Safety assessment method and device for ground surface settlement risk caused by composite stratum construction

Abstract

The invention belongs to the technical field of shield tunneling machine tunnel construction, and particularly discloses a safety assessment method and device for ground surface settlement risks caused by composite stratum construction. According to the method and the device, the ground surface settlement risk state caused by the shield tunneling machine in the future construction tunnel is evaluated in real time by utilizing the calculated probability of the settlement safety risk level where the predicted value of the ground surface settlement of the shield tunneling machine in the future construction tunnel is located, so that the potential risk in the shield tunneling machine tunnel construction process is predicted in advance; the occurrence of engineering accidents such as ground collapse and peripheral structure damage is reduced, and the construction safety and efficiency are improved.

Description

Technical Field

[0001] The present application belongs to the field of shield machine tunnel construction, and more specifically, to a method and device for safely assessing the risk of surface subsidence caused by composite stratum construction. Background Art

[0002] At present, the prediction of ground settlement caused by shield tunnel construction mainly adopts deterministic methods, which cannot effectively deal with the uncertainty of parameters and cannot timely assess construction risks. Under complex geological conditions, traditional methods are difficult to cope with the variability of geological and construction data, which can easily cause engineering accidents such as ground collapse and damage to surrounding structures. Summary of the invention

[0003] In view of the defects of the prior art, the purpose of this application is to provide a method and device for safely assessing the risk of surface subsidence caused by composite stratum construction, aiming to solve the problem that the prior art is difficult to cope with the variability of geological and construction data, resulting in frequent engineering accidents.

[0004] To achieve the above objectives, in a first aspect, the present application provides a method for safety assessment of surface subsidence risk caused by composite stratum construction, comprising:

[0005] Based on the Monte Carlo simulation method, the first tunnel burial depth in the N+1th ring tunnel to be constructed by the shield machine in the future, the first weighted average value of the geological data, and the first average value of the stable phase data in the shield machine construction data are sampled to obtain a first sampling sample;

[0006] Based on the first sampling sample, a first predicted value of the surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future is obtained;

[0007] According to the probability corresponding to the settlement safety risk level of the first predicted value of surface settlement, the surface settlement risk caused by the N+1th ring tunnel to be constructed by the shield machine in the future is evaluated.

[0008] In some embodiments, based on the first sampling sample, obtaining a first predicted value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future includes:

[0009] Inputting the first sampling sample into the target support vector regression model to obtain a first predicted value of surface subsidence;

[0010] Among them, the target support vector regression model is obtained by the following method:

[0011] Obtaining a second weighted average of geological data in N ring tunnels built by the shield machine;

[0012] Remove abnormal values ​​and end-stage data from the shutdown phase data, startup phase data, and stable phase data of the shield machine construction data in the N-ring tunnel built by the shield machine, and obtain the second average value of the stable phase data;

[0013] According to the buried depth of the second tunnel in the N-ring tunnel built by the shield machine, the monitored value of the surface settlement in the N-ring tunnel built by the shield machine, the second weighted average value and the second average value, the support vector regression model is trained, and the parameters in the support vector regression model are optimized based on the covariance matrix adaptive evolutionary strategy optimization algorithm until the support vector regression model converges;

[0014] The converged support vector regression model is used as the target support vector regression model.

[0015] In some embodiments, obtaining a second weighted average of geological data in N ring tunnels built by a shield machine includes:

[0016] The second weighted average is calculated based on the following formula:

[0017]

[0018] In the formula, gc weighted is the second weighted average, n is the number of soil layers, gc i is the physical and mechanical properties of the geological data of the i-th layer in the N-ring tunnel built by the shield machine, w i is the weighted value of the i-th layer of soil, and the specific calculation formula is:

[0019]

[0020] In the formula, s i is the weighted area of ​​the i-th soil layer, R is the excavation radius of the shield machine, θ i It is half of the angle between the lower chord of the i-th soil layer and the center of the circle.

[0021] In some embodiments, a method for obtaining the probability corresponding to the settlement safety risk level at which the first predicted value of surface settlement is located includes:

[0022] Based on the failure probability function, obtaining the probability corresponding to the settlement safety risk level of the first prediction value;

[0023] Among them, the specific form of the failure probability function is:

[0024]

[0025] In the formula, PF MC is the failure probability function, X is a random variable, M is the total number of the first sampling samples, Ig(X) is the indicator function, The number of first sampling samples, P(g(X)≤0) is the probability, g(X) is the performance function, and the calculation formula is as follows:

[0026]

[0027] Where δ is a positive integer, MGS low is the lower limit of the subsidence surface, MGS up is the upper limit of the subsidence surface, and MGS(X) is the first predicted value.

[0028] In some embodiments, a method for obtaining the settlement safety risk level of the first predicted value of surface settlement includes:

[0029] When the first predicted value is in the interval (-20mm, +7mm), the settlement safety risk level of the first predicted value is level one;

[0030] When the first predicted value is between the interval (-30mm, -20mm) and the interval [+7mm, +10mm], the settlement safety risk level of the first predicted value is level 2;

[0031] When the first predicted value is in the interval (-∞, -30mm) or the interval (+10mm, +∞), the settlement safety risk level of the first predicted value is level three.

