Tunnel health assessment method and device based on digital twinning and medium

Abstract

The invention discloses a tunnel health assessment method and device based on digital twinning and a medium, and relates to the technical field of digital twinning, and the method comprises the steps: carrying out the time-space alignment processing of tunnel health monitoring data, so as to obtain a structured tunnel state data set; performing tunnel equipment physical drive analysis on the structured tunnel equipment state data to determine tunnel equipment performance data; performing finite element analysis on the structured tunnel environment state data to determine tunnel environment state data; based on the tunnel equipment performance data and the tunnel environment state data, performing bidirectional coupling processing to obtain a dynamically updated digital twinborn body; determining tunnel state driving simulation data through tunnel data twinning dynamic interaction according to the dynamically updated digital twinborn body; and performing multi-level health index operation on the tunnel state driving simulation data to obtain a tunnel health assessment score. According to the method, the technical problem that tunnel equipment and environment cannot be linked in tunnel health assessment is solved.

Description

Technical Field

[0001] This application relates to the field of digital twin technology, and in particular, to a tunnel health assessment method, device, and medium based on digital twin. Background Art

[0002] As a core infrastructure of the transportation network, the structural health of tunnels and the reliability of equipment are directly related to driving safety, operation efficiency, and the life-cycle cost. With the increase in the service life of tunnels, risks such as surrounding rock creep, equipment aging, and environmental corrosion are intensifying, which may trigger major accidents such as lining cracking, ventilation failure, and fires. According to statistics, the maintenance cost caused by tunnel structure damage accounts for more than 40% of the total operation cost, and sudden failures may cause serious consequences such as traffic interruption and casualties. Therefore, tunnel health assessment technology has become the key to ensuring the safety of infrastructure, and there is an urgent need to achieve an intelligent upgrade from "passive after-the-fact maintenance" to "active pre-event intervention".

[0003] Current tunnel health assessment technologies mainly rely on threshold alarms based on statistical analysis and machine learning assessments driven by data. Due to the isolated analysis of environmental data and equipment data, it is impossible to specifically analyze the interaction between tunnel equipment and the environment, and thus a more comprehensive health assessment of the tunnel health status cannot be achieved. Summary of the Invention

[0004] The embodiments of this application provide a tunnel health assessment method, device, and medium based on digital twin, which solve the technical problem that tunnel health assessment in the prior art cannot link tunnel equipment and the tunnel environment.

[0005] In a first aspect, the embodiments of this application provide a tunnel health assessment method based on digital twin, which is characterized in that the method includes: obtaining tunnel health monitoring data and performing spatio-temporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel state data set; wherein, the structured tunnel state data set includes: structured tunnel equipment state data and structured tunnel environment state data; performing tunnel equipment physical drive analysis on the structured tunnel equipment state data to determine tunnel equipment performance data; performing finite element analysis on the structured tunnel environment state data to determine tunnel environment state data; based on the tunnel equipment performance data and the tunnel environment state data, through two-way coupling processing, to obtain a dynamically updated digital twin; according to the dynamically updated digital twin, through tunnel data twin dynamic interaction, determining tunnel state drive simulation data; performing multi-level health index operations on the tunnel state drive simulation data to obtain a tunnel health assessment score.

[0006] In an implementation manner of the present application, spatio-temporal alignment processing is performed on tunnel health monitoring data to obtain a structured tunnel status data set, which specifically includes: performing data cleaning on the tunnel health monitoring data to obtain pure tunnel health monitoring data; wherein, the data cleaning includes: abnormal distribution determination and wavelet noise reduction processing; performing timestamp alignment processing on the pure tunnel health monitoring data to determine time-synchronized tunnel detection data; performing data spatial registration processing on the pure tunnel health monitoring data to determine spatially aligned tunnel detection data; based on the time-synchronized tunnel detection data and the spatially aligned tunnel detection data, through dual-end state feature extraction, obtaining a structured tunnel status data set; wherein, the dual-end state feature extraction includes: device-end abnormal feature extraction and environment-end strain gradient analysis. In an implementation manner of the present application, tunnel equipment physical drive analysis is performed on the structured tunnel equipment status data to determine tunnel equipment performance data, which specifically includes: obtaining the tunnel equipment physical equation, and based on the structured tunnel equipment status data and the equipment physical equation, through historical fault analysis, constructing the initial tunnel equipment physical drive; performing LSTM data-driven correction on the initial tunnel equipment physical drive to determine the tunnel equipment physical drive; according to the tunnel equipment physical drive, through the actual performance calculation of the tunnel equipment, determining the tunnel equipment performance data.

