Method and system for predicting excavation settlement value of subway double-side extension

Abstract

The invention relates to the technical field of extension compensation models, in particular to a subway double-side extension excavation settlement value prediction method and system, and the method comprises the steps: building a geological survey sub-model and an extension calculation sub-model through collecting initial monitoring data and historical settlement data; and determining a corresponding relation by analyzing the influence degree among the sub-models, establishing a test environment, and calculating an influence factor of the variable on settlement. And based on the influence factors and the degrees, establishing a test model and screening out a first settlement prediction model. And combining the historical data optimization model to form a second settlement prediction model for real-time settlement prediction and compensation. According to the method, multiple models are fused, the settlement prediction accuracy is improved, the construction parameters are optimized, personalized settlement control is achieved, the construction risk is reduced, the construction safety and the surrounding environment stability are guaranteed, meanwhile, the construction efficiency is improved, and the construction period is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of expansion and construction compensation models, and in particular to a method and system for predicting excavation settlement values ​​of subway double-sided expansion and construction. Background Art

[0002] With the acceleration of urbanization, subways, as an important part of urban transportation, are receiving increasing attention for their construction and expansion. Metro double-sided expansion refers to the expansion on both sides of the existing subway line to increase transportation capacity and relieve traffic pressure. However, during the double-sided expansion of subways, construction activities such as earth excavation, groundwater management, backfilling, etc. will cause settlement effects on subways and underground structures, which not only threatens construction safety, but may also cause damage to the surrounding environment. Therefore, how to effectively control the settlement problem during the double-sided expansion of subways has become a technical problem that needs to be solved urgently.

[0003] At present, some technical means have been widely used to solve the settlement problem in the process of subway expansion on both sides. For example, geological surveys are used to understand the distribution and properties of underground soil layers to provide basic data for construction design; on-site monitoring equipment is used to monitor the settlement of subways and underground structures in real time so that problems can be discovered and dealt with in a timely manner; advanced construction technologies and management measures are used, such as layered excavation, precipitation control, and reinforcement treatment, to reduce the impact of construction on subways and underground structures. In addition, some scholars and research institutions are committed to developing new settlement prediction and control methods to improve the accuracy and effectiveness of settlement control.

[0004] Although existing technologies have achieved certain results in controlling settlement during the bilateral expansion of subways, there are still some technical problems that need to be solved. First of all, how to accurately predict the amount of settlement is one of the main challenges currently faced. Due to the influence of multiple factors such as geological conditions, construction parameters, and environmental factors, the prediction of settlement has great uncertainty and complexity. Secondly, how to adjust the construction parameters in a timely and effective manner according to the prediction results to reduce the impact of settlement is also a difficult problem. In the actual construction process, the adjustment of construction parameters is often restricted by multiple factors, such as construction period, cost, technical feasibility, etc., which makes the implementation of settlement control more difficult. Finally, how to optimize the settlement adjustment under complex geological and construction conditions is also a problem that needs to be solved urgently. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention provides a method for predicting excavation settlement values ​​for two-sided extension of a subway, comprising: Step S1, collecting initial monitoring data of the subway extension area, and obtaining historical settlement data and extension design data of the subway extension area, the initial monitoring data including geological survey data and on-site monitoring data; Step S2, constructing a single model according to the single data type of the initial monitoring data, and establishing several geological survey sub-models and construction design sub-models respectively; Step S3, determining the influence degree of each geological survey sub-model on the extension design sub-model, and determining the corresponding relationship between each geological survey sub-model and the extension design sub-model according to each influence degree; Step S4, in the models included in the same corresponding relationship, a test environment for superimposing various variables is established to determine the influence factors of the variables in each sub-model on the field monitoring data; Step S5, re-establishing a number of test models according to the impact degree and the impact factor, and performing simulation prediction on each field monitoring data, and determining a first settlement prediction model according to the prediction results; Step S6, using the historical settlement data to analyze and predict the first settlement prediction model, and adjusting the influence weight of each variable in each test model in the first settlement prediction model according to the gap between the prediction result and the field monitoring data, to obtain a second settlement prediction model; Step S7, using the second settlement prediction model to perform simulation to obtain a subway settlement prediction value, and performing compensation according to the subway settlement prediction value.

[0006] As a preferred technical solution for the excavation settlement value prediction method for the two-side extension of the subway, the geological survey data includes soil type, soil density and soil internal friction angle; The on-site monitoring data includes subway settlement monitoring data, horizontal displacement of the top of the support pile, and vertical displacement of the top of the support pile; The expansion design data includes foundation pit dimensions and support structure forms.

[0007] As a preferred technical solution for the excavation settlement value prediction method for the two-side extension of the subway, the geological survey sub-model includes a soil type sub-model, a soil density sub-model, and a soil internal friction angle sub-model; The expansion design sub-model includes a foundation pit size sub-model and a support structure sub-model.

