A method and device for analyzing service performance of subway tunnel structure

Abstract

A subway tunnel structure service performance analysis method and device, the method constructs a prediction model database based on physical experiments and numerical simulations, uses an interpretable machine learning method to determine the main factors affecting the tunnel structure service process, and realizes accurate evaluation of the tunnel structure service performance under small sample conditions through coupling with physical equations, avoiding the "black box" characteristics of low prediction accuracy under small sample conditions in existing machine learning methods; the tunnel structure service performance prediction model constructed by the present invention can qualitatively evaluate the subway service performance (safety performance) from an objective perspective, thereby monitoring, evaluating and warning the service status of the lining structure, identifying and handling problems existing in the current structure under the evaluation framework of "monitoring-analysis-assessment-warning-disposal-decision-making", and providing solid technical guarantee for tunnel safety and continuous service.

Description

Technical Field

[0001] The invention belongs to the technical field of subway tunnels, and in particular relates to a method and a device for analyzing the service performance of a subway tunnel structure. Background Art

[0002] As the service environment faced by subway tunnels is very complex, such as the uncertainty of rock and soil activities, the complexity of the mechanical characteristics of the lining structure, and the new background of groundwater level recovery, the research on the mechanical properties of subway tunnels is also relatively complex. It is of great significance to carry out numerical simulation and model test research on the service performance of subway tunnel structures under complex service environments, which can provide a basis and guidance for tunnel health status evaluation and safe operation.

[0003] At present, the commonly used method for studying the service performance evaluation method of subway tunnel structures is to obtain data from each monitoring point of the tunnel structure through physical experiments and numerical simulations of the tunnel structure under different working conditions. Then, the data from different data sources are integrated to build a database. Finally, considering the influencing factors such as groundwater level changes, train operating loads, and surrounding rock strength, a subway tunnel structure service performance prediction model based on machine learning methods is built to quantitatively evaluate the service performance of subway tunnel structures. However, the existing technology has the following problems:

[0004] Due to the high cost of the test and the complexity of the test operation, less test data is often obtained. In addition, the accuracy of the bearing capacity model developed using traditional machine learning methods directly depends on the number of samples obtained, which affects the accuracy of the model. The low accuracy in evaluating the service performance of subway tunnel structures greatly reduces the applicability of the model. The traditional machine learning method is a "black box" model, which is often difficult to reflect the physical laws between input and output parameters, and the prediction results may not be consistent with the physical laws. Different subway tunnel structure service performance prediction models are greatly affected by input parameters. The commonly used method is a subjective factor screening method, which is difficult to determine the input parameters that have the greatest impact on the model from an objective perspective. The model usually gives the strength value of a certain monitoring point, which makes it difficult to evaluate the safety of the overall tunnel structure. Summary of the invention

[0005] To this end, the present invention provides a subway tunnel structure service performance analysis method and device to solve the problems of low accuracy, poor model applicability, possible inconsistency between prediction results and physical laws, and poor objectivity and integrity in traditional technologies.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for analyzing the service performance of a subway tunnel structure, comprising:

[0007] Constructing a tunnel structure service safety performance index evaluation table, wherein the fields of the safety performance index evaluation table include structural safety factor, lining concrete stress, vertical displacement and safety risk level;

[0008] Constructing an original monitoring database, wherein the original monitoring database includes tunnel monitoring data, geological survey reports, and operation record data;

[0009] Preprocessing the tunnel monitoring data, geological survey report, and operation record data in the original monitoring database, and converting the preprocessed tunnel monitoring data, geological survey report, and operation record data into a target data format;

[0010] Quantify the service performance of subway tunnel structures, obtain the quantitative indicators of subway tunnel structure service performance, and define the physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process;

[0011] The physical damage function is combined with machine learning to form a fusion physics and machine learning framework, and specified model parameters are input into the fusion physics and machine learning framework to obtain a tunnel structure service performance prediction model;

[0012] The tunnel structure service performance prediction model is used to quantitatively evaluate the service performance of the subway tunnel structure by using the tunnel monitoring data, geological survey reports, and operation record data converted into the target data format;

[0013] According to the service performance evaluation results of the subway tunnel structure, combined with the safety performance index evaluation table, the safety status of the subway tunnel lining structure is determined and the corresponding safety risk level is given.

