A method and related equipment for predicting the probability of functional failure of shield tunnels based on multiple variables.

Abstract

This application discloses a method and related equipment for predicting the functional failure probability of shield tunnels based on multiple variables. The method includes: constructing an integrated damage-function index system covering multiple scales and quantifying the mapping relationship between damage and function; optimizing the probabilistic seismic demand model using interval estimation methods and selecting the best vibration intensity index by combining fuzzy multi-criteria decision-making; introducing the Copula function to accurately characterize the nonlinear correlation between multidimensional damage / function parameters; and finally establishing a multivariate vulnerability analysis model that can output the failure probability of each function of the tunnel and the overall failure probability of the system. This provides reliable technical support for the seismic design, post-earthquake assessment, and operation and maintenance decisions of shield tunnels. It can accurately assess the seismic risk of shield tunnels under non-uniform liquefaction development, improve the reliability and robustness of the results, and can be widely applied in the field of computer technology.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and related equipment for predicting the probability of functional failure of shield tunnels based on multiple variables. Background Technology

[0002] With the rapid development of urban rail transit construction, shield tunnels, as the core structure of underground transportation, widely traverse liquefiable strata such as soft soil and saturated sand. Under seismic action, liquefiable sites are prone to non-uniform liquefaction development, leading to multi-scale and multi-mode seismic damage in shield tunnels, such as segment joint opening, lining deformation, and excessive internal forces. This can result in problems such as tunnel waterproofing failure, traffic obstruction, and even loss of structural load-bearing capacity, seriously threatening the operational safety of the tunnel.

[0003] Seismic vulnerability analysis is a key technology for assessing the seismic risk of shield tunnels and guiding seismic design and operation and maintenance. Its core lies in establishing a quantitative relationship between seismic motion and structural damage-functional failure to predict the failure probability of tunnels under different seismic intensities. In recent years, scholars have conducted extensive research on the seismic vulnerability analysis of shield tunnels. However, existing research still struggles to accurately characterize the evolution process from physical damage to functional failure under non-uniform liquefaction development, and cannot effectively consider the nonlinear correlations between multidimensional damage parameters. This results in insufficient accuracy and practicality in seismic risk assessment, making it difficult to support actual seismic decision-making in engineering projects.

[0004] The relevant technologies suffer from the following problems: 1. Damage parameters are selected in a single way, failing to form a systematic multi-dimensional damage characterization system. They can only describe one aspect of the tunnel's mechanical properties and cannot comprehensively reflect the multi-scale catastrophic effects of tunnels under non-uniform liquefaction development. 2. The mapping relationship between damage parameters and the core operational functions of the tunnel (waterproof integrity, cross-sectional passability, and structural load-bearing safety) is vague, lacking quantitative correlation rules. They can only assess the probability of structural damage but cannot predict the risk of functional failure, making it difficult to support engineering decisions. 3. Probabilistic seismic demand models mostly use point estimation methods, failing to fully quantify the uncertainty of tunnel seismic response under non-uniform liquefaction development, resulting in insufficient reliability of model results. 4. The selection of seismic ground motion intensity indicators lacks a systematic optimization method and does not quantitatively assess their characterization ability for multiple damage parameters in conjunction with engineering geological conditions. The rationality of indicator selection needs to be verified. 5. Existing multivariate vulnerability analysis does not consider the nonlinear correlation between different damage modes and functional failure modes, simply superimposing the results of a single parameter, which cannot accurately characterize the true damage mechanism of the tunnel system and is prone to causing bias in seismic risk assessment. Summary of the Invention

[0005] The main objective of this application is to propose a method and related equipment for predicting the functional failure probability of shield tunnels based on multiple variables, which can accurately assess the seismic risk of shield tunnels under non-uniform liquefaction development and improve the reliability and robustness of the results.

[0006] To achieve the above objectives, one aspect of this application proposes a method for predicting the probability of functional failure of shield tunnels based on multiple variables, including: A multi-dimensional damage parameter system is constructed; wherein, the multi-dimensional damage parameters include local deformation, overall deformation, internal force response and distribution characteristics; By fusing the acquired multi-source data, the hierarchical thresholds for each function to be in different states are determined, and then a vectorized function degradation index is constructed. Obtain the nonlinear dynamic analysis results of liquefaction non-uniform working conditions and construct a multi-input and multi-output mapping model; Based on the multidimensional damage parameter system and candidate ground motion intensity indices, a multivariate probabilistic earthquake demand model based on interval estimation is constructed. The ability of the candidate ground motion intensity indices to characterize the multidimensional damage parameters is quantitatively evaluated, a ground motion performance evaluation matrix is ​​constructed, and then the optimal ground motion intensity index is determined. Based on the optimal seismic intensity index and the multivariate probabilistic earthquake demand model, a joint probabilistic earthquake demand model is constructed. Based on the grading threshold and the joint probabilistic earthquake demand model, the functional failure probability and the overall system failure probability under different ground motion intensities are calculated, and the functional failure prediction results for shield tunnels are generated.