[0008] As a preferred technical solution for the method of predicting the excavation settlement value of the two-sided extension of the subway, in step S3, determining the corresponding relationship between each geological survey sub-model and the extension design sub-model includes: Step S31, accumulating data sequences of a single type of geological survey sub-model according to historical settlement data to obtain a corresponding geological survey update data sequence; Step S32, accumulating data sequences of a single type of extension and construction design sub-model according to the same historical settlement data, to obtain a corresponding extension and construction design update data sequence; Step S33, calculating the influence degree between the geological survey update data sequence and the expansion design update data sequence; Step S34, repeating step S33, determining the influence degree of each geological survey sub-model and each extension design sub-model, and determining the correspondence between each geological survey sub-model and the extension design sub-model according to the influence degree of each geological survey update data sequence and the extension design update data sequence.

[0009] As a preferred technical solution for the method of predicting the excavation settlement value of the two-sided extension of the subway, in step S4, the factors affecting the variables in the sub-model of the current corresponding relationship on the on-site monitoring data include: Determine the test variable in the current sub-model, take it and the variable as constants, adjust the test variable, obtain the actual value of each field monitoring data and the change amount of each time in the historical settlement data, and calculate the impact factor of the current test variable on the field monitoring data; Adjusting the test variables and constants in the current sub-model, and re-determining the impact factors of the new test variables on the field monitoring data; The process of replacing variables to calculate the impact factors is repeated until the impact factors of all variables in the sub-model of the current corresponding relationship are determined.

[0010] As a preferred technical solution of the method for predicting the excavation settlement value of the two-sided extension of the subway, in step S6, determining the first settlement prediction model according to the prediction result includes: Use each tested model to predict all types of field monitoring data; According to the prediction results of each field monitoring data, the test model corresponding to the smallest prediction error of each field monitoring data is screened out as the first settlement prediction model.

[0011] As a preferred technical solution of the method for predicting excavation settlement values ​​for two-sided extension of a subway, in step S6, adjusting the influence weights of each variable in each test model in the first settlement prediction model includes: Adjust the influence weight of each variable in the first settlement prediction model according to the principle of minimum simulation error; The principle of minimum simulation error is that the error rate of the prediction result of the first settlement prediction model determined by the influence weights of the adjusted variables is minimized.

[0012] As an optimal technical solution for the method of predicting excavation settlement values ​​for two-sided subway expansion, in step S7, if the predicted subway settlement value exceeds the standard predicted value, the test model with the smallest prediction error in each on-site monitoring data is selected for separate predictions, and the predicted maximum value of each on-site monitoring data is selected as the final subway settlement prediction value, and backfill and axial force servo systems are used for compensation.

[0013] The present invention also provides a system for predicting excavation settlement values ​​for subway double-sided expansion, comprising: An information collection module is used to collect initial monitoring data of the subway expansion area, as well as to obtain historical settlement data and expansion design data of the subway expansion area; An information processing module, which is connected to the information acquisition module, and is used to establish the geological survey sub-model and the extension and construction design sub-model, determine the influence degree of each geological survey sub-model on the extension and construction design sub-model, and determine the corresponding relationship between each geological survey sub-model and the extension and construction design sub-model; A model building module, which is connected to the information acquisition module and the information processing module respectively, and is used to establish a test environment for superimposing various variables, determine the influence factors of the variables in each sub-model on the field monitoring data, establish several test models and perform simulation prediction to determine the first settlement prediction model; A model optimization module, which is connected to the information collection module and the model building module respectively, and is used to analyze and predict the first settlement prediction model according to the historical settlement data, and adjust the influence weight of each variable in each test model in the first settlement prediction model according to the gap between the prediction result and the field monitoring data, so as to obtain a second settlement prediction model; A compensation module is connected to the model optimization module and the information acquisition module respectively, and is used to compensate according to the subway settlement prediction value simulated by the second settlement prediction model.

[0014] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: The present invention can make full use of historical settlement data and initial monitoring data by fusing multiple models, improve the accuracy and reliability of settlement prediction, help identify potential settlement risks in advance, and provide a basis for timely adjustment of construction strategies; secondly, by establishing an objective function and optimizing multiple adjustment methods, the present invention can quickly determine the optimal adjustment method after predicting the settlement trend, realize real-time compensation and adjustment of settlement, help reduce the settlement amount during the construction process, and ensure construction safety and stability of the surrounding environment; in addition, the method provided by the present invention can flexibly adjust construction parameters according to different geological conditions, construction environment and settlement prediction results, realize personalized settlement control schemes, enhance the flexibility and adaptability of the construction process, and help cope with complex and changeable construction challenges. The present invention helps to reduce construction accidents caused by settlement and damage to the surrounding environment through accurate prediction and timely adjustment, thereby reducing construction risks and costs. At the same time, the optimized construction scheme also helps to improve construction efficiency and shorten construction period.