[0014] As a preferred scheme for the service performance analysis method of subway tunnel structures, the safety risk levels include primary safety risk, secondary safety risk and tertiary safety risk; the safety risk levels are determined based on the correlation between the structural safety factor, lining concrete stress and vertical displacement.

[0015] As a preferred solution for the subway tunnel structure service performance analysis method, the tunnel monitoring data includes lining structure deformation, cracks, water leakage, groundwater pressure, and surrounding rock pressure monitoring data;

[0016] The geological survey report includes geological condition information of the area where the subway tunnel is located; the operation record data includes load and environmental change information during the operation of the subway tunnel.

[0017] As the optimal solution for the analysis of the service performance of subway tunnel structures, the physical damage function is defined according to the physical control equations and boundary conditions of the tunnel lining service process:

[0018] The Culmann formula is introduced to determine the confining pressure acting on the tunnel lining structure:

[0019]

[0020] In the formula, represents the surrounding rock pressure, represents the free difference, Represents the rock mass density, represents the depth of overburden;

[0021] For the water pressure on the tunnel lining structure affected by the groundwater level:

[0022]

[0023] In the formula, is the external water pressure acting on the lining; is the water pressure correction coefficient of the initial seepage field; is the correction coefficient of the relative relationship between the permeability of the lining and the surrounding rock; Correction factor to prevent drainage measures from affecting the external water pressure of the lining; is the hydrostatic pressure generated by the groundwater level at the calculation point.

[0024] As the optimal solution for the analysis method of subway tunnel structure service performance, the subway tunnel is subject to the Winkle formula during service:

[0025]

[0026] In the formula, is the elastic resistance coefficient of surrounding rock; For the surrounding rock The elastic resistance generated at the point; Any point on the tunnel lining surface Compression deformation;

[0027] Under the influence of geological conditions and groundwater level environment, the geometric parameters of the lining The calculation formula is:

[0028]

[0029] In the formula, is the peak strain produced in the masonry shell, is the elastic modulus of masonry.

[0030] As the preferred method for analyzing the service performance of subway tunnel structures, it also includes:

[0031] According to the service performance evaluation results of subway tunnel structures, dynamic early warning of the safety status of subway tunnel lining structures is carried out; when the monitoring value or prediction result exceeds the preset warning value, an early warning message is issued;

[0032] For lining structures with level one safety risk, level two safety risk or those that have exceeded the limit, field review is carried out, and numerical simulation and expert judgment methods are used to analyze the weak areas of the lining structure and their causes, and specific reinforcement measures are proposed.

[0033] The present invention also provides a subway tunnel structure service performance analysis device, comprising:

[0034] A safety performance index evaluation table construction module is used to construct a tunnel structure service safety performance index evaluation table, wherein the fields of the safety performance index evaluation table include structural safety factor, lining concrete stress, vertical displacement and safety risk level;

[0035] An original monitoring database construction module is used to construct an original monitoring database, wherein the original monitoring database includes tunnel monitoring data, geological survey reports, and operation record data;

[0036] The original monitoring data processing module is used to pre-process the tunnel monitoring data, geological survey reports, and operation record data in the original monitoring database, and convert the pre-processed tunnel monitoring data, geological survey reports, and operation record data into a target data format;

[0037] The service performance index quantification module is used to quantify the service performance of the subway tunnel structure, obtain the service performance quantification index of the subway tunnel structure, and define the physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process;

[0038] A tunnel structure service performance prediction model building module is used to combine the physical damage function with machine learning to form a fusion physics and machine learning framework, input specified model parameters into the fusion physics and machine learning framework, and obtain a tunnel structure service performance prediction model;

[0039] A subway tunnel structure service performance evaluation module, which is used to quantitatively evaluate the service performance of a subway tunnel structure by using the tunnel monitoring data, geological survey reports, and operation record data converted into a target data format through the tunnel structure service performance prediction model;

[0040] The safety risk level determination module is used to determine the safety status of the subway tunnel lining structure and give a corresponding safety risk level based on the subway tunnel structure service performance evaluation result and in combination with the safety performance index evaluation table.

[0041] As a preferred solution of the subway tunnel structure service performance analysis device, in the safety performance index evaluation table construction module, the safety risk level includes first-level safety risk, second-level safety risk and third-level safety risk; the safety risk level is determined according to the correlation between the structural safety factor, lining concrete stress and vertical displacement;

[0042] In the original monitoring database construction module:

[0043] The tunnel monitoring data includes monitoring data of lining structure deformation, cracks, water leakage, groundwater pressure, and surrounding rock pressure;

[0044] The geological survey report includes geological condition information of the area where the subway tunnel is located; the operation record data includes load and environmental change information during the operation of the subway tunnel.