[0007] In some embodiments, constructing a multi-dimensional damage parameter system includes: Local deformation parameters are constructed, including circumferential joint opening and circumferential misalignment. The circumferential joint opening is used to characterize the degree of separation of the contact surfaces between segments, determine the working state and failure risk of the waterproof sealing system, and identify the damage mode of joint water-stopping failure and leakage path formation. The circumferential misalignment is used to characterize the tangential relative slippage or rotation between adjacent segments within the cross-section, reflect the joint shear deformation and bending moment transmission capacity, and identify the damage mode of joint shear failure, bolt shearing, and local stress concentration. An overall deformation parameter is constructed, which includes the rate of change of the horizontal diameter of the cross-section, the rate of change of the vertical diameter of the cross-section, and the centroid offset of the cross-section. The rate of change of the horizontal diameter characterizes the relative change in the horizontal diameter, reflecting the compression or expansion of the cross-section caused by lateral earth pressure or lateral liquefaction deformation, and identifying damage modes such as cross-section ellipticization, lining ring lateral convergence or expansion. The rate of change of the vertical diameter characterizes the relative change in the vertical diameter of the cross-section, reflecting the cross-section deformation caused by uneven vertical loads, base liquefaction uplift or settlement, and identifying damage modes such as cross-section ellipticization, base softening or uplift. The centroid offset characterizes the translation of the cross-section centroid relative to the initial centroid, reflecting the asymmetry of the resultant force acting on the cross-section, and identifying damage modes such as overall cross-section translation, biased stress, and severely uneven load distribution. Internal force response parameters are constructed, including segment section bending moment, segment section axial force, and moment-curvature deviation index. The segment section bending moment characterizes the translation of the centroid relative to the initial centroid, reflecting the asymmetry of the resultant force acting on the segment and identifying damage modes such as segment cracking, concrete crushing, and steel yielding. The segment section axial force characterizes the axial force at various locations on the segment section, reflecting the compressive or tensile state of the section and identifying damage modes such as crushing instability and tensile cracking. The moment-curvature deviation index characterizes the degree of deviation between the actual moment-curvature response and the elastic theoretical value, quantifying the degree to which the section enters plasticity and identifying damage modes such as the development of plastic hinges and stiffness degradation. A distribution characteristic parameter is constructed, which includes the cross-sectional internal force / deformation variation coefficient and the most unfavorable position angle. The cross-sectional internal force / deformation variation coefficient is used to characterize the ratio of the standard deviation to the mean of a parameter at different locations within the same cross-section, quantify the non-uniformity of the response within the cross-section, and identify and reveal the circumferential concentrated distribution of load or damage, reflecting the damage mode of non-uniform load action. The most unfavorable position angle is used to characterize the azimuth angle at which the key responses of maximum bending moment and maximum opening occur in the circumferential direction of the cross-section, and to establish a direct spatial correlation between "non-uniform liquefaction development - the most unfavorable response location of the structure".

[0008] In some embodiments, the step of calibrating the hierarchical thresholds of each function in different states through the fusion of acquired multi-source data, and then constructing a vectorized function degradation index, includes: With waterproof integrity, cross-sectional passability, and structural load-bearing safety as the core functional dimensions, and system risk distribution as the correction dimension, a vectorized functional degradation index is defined, and the grading thresholds of each function from intact to completely failed are calibrated through multi-source data fusion. Among them, the waterproof integrity is used to characterize the joint opening amount as the core related parameter. By integrating standard specification limits, waterproof performance test data, and shield tunnel leakage statistics, the safety limit of joint opening amount, bolt yield threshold, maximum allowable opening amount, and the degree of degradation of waterproof function are calibrated. The cross-sectional accessibility is used to characterize the ratio of available net space area as a quantitative indicator, through non-uniform rational... B Spline curves are used to reconstruct the profile of the tunnel section after the earthquake. The profile of the tunnel section after the earthquake is discretized into a point set and compared with the standard building clearance. The encroachment area is calculated, and then the classification threshold of the passability is determined. The structural load-bearing safety is used to characterize the threshold of different safety states, with the load-bearing capacity safety factor as a quantitative indicator. The system risk distribution is used as a correction dimension to characterize the indicators of the core functional dimension by using the cross-sectional internal force / deformation variation coefficient and the most unfavorable position angle, thereby reflecting the impact of the uniformity of damage distribution on system risk.

[0009] In some embodiments, obtaining the nonlinear dynamic analysis results of liquefaction non-uniform conditions and constructing a multi-input and multi-output mapping model includes: Using a physical constraint neural network as the core architecture, embedding prior physical knowledge as training constraints, a mapping model between multiple inputs and multiple outputs is trained. SHAP value analysis reveals the weight of key damage parameters on the failure of specific functions; The uncertainty of the mapping relationship in the mapping model is quantified using a Bayesian framework to obtain a set of damage-function association rules with probabilistic output capability.

[0010] In some embodiments, constructing a multivariate probabilistic earthquake demand model based on interval estimation according to the multidimensional damage parameter system and candidate ground motion intensity indices includes: Based on the multi-dimensional damage parameter system and candidate ground motion intensity indices, a nonlinear dynamic analysis of the liquefaction non-uniform working condition is performed. An interval estimation method was used to fit the statistical relationship between the ground motion intensity index and various damage parameters, and the confidence range of the model regression parameters was quantified. A multivariate probabilistic earthquake demand model based on interval estimation is constructed to achieve interval prediction of damage parameters.

[0011] In some embodiments, constructing a joint probabilistic earthquake demand model based on the optimal seismic intensity index and the multivariate probabilistic earthquake demand model includes: A multidimensional joint probability model is constructed by introducing a Copula function to connect the marginal distribution of damage / functional parameters; Based on the optimal ground motion intensity index, the marginal conditional probability distribution of each damage parameter under different ground motion intensity index levels is obtained through a probabilistic earthquake demand model based on interval estimation. Calculate the Kendall rank correlation coefficients among the various functional degradation indicators to quantify the nonlinear correlation of each functional degradation indicator; A family of Copula functions suitable for multidimensional analysis was selected to fit the three-dimensional functional degradation index; The parameters of each Copula function are estimated using the maximum likelihood estimation method, and the goodness of fit is evaluated using the Akaike information criterion. By using the optimal Copula function, the marginal distributions of each functional degradation index are coupled into a three-dimensional joint probabilistic seismic demand model.

[0012] In some embodiments, the step of calculating the functional failure probability and the overall system failure probability under different seismic motion intensities based on the grading threshold and the joint probabilistic seismic demand model, and generating functional failure prediction results for the shield tunnel, includes: Based on the aforementioned classification threshold, the failure domain corresponding to each functional failure event is determined; Given a seismic intensity index, a large number of samples were taken from the joint probability distribution through Copula-based Monte Carlo simulation. The proportion of samples falling into each failure domain was statistically analyzed to obtain the conditional probability threshold of each functional failure. The overall failure probability of the system is calculated using probability formulas, resulting in the vulnerability curves for each functional failure and the overall system failure.

[0013] Another aspect of this application provides a device for predicting the probability of functional failure of a shield tunnel based on multiple variables, including: The first module is used to construct a multi-dimensional damage parameter system; wherein, the multi-dimensional damage parameters include local deformation, overall deformation, internal force response and distribution characteristics; The second module is used to calibrate the hierarchical thresholds of each function in different states by fusing the acquired multi-source data, and then construct a vectorized function degradation index. The third module is used to obtain the nonlinear dynamic analysis results of liquefaction non-uniform working conditions and to construct a multi-input and multi-output mapping model. The fourth module is used to construct a multivariate probabilistic earthquake demand model based on interval estimation, according to the multidimensional damage parameter system and candidate ground motion intensity indices. The fifth module is used to quantitatively evaluate the characterization ability of the multi-dimensional damage parameters based on the candidate ground motion intensity indices, construct a ground motion performance evaluation matrix, and then determine the optimal ground motion intensity index. The sixth module is used to construct a joint probabilistic earthquake demand model based on the optimal ground motion intensity index and the multivariate probabilistic earthquake demand model. The seventh module is used to calculate the functional failure probability and the overall system failure probability under different ground motion intensities based on the classification threshold and the joint probabilistic earthquake demand model, and generate functional failure prediction results for shield tunnels.