[0015] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of a method for predicting excavation settlement values ​​for two-sided extension of a subway according to an embodiment of the present invention; Figure 2 A flow chart for determining a corresponding relationship according to an embodiment of the present invention; Figure 3 A flow chart for determining impact factors according to an embodiment of the present invention; Figure 4 It is a structural schematic diagram of a real-time compensation system for excavation of a subway double-sided expansion according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0019] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0020] See also Figure 1 As shown, it is a flow chart of a method for predicting excavation settlement values ​​of subway double-sided extension construction according to an embodiment of the present invention; the present invention provides a method for predicting excavation settlement values ​​of subway double-sided extension construction, comprising: Step S1, collecting initial monitoring data of the subway extension area, and obtaining historical settlement data and extension design data of the subway extension area, the initial monitoring data including geological survey data and on-site monitoring data; Step S2, constructing a single model according to the single data type of the initial monitoring data, and establishing several geological survey sub-models and construction design sub-models respectively; Step S3, determining the influence degree of each geological survey sub-model on the extension design sub-model, and determining the corresponding relationship between each geological survey sub-model and the extension design sub-model according to each influence degree; Step S4, in the models included in the same corresponding relationship, a test environment for superimposing various variables is established to determine the influence factors of the variables in each sub-model on the field monitoring data; Step S5, re-establishing a number of test models according to the impact degree and the impact factor, and performing simulation prediction on each field monitoring data, and determining a first settlement prediction model according to the prediction results; Step S6, using the historical settlement data to analyze and predict the first settlement prediction model, and adjusting the influence weight of each variable in each test model in the first settlement prediction model according to the gap between the prediction result and the field monitoring data, to obtain a second settlement prediction model; Step S7, using the second settlement prediction model to perform simulation to obtain a subway settlement prediction value, and performing compensation according to the subway settlement prediction value.

[0021] In this embodiment, the number of geological survey sub-models and construction design sub-models is the same as the number of data types included in the geological survey data and the construction design data, respectively.

[0022] The number of test models is the same as the number of corresponding relationships of the extended design sub-models.

[0023] The present invention can make full use of historical settlement data and initial monitoring data by fusing multiple models, improve the accuracy and reliability of settlement prediction, help identify potential settlement risks in advance, and provide a basis for timely adjustment of construction strategies; secondly, by establishing an objective function and optimizing multiple adjustment methods, the present invention can quickly determine the optimal adjustment method after predicting the settlement trend, realize real-time compensation and adjustment of settlement, help reduce the settlement amount during the construction process, and ensure construction safety and stability of the surrounding environment; in addition, the method provided by the present invention can flexibly adjust construction parameters according to different geological conditions, construction environment and settlement prediction results, realize personalized settlement control schemes, enhance the flexibility and adaptability of the construction process, and help cope with complex and changeable construction challenges. The present invention helps to reduce construction accidents caused by settlement and damage to the surrounding environment through accurate prediction and timely adjustment, thereby reducing construction risks and costs. At the same time, the optimized construction scheme also helps to improve construction efficiency and shorten construction period.

[0024] Specifically, the geological survey data includes soil type, soil density and soil internal friction angle; The on-site monitoring data includes subway settlement monitoring data, horizontal displacement of the top of the support pile, and vertical displacement of the top of the support pile; The expansion design data includes foundation pit dimensions and support structure forms.

[0025] In this embodiment, the soil type can be determined by on-site observation or laboratory analysis, such as collecting soil samples and bringing them back to the laboratory for particle analysis tests, using sieving analysis, densitometer method, etc. to determine the content of particles of different sizes in the soil, thereby determining the soil type according to relevant standards.

[0026] Soil density can be determined by the knife ring method or the nuclear density meter method. The knife ring method is to take soil samples on site with a knife ring, weigh the mass and volume of the soil in the knife ring, calculate the wet density of the soil, and then determine the soil moisture content by the drying method, and then calculate the dry density; the nuclear density meter method uses the interaction between the rays emitted by the nuclear density meter and the soil, and determines the soil density based on the absorption and scattering of the rays.

[0027] The internal friction angle of soil can be determined through direct shear test or triaxial compression test. The direct shear test is to place the soil sample in a direct shear apparatus in the laboratory, apply vertical pressure and horizontal shear force, measure the shear strength of the soil sample under different vertical pressures, and calculate the internal friction angle of soil according to Coulomb's law; the triaxial compression test is to apply surrounding pressure and axial pressure to the cylindrical soil sample, so that the soil sample undergoes shear failure under the triaxial stress state, and the internal friction angle of soil is determined through the stress-strain relationship and Mohr-Coulomb strength theory.

[0028] Subway settlement monitoring data can be obtained through leveling or GPS measurement. Leveling is to set up settlement monitoring points in the subway, use a level and a level rod to measure the height difference between the monitoring point and the known elevation point, and calculate the settlement of the monitoring point. GPS measurement is to use a global positioning system (GPS) receiver to receive satellite signals, determine the three-dimensional coordinates of the monitoring point, and obtain subway settlement data by regularly observing the coordinate changes. It has the advantages of high accuracy and high speed.

[0029] The horizontal displacement of the top of the supporting pile can be obtained by total station measurement or inclinometer. A reference point is set at a stable position far away from the supporting pile, and the horizontal angle and distance change between the monitoring point on the top of the supporting pile and the reference point are measured using a total station to calculate the horizontal displacement. Alternatively, an inclinometer tube is pre-buried in the supporting pile, and the inclinometer probe is placed in the inclinometer tube to measure the inclination angle at different depths. The horizontal displacement of the top of the supporting pile is obtained through data processing.