[0045] As a preferred solution for the subway tunnel structure service performance analysis device, in the service performance index quantification module:

[0046] The Culmann formula is introduced to determine the confining pressure acting on the tunnel lining structure:

[0047]

[0048] In the formula, represents the surrounding rock pressure, represents the free difference, Represents the rock mass density, represents the depth of overburden;

[0049] In the service performance index quantification module, the water pressure on the lining structure of the tunnel affected by the groundwater level is introduced as follows:

[0050]

[0051] is the external water pressure acting on the lining; is the water pressure correction coefficient of the initial seepage field; is the correction coefficient of the relative relationship between the permeability of the lining and the surrounding rock; Correction factor to prevent drainage measures from affecting the external water pressure of the lining; is the hydrostatic pressure generated by the groundwater level at the calculation point;

[0052] In the service performance index quantification module, the subway tunnel follows the Winkle formula during service:

[0053]

[0054] In the formula, is the elastic resistance coefficient of surrounding rock; For the surrounding rock The elastic resistance generated at the point; Any point on the tunnel lining surface Compression deformation;

[0055] In the service performance index quantification module, the geometric parameters of the lining are affected by the geological conditions and groundwater level environment. The calculation formula is:

[0056] In the formula, is the peak strain produced in the masonry shell, is the elastic modulus of masonry.

[0057] As the preferred solution for the subway tunnel structure service performance analysis device, it also includes:

[0058] The safety dynamic warning module is used to provide dynamic warning of the safety status of the subway tunnel lining structure based on the service performance evaluation results of the subway tunnel structure; it issues a warning message when the monitoring value or prediction result exceeds the preset warning value;

[0059] The reinforcement measures analysis module is used to conduct field reviews of lining structures with primary safety risks, secondary safety risks or those that have exceeded the limit, and uses numerical simulation and expert judgment methods to analyze the weak areas of the lining structure and their causes, and propose targeted reinforcement measures.

[0060] The present invention has the following advantages: a database of prediction models is constructed based on physical experiments and numerical simulations, and the main factors affecting the service process of tunnel structures are determined by using interpretable machine learning methods. Accurate evaluation of the service performance of tunnel structures under small sample conditions is achieved through coupling with physical equations, thereby avoiding the "black box" characteristics of low prediction accuracy under small sample conditions in existing machine learning methods. The tunnel structure service performance prediction model constructed by the present invention can qualitatively evaluate the service performance (safety performance) of the subway from an objective perspective, thereby monitoring, evaluating and warning the service status of the lining structure, identifying and handling problems existing in the current structure under the evaluation framework of "monitoring-analysis-evaluation-warning-disposal-decision-making", and providing solid technical guarantees for tunnel safety and continuous service. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0062] Figure 1A schematic diagram of a process flow of a subway tunnel structure service performance analysis method provided in an embodiment of the present invention;

[0063] Figure 2 The subway tunnel service performance evaluation process provided by the embodiment of the present invention;

[0064] Figure 3 A fusion physics and machine learning model framework provided by an embodiment of the present invention;

[0065] Figure 4 A schematic diagram of parameter analysis based on explainable machine learning (SHAP) provided in an embodiment of the present invention;

[0066] Figure 5 A schematic diagram of the force on the tunnel structure provided by an embodiment of the present invention;

[0067] Figure 6 This is a schematic diagram of the architecture of a subway tunnel structure service performance analysis device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0069] See also Figure 1 and Figure 2 Embodiment 1 of the present invention provides a method for analyzing the service performance of a subway tunnel structure, comprising the following steps:

[0070] S1. Constructing a tunnel structure service safety performance index evaluation table, wherein the fields of the safety performance index evaluation table include structural safety factor, lining concrete stress, vertical displacement and safety risk level;

[0071] S2. Build an original monitoring database, which includes tunnel monitoring data, geological survey reports, and operation record data;

[0072] S3, preprocessing the tunnel monitoring data, geological survey report, and operation record data in the original monitoring database, and converting the preprocessed tunnel monitoring data, geological survey report, and operation record data into a target data format;

[0073] S4. Quantify the service performance of the subway tunnel structure, obtain the quantitative index of the service performance of the subway tunnel structure, and define the physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process;

[0074] S5, combining the physical damage function with machine learning to form a fusion physics and machine learning framework, inputting specified model parameters into the fusion physics and machine learning framework, and obtaining a tunnel structure service performance prediction model;

[0075] S6. Quantitatively evaluate the service performance of the subway tunnel structure by using the tunnel monitoring data, geological survey report, and operation record data converted into the target data format through the tunnel structure service performance prediction model;

[0076] S7. According to the service performance evaluation results of the subway tunnel structure, the safety status of the subway tunnel lining structure is determined in combination with the safety performance index evaluation table and a corresponding safety risk level is given.