[0014] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0015] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0016] This application also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0017] The embodiments of this application include at least the following beneficial effects: This application provides a method and related equipment for predicting the probability of functional failure of shield tunnels based on multiple variables. This scheme constructs an integrated damage-function index system covering multiple scales, quantifies the mapping relationship between damage and function, optimizes the probabilistic seismic demand model using interval estimation method, and selects the best vibration intensity index by combining fuzzy multi-criteria decision-making, introduces the Copula function to accurately characterize the nonlinear correlation between multidimensional damage / function parameters, and finally establishes a multivariate vulnerability analysis model that can output the failure probability of each function of the tunnel and the overall failure probability of the system. This provides reliable technical support for the seismic design, post-earthquake assessment and operation and maintenance decision-making of shield tunnels, and can accurately assess the seismic risk of shield tunnels under non-uniform liquefaction development, improving the reliability and robustness of the results. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application; Figure 2 This is a flowchart of the overall steps provided in the embodiments of this application; Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0020] It is understood that the terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0023] Before providing a detailed description of the embodiments of this application, some related technologies involved in the embodiments of this application will be described first, as follows: Seismic vulnerability analysis: an analytical method used to predict the probability of different degrees of damage to structures under different earthquake intensities, and a core means of assessing the seismic risk of structures.

[0024] Damage parameters (DP): These are performance indicators that condense the complex seismic dynamic response into quantifiable values ​​that are directly related to structural damage. They are key parameters for characterizing the degree of seismic damage to structures.

[0025] Intensity index (IM): A physical parameter used to describe the intensity of earthquake motion. It is a core variable input in seismic vulnerability analysis and is used to correlate seismic action with structural response.

[0026] Functional Degradation Index (FDI): A quantitative indicator that characterizes the degree of degradation of tunnel operational functions (waterproof integrity, cross-sectional passability, structural load-bearing safety, etc.), and establishes a correlation between physical damage and functional status.

[0027] Probabilistic Seismic Demand Model (PSDM): A model that describes the statistical relationship between seismic motion intensity indices and structural damage parameters, and is the basic model for seismic vulnerability analysis.

[0028] Copula function: A function that can connect the marginal distributions of multiple random variables into a joint distribution, which can accurately characterize the nonlinear correlation between variables.

[0029] Non-uniform development of liquefaction: Under seismic action, the soil in different areas of a liquefiable site exhibits non-uniform distribution characteristics in terms of the time of liquefaction, degree of liquefaction, and liquefaction range.

[0030] Physically constrained neural networks: Neural network models that embed prior physical knowledge as training constraints, combining data-driven prediction capabilities with the interpretability of physical laws.

[0031] Bayesian update method: A statistical method that corrects the prior probability distribution based on new observation data to obtain the posterior probability distribution, which can effectively integrate multi-source data and quantify uncertainty.

[0032] Non-uniform rational B-spline curve: a parametric curve used to accurately describe complex geometric contours, enabling high-precision reconstruction of the cross-sectional contour of deformed tunnels.

[0033] Existing seismic vulnerability analysis of shield tunnels mainly revolves around the construction of probabilistic seismic demand models for single damage parameters, with the core technical solution being: (1) Select a single damage parameter to characterize tunnel damage, such as diameter deformation rate and section bending moment ratio for circular tunnels, and joint opening amount and lining strain ratio for segmented tunnels.

[0034] (2) Select a single ground motion intensity index (such as peak ground acceleration PGA) as input, and establish the statistical relationship between ground motion intensity and single damage parameter through nonlinear dynamic analysis, i.e., probabilistic earthquake demand model.

[0035] (3) Combine the structural seismic resistance threshold to calculate the damage probability of the tunnel under different earthquake intensities and obtain the vulnerability curve.

[0036] (4) Although some studies have attempted to introduce multiple damage indicators to conduct preliminary multivariate vulnerability analysis, they simply superimpose the analysis results of each single parameter without systematically considering the nonlinear correlation between different damage modes (joint opening, lining bending moment, diameter convergence, etc.) or establishing a clear and quantitative mapping relationship between damage parameters and the core operational functions of the tunnel. This makes it impossible to realize the transformation from "damage probability" to "functional failure probability" and is difficult to meet the refined requirements of engineering practice for tunnel seismic risk assessment.

[0037] The aforementioned technologies have the following drawbacks: 1. The damage parameters are selected in a single way, and a systematic multi-dimensional damage characterization system has not been formed. It can only describe the mechanical properties of the tunnel in a certain aspect and cannot fully reflect the multi-scale catastrophic effects of the tunnel under the non-uniform development of liquefaction.

[0038] 2. The mapping relationship between damage parameters and the core operational functions of the tunnel (waterproof integrity, cross-sectional passability, and structural load-bearing safety) is vague and lacks quantitative correlation rules. It can only assess the probability of structural damage, cannot predict the risk of functional failure, and is difficult to support engineering decisions.

[0039] 3. Probabilistic earthquake demand models often use point estimation methods, which do not fully quantify the uncertainty of tunnel seismic response under non-uniform liquefaction development, resulting in insufficient reliability of model results.

[0040] 4. There is a lack of systematic optimization methods for the selection of seismic intensity indicators. The ability of these indicators to characterize multiple damage parameters has not been quantitatively assessed in conjunction with engineering geological conditions (such as complex geology). The rationality of the selected indicators needs to be verified.

[0041] 5. Existing multivariate vulnerability analysis does not consider the nonlinear correlation between different damage modes and functional failure modes. It simply superimposes the results of a single parameter, which cannot accurately depict the real failure mechanism of the tunnel system and is prone to causing deviations in earthquake risk assessment.

