of the first principal component;

[0082] For each sample from an abnormal time period, the PC1 score, i.e. the risk assessment value, is calculated by substituting the centered variable values.

[0083] A3: Based on the risk assessment value, compare it with the risk assessment threshold to identify the degree of construction risk. If the construction risk is low, adjust the analysis period.

[0084] In some embodiments, a risk assessment value is obtained and compared with a risk assessment threshold, wherein the risk assessment threshold is set by a person skilled in the art based on historical experimental data and experience.

[0085] If the risk assessment value is less than or equal to the risk assessment threshold, it indicates that the construction risk at that monitoring time point is low, and a low construction risk signal is generated.

[0086] Acquire monitoring points that generate low construction risk signals, and obtain the difference and mean of abnormal parameters for all support parameters during the analysis period for these monitoring points;

[0087] During each period when all support parameters are abnormal, the ratio of the difference between the abnormal parameters to the mean of the abnormal parameters is calculated to obtain the difference ratio.

[0088] The control ratio is obtained by summing and averaging the differences in the ratios of abnormal support parameters during all periods within the analysis period.

[0089] The time value of the analysis period is multiplied by the control ratio to obtain the time control value. The difference between the time value of the analysis period and the time control value is calculated to obtain the target time period value.

[0090] The target time period value obtained above is the new analysis time period value after the monitoring point that generates the low construction risk signal. This allows for more frequent analysis of the monitoring point that generates the low construction risk signal, reducing the risks and safety hazards that may occur during the construction process.

[0091] If the risk assessment value is greater than the risk assessment threshold, it indicates that the construction risk at that monitoring time point is relatively high, and a high construction risk signal is generated.

[0092] Based on the generated high construction risk signals, those skilled in the art will be arranged to inspect, maintain and improve the monitoring points that generated the high construction risk signals, so as to prevent construction risks and increase construction safety.

[0093] The technical solution of this invention is mainly as follows: First, by real-time monitoring of the support parameters during tunnel construction and judging the support parameters, when generating the support parameter analysis signal, the support parameters during the analysis period of the signal generation are further analyzed to obtain the abnormal periods of the support parameters during the analysis period, and the support parameters during the abnormal periods are analyzed to calculate the degree value of the abnormal parameters. Based on the obtained degree value of the abnormal parameters and the time value of the abnormal periods of the support parameters, the abnormal parameter characterization value is calculated, and all abnormal parameter characterization values ​​within the analysis period are summed to obtain the abnormal parameter judgment value. Thus, the support parameters can be monitored in real time during construction, and abnormal stress conditions of the support structure can be detected in a timely manner, providing strong support for safety management and decision-making during construction. This not only improves the safety and stability of tunnel construction but also reduces construction risks.

[0094] In the case of low-degree anomaly signals, the support parameters during the abnormal period are analyzed. A two-dimensional model is established, and the change curves of the support parameters are plotted. The change curves are analyzed to calculate the proportion of growth sub-curve segments and the average growth rate ratio. Based on the proportion of growth sub-curve segments and the average growth rate ratio, data processing is performed to calculate the risk assessment value, which is then compared with the risk assessment threshold to analyze the degree of construction risk at the corresponding monitoring points. Thus, by analyzing the support parameters with low-degree anomaly signals, monitoring points with multiple growth trends and large growth rates can be inspected and maintained in advance, thereby preventing construction risks, increasing construction safety, and reducing the accident rate.

[0095] By acquiring the corresponding abnormal support parameter periods, as well as the corresponding abnormal parameter differences and average abnormal parameter values, and performing analysis and processing, the control ratio is calculated. Based on the control ratio and the time value of the analysis period, the time control value is calculated. By calculating the difference between the time value of the analysis period and the time control value, the target time period value can be obtained. Thus, the acquired target time period value is used as the new analysis period time value, increasing the analysis frequency, timely understanding of construction risks, and reducing potential safety hazards during construction.

[0096] Example 3:

[0097] Based on the embodiments, please refer to Figure 3 As shown in the embodiment of the present invention, a tunnel construction stability prediction system includes:

[0098] Support parameter analysis module: acquires real-time support parameters of the support structure, compares them with support parameter thresholds, determines whether the support parameters are normal, and if not, acquires the abnormal support parameter periods, analyzes and processes the support parameters during the abnormal periods, and calculates the abnormal parameter judgment value.

[0099] The support parameter analysis module is used to perform the following methods:

[0100] Several monitoring points are set on each support structure to obtain the real-time support parameters of each monitoring point; the analysis period is preset; the support parameters are compared with the support parameter threshold; if the support parameter is greater than the support parameter threshold, a support parameter analysis signal is generated.