[0077] In this embodiment, in step S1, the safety risk level includes level one safety risk, level two safety risk and level three safety risk; the safety risk level is determined according to the correlation between the structural safety factor, lining concrete stress and vertical displacement.

[0078] Specifically, based on the existing specifications and existing tunnel research, it can be seen that the safety factor, stress and deformation of the structure are important indicators for measuring structural safety and are important bases for evaluating the service performance (safety) status of the structure. They are of great significance for discovering the weak links of the structure and guiding the maintenance and reinforcement of the structure. Therefore, from the perspective of current technical specifications, the deformation range of the lining structure is relatively safe within 10mm. On the basis of the specification values, combined with the existing research results, a tunnel lining structure safety evaluation method is constructed that is interrelated with the structural safety factor, lining concrete stress, vertical displacement and safety risk level. According to the distribution of the numerical range of each indicator, a tunnel structure service safety performance index evaluation table is established, as shown in Table 1:

[0079] Table 1 Tunnel structure safety assessment classification

[0080]

[0081] In this embodiment, in step S2, in order to establish a tunnel structure service performance prediction model, it is necessary to obtain data to build an original monitoring database, so as to automatically evaluate the tunnel service performance law. Therefore, the following data needs to be collected: tunnel monitoring data, including lining structure deformation, cracks, water leakage, groundwater pressure, and surrounding rock pressure monitoring data; geological survey reports, including geological condition information of the area where the subway tunnel is located; operation record data, including load and environmental change information during the operation of the subway tunnel.

[0082] In this embodiment, in step S3, the collected raw monitoring data is systematically preprocessed according to the specification requirements and engineering needs, including outlier removal, data improvement, data cleaning, denoising and feature extraction, etc., to improve the data quality and reliability, and convert it into a target data format suitable for analysis, thereby providing data support for the subsequent screening of input factors and safety warning (service performance prediction) of the tunnel structure service performance prediction model. Among them, outlier removal, data improvement, data cleaning, denoising and feature extraction themselves belong to the existing technology and will not be repeated here.

[0083] In this embodiment, in step S4, in order to construct a tunnel structure service performance prediction model, the service performance is first quantified to obtain service performance quantitative indicators, such as lining deformation, stress, surrounding rock strength, operating load, etc. Then, according to the physical equation of the tunnel lining service process and its boundary conditions, a fusion physics and machine learning method framework is developed based on test and monitoring data, such as Figure 3 As shown in Figure 2, a prediction model for tunnel service performance under small sample conditions is established. Figure 4 Among them, the input parameters of the tunnel structure service performance prediction model are determined based on the interpretable machine learning method (SHAP), including but not limited to tunnel surrounding rock parameters, surface load, groundwater level, lining geometry parameters, lining material parameters, tunnel segment parameters, etc.

[0084] Specifically, the tunnel lining is simplified to Figure 5 The mechanical model shown in part (a) of the paper is used, and according to the force characteristics, the mechanical model of the tunnel is assumed to be as follows Figure 5 As shown in part (b) of the figure. When calculating the mechanical properties of the tunnel lining structure, it is necessary to clearly define the confining pressure acting on the tunnel lining structure. Therefore, in the process of defining the physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process, the Culmann formula is introduced to determine the confining pressure acting on the tunnel lining structure:

[0085]

[0086] In the formula, represents the surrounding rock pressure, represents the free difference, Represents the rock mass density, represents the depth of overburden;

[0087] For the water pressure on the tunnel lining structure affected by the groundwater level:

[0088]

[0089] In the formula, is the external water pressure acting on the lining; is the water pressure correction coefficient of the initial seepage field; is the correction coefficient of the relative relationship between the permeability of the lining and the surrounding rock; Correction factor to prevent drainage measures from affecting the external water pressure of the lining; is the hydrostatic pressure generated by the groundwater level at the calculation point.