[0032] In some embodiments, the method further comprises:

[0033] Based on the Monte Carlo simulation method, the second tunnel burial depth in the N-ring tunnel built by the shield machine, the second weighted average value of the geological data, and the second average value of the stable phase data in the shield machine construction data are sampled to obtain a second sampling sample;

[0034] Based on the second sampling sample, a second predicted value of the surface settlement in the N-ring tunnel built by the shield machine is obtained;

[0035] According to the probability corresponding to the settlement safety risk level of the second predicted value of surface settlement, the surface settlement risk caused by the N-ring tunnel built by the shield machine is evaluated.

[0036] In some embodiments, the method further comprises:

[0037] Based on the Sobol method, the first-order sensitivity index and the total sensitivity index corresponding to the second tunnel burial depth, the second weighted average value and the second average value are obtained respectively;

[0038] According to the first-order sensitivity index and the total sensitivity index, the influence of the second tunnel burial depth, the second weighted average value and the second average value on the monitoring value of the surface settlement is determined.

[0039] In a second aspect, the present application provides a device for safely assessing the risk of surface subsidence caused by composite stratum construction, comprising:

[0040] An acquisition module is used to sample the first tunnel burial depth in the N+1th ring tunnel to be constructed by the shield machine in the future, the first weighted average value of the geological data, and the first average value of the stable phase data in the shield machine construction data based on the Monte Carlo simulation method to obtain a first sampling sample;

[0041] A prediction module, for obtaining a first prediction value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future based on the first sampling sample;

[0042] The evaluation module is used to evaluate the surface settlement risk caused by the N+1th ring tunnel to be constructed by the shield machine in the future according to the probability corresponding to the settlement safety risk level of the first predicted value of the surface settlement.

[0043] In a third aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the method described in the first aspect or any embodiments of the first aspect.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program. When the computer program runs on a processor, the processor executes the method of the first aspect or any embodiments of the first aspect.

[0045] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any embodiments of the first aspect.

[0046] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:

[0047] The method and device for safety assessment of surface subsidence risk caused by composite stratum construction provided in the present application, by utilizing the calculated probability of the settlement safety risk level of the predicted value of the surface subsidence of the future tunnel construction by the shield machine, evaluates in real time the surface subsidence risk status caused by the future tunnel construction by the shield machine, so as to predict the potential risks in the tunnel construction process of the shield machine in advance, reduce the occurrence of engineering accidents such as ground collapse and damage to surrounding structures, and improve construction safety and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is one of the flow diagrams of the method for safety assessment of surface subsidence risk caused by composite stratum construction provided in the embodiment of the present application;

[0049] Figure 2 It is a schematic diagram of the shield machine construction data processing flow provided in the embodiment of the present application;

[0050] Figure 3 is a schematic diagram of thrust processing results provided by an embodiment of the present application;

[0051] Figure 4 It is a schematic diagram of the processing result of the excavation speed provided in the embodiment of the present application;

[0052] Figure 5 It is a schematic diagram of the geological data processing flow provided in the embodiment of the present application;

[0053] Figure 6 It is a schematic diagram of the calculation principle of the area of ​​each soil layer within the tunnel face range provided in the embodiment of the present application;

[0054] Figure 7 It is a schematic diagram of the process of constructing a risk assessment model provided in an embodiment of the present application;

[0055] Figure 8 is a schematic diagram of the dynamic risk assessment results provided by an embodiment of the present application;

[0056] Fig. 9 It is a schematic diagram of the settlement safety risk level caused by the current ring excavation provided in the embodiment of the present application;

[0057] Fig.10 It is a schematic diagram of a process for constructing a target support vector regression model provided in an embodiment of the present application;

[0058] Fig.11 is a schematic diagram of surface subsidence prediction results provided by an embodiment of the present application;

[0059] Fig.12 It is a schematic diagram of the sensitivity analysis process provided in the embodiment of the present application;

[0060] Fig.13 It is a schematic diagram of the first-order sensitivity index results provided in the embodiment of the present application;

[0061] Fig.14 It is a schematic diagram of the total sensitivity index results provided in the embodiments of the present application;

[0062] Fig.15 This is the second flow chart of the method for safety assessment of surface subsidence risk caused by composite stratum construction provided in the embodiment of the present application;

[0063] Fig.16 It is a schematic diagram of the structure of a device for safely assessing the risk of surface subsidence caused by composite stratum construction provided in an embodiment of the present application;

[0064] Fig.17It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0067] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects. For example, a first sample and a second sample are used to distinguish different samples rather than to describe a specific order of the samples.

[0068] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0069] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0070] See also Figure 1 The method for safely assessing the risk of surface subsidence caused by composite stratum construction provided in an embodiment of the present application may include: step 110, step 120 and step 130.

[0071] Step 110 samples the first tunnel burial depth in the N+1th ring tunnel to be constructed by the shield machine in the future, the first weighted average value of the geological data, and the first average value of the stable phase data in the shield machine construction data based on the Monte Carlo simulation method to obtain a first sampling sample;

[0072] Step 120 obtains a first predicted value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future based on the first sampling sample;

[0073] Step 130 evaluates the risk of surface settlement caused by the N+1th ring tunnel to be constructed by the shield machine in the future according to the probability corresponding to the settlement safety risk level of the first predicted value of the surface settlement.