[0101] The process involves: acquiring the analysis period corresponding to the generated support parameter analysis signal; identifying the time periods within the analysis period where the support parameter is greater than the support parameter threshold, marking these as abnormal support parameter periods; obtaining the time values ​​of these abnormal support parameter periods; for each abnormal support parameter period, substituting the support parameter into the variance formula to calculate the abnormal parameter variance value; summing and averaging the support parameters to obtain the abnormal parameter mean value; calculating the difference between the abnormal parameter mean value and the support parameter threshold to obtain the abnormal parameter difference value; and then rationing the support parameter difference value to the support parameter threshold to obtain the abnormal parameter deviation ratio; inputting the abnormal parameter variance value and the abnormal parameter deviation ratio into a pre-constructed abnormal parameter severity model to output the abnormal parameter severity value; multiplying the abnormal parameter severity value by the abnormal period time value to obtain the abnormal parameter characterization value; and finally summing the abnormal parameter characterization values ​​for all abnormal support parameter periods to obtain the abnormal parameter judgment value.

[0102] Risk Analysis Module: Based on the abnormal parameter judgment value, it compares it with the abnormal parameter judgment threshold to identify the degree of abnormality of the support parameter. If the degree of abnormality is low, it performs change analysis on the support parameter during the abnormal period and calculates the risk assessment value based on the change analysis results.

[0103] The risk module is used to execute the following methods:

[0104] Obtain the abnormal parameter judgment value and compare it with the abnormal parameter judgment threshold; if the abnormal parameter judgment value is less than the abnormal parameter judgment threshold, generate a low abnormality signal.

[0105] Obtain the support parameters during periods of abnormal support parameters, establish a two-dimensional model with time as the X-axis and support parameters as the Y-axis, substitute the support parameters into the two-dimensional model, and plot the support parameter change curves.

[0106] The support parameter variation curve is divided into several sub-curve segments for analysis, and the slope of each sub-curve segment is calculated. The number of sub-curve segments with positive slopes is counted, and the ratio of the number of sub-curve segments with positive slopes to the total number of sub-curve segments is calculated to obtain the proportion of growth sub-curve segments. For each sub-curve segment with a positive slope, the maximum and minimum values ​​of the support parameters are extracted, and the difference is calculated. The ratio of this difference to the minimum value of the support parameter is calculated to obtain the growth rate ratio. All growth rate ratios are summed and averaged to obtain the mean growth rate ratio. Based on the proportion of growth sub-curve segments and the mean growth rate ratio, principal component analysis is used to fuse the data and calculate the risk assessment value.

[0107] Adjustment and optimization module: Based on the risk assessment value, it compares it with the risk assessment threshold to identify the degree of construction risk. If the construction risk is low, the analysis period is adjusted.

[0108] The adjustment and optimization module is used to execute the following methods:

[0109] Obtain the risk assessment value and compare it with the risk assessment threshold; if the risk assessment value is less than or equal to the risk assessment threshold, a low construction risk signal is generated.

[0110] The system acquires monitoring points that generate low construction risk signals and obtains the abnormal parameter differences and average abnormal parameter values ​​for all support parameter abnormal periods within the analysis period. For each abnormal period of all support parameters, the ratio of the abnormal parameter difference to the average abnormal parameter value is calculated to obtain the difference ratio. The summation and average of the difference ratios for all abnormal periods of support parameters within the analysis period are then calculated to obtain the control ratio. The time value of the analysis period is multiplied by the control ratio to obtain the time control value. Finally, the difference between the time value of the analysis period and the time control value is calculated to obtain the target time period value.