[0090] As the optimal solution for the analysis method of subway tunnel structure service performance, the subway tunnel is subject to the Winkle formula during service:

[0091]

[0092] In the formula, is the elastic resistance coefficient of surrounding rock; For the surrounding rock The elastic resistance generated at the point; Any point on the tunnel lining surface Compression deformation;

[0093] Under the influence of geological conditions and groundwater level environment, the geometric parameters of the lining The calculation formula is:

[0094]

[0095] In the formula, is the peak strain produced in the masonry shell, is the elastic modulus of masonry.

[0096] Thus, in step S5, the physical control equations and boundary conditions are derived based on the physical calculation formulas proposed above, and the physical damage function is defined. The derived physical control equations and the physical damage function defined by the boundary conditions are combined with the machine learning method, and the input parameters of the tunnel structure service performance prediction model are determined based on the explainable machine learning method (SHAP), and the established fusion physics and machine learning method is updated, thereby forming an algorithm of a physical information network suitable for predicting the service performance of the tunnel structure, and obtaining the tunnel structure service performance prediction model.

[0097] In this embodiment, in step S6, the processed monitoring data is imported into the pre-established tunnel structure service performance prediction model, and the safety factor distribution of the lining structure of the monitoring section in the current state is obtained through prediction analysis. In step S7, based on the prediction of the lining safety factor, the settlement, convergence deformation and stress state monitoring results of each monitoring point of the lining structure are comprehensively considered, and the deformation, stress state and safety factor distribution of the lining structure are comprehensively evaluated in combination with the lining structure safety evaluation index system. The numerical values ​​between the monitoring data, the prediction value and the corresponding threshold are compared to determine the safety state of the lining structure and give the corresponding safety level.

[0098] In a possible embodiment, it further includes:

[0099] According to the service performance evaluation results of subway tunnel structures, dynamic early warning of the safety status of subway tunnel lining structures is carried out; when the monitoring value or prediction result exceeds the preset warning value, a warning message is issued.

[0100] Specifically, based on the service performance evaluation results of the subway tunnel structure, a dynamic early warning is given to the safety status of the lining structure. When the monitoring value or prediction result exceeds the preset warning value, an early warning message is issued in time to attract the attention of the tunnel maintenance department and facilitate the adoption of corresponding emergency measures. At the same time, taking into account the risk impact and maintenance cost of the lining structure, the optimal maintenance and reinforcement decision-making plan is formed on the basis of multi-objective optimization to guide the subsequent structural reinforcement and treatment work.

[0101] In a possible embodiment, it further includes:

[0102] For lining structures with level one safety risk, level two safety risk or those that have exceeded the limit, field review is carried out, and numerical simulation and expert judgment methods are used to analyze the weak areas of the lining structure and their causes, and specific reinforcement measures are proposed.

[0103] Specifically, for lining structures with a low safety risk assessment level or that have exceeded the limit, it is necessary to conduct field reviews in a timely manner to find out the reasons. In addition, numerical simulation, expert judgment and other methods are used to analyze the weak areas and causes of the lining structure, and to propose targeted reinforcement measures, such as resin grouting reinforcement, steel ring reinforcement and other mature and effective reinforcement technologies for treatment. After reinforcement, evaluation should be carried out through subsequent monitoring data, and maintenance plans should be optimized in a timely manner to improve the safety and durability of the lining structure.

[0104] In summary, the present invention constructs a tunnel structure service safety performance index evaluation table, the fields of which include structural safety factor, lining concrete stress, vertical displacement and safety risk level; constructs an original monitoring database, the original monitoring database includes tunnel monitoring data, geological survey reports, and operation record data; pre-processes the tunnel monitoring data, geological survey reports, and operation record data in the original monitoring database, and converts the pre-processed tunnel monitoring data, geological survey reports, and operation record data into a target data format; quantifies the service performance of the subway tunnel structure to obtain a quantitative index of the service performance of the subway tunnel structure, and defines a physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process; combines the physical damage function with machine learning to form a fusion physics and machine learning framework, inputs specified model parameters into the fusion physics and machine learning framework, and obtains a tunnel structure service performance prediction model; quantitatively evaluates the service performance of the subway tunnel structure by using the tunnel monitoring data, geological survey reports, and operation record data converted into the target data format through the tunnel structure service performance prediction model; determines the safety status of the subway tunnel lining structure according to the evaluation result of the subway tunnel structure service performance and combines the safety performance index evaluation table to give a corresponding safety risk level. The present invention constructs a database of prediction models based on physical experiments and numerical simulations, uses interpretable machine learning methods to determine the main factors affecting the service process of tunnel structures, and realizes accurate evaluation of the service performance of tunnel structures under small sample conditions through coupling with physical equations, avoiding the "black box" characteristics of low prediction accuracy under small sample conditions in existing machine learning methods; the tunnel structure service performance prediction model constructed by the present invention can qualitatively evaluate the service performance (safety performance) of the subway from an objective perspective, thereby monitoring, evaluating and warning the service status of the lining structure, identifying and dealing with problems existing in the current structure under the evaluation framework of "monitoring-analysis-evaluation-warning-disposal-decision-making", and providing solid technical guarantees for tunnel safety and continuous service.