[0042] In view of this, this application provides a method for predicting the probability of functional failure of shield tunnels based on multivariate analysis. This method accurately assesses the seismic risk of shield tunnels under non-uniform liquefaction development, realizing the probability prediction from "physical damage" to "functional failure". This application proposes a multivariate "damage-function" probability prediction method for shield tunnels considering non-uniform liquefaction development. This method constructs an integrated damage-function index system covering multiple scales, quantifying the mapping relationship between damage and function; it optimizes the probabilistic seismic demand model using interval estimation methods, and combines fuzzy multi-criteria decision-making to select the best vibration intensity index; it introduces the Copula function to accurately characterize the nonlinear correlation between multidimensional damage / function parameters, and finally establishes a multivariate vulnerability analysis model that can output the failure probability of each function of the tunnel and the overall failure probability of the system, providing reliable technical support for the seismic design, post-earthquake assessment, and operation and maintenance decisions of shield tunnels.

[0043] The method and related equipment for predicting the probability of functional failure of shield tunnels based on multiple variables provided in this application relate to the fields of computer technology, earthquake prediction technology, and building loss assessment. The method for predicting the probability of functional failure of shield tunnels based on multiple variables provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the method for predicting the probability of functional failure of shield tunnels based on multiple variables, but is not limited to the above forms.

[0044] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0045] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0046] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided in an embodiment of this application. (Refer to...) Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0047] Server 101 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0048] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0049] Terminal 102 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc. It can also be a vehicle-mounted terminal of the various device types described above, but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment does not impose any limitations.

[0050] Exemplary based on Figure 1 The implementation environment shown in this application embodiment provides a method for predicting the probability of functional failure based on multiple variables of a shield tunnel. The following description uses the application of this method for predicting the probability of functional failure based on multiple variables of a shield tunnel in server 101 as an example. It can be understood that this method can also be applied to terminal 102.

[0051] Reference Figure 2 , Figure 2 The flowchart illustrates a method for predicting the probability of functional failure of a shield tunnel based on multiple variables, applied to a server, as provided in this application embodiment. The execution subject of this method can be any of the aforementioned computer devices (including a server or a terminal). (Refer to...) Figure 2 The method may include the following steps: S210. Construct a multi-dimensional damage parameter system; wherein, the multi-dimensional damage parameters include local deformation, overall deformation, internal force response and distribution characteristics; S220. By fusing the acquired multi-source data, the hierarchical thresholds for each function in different states are determined, and then a vectorized function degradation index is constructed. S230. Obtain the nonlinear dynamic analysis results of the liquefaction non-uniform working condition and construct a multi-input and multi-output mapping model; S240. Based on the multidimensional damage parameter system and candidate ground motion intensity indices, construct a multivariate probabilistic earthquake demand model based on interval estimation. S250. Quantitatively evaluate the characterization ability of the multi-dimensional damage parameters based on the candidate ground motion intensity indices, construct a ground motion performance evaluation matrix, and then determine the optimal ground motion intensity index. S260. Based on the optimal ground motion intensity index and the multivariate probabilistic earthquake demand model, construct a joint probabilistic earthquake demand model; S270. Based on the grading threshold and the joint probabilistic earthquake demand model, calculate the functional failure probability and the overall system failure probability under different ground motion intensities, and generate functional failure prediction results for shield tunnels.

[0052] The following describes the specific implementation process of the above steps in detail, using a specific application scenario as an example: For S210, a multi-dimensional damage parameter system is constructed; wherein, the multi-dimensional damage parameters include local deformation, overall deformation, internal force response and distribution characteristics, specifically: This application's embodiments are based on the typical disaster mode of shield tunnels under non-uniform liquefaction development, and construct a four-dimensional damage parameter covering local deformation, overall deformation, internal force response, and distribution characteristics. DP This system enables the systematic quantification of multi-scale catastrophic effects on tunnels. (1) Local deformation parameters Circumferential joint opening δ (mm): Reflects the degree of separation between the contact surfaces of the segments, determines the working status and failure risk of the waterproof sealing system; can identify the damage mode of joint water-stopping failure and leakage path formation.

[0053] Circumferential misalignment (mm): Characterizes the tangential relative slippage or rotation between adjacent segments within the cross section, reflecting the joint shear deformation and bending moment transmission capacity; it can identify damage modes such as joint shear failure, bolt shearing, and local stress concentration.

[0054] (2) Overall deformation parameters Rate of change of horizontal diameter of cross section ΔD h / D 0 (%): The relative change in the horizontal diameter of the cross section reflects the compression or expansion of the cross section caused by lateral earth pressure or lateral liquefaction deformation; it can identify damage modes such as cross section ellipticization (horizontal compression), lateral convergence or expansion of the lining ring.

[0055] Rate of change of vertical diameter of cross section ΔD v / D 0 (%): The relative change in the vertical diameter of the cross section reflects the cross section deformation caused by uneven vertical load, liquefaction and uplift of the base or settlement; it can identify damage modes such as cross section ellipticization (vertical tension), base softening or uplift.

[0056] Cross-sectional centroid offset ( ΔX , ΔZ ()( mm The translation of the centroid of the cross section relative to the initial centroid directly reflects the asymmetry of the resultant force acting on the cross section; it can identify damage modes such as overall translation of the cross section, biased stress, and severely uneven load distribution.

[0057] (3) Internal force response parameters Segment section bending moment M ( kN mThe translation of the centroid of the cross section relative to the initial centroid directly reflects the asymmetry of the resultant force acting on the cross section; it can identify damage modes such as segment cracking, concrete crushing, and steel bar yielding.

[0058] Axial force of segment section N ( kN ): The axial force at each position of the segment section reflects the state of the section under compression or tension; it can identify the damage mode of section crushing instability and tensile cracking.

[0059] Moment-curvature deviation index: Characterizes the degree of deviation between the actual moment-curvature response of the cross section and the elastic theoretical value, quantifies the degree to which the cross section enters plasticity; can identify the damage mode of cross section plastic hinge development and stiffness degradation.

[0060] (4) Distribution characteristic parameters Cross-sectional internal force / deformation variation coefficient CV Within the same cross-section, the ratio of the standard deviation to the mean of a parameter at different locations quantifies the non-uniformity of the response within the cross-section; it can identify and reveal the circumferential concentrated distribution of load or damage, reflecting the damage mode of non-uniform load action.

[0061] Most unfavorable position angle θ (°): The azimuth angle at which key responses such as maximum bending moment and maximum opening occur in the circumferential direction of the cross section; a direct spatial correlation can be established between "uniform development of liquefaction - the most unfavorable response location of the structure".