[0111] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A method for predicting the stability of tunnel construction, characterized in that, Specifically, the following steps are included: During tunnel construction, the support parameters of the support structure are acquired in real time within a preset analysis period, and the status of the support parameters is identified. If the support parameters are abnormal, the abnormal time period corresponding to the abnormal support parameters is obtained, and the support parameters during the abnormal time period are statistically analyzed to calculate the abnormal parameter judgment value. The degree of abnormality of support parameters is judged based on the abnormal parameter judgment value. If the degree of abnormality is low, the trend analysis of support parameters during the abnormal period is carried out, and the risk assessment value is calculated based on the change analysis results. The process for obtaining the risk assessment value is as follows: Construct support parameter variation curves based on support parameters during abnormal time periods; The support parameter variation curve is divided into several sub-curve segments for analysis; The sub-curve segments with positive slopes are processed in terms of quantity and growth rate to obtain the proportion of growth sub-curve segments and the average growth rate. The risk assessment value is calculated by fusing the proportion of the growth sub-curve segment with the mean of the growth rate ratio using principal component analysis. The degree of construction risk is identified based on the risk assessment value. If the construction risk is low, the duration of the analysis period is adjusted. The stability prediction analysis of the support parameters is completed through analysis periods of different durations. The adjustment process for the analysis period is as follows: Obtain the monitoring points corresponding to low construction risk and the difference of abnormal parameters for all support parameters during the analysis period for each monitoring point; During each period when all support parameters are abnormal, the ratio of the difference between the abnormal parameters to the mean of the abnormal parameters is calculated to obtain the difference ratio. The average of the differences in the ratios of all abnormal support parameters during the analysis period is taken as the control ratio. The time value of the analysis period is multiplied by the control ratio to obtain the time control value. The difference between the time value of the analysis period and the time control value is calculated to obtain the target time period value.

2. The method for predicting the stability of tunnel construction according to claim 1, characterized in that, The support parameter status identification process is as follows: Several monitoring points are set on each support structure to obtain the real-time support parameters of each monitoring point, and the support parameters are compared with the support parameter threshold. If the support parameter threshold is less than or equal to the support parameter threshold, then the support parameter is normal. If the value exceeds the support parameter threshold, the support parameter is considered abnormal, and a support parameter analysis signal is generated.

3. The method for predicting the stability of tunnel construction according to claim 1, characterized in that, The process for obtaining the abnormal parameter judgment value is as follows: Obtain the analysis period corresponding to the abnormal support parameters, and take the time period when the support parameters are greater than the support parameter threshold within the analysis period as the abnormal support parameter period, and obtain the time value of the abnormal support parameter period. The abnormal period time value is multiplied by the corresponding abnormal parameter degree value to obtain the abnormal parameter characterization value. The abnormal parameter values ​​during all abnormal support parameter periods are summed to obtain the abnormal parameter judgment value.

4. The method for predicting the stability of tunnel construction according to claim 3, characterized in that, The process for obtaining the abnormal parameter severity value is as follows: The abnormal periods of each support parameter are integrated to obtain the variance and mean of the abnormal parameters. The difference between the mean of abnormal parameters and the threshold of support parameters is calculated to obtain the abnormal parameter difference. The ratio of the abnormal parameter difference to the support parameter threshold is used as the abnormal parameter deviation ratio. Based on the variance of outliers and the deviation ratio of outliers, a pre-built model of the degree of outliers is input, and the degree of outliers is output.

5. The method for predicting the stability of tunnel construction according to claim 1, characterized in that, The process for obtaining the proportion of the growth sub-curve segment is as follows: The ratio of the number of sub-curve segments with positive slopes to the total number of sub-curve segments is used to obtain the percentage of growing sub-curve segments.

6. The method for predicting tunnel construction stability according to claim 5, characterized in that, The process for obtaining the growth rate ratio to the mean is as follows: The difference between the maximum and minimum values ​​of the support parameters in the sub-curve segment with a positive slope is calculated, and the ratio of the obtained difference to the minimum value of the support parameter is processed to obtain the growth rate ratio.

7. The method for predicting the stability of tunnel construction according to claim 1, characterized in that, The process of identifying the degree of construction risk is as follows: Compare the risk assessment value with the risk assessment threshold; If the risk assessment value is greater than the risk assessment threshold, then a high construction risk is generated; If the risk assessment value is less than or equal to the risk assessment threshold, the construction risk is low.

8. A tunnel construction stability prediction system, characterized in that, The system is used to perform the method according to any one of claims 1-7, the system comprising: Support parameter analysis module: During tunnel construction, the support parameters of the support structure are acquired in real time within a preset analysis period, and the status of the support parameters is identified. If the support parameters are abnormal, the abnormal time period corresponding to the abnormal support parameters is obtained, and the support parameters during the abnormal time period are statistically analyzed to calculate the abnormal parameter judgment value. Risk Analysis Module: Based on the abnormal parameter judgment value, the degree of abnormality of the support parameters is judged. If the degree of abnormality is low, the trend analysis of the support parameters during the abnormal period is performed, and the risk assessment value is calculated based on the change analysis results. Adjustment and optimization module: Based on the risk assessment value, the degree of construction risk is identified. If the construction risk is low, the duration of the analysis period is adjusted. The stability prediction analysis of the support parameters is completed through analysis periods of different durations.

Images