[0030] The method for obtaining the vertical displacement of the top of the support pile is the same as the method for obtaining subway settlement monitoring data. Leveling or GPS measurement can be used to obtain the displacement change data of the top of the support pile in the vertical direction.

[0031] Tunnel dimensions can be obtained directly from design drawings or field measurements.

[0032] The support structure form can be determined through design calculation: according to the geological conditions, burial depth, size, use requirements and other factors of the tunnel, the appropriate support structure form can be determined through mechanical calculation and analysis, such as sprayed anchor support, steel arch support, lining support, etc.

[0033] In this embodiment, the method of acquiring the above data is the existing technology, and the method and process of data acquisition are not specifically limited and will not be described here.

[0034] Specifically, the geological survey sub-model includes a soil type sub-model, a soil density sub-model, and a soil internal friction angle sub-model; The expansion design sub-model includes a foundation pit size sub-model and a support structure sub-model.

[0035] In this embodiment, changes in any sub-data in the construction design data and the geological survey data will lead to changes in the on-site monitoring data under the same construction situation.

[0036] It is understandable that expansion design data and geological survey data are basic information for subway construction. Any changes in these data will directly affect the actual performance during the construction process, and thus lead to changes in on-site monitoring data.

[0037] Different types of soil have different mechanical properties for changes in soil type. For example, there are significant differences between clay and sand in terms of shear strength, compressibility, and permeability. If the soil type changes (such as from sand to clay), the deformation characteristics, settlement rate, and settlement amount of the soil will change during construction. For example, the settlement of sandy soil is usually faster but the total amount is smaller, while the settlement of clay may be slower but the total amount is larger. Therefore, subway settlement monitoring data and underground pipeline settlement monitoring data will show different settlement trends and rates due to changes in soil type.

[0038] Regarding the change of soil density, soil density is related to the compaction degree and particle arrangement of the soil, which directly affects the bearing capacity and deformation resistance of the soil. Soil with higher density usually has higher shear strength and lower compressibility, and vice versa, it is easy to deform and settle. If the soil density decreases (such as due to construction disturbance or groundwater immersion), the horizontal and vertical displacements of the support piles will increase, and the subway settlement will also increase.

[0039] Regarding the change of the internal friction angle of soil, the internal friction angle is an indicator of the friction between soil particles and directly affects the shear strength of the soil. The larger the internal friction angle, the higher the shear strength of the soil and the better the stability; conversely, the soil is more likely to shear deformation and settlement. If the internal friction angle decreases, the stability of the soil decreases, resulting in increased deformation of the support structure, and increased settlement of the subway and underground pipelines.

[0040] The expansion design data include tunnel size, tunnel burial depth, support structure type, etc. These data determine the mechanical environment and construction methods during the construction process.

[0041] For changes in tunnel size, the cross-sectional size of the tunnel directly affects the scope and degree of soil disturbance during construction. If the tunnel size is large, the scope of disturbance to the surrounding soil during construction will also increase, resulting in greater ground deformation and settlement. The increase in tunnel size leads to increased settlement of subways and underground pipelines, and the displacement of support piles also increases.

[0042] Regarding the change of the support structure form, the support structure form determines the support capacity and stability of the soil during the construction process. Different support structures (such as anchor support, steel support, concrete support, etc.) have different restraining capabilities on the soil. If the support structure form changes, the stability of the soil will also change. If the support structure form is changed from steel support to anchor support, the horizontal and vertical displacements of the support piles may change, and the subway settlement may also increase or decrease due to the change in support capacity. Different support structures will cause different settlement effects as the construction progresses.

[0043] See also Figure 2As shown, it is a flow chart of determining the corresponding relationship in an embodiment of the present invention. In step S3, determining the corresponding relationship between each geological survey sub-model and the extension design sub-model includes: Step S31, accumulating data sequences of a single type of geological survey sub-model according to historical settlement data to obtain a corresponding geological survey update data sequence; Step S32, accumulating data sequences of a single type of extension and construction design sub-model according to the same historical settlement data, to obtain a corresponding extension and construction design update data sequence; Step S33, calculating the influence degree between the geological survey update data sequence and the expansion design update data sequence; Step S34, repeating step S33, determining the influence degree of each geological survey sub-model and each extension design sub-model, and determining the correspondence between each geological survey sub-model and the extension design sub-model according to the influence degree of each geological survey update data sequence and the extension design update data sequence.

[0044] In implementation, in step S31, data sequences of a single type of geological survey sub-model are accumulated to obtain a corresponding geological survey update data sequence, and the process includes: selecting a geological survey sub-model (such as soil type sub-model, soil density sub-model, etc.), and accumulating the data related to the sub-model (such as soil type data and soil density data at different monitoring points or in different periods) in a certain order of construction time to obtain an updated data sequence, which reflects the overall characteristics or change trends of the geological survey sub-model within the accumulation range, and is called a geological survey update data sequence.