[0007] In an implementation manner of the present application, finite element analysis is performed on the structured tunnel environment status data to determine the tunnel environment status data, which specifically includes: performing tunnel mesh division on the structured tunnel environment status data to obtain tunnel mesh data; based on the tunnel mesh data, through tunnel environment status balance analysis, determining the key risk areas; performing FEM prediction update on the key risk areas to obtain the tunnel environment status data.

[0008] In an implementation manner of the present application, based on the tunnel equipment performance data and the tunnel environment status data, through two-way coupling processing, a dynamically updated digital twin is obtained, which specifically includes: performing coupling of the device impact on the tunnel environment boundary conditions on the tunnel equipment performance data to determine the coupling data of the tunnel equipment on the tunnel environment; performing coupling of the device monitoring threshold conditions on the tunnel environment status data to determine the coupling data of the tunnel environment on the tunnel equipment; performing data dynamic update on the coupling data of the device on the tunnel environment and the coupling data of the tunnel environment on the tunnel equipment to obtain a dynamically updated digital twin.

[0009]

[0010] ​In an implementation manner of the present application, according to the dynamically updated digital twin, through the dynamic interaction of tunnel data twins, the tunnel state-driven simulation data is determined, specifically including: obtaining the real-time monitoring data stream of the tunnel, and performing grid threshold simulation processing on the real-time monitoring data stream of the tunnel to obtain dynamically adjusted tunnel simulation configuration parameters; based on the tunnel simulation configuration parameters, through dynamic federated learning drive processing, determining the simulation configuration parameters; according to the simulation configuration parameters, through the tunnel multi-objective adaptive control strategy configuration, obtaining the tunnel hierarchical state determination strategy; embedding the tunnel hierarchical state determination strategy into the dynamically updated digital twin to determine the tunnel state-driven simulation data.

[0011] In an implementation manner of the present application, a multi-level health index operation is performed on the tunnel state-driven simulation data to obtain a tunnel health assessment score, specifically including: analyzing the health state of tunnel equipment for the tunnel state-driven simulation data to determine the first tunnel assessment parameter; performing a tunnel environment risk assessment on the tunnel state-driven simulation data to determine the second tunnel assessment parameter; performing a two-way influence analysis on the first tunnel assessment parameter and the second tunnel assessment parameter to obtain the tunnel health assessment score.

[0012] In an implementation manner of the present application, after performing a multi-level health index operation on the tunnel state-driven simulation data to obtain a tunnel health assessment score, the method further includes: based on the tunnel health assessment score, through maintenance strategy configuration, determining the current tunnel maintenance requirements; according to the current tunnel maintenance requirements, through the operation and maintenance work order priority assessment, obtaining the tunnel operation and maintenance priority ranking work order.

[0013] In a second aspect, an embodiment of the present application further provides a tunnel health assessment device based on digital twins, characterized in that the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: obtain tunnel health monitoring data, and perform spatio-temporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel state data set; wherein, the structured tunnel state data set includes: structured tunnel equipment state data, structured tunnel environment state data; perform tunnel equipment physical drive analysis on the structured tunnel equipment state data to determine tunnel equipment performance data; perform finite element analysis on the structured tunnel environment state data to determine tunnel environment state data; based on the tunnel equipment performance data and the tunnel environment state data, through two-way coupling processing, to obtain a dynamically updated digital twin; according to the dynamically updated digital twin, through the dynamic interaction of tunnel data twins, determine the tunnel state-driven simulation data; perform a multi-level health index operation on the tunnel state-driven simulation data to obtain a tunnel health assessment score.