[0074] In the specific implementation, the tunnel geometry data, geological data, shield machine construction data and stratum settlement monitoring records in the shield machine tunnel construction are collected through data acquisition. Among them, the tunnel geometry data is the tunnel burial depth. The geological data includes the spatial distribution (thickness) of the soil strata and the physical and mechanical parameters of each soil layer (for example, including cohesion (c), internal friction angle (φ) and compression modulus (Es), etc.). These parameters are determined by detailed drilling surveys and laboratory tests on the center line of the tunnel. The shield machine construction data includes the total thrust (T) of the shield machine, the propulsion speed (AS), the cutter head speed (CRS), the cutter head torque (CRT), the grouting pressure (GP) and the excavation chamber pressure (ECP), etc., which are extracted from the shield machine database. In the embodiment of the present application, the stratum settlement monitoring record mainly refers to the maximum surface settlement (MGS).

[0075] Based on the above data collected, the tunnel depth (i.e., the first tunnel depth) of the N+1th ring tunnel to be constructed by the shield machine in the future, the weighted average value of the geological data (i.e., the first weighted average value), and the average value of the stable phase data in the shield machine construction data (i.e., the first average value) are obtained. Where N is an integer greater than 1.

[0076] The first tunnel burial depth, the first weighted average value and the first average value obtained above are sampled based on the Monte Carlo simulation method (MCS), and the obtained sampled samples are the first sampled samples.

[0077] In the embodiment of the present application, the construction data of the shield machine can be recorded at 20mm intervals during the tunneling cycle of each ring of the shield machine, and 101 sets of data are collected during each tunneling cycle, including data of the shield machine in the four stages of shutdown (P0), start-up (P1), stability (P2) and end (P3). Among them, the above-mentioned stable stage data is the construction data of the shield machine in the stable (P2) stage.

[0078] Based on the first sampling sample obtained above, the surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future can be predicted to obtain a predicted value of the surface settlement, that is, a first predicted value.

[0079] The settlement safety risk level of the first predicted value is determined. In the embodiment of the present application, the settlement safety risk level is divided into level 1 to level 3. The calculated probability of the settlement safety risk level of the first predicted value is used as an evaluation index for the surface settlement risk caused by the N+1 ring tunnel to be constructed by the shield machine in the future, and the surface settlement risk caused by the N+1 ring tunnel to be constructed by the shield machine in the future is evaluated.

[0080] The method for safety assessment of surface subsidence risk caused by composite stratum construction provided in the embodiment of the present application, by utilizing the calculated probability of the settlement safety risk level of the predicted value of the surface subsidence of the future tunnel construction by the shield machine, evaluates in real time the surface subsidence risk status caused by the future tunnel construction by the shield machine, so as to predict the potential risks in the tunnel construction process of the shield machine in advance, reduce the occurrence of engineering accidents such as ground collapse and damage to surrounding structures, and improve construction safety and efficiency.

[0081] Further, in some embodiments, step 120, based on the first sampling sample, obtaining a first predicted value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future, may include:

[0082] Inputting the first sampling sample into the target support vector regression model to obtain a first predicted value of surface subsidence;

[0083] Among them, the target support vector regression model is obtained by the following method:

[0084] Obtaining a second weighted average of geological data in N ring tunnels built by the shield machine;

[0085] Remove abnormal values ​​and end-stage data from the shutdown phase data, startup phase data, and stable phase data of the shield machine construction data in the N-ring tunnel built by the shield machine, and obtain the second average value of the stable phase data;

[0086] According to the buried depth of the second tunnel in the N-ring tunnel built by the shield machine, the monitored value of the surface settlement in the N-ring tunnel built by the shield machine, the second weighted average value and the second average value, the support vector regression model is trained, and the parameters in the support vector regression model are optimized based on the covariance matrix adaptive evolutionary strategy optimization algorithm until the support vector regression model converges;

[0087] The converged support vector regression model is used as the target support vector regression model.

[0088] In the specific implementation, the first predicted value of the surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future is used as the prediction target of the target support vector regression model (CMAES-SVR). The first sampling sample obtained above is input into the pre-trained target support vector regression model, and the first predicted value is obtained according to the output of the target support vector regression model.

[0089] The target support vector regression model is obtained by training the support vector regression model as follows:

[0090] Through data collection, the tunnel burial depth (i.e., the burial depth of the second tunnel) in the N-ring tunnel built by the shield machine, geological data, and shield machine construction data are obtained, as shown in Table 1.

[0091] Table 1

[0092]

[0093]

[0094] The geological data and shield machine construction data are processed in the following ways:

[0095] Geological data processing:

[0096] Since the geology is distributed in layers in the horizontal direction, the thickness of each layer and the physical and mechanical parameters of the soil are different. For the geological data at each ring of monitoring points, the weighted average method is used to calculate the weighted average of a physical and mechanical parameter of each monitoring point.