[0105] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0106] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous. Example 2

[0107] See also Figure 6 Embodiment 2 of the present invention further provides a subway tunnel structure service performance analysis device, comprising:

[0108] A safety performance index evaluation table construction module 100 is used to construct a tunnel structure service safety performance index evaluation table, wherein the fields of the safety performance index evaluation table include structural safety factor, lining concrete stress, vertical displacement and safety risk level;

[0109] The original monitoring database construction module 200 is used to construct the original monitoring database, which includes tunnel monitoring data, geological survey reports, and operation record data;

[0110] The original monitoring data processing module 300 is used to pre-process the tunnel monitoring data, geological survey reports, and operation record data in the original monitoring database, and convert the pre-processed tunnel monitoring data, geological survey reports, and operation record data into a target data format;

[0111] The service performance index quantification module 400 is used to quantify the service performance of the subway tunnel structure, obtain the service performance quantification index of the subway tunnel structure, and define the physical damage function according to the physical control equation and boundary conditions of the tunnel lining service process;

[0112] The tunnel structure service performance prediction model building module 500 is used to combine the physical damage function with machine learning to form a fusion physics and machine learning framework, input the specified model parameters into the fusion physics and machine learning framework, and obtain the tunnel structure service performance prediction model;

[0113] The subway tunnel structure service performance evaluation module 600 is used to quantitatively evaluate the subway tunnel structure service performance by using the tunnel monitoring data, geological survey report, and operation record data converted into the target data format through the tunnel structure service performance prediction model;

[0114] The safety risk level determination module 700 is used to determine the safety status of the subway tunnel lining structure and give a corresponding safety risk level based on the subway tunnel structure service performance evaluation result and in combination with the safety performance index evaluation table.

[0115] In this embodiment, in the safety performance index evaluation table construction module 100, the safety risk level includes level one safety risk, level two safety risk and level three safety risk; the safety risk level is determined according to the correlation between the structural safety factor, the lining concrete stress and the vertical displacement;

[0116] In the original monitoring database construction module 200:

[0117] The tunnel monitoring data includes monitoring data of lining structure deformation, cracks, water leakage, groundwater pressure, and surrounding rock pressure;

[0118] The geological survey report includes geological condition information of the area where the subway tunnel is located; the operation record data includes load and environmental change information during the operation of the subway tunnel.

[0119] In this embodiment, in the service performance index quantification module 400:

[0120] The Culmann formula is introduced to determine the confining pressure acting on the tunnel lining structure:

[0121]

[0122] In the formula, represents the surrounding rock pressure, represents the free difference, Represents the rock mass density, represents the depth of overburden;

[0123] In the service performance index quantification module 400, the water pressure of the lining structure of the tunnel affected by the groundwater level is introduced as follows:

[0124]

[0125] In the formula, is the external water pressure acting on the lining; is the water pressure correction coefficient of the initial seepage field; is the correction coefficient of the relative relationship between the permeability of the lining and the surrounding rock; Correction factor to prevent drainage measures from affecting the external water pressure of the lining; is the hydrostatic pressure generated by the groundwater level at the calculation point;

[0126] In the service performance index quantification module 400, the subway tunnel is subject to the Winkle formula during the service process:

[0127]

[0128] In the formula, is the elastic resistance coefficient of surrounding rock; For the surrounding rock The elastic resistance generated at the point; Any point on the tunnel lining surface Compression deformation;

[0129] In the service performance index quantification module 400, the geometric parameters of the lining are affected by the geological conditions and the groundwater level environment. The calculation formula is:

[0130]

[0131] In the formula, is the peak strain produced in the masonry shell, is the elastic modulus of masonry.