[0045] In step S32, based on the same historical settlement data, the data sequence of a single type of extension design sub-model is accumulated to obtain a corresponding extension design update data sequence. The process includes: selecting an extension design sub-model (such as a foundation pit size sub-model, a support structure sub-model, etc.), and based on the same historical settlement data, accumulating the data related to the extension design sub-model (such as settlement data under different foundation pit sizes, settlement data under different support structure forms, etc.) in the same construction time sequence to obtain an updated data sequence, which reflects the overall characteristics or change trends of the extension design sub-model within the accumulation range, and is called the extension design update data sequence.

[0046] In step S33, the degree of influence between the geological survey update data sequence and the extension design update data sequence is calculated. The process includes: selecting a geological survey update data sequence and a extension design update data sequence, quantifying the degree of association or mutual influence between the two update data sequences, and the calculation result is the degree of influence between the geological survey sub-model and the extension design sub-model, which reflects the common influence of geological survey factors and extension design factors on settlement.

[0047] In step S34, step S33 is repeated to determine the influence degree of each geological survey sub-model and each extension design sub-model. The process of determining the correspondence between each geological survey sub-model and the extension design sub-model according to the influence degree of each geological survey update data sequence and the extension design update data sequence includes: For each geological survey sub-model, the above process of calculating the influence degree with the extension design sub-model is repeated. At the same time, for each extension design sub-model, the process of calculating the influence degree with the geological survey sub-model is also repeated. Through multiple calculations and comparisons, the corresponding relationship between each geological survey sub-model and the extension design sub-model is determined. This corresponding relationship shows that in terms of settlement impact, the sub-data in the geological survey data and the sub-data in the extension design data have a high degree of mutual influence, which provides a basis for subsequent settlement prediction and compensation.

[0048] The degree of impact is determined according to the following formula: Among them, xi is the geological survey sub-type data, yi is the construction design sub-model data, is the average value of the geological survey subtype data, is the average value of the design sub-model data, i is an integer greater than 0, and n is the total number of data in the field monitoring data sub-type.

[0049] The Pearson correlation coefficient is a statistic that measures the degree of correlation between two variables, and its value range is [-1, 1]. The closer the absolute value of the correlation coefficient is to 1, the higher the linear correlation between the two variables; the closer the absolute value is to 0, the lower the linear correlation.

[0050] Generally speaking, the value of the Pearson correlation coefficient can be interpreted according to the following standards: 0.8 to 1.0 indicates a very strong correlation; 0.6 to 0.8 indicates a strong correlation.

[0051] In this embodiment, the extension design data subtypes with an impact degree greater than 0.6 and the corresponding geological survey data subtypes are recorded as a set of correspondences, that is, the correspondences between the extension design data subtypes and the geological survey data subtypes are not unique.

[0052] It can be understood that the corresponding relationship represents the degree of influence of various geological survey data types and various expansion design data on the settlement during the expansion process under the same settlement conditions.

[0053] In the present invention, in the construction of subway bilateral extension, the influence of geological survey data and construction design parameters on settlement is interrelated. Through historical settlement data, the geological survey sub-model and the extension design sub-model are accumulated with data sequence, the influence degree of the two is calculated, and the variable combination with higher correlation is screened out. The linear correlation between geological survey data and construction design parameters is calculated by Pearson correlation coefficient. When the correlation coefficient is greater than 0.6, it shows that the influence degree of the two on settlement is high, which can be used as a set of corresponding relationships. This corresponding relationship shows that under the same settlement conditions, the combination of specific geological survey data types and construction design parameters has a high influence degree on settlement. When establishing a test model, variables can be screened according to the conditions such as the influencing factors in the sub-models included in the corresponding relationship, which can ensure that the variables included in the model are all important factors closely related to settlement, improve the reliability and effectiveness of the prediction model, and make the prediction results more reflect the actual settlement situation, and provide more accurate guidance for real-time compensation and subsequent construction of the project.

[0054] See also Figure 3 As shown, it is a flow chart of determining the influencing factors according to an embodiment of the present invention. In step S4, determining the influencing factors of the variables in the sub-model of the current corresponding relationship on the field monitoring data includes: Determine the test variable in the current sub-model, take it and the variable as constants, adjust the test variable, obtain the actual value of each field monitoring data and the change amount of each time in the historical settlement data, and calculate the impact factor of the current test variable on the field monitoring data; Adjusting the test variables and constants in the current sub-model, and re-determining the impact factors of the new test variables on the field monitoring data; The process of replacing variables to calculate the impact factors is repeated until the impact factors of all variables in the sub-model of the current corresponding relationship are determined.

[0055] In practice, the influence of soil-related data and tunnel construction parameters on settlement interacts with each other. The mechanical properties of the soil (such as type, density, internal friction angle and water content) determine the degree of soil response to construction disturbance, while the size, burial depth and support structure of the tunnel directly affect the scope and degree of construction disturbance on the soil.