[0097] Shield machine construction data processing:

[0098] During each tunneling cycle of the shield machine, the data processing flow is as follows: Figure 2 As shown in Figure 1, the construction data of the shield machine was recorded at 20 mm intervals, and 101 sets of data were collected in each excavation cycle, including four stages: shutdown (P0), start-up (P1), stability (P2) and end (P3).

[0099] In order to obtain stable construction data for each tunnel segment, the collected data is denoised, and the IF (Information Fusion) algorithm is used to filter out abnormal values ​​and end-stage data in the shutdown phase data, startup phase data, and stable phase data in the shield machine construction data, and the average value of the stable phase data is calculated to ensure the accuracy and reliability of the data. Finally, these parameters are matched with the tunnel segment number.

[0100] The IF algorithm determines the degree of abnormality of a data point based on the path length. Generally, normal points require more segmentation steps (i.e., longer path lengths) to be isolated, while abnormal points are easier to isolate (i.e., shorter path lengths). The calculation formula for the abnormal score s(x,p) is as follows:

[0101]

[0102] Where E(h(x)) is the average path length of the stable phase data x, and c(p) is a normalization constant for a given stable phase data set size of p, which is used to adjust the expected value of the path length. In general, the higher the anomaly score, the more likely it is an anomaly.

[0103] Taking the processing of thrust and tunneling speed as an example, the processing results are as follows: Figure 3 and Figure 4After denoising, the data of the stable stage are obtained, and the average value of the data of the stable stage is calculated as the shield construction data for subsequent calculations.

[0104] A support vector regression model was constructed, and the parameters of the support vector regression model were optimized using the covariance matrix adaptive evolutionary strategy optimization algorithm (CMAES). The training data used in the training process included the geological parameters, construction data, tunnel depth, and MGS monitoring records that had been processed as described above. The number of training samples m was required to be no less than the number of features (including shield machine construction data, tunnel depth, geological data, and MGS monitoring records). The selection of training samples took into account the shield machine excavation position, and the first m samples close to the shield machine excavation position were selected.

[0105] The processed shield machine construction data of the N-ring tunnel built by the shield machine (specifically the second average value of the stable stage data in the shield machine construction data), geological data (specifically the second weighted average value of the geological data), the second tunnel burial depth and MGS monitoring records are packaged together to form a new MGS database.

[0106] Based on the above-obtained second tunnel burial depth in the N-ring tunnels before the shield machine has been built, the monitoring values ​​of the surface settlement in the N-ring tunnels before the shield machine has been built (which can be obtained from the MGS monitoring records obtained above), the above-mentioned second weighted average value and the above-mentioned second average value, the support vector regression model is trained, and based on the covariance matrix adaptive evolutionary strategy optimization algorithm, the parameters in the support vector regression model are optimized until the support vector regression model converges.

[0107] The converged support vector regression model is used as the target support vector regression model.

[0108] The surface settlement risk safety assessment method caused by composite stratum construction provided in the embodiment of the present application greatly improves the accuracy of stratum settlement prediction through dynamic data update and support vector regression model combined with covariance matrix adaptive evolution strategy optimization algorithm. Through data denoising and multi-parameter optimization, it effectively copes with the variability of complex geological and construction data, reduces construction accidents caused by complex geological conditions, and is particularly suitable for shield tunnel construction under complex geological conditions, such as subway tunnels, municipal pipelines, etc. It significantly improves the safety, efficiency and reliability of shield tunnel construction, and provides important technical support for the smooth implementation of underground projects.

[0109] Further, in some embodiments, in the above steps, obtaining the second weighted average value of geological data in the N-ring tunnels built by the shield machine may include:

[0110] The second weighted average is calculated based on the following formula:

[0111]

[0112] In the formula, gc weighted is the second weighted average, n is the number of soil layers, gc i is the physical and mechanical properties of the geological data of the i-th layer in the N-ring tunnel built by the shield machine, w i is the weighted value of the i-th layer of soil, and the specific calculation formula is:

[0113]

[0114] In the formula, s i is the weighted area of ​​the i-th soil layer, R is the excavation radius of the shield machine, θ i It is half of the angle between the lower chord of the i-th soil layer and the center of the circle.

[0115] In the embodiment of the present application, for a certain monitoring point, the corresponding geological data processing flow is as follows: Figure 5 The weighted average values ​​of geophysical and mechanical parameters are calculated as follows:

[0116] For the geological data of n soil layers, calculate the second weighted average:

[0117]

[0118] In the formula, gc weighted is the second weighted average, n is the number of soil layers, gc i is the physical and mechanical properties of the geological data of the i-th layer in the N-ring tunnel built by the shield machine, w i is the weighted value of the i-th layer of soil, and the specific calculation formula is:

[0119]

[0120] In the formula, s i is the weighted area of ​​the i-th layer of soil, and the calculation principle is as follows Figure 6 As shown, h1~h n is the spatial distribution of soil strata from the first layer to the nth layer, R is the excavation radius of the shield machine, θ i It is half of the angle between the lower chord of the i-th soil layer and the center of the circle, which can be calculated by the spatial distribution of the i-th soil layer.