[0062] Based on the nonlinear dynamic analysis results of liquefaction nonuniform conditions, and combined with principal component analysis, the sensitivity of each parameter to the nonuniform development of liquefaction is quantified, and its statistical characteristics and confidence intervals are determined, forming a multivariate damage parameter system that comprehensively characterizes the nonlinear dynamic response of the structure.

[0063] For S220 above, the hierarchical thresholds for each function's different states are determined by fusing the acquired multi-source data, thereby constructing a vectorized function degradation index; specifically: With waterproof integrity, cross-sectional passability, and structural load-bearing safety as the core functional dimensions, and system risk distribution as the correction dimension, a vectorized functional degradation index is defined. FDI ) F =[ F leakage , F passage , F safety ] T Furthermore, by fusing multi-source data, the threshold values ​​for each function, ranging from "intact" to "completely failed," were determined. Waterproof integrity ( F leakage): Taking the joint opening amount as the core related parameter, integrating relevant engineering design standards and other specification limits, waterproof performance test data, and shield tunnel leakage statistics, to calibrate the safety limit of the joint opening amount, bolt yield threshold, and maximum allowable opening amount, and quantify the degree of degradation of waterproof function; Cross-sectional accessibility ( F passage ): Based on the ratio of available net open area ( R clearance ) is a quantitative indicator: , A limit Represents the standard building clearance area; A encroach Represents the encroachment area; the embodiments of this application utilize non-uniform rational... B The spline curves reconstruct the profile of the tunnel cross section after the earthquake, discretize it into a point set and compare it with the standard building clearance to calculate the encroachment area; according to relevant subway design standards and other specifications, the grading threshold of passability is calibrated.

[0064] Structural load-bearing safety F safety ): Based on the bearing capacity safety factor (seismic bending moment required for tunnel segment cross-section) M With remaining flexural capacity M u,residual The ratio of ( ) is used as a quantitative indicator, and thresholds for different safety states such as steel bar yielding and loss of cross-sectional bearing capacity are determined with reference to relevant research results.

[0065] System risk distribution correction: using the coefficient of variation of cross-sectional internal forces / deformation. CV and the most unfavorable position angle θ The above three-dimensional functional indicators are modified to reflect the impact of the uniformity of damage distribution on system risk (concentrated damage leads to a sharp increase in risk, while uniform damage results in high system redundancy).

[0066] By employing a Bayesian update method, integrating physical model test data, standard limits, historical earthquake damage cases, and expert questionnaire results, the threshold values ​​of each function are expressed in the form of a probability distribution, objectively reflecting cognitive uncertainty.

[0067] For the above S230, obtain the nonlinear dynamic analysis results of the liquefaction non-uniform working condition, and construct a multi-input and multi-output mapping model; specifically: This application's embodiments construct a "multi-input (DP vector) - multi-output (FDI vector)" mapping database based on the results of nonlinear dynamic analysis of a large number of liquefaction non-uniform working conditions. Using a physically constrained neural network as the core architecture, prior physical knowledge (such as the monotonically increasing relationship between joint opening and leakage risk, and the mechanical relationship between bending moment and curvature) is embedded as training constraints to train the mapping model between DP and FDI. The influence weights of key damage parameters on specific functional failures are revealed through SHAP value analysis, enhancing the model's interpretability. A Bayesian framework is employed to quantify the uncertainty of the mapping relationship, forming a damage-function association rule set with probabilistic output capabilities, enabling automated functional state diagnosis of seismic motion-structural response samples.

[0068] It should be noted that the SHAP value stands for SHapley Additive exPlanations, which is a model interpretability metric used to quantify the contribution weight of each damage parameter to the tunnel functional failure outcome.

[0069] In this embodiment, the model input is multidimensional damage parameters DP (joint opening, bending moment, diameter deformation, etc.), and the output is the functional degradation index FDI (waterproofing, passage, and load-bearing failure). The SHAP value can be used to calculate the weight of joint opening on waterproofing failure; the weight of cross-sectional deformation on passage failure; and the weight of cross-sectional bending moment on load-bearing failure. The aim is to give the model results physical meaning, proving that the predictions of this scheme are not purely data fitting, but conform to the laws of tunnel mechanics, supporting the practicality and interpretability of the patent.

[0070] Simply put, the SHAP value is to "score" each damage parameter to see which has a greater impact on tunnel function failure, making the black box model transparent.

[0071] In some embodiments, a Support Vector Machine (SVM) can be used instead of a physically constrained neural network to construct a DP-FDI mapping model, which can realize the correlation analysis between damage and function under small sample datasets and is suitable for scenarios with a small number of liquefied chemical condition samples.

[0072] In some embodiments, the response surface methodology can be used to replace nonlinear dynamic analysis, quickly establishing the statistical relationship between seismic intensity and damage parameters, which can significantly reduce the computational load and is suitable for rapid seismic risk assessment in the preliminary design stage of engineering projects.

[0073] For S240 above, based on the multi-dimensional damage parameter system and candidate ground motion intensity indices, a multivariate probabilistic earthquake demand model based on interval estimation is constructed; specifically: To address the significant uncertainty in tunnel seismic response under non-uniform liquefaction development, the conventional point estimation method is extended to an interval estimation method: Using the multidimensional damage parameters constructed in step S210 as output and candidate ground motion intensity indices as input, nonlinear dynamic analyses are conducted on numerous liquefaction-inhomogeneous conditions. An interval estimation method is used to fit the statistical relationship between the ground motion intensity indices and each damage parameter, quantifying the confidence range of the model's regression parameters. A multivariate probabilistic seismic demand model based on interval estimation is constructed to achieve interval prediction of damage parameters, fully considering the uncertainty of seismic response.

[0074] For S250 above, the ability of the candidate seismic intensity indices to characterize the multi-dimensional damage parameters is quantitatively evaluated, a seismic performance evaluation matrix is ​​constructed, and then the optimal seismic intensity index is determined; specifically: Based on five criteria—effectiveness, practicality, applicability, sufficiency, and calculable risk—and combining fuzzy hierarchical analysis (FAHP) and the best-in-best solution distance method (TOPSIS), the optimal IM is selected. The ability of each candidate IM (such as PGA, PGV, Sa(T1)) to characterize the multi-dimensional damage parameters in step S210 is quantitatively evaluated, and an IM performance evaluation matrix is ​​constructed. The weights of the five evaluation criteria are determined using fuzzy hierarchical analysis, considering the fuzziness and subjectivity between criteria. The superior-inferior solution distance method is used to rank each candidate IM using multiple indicators, integrating their comprehensive performance on all damage parameters. The seismic intensity index with the best comprehensive ranking is selected as the core input for subsequent multivariate probabilistic prediction.