[0056] The influence of soil internal friction angle and tunnel depth on settlement. The smaller the soil internal friction angle, the lower the shear strength of the soil and the higher the settlement risk. The shallower the tunnel depth, the more significant the impact of construction on the subway and the greater the settlement. Soil with a low internal friction angle (such as clay) is more likely to undergo shear deformation when stress changes. When constructing shallow tunnels, the stress redistribution of the soil has a more direct impact on the subway, leading to increased settlement.

[0057] The influence of soil type and support structure on settlement. Clayey soil (such as clay) is more prone to settlement than sandy soil. When the support structure is unreasonable, the risk of settlement increases significantly. The shear strength of clayey soil is sensitive to changes in moisture and stress, and it has high compressibility, which makes it easy for large settlement to occur during construction.

[0058] The influence of soil density and tunnel construction parameters on settlement. The lower the soil density, the weaker the bearing capacity of the soil and the higher the settlement risk. When the tunnel construction parameters (such as size and burial depth) are unreasonable, the settlement risk increases significantly. Low-density soils usually have lower shear strength and higher compressibility, and are prone to deformation and settlement under construction disturbance. Changes in tunnel size and burial depth will directly affect the scope and degree of stress disturbance caused by construction on the soil.

[0059] In practice, soil types have essential differences in physical and mechanical properties, which are the basic factors that determine tunnel settlement. For example, soft soil and silty soil have the characteristics of high compressibility and low strength. During and after tunnel construction, they will produce large settlements, and this settlement is often long-lasting and difficult to stabilize. For large-sized tunnels, excavation in soft soil layers will cause large disturbances to the soft soil due to the large excavation section. The stress release and redistribution of the soil will be more complicated, which will lead to significant settlement. Even if the same support structure is used, tunnels in soft soil are more likely to experience excessive settlement or even failure of the support structure. Hard rock soils, on the other hand, have high strength, high rigidity, and good stability, and can provide a good bearing foundation for tunnels. Regardless of the size and depth of the tunnel, or the type of support structure used, the settlement is usually small.

[0060] Therefore, for each test model, there are usually multiple variables that affect the field monitoring data; For example, the current design submodel includes variables such as the effect of soil internal friction angle, soil type, and tunnel depth on settlement.

[0061] In the specific implementation process, when manufacturing the test environment of each variable, each variable of the designed sub-model is superimposed respectively to obtain the influence factor of each variable on each type of field monitoring data.

[0062] Specifically, in step S6, determining the first settlement prediction model according to the prediction result includes: Use each tested model to predict all types of field monitoring data; According to the prediction results of each field monitoring data, the test model corresponding to the smallest prediction error of each field monitoring data is screened out as the first settlement prediction model.

[0063] In implementation, for one type of field monitoring data, if there are more than two test models with the same simulation results, the test model with the smallest overall error is determined through other types of field monitoring data.

[0064] In this embodiment, when establishing the test model, the variables whose influencing factors account for a higher proportion than the average value and whose corresponding number of variables is greater than 1 / 4 of the total number are established according to the sub-models included in the corresponding relationship.

[0065] It is understandable that variables with a higher proportion of influencing factors than the average have a greater impact on the on-site monitoring data and are important factors leading to phenomena such as settlement. These variables are selected to establish a test model so that the model can more accurately reflect the actual situation and reduce the errors caused by interference from minor factors, thereby more accurately predicting settlement and other conditions during the expansion of the subway on both sides. The number of corresponding variables is greater than 1 / 4 of the total number, ensuring that a sufficient number of important variables are included in the model, avoiding the situation where only a few factors are considered and other important influences are ignored, enabling the model to comprehensively consider the impact of various factors on on-site monitoring data from multiple perspectives, more comprehensively simulate the actual physical process, and further improve the accuracy and reliability of the model. At the same time, the amount of calculation and data processing is reduced, the operating efficiency and calculation speed of the model are improved, and the model can give prediction results more quickly to meet the timeliness requirements of actual application scenarios such as real-time compensation. In the process of model optimization, these key variables can be adjusted and improved more specifically to improve the optimization efficiency of the model, find the optimal model parameters and structure more quickly, and improve the overall performance of the model.

[0066] In addition, overfitting can be avoided. If only a few variables with extremely high influencing factors are selected to build a model, the model will be overly dependent on these specific variables, overfitting the training data, and performing poorly when faced with new, unseen data. A combination of variables with a higher than average influencing factor ratio and a sufficient number can form a relatively balanced relationship in the model. Different variables restrict and influence each other and work together to predict field monitoring data. This balanced relationship helps the model to give reasonable prediction results in various situations, and will not cause large fluctuations in model output due to abnormal changes in a certain variable, thereby enhancing the stability of the model.

[0067] Specifically, in step S6, adjusting the influence weight of each variable in each test model in the first settlement prediction model includes: Adjust the influence weight of each variable in the first settlement prediction model according to the principle of minimum simulation error; The principle of minimum simulation error is that the error rate of the prediction result of the first settlement prediction model determined by the influence weights of the adjusted variables is less than the error rate of any prediction result of the first settlement prediction model determined by the influence weights of the variables other than the adjusted variables.