[0121] Furthermore, in some embodiments, in the above steps, the method for obtaining the probability corresponding to the settlement safety risk level of the first predicted value of the surface settlement may include:

[0122] Based on the failure probability function, obtaining the probability corresponding to the settlement safety risk level of the first prediction value;

[0123] Among them, the specific form of the failure probability function is:

[0124]

[0125] In the formula, PF MC is the failure probability function, X is a random variable, M is the total number of the first sampling samples, Ig(X) is the indicator function, The number of first sampling samples, P(g(X)≤0) is the probability, g(X) is the performance function, and the calculation formula is as follows:

[0126]

[0127] Where δ is a positive integer, MGS low is the lower limit of the subsidence surface, MGS up is the upper limit of the subsidence surface, and MGS(X) is the first predicted value.

[0128] In the specific implementation, the specific form of the failure probability function is:

[0129]

[0130] In the formula, PF MC is the failure probability function, X is a random variable, M is the total number of the first sampling samples, Ig(X) is the indicator function, The number of first sampling samples, P(g(X)≤0) is the probability, g(X) is the performance function, and the calculation formula is as follows:

[0131]

[0132] Where δ is a positive integer, MGS low is the lower limit of the subsidence surface, MGS up is the upper limit of the subsidence surface, and MGS(X) is the first predicted value. “&” and “|” are “AND” and “OR” operators, respectively, and return 1 when the result is true and 0 when it is false.

[0133] The surface subsidence risk safety assessment method caused by composite stratum construction provided in the embodiment of the present application is based on the risk probability assessment model constructed by the MCS method, which can evaluate the risk status during shield tunnel construction in real time to ensure construction safety.

[0134] Furthermore, in some embodiments, in the above steps, the method for obtaining the settlement safety risk level of the first predicted value of the surface settlement may include:

[0135] When the first predicted value is in the interval (-20mm, +7mm), the settlement safety risk level of the first predicted value is level one;

[0136] When the first predicted value is between the interval (-30mm, -20mm) and the interval [+7mm, +10mm], the settlement safety risk level of the first predicted value is level 2;

[0137] When the first predicted value is in the interval (-∞, -30mm) or the interval (+10mm, +∞), the settlement safety risk level of the first predicted value is level three.

[0138] In the specific implementation, when the first predicted value of the surface settlement obtained above is within the interval (-20mm, +7mm), the settlement safety risk of the first predicted value of the surface settlement is determined to be level one, that is, a level one safety risk warning (Level I for short); when the first predicted value of the surface settlement is between the interval (-30mm, -20mm] and the interval [+7mm, +10mm), the settlement safety risk level of the first predicted value is determined to be level two, that is, a level two safety risk warning (Level II for short); when the first predicted value of the surface settlement is in the interval (-∞, -30mm) or the interval (+10mm, +∞), the settlement safety risk level of the first predicted value of the surface settlement is determined to be level three, that is, a level three safety risk warning (Level III for short). For the range of surface settlement values ​​corresponding to the three different warning levels, a probability analysis model corresponding to the settlement safety risk level based on Monte Carlo simulation (MCS) is established, and the probability corresponding to each settlement safety risk level is calculated based on the above failure probability function function, as shown below. Figure 7 shown.

[0139] Furthermore, in some embodiments, the above method may further include:

[0140] Based on the Monte Carlo simulation method, the second tunnel burial depth in the N-ring tunnel built by the shield machine, the second weighted average value of the geological data, and the second average value of the stable phase data in the shield machine construction data are sampled to obtain a second sampling sample;

[0141] Based on the second sampling sample, a second predicted value of the surface settlement in the N-ring tunnel built by the shield machine is obtained;

[0142] According to the probability corresponding to the settlement safety risk level of the second predicted value of surface settlement, the surface settlement risk caused by the N-ring tunnel built by the shield machine is evaluated.

[0143] In a specific implementation, for an already built N-ring tunnel, the surface settlement safety risk warning level caused by the already built N-ring tunnel is analyzed based on historical data. The following steps may be included: (1) obtaining the second tunnel burial depth based on data collection, and obtaining the second weighted average value of the geological data in the already built N-ring tunnel of the shield machine and the second average value of the stable stage data in the shield machine construction data based on the above-mentioned geological data processing and shield machine construction data processing process; (2) training a support vector regression model based on the above-mentioned acquired data to obtain a target support vector regression model; (3) using the MCS method to sample the second tunnel burial depth in the previously built N-ring tunnel of the shield machine, the second weighted average value of the geological data, and the second average value of the stable stage data in the shield machine construction data to obtain a second sampling sample, and using the target support vector regression model to calculate the second predicted value of the MGS corresponding to the second sampling sample; (4) calculating the probability corresponding to the settlement safety risk level of the second predicted value of the MGS of the previously built N-ring tunnel based on the failure probability function.

[0144] In the embodiment of the present application, after the construction of the 10th monitoring point is completed, sufficient training data has been obtained. Therefore, the evaluation function is executed from the 10th monitoring point, and the results are as follows: Figure 8 shown.