[0075] In some embodiments, the entropy weight method is used instead of the fuzzy hierarchical analysis method to determine the criterion weights for the selection of seismic intensity indicators. This can reduce the influence of subjective factors and is suitable for scenarios where the criterion weights are difficult to determine through expert scoring.

[0076] For S260 above, based on the optimal ground motion intensity index and the multivariate probabilistic earthquake demand model, a joint probabilistic earthquake demand model is constructed; specifically: Based on Sklar's theorem, a multidimensional joint probability model is constructed by introducing a Copula function to connect the marginal distributions of the damage / functional parameters: ,in, C [ ]represent Copula function; ξ Characterization n Copula parameters for the correlation between dimensional random variables; x n A random variable representing the damage / functional index of the nth shield tunnel; H(x1,x2,...,x n Let F(x1), F(x2), ..., F(x3) represent the cumulative distribution function of an n-dimensional random variable. n ) represents the probability distribution function of each marginal point.

[0077] The optimal selection in step S250 IM Using this as input, a probabilistic earthquake demand model based on interval estimation is used to obtain various damage parameters at different... IM Marginal conditional probability distribution at the horizontal level.

[0078] Kendall rank correlation coefficients were calculated among the various functional degradation indices to quantify their nonlinear correlations. A family of Copula functions suitable for multidimensional analysis (Gaussian Copula, t-Copula, nested Archimedesian Copula, VineCopula) was selected to fit the three-dimensional functional degradation indices.

[0079] The parameters of each Copula function are estimated using the maximum likelihood estimation method, and the goodness of fit is evaluated by the Akaike Information Criterion (AIC) (the model with the smallest AIC value is the optimal model).

[0080]

[0081] in, K The number of parameters representing the Copula function depends on the type of Copula function used and the dimension of the distribution. D represents the damage parameter; N represents the total number of all valid analysis samples used for Copula function fitting; F... n (x n ,i) represents the marginal probability distribution function value corresponding to the i-th sample point in the n-th dimension of the multidimensional random variable.

[0082] By using the optimal Copula function, the marginal distributions of each functional degradation index are coupled into a three-dimensional joint probabilistic seismic demand model, which accurately characterizes the nonlinear dependency structure between parameters.

[0083] For S270 above, based on the grading threshold and the joint probabilistic earthquake demand model, the functional failure probability and the overall system failure probability under different seismic motion intensities are calculated to generate functional failure prediction results for the shield tunnel; specifically: The failure of a tunnel system is defined as the loss of any core function (waterproofing, passage, load-bearing). The probability of functional failure and the overall system failure are calculated under different seismic intensities. Based on the functional classification threshold calibrated in step S220, the failure domain Ωk (the region in the damage parameter space that satisfies functional failure) corresponding to each functional failure event Ek is determined. Under a given seismic intensity IM=im, a large number of samples are taken from the joint probability distribution using Copula-based Monte Carlo simulation. The proportion of samples falling into each failure domain is statistically analyzed to obtain the conditional probability threshold for each functional failure. The overall system failure is defined as "waterproofing failure ∪ passage failure ∪ load-bearing failure," and the overall system failure probability is calculated using a probability formula. The above calculation is repeated for a series of different IM values ​​to obtain the vulnerability curves for each functional failure and the overall system failure, achieving a comprehensive prediction of the multivariate "damage-function" probability of shield tunnels under non-uniform liquefaction development.

[0084] In some embodiments, Markov Chain Monte Carlo (MCMC) can be used instead of conventional Monte Carlo simulation to sample the joint probability distribution and calculate the failure probability, which can improve the calculation efficiency and accuracy of low-probability failure events.

[0085] In summary, compared with existing methods for analyzing the seismic vulnerability of shield tunnels, this application achieves several technological breakthroughs, with key technical features including: (1) A four-dimensional damage parameter system covering local deformation, overall deformation, internal force response and distribution characteristics was constructed, as well as a functional degradation index system with waterproof integrity, cross-sectional passability and structural bearing safety as the core, realizing the systematic characterization of multi-scale damage and core functions of shield tunnels.

[0086] (2) A data-physical fusion DP-FDI mapping method was proposed, which combines physical constraint neural network with Bayesian update, embeds prior physical knowledge and quantifies uncertainty, and establishes quantitative correlation rules between damage parameters and functional degradation indicators.

[0087] (3) The interval estimation method was introduced into the construction of the probabilistic earthquake demand model, which quantified the uncertainty of tunnel seismic response under non-uniform liquefaction development and improved the reliability of the model.

[0088] (4) A method for optimizing seismic intensity index based on fuzzy hierarchical analysis and superior-inferior solution distance method is proposed, which realizes the comprehensive ranking and screening of IM under multiple damage parameters and is applicable to complex geological conditions in Guangdong.

[0089] (5) The Copula function was introduced to accurately characterize the nonlinear correlation between multidimensional functional degradation indicators, and a multivariate joint probabilistic earthquake demand model was constructed, which broke through the limitations of traditional single-parameter vulnerability analysis.

[0090] (6) A vulnerability calculation method for tunnel systems considering the failure of any function was established. The failure probability of each function and the overall failure probability of the system were quantitatively predicted through Monte Carlo simulation, realizing the transformation from "damage probability" to "functional failure probability".

[0091] Compared with existing technologies, this application has the following advantages: (1) The multi-dimensional damage-function integrated index system is constructed, which fully covers the multi-scale catastrophic effects of tunnels under non-uniform liquefaction development, establishes a quantitative mapping relationship between physical damage and operational functions, and upgrades the traditional "damage probability assessment" to "functional failure probability prediction", which is more in line with the actual seismic decision-making needs of engineering.

[0092] (2) The probabilistic earthquake demand model based on interval estimation fully quantifies the uncertainty of earthquake response caused by non-uniform development of liquefaction. Compared with the traditional point estimation model, the reliability and robustness of the results are significantly improved.

[0093] (3) The proposed method for optimizing seismic intensity index takes into account the characterization requirements of multiple damage parameters and engineering criteria. The optimal IM selected is more suitable for seismic analysis of shield tunnels under complex geological conditions, avoiding the one-sidedness of selecting a single IM.