[0014] In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium for tunnel health assessment based on digital twins, storing computer-executable instructions, characterized in that the computer-executable instructions are set to: obtain tunnel health monitoring data, and perform spatio-temporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel status data set; wherein, the structured tunnel status data set includes: structured tunnel equipment status data, structured tunnel environmental status data; perform tunnel equipment physical drive analysis on the structured tunnel equipment status data to determine tunnel equipment performance data; perform finite element analysis on the structured tunnel environmental status data to determine tunnel environmental status data; based on the tunnel equipment performance data and the tunnel environmental status data, through two-way coupling processing, to obtain a dynamically updated digital twin; according to the dynamically updated digital twin, through tunnel data twin dynamic interaction, determine tunnel status drive simulation data; perform multi-level health index operations on the tunnel status drive simulation data to obtain a tunnel health assessment score.

[0015] The embodiment of the present application provides a method, device and medium for tunnel health assessment based on digital twins. Through the two-way dynamic coupling analysis of tunnel equipment and tunnel environment and the dynamically updated digital twin, it solves the technical problem that tunnel health assessment in the prior art cannot link tunnel equipment and tunnel environment, realizes tunnel health assessment based on the interaction between tunnel equipment and tunnel environment, improves the practicability and comprehensiveness of tunnel health assessment, and optimizes the data discretization processing of tunnel health assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation to the present application. In the drawings: Figure 1 It is a flowchart of a method for tunnel health assessment based on digital twins provided by an embodiment of the present application; Figure 2 It is a schematic internal structure diagram of a device for tunnel health assessment based on digital twins provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] To make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0018] The embodiments of the present application provide a tunnel health assessment method, device, and medium based on digital twins. Through the bidirectional dynamic coupling analysis of tunnel devices and the tunnel environment, as well as a dynamically updated digital twin, the technical problem in the prior art that tunnel health assessment cannot link tunnel devices and the tunnel environment is solved. The tunnel health assessment based on the interaction between tunnel devices and the tunnel environment is realized, the practicability and comprehensiveness of tunnel health assessment are improved, and the data discretization processing of tunnel health assessment is optimized.

[0019] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0020] Figure 1 It is a flowchart of a tunnel health assessment method based on digital twins provided by the embodiments of the present application. As Figure 1 shown, a tunnel health assessment method based on digital twins provided by the embodiments of the present application specifically includes the following steps: Step 101: Obtain tunnel health monitoring data and perform spatio-temporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel state data set.

[0021] Exemplarily, the structured tunnel state data set includes: structured tunnel device state data and structured tunnel environment state data. Since it is necessary to comprehensively analyze tunnel devices and the tunnel environment, the obtained tunnel health monitoring data also needs to include tunnel device monitoring data and tunnel environment monitoring data. The spatio-temporal alignment of the tunnel health monitoring data for devices and the environment realizes the one-to-one correspondence in space and time between tunnel devices and the tunnel environment for coupling analysis.

[0022] Specifically, performing spatio-temporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel state data set includes: performing data cleaning on the tunnel health monitoring data to obtain pure tunnel health monitoring data; wherein, data cleaning includes: 3 abnormal distribution determination and wavelet denoising processing; performing timestamp alignment processing on the pure tunnel health monitoring data to determine time-synchronized tunnel detection data; performing data space registration processing on the pure tunnel health monitoring data to determine space-aligned tunnel detection data; based on the time-synchronized tunnel detection data and the space-aligned tunnel detection data, through dual-end state feature extraction, obtaining a structured tunnel state data set; wherein, dual-end state feature extraction includes: device-end abnormal feature extraction and environment-end strain gradient analysis.

[0023] In one embodiment, first, data cleaning is performed on the original tunnel health monitoring data, specifically including using 3 abnormal distribution determination to remove outliers and using wavelet denoising processing to eliminate high-frequency noise to generate pure tunnel health monitoring data.

[0024] Then, perform timestamp alignment processing on the pure data, unify the sampling time intervals of different sensors through interpolation algorithms, and generate time-synchronized tunnel detection data; and perform spatial registration processing on the pure data, map it to the tunnel three-dimensional model based on the sensor spatial coordinates, and generate spatially aligned tunnel detection data.