[0145] For the prediction of the future tunnel safety risk warning level, by continuously acquiring new shield construction data, the surface settlement safety risk warning level caused by future tunnel construction is analyzed, including the following steps: (1) acquiring new shield machine construction data within the N+1 ring excavation cycle, processing the shield machine construction data within the N+1 ring excavation cycle according to the above-mentioned shield machine construction data processing process, and obtaining the first tunnel burial depth in the N+1 ring tunnel constructed by the shield machine, the first weighted average value of the geological data, and the first average value of the stable stage data in the shield machine construction data; (2) obtaining the target support vector regression model according to the above-mentioned training process; (3) using the MCS method to sample the first tunnel burial depth in the N+1 ring tunnel, the first weighted average value of the geological data, and the first average value of the stable stage data in the shield machine construction data to obtain a first sampling sample, and inputting the first sampling sample into the target support vector regression model to obtain a first predicted value of surface settlement; (4) calculating the probability corresponding to the settlement safety risk level of the first predicted value according to the failure probability function function.

[0146] In the present embodiment, after the construction of the 10th monitoring point is completed, sufficient training data has been obtained. Therefore, the prediction function is executed from the 11th monitoring point. The result is as follows: Fig. 9 shown.

[0147] In the embodiment of the present application, 1) data input. After all the data are collected, the support vector regression model is trained and predicted. The process is as follows: Fig.10 As shown. Since the embodiment of the present application has 10 input features (respectively, tunnel burial depth, geological data (physical and mechanical parameters of soil layer including cohesion (c), internal friction angle (φ) and compression modulus (Es)) and shield machine construction data (including total thrust (T), propulsion speed (AS), cutterhead speed (CRS), cutterhead torque (CRT), grouting pressure (GP) and excavation chamber pressure (ECP)), the number of training samples is set to 10, and the 10 sets of data closest to the monitoring point are selected as training samples in each training.

[0148] 2) Real-time prediction of shield tunneling process. As the shield machine advances, new shield machine construction data is continuously acquired. The newly acquired shield machine construction data is processed using the above-mentioned shield machine construction data processing method. The geological data at the current location is processed using the above-mentioned geological data processing method. The processed construction data, geological data, tunnel burial depth and MGS monitoring records are packaged together to form a new MGS database.

[0149] 3) SVR model training. In the embodiment of the present application, during the model training process, the kernel function of the SVR model selects Gaussian Kernel, the Loss function selects L1 loss function, and k-10 in k-fold cross validation. The hyperparameters of SVM include C, ε, and γ, and these three hyperparameters are optimized according to the CMAES algorithm.

[0150] 4) Optimization of the SVR model. In the implementation of this application, the initial values ​​of the three hyperparameters C, ε, and γ are C = 1, ε = 1 / 10, and γ = 5, respectively. During the optimization process, CMAES generates a hyperparameter search space based on the initial values, and for each individual in the search space, that is, a hyperparameter combination, calculates the prediction performance of SVR under the hyperparameter combination. The prediction performance of the SVM model is expressed by fitness (fit). According to the MGS monitoring records (i.e., MGS monitoring values) and the predicted MGS (i.e., MGS predicted values), the calculation formula of fit is as follows:

[0151] fit = error = |MGS (monitoring value) - MGS (prediction value) |;

[0152] 5) Prediction results. After the construction of the 10th monitoring point is completed, sufficient training data has been obtained to start the training process. Therefore, the prediction function is executed from the 11th monitoring point. The monitoring results, prediction results and absolute errors are shown in Fig.11 shown.

[0153] Furthermore, in some embodiments, the above method may further include:

[0154] Based on the Sobol method, the first-order sensitivity index and the total sensitivity index corresponding to the second tunnel burial depth, the second weighted average value and the second average value are obtained respectively;

[0155] According to the first-order sensitivity index and the total sensitivity index, the influence of the second tunnel burial depth, the second weighted average value and the second average value on the monitoring value of the surface settlement is determined.

[0156] In the specific implementation, after obtaining enough data, the Sobol method is used to calculate the sensitivity coefficient of the input feature to MGS. The whole process is as follows: Fig.12 As shown. Specifically, it includes: (1) obtaining the input-output feature system corresponding to the built N-ring shield tunnel, the input-output feature system includes: the input features and output features corresponding to the built N-ring tunnel, wherein the input features include the second tunnel burial depth of the built N-ring tunnel, the second weighted average value of the geological data and the second average value of the stable stage data in the shield machine construction data; the output features include the MGS monitoring records of the built N-ring tunnel; (2) using the MGS input-output feature system corresponding to the previous N-ring tunnel to construct a target support vector regression model; (3) using the MCS method to sample the input features corresponding to the previous N-ring tunnel to obtain a second sampling sample; (4) using the Sobol method to calculate the first-order sensitivity index and the total sensitivity index of each input feature in the second sampling sample, and determining the degree of influence of each input feature on MGS based on the first-order sensitivity index and the total sensitivity index.

[0157] First-order sensitivity index S j and the total sensitivity index S Tj The calculation method is as follows:

[0158]

[0159]

[0160] In the formula, x j is the jth input feature, x ～j Divide x by the second sample j Other input features, E x～j (Y|x j ) is the expected output Y at a fixed x j The value of x * j In the case of x ～j The value of V xj [E x～j (Y|x j )] is the j Other input features except for the fixed x j The value of x * jIn the case of , the expectation of output Y, V(Y) represents the variance of output Y, x * j is the input feature x in the second sample j The average of all values, E[V(Y|x ～j )], for the j Other input features except for the fixed x j The value of x * j The variance of the output Y in the case of , where Y is the MGS output by the target support vector regression model.