[0132] In this embodiment, it also includes:

[0133] The safety dynamic warning module 800 is used to provide dynamic warning of the safety status of the subway tunnel lining structure according to the service performance evaluation results of the subway tunnel structure; and to issue a warning message when the monitoring value or prediction result exceeds the preset warning value;

[0134] The reinforcement measures analysis module 900 is used to conduct field reviews of lining structures with primary safety risks, secondary safety risks or those that have exceeded the limit, and to use numerical simulation and expert judgment methods to analyze the weak areas and causes of the lining structure and propose targeted reinforcement measures.

[0135] It should be noted that the information interaction, execution process and other contents between the above-mentioned device modules are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown above in the present application, and will not be repeated here. Example 3

[0136] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a subway tunnel structure service performance analysis method is stored. The program code includes instructions for executing embodiment 1 or any possible implementation method of a subway tunnel structure service performance analysis method.

[0137] Computer-readable storage media can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can 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)). Example 4

[0138] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0139] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute a subway tunnel structure service performance analysis method of embodiment 1 or any possible implementation thereof.

[0140] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0141] 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 invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0142] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0143] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for analyzing the service performance of a subway tunnel structure, characterized in that: include: Constructing a tunnel structure service safety performance index evaluation table, wherein the fields of the safety performance index evaluation table include structural safety factor, lining concrete stress, vertical displacement and safety risk level; Constructing an original monitoring database, wherein the original monitoring database includes tunnel monitoring data, geological survey reports, and operation record data; Preprocessing the tunnel monitoring data, geological survey report, and operation record data in the original monitoring database, and converting the preprocessed tunnel monitoring data, geological survey report, and operation record data into a target data format; Quantify the service performance of subway tunnel structures, obtain the quantitative indicators of subway tunnel structure service performance, and define the physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process; The physical damage function is combined with machine learning to form a fusion physics and machine learning framework, and specified model parameters are input into the fusion physics and machine learning framework to obtain a tunnel structure service performance prediction model; The tunnel structure service performance prediction model is used to quantitatively evaluate the service performance of the subway tunnel structure by using the tunnel monitoring data, geological survey reports, and operation record data converted into the target data format; According to the service performance evaluation results of the subway tunnel structure, combined with the safety performance index evaluation table, the safety status of the subway tunnel lining structure is determined and the corresponding safety risk level is given; In the process of defining the physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process: The Culmann formula is introduced to determine the confining pressure acting on the tunnel lining structure: In the formula, p represents the surrounding rock pressure, a represents the free difference, γ represents the rock mass density, and H represents the overburden depth; For the water pressure on the tunnel lining structure affected by the groundwater level: P=β1β2β3p` Where, P is the external water pressure acting on the lining; β1 is the water pressure correction coefficient of the initial seepage field; β2 is the correction coefficient of the relative relationship between lining and surrounding rock permeability; β3 is the correction coefficient for the influence of drainage measures on the external water pressure of the lining; p` is the hydrostatic pressure generated by the groundwater level at the calculation point.

2. A subway tunnel structure service performance analysis method according to claim 1, characterized in that: The safety risk levels include primary safety risk, secondary safety risk and tertiary safety risk; the safety risk levels are determined based on the correlation between the structural safety factor, lining concrete stress and vertical displacement.

3. A subway tunnel structure service performance analysis method according to claim 1, characterized in that: The tunnel monitoring data includes monitoring data of lining structure deformation, cracks, water leakage, groundwater pressure, and surrounding rock pressure; The geological survey report includes geological condition information of the area where the subway tunnel is located; the operation record data includes load and environmental change information during the operation of the subway tunnel.

4. A subway tunnel structure service performance analysis method according to claim 3, characterized in that: The subway tunnel follows the Winkle formula during its service life: s i =kδ i Where k is the elastic resistance coefficient of surrounding rock; σ i is the elastic resistance generated by the surrounding rock at point i; i is the compression deformation of any point i on the tunnel lining surface; Under the influence of geological conditions and groundwater level environment, the calculation formula of the lining geometric parameter t is: Where Δσ is the peak strain generated by the shell of the masonry, and σ is the elastic modulus of the masonry.