[0094] (4) The Copula function is used to accurately characterize the nonlinear correlation between multidimensional functional failure modes, which breaks through the shortcomings of traditional multivariate analysis that simply superimposes the results of a single parameter. It can truly reflect the overall failure mechanism of the tunnel system under non-uniform liquefaction development and greatly reduce the bias of earthquake risk assessment.

[0095] (5) The whole method integrates multiple sources of knowledge such as numerical simulation, machine learning, statistical analysis, and standard specifications. It has both data-driven prediction capabilities and the interpretability of physical laws. Moreover, each step is modular and expandable, and it can be applied to the seismic vulnerability analysis of shield tunnels under different geological conditions and of different types, and has wide engineering applicability.

[0096] Another aspect of this application provides a device for predicting the probability of functional failure of a shield tunnel based on multiple variables, including: The first module is used to construct a multi-dimensional damage parameter system; wherein, the multi-dimensional damage parameters include local deformation, overall deformation, internal force response and distribution characteristics; The second module is used to calibrate the hierarchical thresholds of each function in different states by fusing the acquired multi-source data, and then construct a vectorized function degradation index. The third module is used to obtain the nonlinear dynamic analysis results of liquefaction non-uniform working conditions and to construct a multi-input and multi-output mapping model. The fourth module is used to construct a multivariate probabilistic earthquake demand model based on interval estimation, according to the multidimensional damage parameter system and candidate ground motion intensity indices. The fifth module is used to quantitatively evaluate the characterization ability of the multi-dimensional damage parameters based on the candidate ground motion intensity indices, construct a ground motion performance evaluation matrix, and then determine the optimal ground motion intensity index. The sixth module is used to construct a joint probabilistic earthquake demand model based on the optimal ground motion intensity index and the multivariate probabilistic earthquake demand model. The seventh module is used to calculate the functional failure probability and the overall system failure probability under different ground motion intensities based on the classification threshold and the joint probabilistic earthquake demand model, and generate functional failure prediction results for shield tunnels.

[0097] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0098] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for predicting the probability of functional failure based on multiple variables in a shield tunnel. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0099] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0100] Please see Figure 3 , Figure 3 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 201 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 202 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 202 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 202 and is called and executed by the processor 201 using the method for predicting the functional failure probability of shield tunnels based on multiple variables, as described in this application embodiment. Input / output interface 203 is used to implement information input and output; The communication interface 204 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 205 transmits information between various components of the device (e.g., processor 201, memory 202, input / output interface 203, and communication interface 204); The processor 201, memory 202, input / output interface 203 and communication interface 204 are connected to each other within the device via bus 205.

[0101] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for predicting the probability of functional failure based on multiple variables in a shield tunnel.

[0102] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0103] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0104] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0105] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0106] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0107] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0109] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0110] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for predicting the probability of functional failure of shield tunnels based on multiple variables, characterized in that, include: A multi-dimensional damage parameter system is constructed; wherein, the multi-dimensional damage parameters include local deformation, overall deformation, internal force response and distribution characteristics; By fusing the acquired multi-source data, the hierarchical thresholds for each function to be in different states are determined, and then a vectorized function degradation index is constructed. Obtain the nonlinear dynamic analysis results of liquefaction non-uniform working conditions and construct a multi-input and multi-output mapping model; Based on the multidimensional damage parameter system and candidate ground motion intensity indices, a multivariate probabilistic earthquake demand model based on interval estimation is constructed. The ability of the candidate ground motion intensity indices to characterize the multidimensional damage parameters is quantitatively evaluated, a ground motion performance evaluation matrix is ​​constructed, and then the optimal ground motion intensity index is determined. Based on the optimal seismic intensity index and the multivariate probabilistic earthquake demand model, a joint probabilistic earthquake demand model is constructed. Based on the grading threshold and the joint probabilistic earthquake demand model, the functional failure probability and the overall system failure probability under different ground motion intensities are calculated, and the functional failure prediction results for shield tunnels are generated.

2. The method for predicting the probability of functional failure of a shield tunnel based on multiple variables as described in claim 1, characterized in that, The construction of the multi-dimensional damage parameter system includes: Local deformation parameters are constructed, including circumferential joint opening and circumferential misalignment. The circumferential joint opening is used to characterize the degree of separation of the contact surfaces between segments, determine the working state and failure risk of the waterproof sealing system, and identify the damage mode of joint water-stopping failure and leakage path formation. The circumferential misalignment is used to characterize the tangential relative slippage or rotation between adjacent segments within the cross-section, reflect the joint shear deformation and bending moment transmission capacity, and identify the damage mode of joint shear failure, bolt shearing, and local stress concentration. An overall deformation parameter is constructed, which includes the rate of change of the horizontal diameter of the cross-section, the rate of change of the vertical diameter of the cross-section, and the centroid offset of the cross-section. The rate of change of the horizontal diameter characterizes the relative change in the horizontal diameter, reflecting the compression or expansion of the cross-section caused by lateral earth pressure or lateral liquefaction deformation, and identifying damage modes such as cross-section ellipticization, lining ring lateral convergence or expansion. The rate of change of the vertical diameter characterizes the relative change in the vertical diameter of the cross-section, reflecting the cross-section deformation caused by uneven vertical loads, base liquefaction uplift or settlement, and identifying damage modes such as cross-section ellipticization, base softening or uplift. The centroid offset characterizes the translation of the cross-section centroid relative to the initial centroid, reflecting the asymmetry of the resultant force acting on the cross-section, and identifying damage modes such as overall cross-section translation, biased stress, and severely uneven load distribution. Internal force response parameters are constructed, including segment section bending moment, segment section axial force, and moment-curvature deviation index. The segment section bending moment characterizes the translation of the centroid relative to the initial centroid, reflecting the asymmetry of the resultant force acting on the segment and identifying damage modes such as segment cracking, concrete crushing, and steel yielding. The segment section axial force characterizes the axial force at various locations on the segment section, reflecting the compressive or tensile state of the section and identifying damage modes such as crushing instability and tensile cracking. The moment-curvature deviation index characterizes the degree of deviation between the actual moment-curvature response and the elastic theoretical value, quantifying the degree to which the section enters plasticity and identifying damage modes such as the development of plastic hinges and stiffness degradation. A distribution characteristic parameter is constructed, which includes the cross-sectional internal force / deformation variation coefficient and the most unfavorable position angle. The cross-sectional internal force / deformation variation coefficient is used to characterize the ratio of the standard deviation to the mean of a parameter at different locations within the same cross-section, quantify the non-uniformity of the response within the cross-section, and identify and reveal the circumferential concentrated distribution of load or damage, reflecting the damage mode of non-uniform load action. The most unfavorable position angle is used to characterize the azimuth angle at which the key responses of maximum bending moment and maximum opening occur in the circumferential direction of the cross-section, and to establish a direct spatial correlation between "non-uniform liquefaction development - the most unfavorable response location of the structure".