[0161] In the present embodiment, after the construction of the 10th monitoring point is completed, sufficient training data has been obtained. Therefore, the global sensitivity analysis function of the construction data is performed starting from the 10th monitoring point. The first-order sensitivity and total sensitivity results are as follows: Fig.13 and Fig.14 shown.

[0162] Exemplarily, the present application embodiment collects a total of 301 sets of tunnel depth, geological data, shield machine construction data and MGS monitoring records. The specific description of this example is as follows:

[0163] like Fig.15 As shown, the second flow diagram of the surface settlement risk safety assessment method caused by composite stratum construction provided by the present application may include: (1) Data collection: Collect tunnel geometry data, geological data, shield machine construction data and stratum settlement monitoring records in shield tunnel construction. (2) Data preprocessing: 1) Use the IF algorithm to denoise the shield machine construction data; 2) Use the area weighted algorithm to calculate the weighted average of the geological data. (3) Prediction model construction: Combine the support vector regression model and the covariance matrix adaptive evolutionary strategy optimization algorithm to propose a stratum settlement prediction model for shield tunnel construction. (4) Risk probability assessment model construction: Construct a stratum settlement risk probability assessment model based on the Monte Carlo simulation method, and calculate the probability corresponding to the settlement safety risk level of the predicted value of the surface settlement. (5) Global sensitivity analysis (GSA): Use the Sobol method to calculate the dynamic sensitivity of the shield construction process parameters (including the first-order sensitivity index and the total sensitivity index) to identify the key factors affecting the stratum settlement.

[0164] This application significantly improves the accuracy of ground settlement prediction through dynamic data updates and advanced machine learning algorithms, and can evaluate the risks of shield tunnel construction in real time. Compared with the existing technology, this application has obvious advantages in dealing with complex geological conditions and uncertain parameters, and solves the problem of complex geological conditions as input data. It reduces the incidence of engineering accidents and improves construction safety and efficiency. Specific test results show that this method can effectively predict ground settlement under complex geological conditions and provide reliable risk assessment.

[0165] The embodiment of the present application provides a method for safely assessing the risk of surface subsidence caused by composite stratum construction, which uses the Sobol method to perform a global sensitivity analysis, identify key factors affecting stratum subsidence, provide targeted optimization suggestions, and further reduce construction risks.

[0166] The following is a description of the surface subsidence risk safety assessment device caused by composite stratum construction provided by the present invention. The surface subsidence risk safety assessment device caused by composite stratum construction described below and the surface subsidence risk safety assessment method caused by composite stratum construction described above can be referenced to each other.

[0167] See also Fig.16 The surface subsidence risk safety assessment device caused by composite stratum construction provided in the embodiment of the present application may include: an acquisition module 1610, a prediction module 1620 and an assessment module 1630.

[0168] The acquisition module 1610 is used to sample the first tunnel burial depth in the N+1th ring tunnel to be constructed by the shield machine in the future, the first weighted average value of the geological data, and the first average value of the stable phase data in the shield machine construction data based on the Monte Carlo simulation method to obtain a first sampling sample;

[0169] Prediction module 1620, for obtaining a first prediction value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future based on the first sampling sample;

[0170] The evaluation module 1630 is used to evaluate the surface settlement risk caused by the N+1th ring tunnel to be constructed by the shield machine in the future according to the probability corresponding to the settlement safety risk level of the first predicted value of the surface settlement.

[0171] The surface subsidence risk safety assessment device caused by composite stratum construction provided in the embodiment of the present application evaluates the surface subsidence risk status caused by the future construction of the tunnel by the shield machine in real time by utilizing the calculated probability of the settlement safety risk level of the predicted value of the surface subsidence of the future tunnel construction by the shield machine, so as to predict the potential risks in the tunnel construction process of the shield machine in advance, reduce the occurrence of engineering accidents such as ground collapse and damage to surrounding structures, and improve construction safety and efficiency.

[0172] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0173] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0174] Based on the method in the above embodiment, the present application embodiment provides an electronic device, see Fig.17 The electronic device may include: a processor (Processor) 1710, a communication interface (Communications Interface) 1720, a memory (Memory) 1730 and a communication bus 1740, wherein the processor 1710, the communication interface 1720, and the memory 1730 communicate with each other through the communication bus 1740. The processor 1710 may call the logic instructions in the memory 1730 to execute the method in the above embodiment.

[0175] In addition, the logic instructions in the above-mentioned memory 1730 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0176] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0177] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0178] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0179] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0180] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0181] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0182] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for safety assessment of surface subsidence risk caused by composite stratum construction, characterized in that: include: Based on the Monte Carlo simulation method, sampling is performed on the first tunnel burial depth in the N+1th ring tunnel to be constructed by the shield machine in the future, the first weighted average value of the geological data, and the first average value of the stable phase data in the shield machine construction data to obtain a first sampling sample; Based on the first sampling sample, a first predicted value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future is obtained; According to the probability corresponding to the settlement safety risk level of the first predicted value of the surface settlement, the surface settlement risk caused by the N+1th ring tunnel to be constructed by the shield machine in the future is evaluated.