[0068] In implementation, when constructing the first settlement prediction model, the error rate of the model prediction results determined by adjusting the influence weights of the variables should be less than the error rate of the model prediction results when any other non-current adjustment method is used to determine the influence weights of the variables. That is, among all possible methods for determining the influence weights of the variables, the adjusted influence weights of the variables can minimize the prediction error of the first settlement prediction model.

[0069] The principle of minimum error rate can obtain the influence weight of variables through data exhaustion and historical variation. The acquisition method is not unique. The appropriate weight value calculation method can be selected according to needs under the existing data processing technology conditions, which will not be elaborated here.

[0070] Specifically, in step S7, if the predicted value of subway settlement exceeds the standard predicted value, the test model with the smallest prediction error in each field monitoring data is selected for separate prediction, and the predicted maximum value of each field monitoring data is selected as the final predicted value of subway settlement and compensated using backfill and axial force servo system.

[0071] In implementation, the standard prediction value is determined based on the maximum on-site monitoring data without additional compensation under the same expansion design data and geological survey data conditions in the historical settlement data.

[0072] See also Figure 4 As shown, it is a structural schematic diagram of a real-time compensation system for excavation of a subway double-sided extension according to an embodiment of the present invention. The present invention also provides a system for predicting an excavation settlement value for subway double-sided extension, including: An information collection module is used to collect initial monitoring data of the subway expansion area, as well as to obtain historical settlement data and expansion design data of the subway expansion area; An information processing module, which is connected to the information acquisition module, and is used to establish the geological survey sub-model and the extension and construction design sub-model, determine the influence degree of each geological survey sub-model on the extension and construction design sub-model, and determine the corresponding relationship between each geological survey sub-model and the extension and construction design sub-model; A model building module, which is connected to the information acquisition module and the information processing module respectively, and is used to establish a test environment for superimposing various variables, determine the influence factors of the variables in each sub-model on the field monitoring data, establish several test models and perform simulation prediction to determine the first settlement prediction model; A model optimization module, which is connected to the information collection module and the model building module respectively, and is used to analyze and predict the first settlement prediction model according to the historical settlement data, and adjust the influence weight of each variable in each test model in the first settlement prediction model according to the gap between the prediction result and the field monitoring data, so as to obtain a second settlement prediction model; A compensation module is connected to the model optimization module and the information acquisition module respectively, and is used to compensate according to the subway settlement prediction value simulated by the second settlement prediction model. Example 1

[0073] The soil type is interlayered silty clay and silt sand, with local interlayers of silty silty clay. The average density of silty clay is 1.9g / cm³, the internal friction angle is 18°, the average density of silt sand is 2.0g / cm³, the internal friction angle is 30°, and the water content is 20%; the average density of silty silty clay is 1.75g / cm³, the internal friction angle is 12°, and the water content is 35%.

[0074] The expansion design data is that the total width of the tunnel after widening on both sides is 12m and the height is 7m. The support system adopts bored cast-in-place piles with a diameter of 1000mm and a spacing of 1500mm plus steel pipe supports and internal supports.

[0075] The on-site monitoring data showed that the maximum settlement of the subway was 35mm, the settlement rate in some areas was 2mm / d, the maximum settlement of underground pipelines was 25mm, the settlement rate was 1.5mm / d, the maximum horizontal displacement of the top of the support pile was 18mm, the displacement rate was 0.8mm / d, the maximum vertical displacement was 10mm, and the displacement rate was 0.5mm / d; The compensation method is to reduce the excavation depth of each layer from 3m in the original design to 2m; use precipitation wells to reduce the original groundwater level from 3m to 5m, so that the groundwater depth is 2m below the bottom of the tunnel; increase the backfill depth from the original 1m in the design to 1.5m on both sides and the top of the tunnel, and use graded sand and gravel backfill; to control the displacement of the support piles, install an axial force servo system on the steel pipe support, and automatically increase the axial force by 100kN when the horizontal displacement of the top of the support pile exceeds 15mm, and increase the axial force by 50kN when the vertical displacement exceeds 8mm.

[0076] After implementing these compensation measures, the subway settlement rate dropped to below 1mm / d, the underground pipeline settlement rate dropped to below 0.8mm / d, and the horizontal and vertical displacements of the top of the support piles were basically stable, meeting the project safety and use requirements.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting excavation settlement values ​​for two-sided subway expansion, characterized in that: include: Step S1, collecting initial monitoring data of the subway extension area, and obtaining historical settlement data and extension design data of the subway extension area, the initial monitoring data including geological survey data and on-site monitoring data; Step S2, constructing a single model according to the single data type of the initial monitoring data, and establishing several geological survey sub-models and construction design sub-models respectively; Step S3, determining the influence degree of each geological survey sub-model on the extension and construction design sub-model, and determining the corresponding relationship between each geological survey sub-model and the extension and construction design sub-model according to each influence degree; Step S4, in the models included in the same corresponding relationship, a test environment for superimposing various variables is established to determine the influence factors of the variables in each sub-model on the field monitoring data; Step S5, re-establishing a number of test models according to the impact degree and the impact factor, and performing simulation prediction on each field monitoring data, and determining a first settlement prediction model according to the prediction results; Step S6, using the historical settlement data to analyze and predict the first settlement prediction model, and adjusting the influence weight of each variable in each test model in the first settlement prediction model according to the gap between the prediction result and the field monitoring data, to obtain a second settlement prediction model; Step S7, using the second settlement prediction model to perform simulation to obtain a subway settlement prediction value, and performing compensation according to the subway settlement prediction value.