3. The method for predicting the probability of functional failure of shield tunnels based on multiple variables as described in claim 1, characterized in that, The process involves fusing and calibrating the hierarchical thresholds for different states of various functions using acquired multi-source data, and then constructing a vectorized functional degradation index, including: With waterproof integrity, cross-sectional passability, and structural load-bearing safety as the core functional dimensions, and system risk distribution as the correction dimension, a vectorized functional degradation index is defined, and the grading thresholds of each function from intact to completely failed are calibrated through multi-source data fusion. Among them, the waterproof integrity is used to characterize the joint opening amount as the core related parameter. By integrating standard specification limits, waterproof performance test data, and shield tunnel leakage statistics, the safety limit of joint opening amount, bolt yield threshold, maximum allowable opening amount, and the degree of degradation of waterproof function are calibrated. The cross-sectional accessibility is used to characterize the ratio of available net space area as a quantitative indicator, through non-uniform rational... B Spline curves are used to reconstruct the profile of the tunnel section after the earthquake. The profile of the tunnel section after the earthquake is discretized into a point set and compared with the standard building clearance. The encroachment area is calculated, and then the classification threshold of the passability is determined. The structural load-bearing safety is used to characterize the threshold of different safety states, with the load-bearing capacity safety factor as a quantitative indicator. The system risk distribution is used as a correction dimension to characterize the indicators of the core functional dimension by using the cross-sectional internal force / deformation variation coefficient and the most unfavorable position angle, thereby reflecting the impact of the uniformity of damage distribution on system risk.

4. The method for predicting the probability of functional failure of shield tunnels based on multiple variables as described in claim 1, characterized in that, The process of obtaining the nonlinear dynamic analysis results of the liquefaction non-uniform operating condition and constructing a multi-input and multi-output mapping model includes: Using a physical constraint neural network as the core architecture, embedding prior physical knowledge as training constraints, a mapping model between multiple inputs and multiple outputs is trained. SHAP value analysis reveals the weight of key damage parameters on the failure of specific functions; The uncertainty of the mapping relationship in the mapping model is quantified using a Bayesian framework to obtain a set of damage-function association rules with probabilistic output capability.

5. The method for predicting the probability of functional failure of shield tunnels based on multiple variables as described in claim 1, characterized in that, The step of constructing a multivariate probabilistic earthquake demand model based on interval estimation, according to the multidimensional damage parameter system and candidate ground motion intensity indices, includes: Based on the multi-dimensional damage parameter system and candidate ground motion intensity indices, a nonlinear dynamic analysis of the liquefaction non-uniform working condition is performed. An interval estimation method was used to fit the statistical relationship between the ground motion intensity index and various damage parameters, and the confidence range of the model regression parameters was quantified. A multivariate probabilistic earthquake demand model based on interval estimation is constructed to achieve interval prediction of damage parameters.

6. The method for predicting the probability of functional failure of a shield tunnel based on multiple variables as described in claim 1, characterized in that, The step of constructing a joint probabilistic earthquake demand model based on the optimal seismic intensity index and the multivariate probabilistic earthquake demand model includes: A multidimensional joint probability model is constructed by introducing a Copula function to connect the marginal distribution of damage / functional parameters; Based on the optimal ground motion intensity index, the marginal conditional probability distribution of each damage parameter under different ground motion intensity index levels is obtained through a probabilistic earthquake demand model based on interval estimation. Calculate the Kendall rank correlation coefficients among the various functional degradation indicators to quantify the nonlinear correlation of each functional degradation indicator; A family of Copula functions suitable for multidimensional analysis was selected to fit the three-dimensional functional degradation index; The parameters of each Copula function are estimated using the maximum likelihood estimation method, and the goodness of fit is evaluated using the Akaike information criterion. By using the optimal Copula function, the marginal distributions of each functional degradation index are coupled into a three-dimensional joint probabilistic seismic demand model.

7. The method for predicting the probability of functional failure of shield tunnels based on multiple variables as described in claim 1, characterized in that, The step involves calculating the functional failure probability and overall system failure probability under different ground motion intensities based on the grading threshold and the joint probabilistic seismic demand model, generating functional failure prediction results for the shield tunnel, including: Based on the aforementioned classification threshold, the failure domain corresponding to each functional failure event is determined; Given a seismic intensity index, a large number of samples were taken from the joint probability distribution through Copula-based Monte Carlo simulation. The proportion of samples falling into each failure domain was statistically analyzed to obtain the conditional probability threshold for each functional failure. The overall failure probability of the system is calculated using probability formulas, resulting in the vulnerability curves for each functional failure and the overall system failure.

8. A device for predicting the probability of functional failure of shield tunnels based on multiple variables, characterized in that, include: The first module is used to construct a multi-dimensional damage parameter system; wherein, the multi-dimensional damage parameters include local deformation, overall deformation, internal force response and distribution characteristics; The second module is used to calibrate the hierarchical thresholds of each function in different states by fusing the acquired multi-source data, and then construct a vectorized function degradation index. The third module is used to obtain the nonlinear dynamic analysis results of liquefaction non-uniform working conditions and to construct a multi-input and multi-output mapping model. The fourth module is used to construct a multivariate probabilistic earthquake demand model based on interval estimation, according to the multidimensional damage parameter system and candidate ground motion intensity indices. The fifth module is used to quantitatively evaluate the characterization ability of the multi-dimensional damage parameters based on the candidate ground motion intensity indices, construct a ground motion performance evaluation matrix, and then determine the optimal ground motion intensity index. The sixth module is used to construct a joint probabilistic earthquake demand model based on the optimal ground motion intensity index and the multivariate probabilistic earthquake demand model. The seventh module is used to calculate the functional failure probability and the overall system failure probability under different ground motion intensities based on the classification threshold and the joint probabilistic earthquake demand model, and generate functional failure prediction results for shield tunnels.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images