2. The method for safety assessment of surface subsidence risk caused by composite stratum construction as claimed in claim 1, characterized in that: The step of obtaining a first predicted value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future based on the first sampling sample includes: Inputting the first sampling sample into a target support vector regression model to obtain a first predicted value of the surface subsidence; The target support vector regression model is obtained by: Obtaining a second weighted average of the geological data in the N-ring tunnels built by the shield machine; Removing abnormal values ​​and ending phase data from the shutdown phase data, the startup phase data, and the stable phase data of the shield machine construction data in the N-ring tunnel built by the shield machine, and obtaining a second average value of the stable phase data; Training a support vector regression model according to the buried depth of the second tunnel in the N-ring tunnels built by the shield machine, the monitored value of the surface settlement in the N-ring tunnels built by the shield machine, the second weighted average value and the second average value, and optimizing the parameters in the support vector regression model based on the covariance matrix adaptive evolutionary strategy optimization algorithm until the support vector regression model converges; The converged support vector regression model is used as the target support vector regression model.

3. The method for safety assessment of surface subsidence risk caused by composite stratum construction as claimed in claim 2, characterized in that: The obtaining of the second weighted average value of the geological data in the N-ring tunnels built by the shield machine comprises: The second weighted average is calculated based on the following formula: In the formula, gc weighted is the second weighted average, n is the number of soil layers, gc i is the physical and mechanical properties of the geological data of the i-th layer in the N-ring tunnel built by the shield machine, w i is the weighted value of the i-th layer of soil, and the specific calculation formula is: In the formula, s i is the weighted area of ​​the i-th soil layer, R is the excavation radius of the shield machine, θ i It is half of the angle between the lower chord of the i-th soil layer and the center of the circle.

4. The method for safety assessment of surface subsidence risk caused by composite stratum construction as claimed in claim 1, characterized in that: The method for obtaining the probability corresponding to the settlement safety risk level at which the first predicted value of the surface settlement is located includes: Based on the failure probability function, obtaining the probability corresponding to the settlement safety risk level of the first prediction value; The specific form of the failure probability function is: In the formula, PF MC is the failure probability function, X is a random variable, M is the total number of the first sampling samples, Ig(X) is the indicator function, is the number of first sampling samples with g(X)≤0, P(g(X)≤0) is the probability, g(X) is the performance function, and the specific calculation formula is: Where δ is a positive integer, MGS low is the lower limit of the subsidence surface, MGS up is the upper limit of the subsidence surface, and MGS(X) is the first predicted value.

5. The method for safety assessment of surface subsidence risk caused by composite stratum construction as claimed in claim 1, characterized in that: The method for obtaining the settlement safety risk level of the first predicted value of the surface settlement includes: When the first predicted value is in the interval (-20mm, +7mm), the settlement safety risk level of the first predicted value is level one; When the first predicted value is between the interval (-30mm, -20mm) and the interval [+7mm, +10mm], the settlement safety risk level of the first predicted value is level 2; When the first predicted value is in the interval (-∞, -30mm) or the interval (+10mm, +∞), the settlement safety risk level of the first predicted value is level three.

6. The method for safety assessment of surface subsidence risk caused by composite stratum construction according to any one of claims 1 to 5, characterized in that: The method further comprises: Based on the Monte Carlo simulation method, the second tunnel burial depth in the N-ring tunnel built by the shield machine, the second weighted average value of the geological data, and the second average value of the stable phase data in the shield machine construction data are sampled to obtain a second sampling sample; Based on the second sampling sample, a second predicted value of the surface settlement in the N-ring tunnel built by the shield machine is obtained; According to the probability corresponding to the settlement safety risk level of the second predicted value of the surface settlement, the surface settlement risk caused by the N-ring tunnel built by the shield machine is evaluated.

7. The method for safety assessment of surface subsidence risk caused by composite stratum construction as claimed in claim 6, characterized in that: The method further comprises: Based on the Sobol method, obtaining a first-order sensitivity index and a total sensitivity index corresponding to the second tunnel burial depth, the second weighted average value, and the second average value, respectively; According to the first-order sensitivity index and the total sensitivity index, the influence degrees of the second tunnel burial depth, the second weighted average value and the second average value on the monitoring value of the surface settlement are determined respectively.

8. A device for safety assessment of surface subsidence risk caused by composite stratum construction, characterized in that: include: An acquisition module is used to sample the first tunnel burial depth in the N+1th ring tunnel to be constructed by the shield machine in the future, the first weighted average value of the geological data, and the first average value of the stable phase data in the shield machine construction data based on the Monte Carlo simulation method to obtain a first sampling sample; A prediction module, used for obtaining a first prediction value of surface settlement in the N+1th ring tunnel to be constructed by the shield machine in the future based on the first sampling sample; An evaluation module is used to evaluate the surface settlement risk caused by the N+1th ring tunnel to be constructed by the shield machine in the future according to the probability corresponding to the settlement safety risk level of the first predicted value of the surface settlement.

9. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method for assessing the risk of surface subsidence caused by shield machine construction as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor executes the method for assessing the risk of surface settlement caused by shield machine construction as described in any one of claims 1 to 7.

Images