2. The method for predicting excavation settlement value of subway double-sided extension according to claim 1 is characterized in that: The geological survey data include soil type, soil density and soil internal friction angle; The on-site monitoring data includes subway settlement monitoring data, horizontal displacement of the top of the support pile, and vertical displacement of the top of the support pile; The expansion design data includes foundation pit dimensions and support structure forms.

3. The method for predicting excavation settlement value of subway double-sided extension according to claim 2 is characterized in that: The geological survey sub-model includes a soil type sub-model, a soil density sub-model, and a soil internal friction angle sub-model; The expansion design sub-model includes a foundation pit size sub-model and a support structure sub-model.

4. The method for predicting excavation settlement value of subway double-sided extension according to claim 1 is characterized in that: In step S3, determining the correspondence between each geological survey sub-model and the extension design sub-model includes: Step S31, accumulating data sequences of a single type of geological survey sub-model according to historical settlement data to obtain a corresponding geological survey update data sequence; Step S32, accumulating data sequences of a single type of extension and construction design sub-model according to the same historical settlement data, to obtain a corresponding extension and construction design update data sequence; Step S33, calculating the influence degree between the geological survey update data sequence and the expansion design update data sequence; Step S34, repeating step S33, determining the influence degree of each geological survey sub-model and each extension design sub-model, and determining the correspondence between each geological survey sub-model and the extension design sub-model according to the influence degree of each geological survey update data sequence and the extension design update data sequence.

5. The method for predicting excavation settlement value of subway double-sided extension according to claim 1 is characterized in that: In step S4, determining the influence factors of the variables in the sub-model of the current corresponding relationship on the field monitoring data includes: Determine the test variable in the current sub-model, take it and the variable as constants, adjust the test variable, obtain the actual value of each field monitoring data and the change amount of each time in the historical settlement data, and calculate the impact factor of the current test variable on the field monitoring data; Adjusting the test variables and constants in the current sub-model, and re-determining the impact factors of the new test variables on the field monitoring data; The process of replacing variables to calculate the impact factors is repeated until the impact factors of all variables in the sub-model of the current corresponding relationship are determined.

6. The method for predicting excavation settlement value of subway double-sided extension according to claim 1 is characterized in that: In step S6, determining the first settlement prediction model according to the prediction result includes: Use each tested model to predict all types of field monitoring data; According to the prediction results of each field monitoring data, the test model corresponding to the smallest prediction error of each field monitoring data is screened out as the first settlement prediction model.

7. The method for predicting excavation settlement value of subway double-sided extension according to claim 1 is characterized in that: In the step S6, adjusting the influence weight of each variable in each test model in the first settlement prediction model includes: Adjust the influence weight of each variable in the first settlement prediction model according to the principle of minimum simulation error; The principle of minimum simulation error is that the error rate of the prediction result of the first settlement prediction model determined by the influence weights of the adjusted variables is minimized.

8. The method for predicting excavation settlement value of subway double-sided extension according to claim 1 is characterized in that: In step S7, if the predicted value of subway settlement exceeds the standard predicted value, the test model with the smallest prediction error in each field monitoring data is selected for separate prediction, and the predicted maximum value of each field monitoring data is selected as the final predicted value of subway settlement and compensated using backfill and axial force servo system.

9. A system applied to the method for predicting excavation settlement value of subway double-sided extension as described in any one of claims 1 to 8, characterized in that: include: An information collection module is used to collect initial monitoring data of the subway expansion area, as well as to obtain historical settlement data and expansion design data of the subway expansion area; An information processing module, which is connected to the information acquisition module, and is used to establish the geological survey sub-model and the extension and construction design sub-model, determine the influence degree of each geological survey sub-model on the extension and construction design sub-model, and determine the corresponding relationship between each geological survey sub-model and the extension and construction design sub-model; A model building module, which is connected to the information acquisition module and the information processing module respectively, and is used to establish a test environment for superimposing various variables, determine the influence factors of the variables in each sub-model on the field monitoring data, establish several test models and perform simulation prediction to determine the first settlement prediction model; A model optimization module, which is connected to the information collection module and the model building module respectively, and is used to analyze and predict the first settlement prediction model according to the historical settlement data, and adjust the influence weight of each variable in each test model in the first settlement prediction model according to the gap between the prediction result and the field monitoring data, so as to obtain a second settlement prediction model; A compensation module is connected to the model optimization module and the information acquisition module respectively, and is used to compensate according to the subway settlement prediction value simulated by the second settlement prediction model.

Images