5. A subway tunnel structure service performance analysis method according to claim 2, characterized in that: Also includes: According to the service performance evaluation results of subway tunnel structures, dynamic early warning of the safety status of subway tunnel lining structures is carried out; Issue warning information when the monitoring value or prediction result exceeds the preset warning value; For lining structures with level one safety risk, level two safety risk or those that have exceeded the limit, field review is carried out, and numerical simulation and expert judgment methods are used to analyze the weak areas of the lining structure and their causes, and specific reinforcement measures are proposed.

6. A subway tunnel structure service performance analysis device, characterized in that: include: A safety performance index evaluation table construction module is used to construct a tunnel structure service safety performance index evaluation table, wherein the fields of the safety performance index evaluation table include structural safety factor, lining concrete stress, vertical displacement and safety risk level; An original monitoring database construction module is used to construct an original monitoring database, wherein the original monitoring database includes tunnel monitoring data, geological survey reports, and operation record data; The original monitoring data processing module is used to pre-process the tunnel monitoring data, geological survey reports, and operation record data in the original monitoring database, and convert the pre-processed tunnel monitoring data, geological survey reports, and operation record data into a target data format; The service performance index quantification module is used to quantify the service performance of the subway tunnel structure, obtain the service performance quantification index of the subway tunnel structure, and define the physical damage function according to the physical control equations and boundary conditions of the tunnel lining service process; A tunnel structure service performance prediction model building module is used to combine the physical damage function with machine learning to form a fusion physics and machine learning framework, input specified model parameters into the fusion physics and machine learning framework, and obtain a tunnel structure service performance prediction model; A subway tunnel structure service performance evaluation module, which is used to quantitatively evaluate the service performance of a subway tunnel structure by using the tunnel monitoring data, geological survey reports, and operation record data converted into a target data format through the tunnel structure service performance prediction model; A safety risk level determination module is used to determine the safety status of the subway tunnel lining structure and give a corresponding safety risk level based on the subway tunnel structure service performance evaluation result and the safety performance index evaluation table; In the service performance index quantification module: The Culmann formula is introduced to determine the confining pressure acting on the tunnel lining structure: In the formula, p represents the surrounding rock pressure, a represents the free difference, γ represents the rock mass density, and H represents the overburden depth; In the service performance index quantification module, the water pressure on the lining structure of the tunnel affected by the groundwater level is introduced as follows: P=β1β2β3p` Where, P is the external water pressure acting on the lining; β1 is the water pressure correction coefficient of the initial seepage field; β2 is the correction coefficient of the relative relationship between lining and surrounding rock permeability; β3 is the correction coefficient for the influence of drainage measures on the external water pressure of the lining; p` is the hydrostatic pressure generated by the groundwater level at the calculation point.

7. A subway tunnel structure service performance analysis device according to claim 6, characterized in that: In the safety performance index evaluation table construction module, the safety risk level includes primary safety risk, secondary safety risk and tertiary safety risk; the safety risk level is determined according to the correlation between the structural safety factor, lining concrete stress and vertical displacement; In the original monitoring database construction module: The tunnel monitoring data includes monitoring data of lining structure deformation, cracks, water leakage, groundwater pressure, and surrounding rock pressure; The geological survey report includes geological condition information of the area where the subway tunnel is located; the operation record data includes load and environmental change information during the operation of the subway tunnel.

8. The subway tunnel structure service performance analysis device according to claim 6, characterized in that: In the service performance index quantification module, the subway tunnel follows the Winkle formula during service: s i =kδ i Where k is the elastic resistance coefficient of surrounding rock; σ i is the elastic resistance generated by the surrounding rock at point i; i is the compression deformation of any point i on the tunnel lining surface; In the service performance index quantification module, under the influence of geological conditions and groundwater level environment, the calculation formula of the lining geometric parameter t is: Where Δσ is the peak strain generated by the shell of the masonry, and σ is the elastic modulus of the masonry.

9. The subway tunnel structure service performance analysis device according to claim 6, characterized in that: Also includes: The safety dynamic early warning module is used to provide dynamic early warning of the safety status of the subway tunnel lining structure based on the service performance evaluation results of the subway tunnel structure; Issue warning information when the monitoring value or prediction result exceeds the preset warning value; The reinforcement measures analysis module is used to conduct field reviews of lining structures with primary safety risks, secondary safety risks or those that have exceeded the limit, and uses numerical simulation and expert judgment methods to analyze the weak areas of the lining structure and their causes, and propose targeted reinforcement measures.

Images