[0025] Finally, perform dual-end state feature extraction on the time-synchronized and spatially aligned data. Among them, the abnormal feature extraction at the device end is realized through frequency-domain energy distribution analysis, and the strain gradient analysis at the environmental end adopts spatial difference calculation, and finally generates structured tunnel state data.

[0026] Step 102: Perform tunnel equipment physical drive analysis on the structured tunnel equipment state data to determine the tunnel equipment performance data.

[0027] Exemplarily, the operation of tunnel equipment is mainly realized by ventilation equipment, drainage equipment, etc. Physical drive analysis of the structured tunnel equipment state data according to the aging degree and operation state of the tunnel equipment realizes the equipment performance analysis at the tunnel equipment end and provides a data basis for the data coupling between the tunnel equipment and the tunnel environment.

[0028] Specifically, performing tunnel equipment physical drive analysis on the structured tunnel equipment state data to determine the tunnel equipment performance data specifically includes: obtaining the tunnel equipment physical equation, and based on the structured tunnel equipment state data and the equipment physical equation, constructing the initial physical drive of the tunnel equipment through historical fault analysis; performing LSTM data-driven correction on the initial physical drive of the tunnel equipment to determine the physical drive of the tunnel equipment; according to the physical drive of the tunnel equipment, calculating through the actual performance of the tunnel equipment to determine the tunnel equipment performance data.

[0029] In one embodiment, first, for key equipment such as the tunnel ventilation system and drainage pumps, establish a physical model based on equipment electromechanical losses. The core construction of the physical model of electromechanical losses is based on key moving parts such as the motors and bearings of tunnel equipment. Typical degradation modes can be extracted from historical fault data, and the mapping relationship between equipment state parameters and equipment physical parameters can be established to construct a model for the initial physical drive of tunnel equipment.

[0030] Then, use the LSTM network to model the residuals between the output values of the physical model and the real-time monitoring values, design a sliding time window (24 hours) to dynamically update the network weights. When the residuals exceed the preset threshold due to sudden equipment anomalies, trigger incremental model training, synchronously update the physical equation parameters and the L network weights, and introduce adversarial sample generation technology to simulate the equipment state under extreme working conditions and enhance the robustness of the model.

[0031] Finally, based on the corrected physics-driven model, calculate the device performance degradation rate, construct a device health assessment matrix, set performance level thresholds in combination with ISO standards, and determine the tunnel device performance data.

[0032] Step 103: Perform finite element analysis on the structured tunnel environment state data to determine the tunnel environment state data.

[0033] Exemplarily, the environment of the tunnel device determines the overall stability of the tunnel. By performing finite element analysis on the structured tunnel environment state data, device performance analysis at the tunnel device end is realized, providing a data basis for data coupling between the tunnel device and the tunnel environment.

[0034] Specifically, performing finite element analysis on the structured tunnel environment state data to determine the tunnel environment state data includes: dividing the structured tunnel environment state data into tunnel grids to obtain tunnel grid data; based on the tunnel grid data, determining key risk areas through tunnel environment state balance analysis; and performing FEM prediction update on the key risk areas to obtain the tunnel environment state data.

[0035] In one embodiment, first, adopt an unstructured grid generation algorithm to dynamically adjust the grid density according to ground penetrating radar detection data and the spatial distribution of geotechnical parameters, and automatically encrypt it to centimeter-level resolution in areas such as soft interlayers and fault zones.

[0036] Then, map the fiber optic sensing data and geological exploration data to the grid nodes to construct a multi-physical field coupling initial model. Then perform multi-condition coupling analysis, calculate the stress concentration coefficient of the surrounding rock and the pore water pressure gradient, and use Monte Carlo simulation to evaluate parameters such as the variation coefficient of rock mass strength, generate a risk probability cloud map, and automatically identify the morphological characteristics of high-risk areas through a convolutional neural network.

[0037] Finally, establish a two-way feedback channel for the finite element model of the monitoring data, convert the distributed fiber optic strain monitoring data into boundary condition correction amounts in real time, and then predict the displacement evolution trend of the tunnel surrounding rock within the next 48 hours to determine the tunnel environment state data.

[0038] Step 104: Based on the tunnel device performance data and the tunnel environment state data, perform two-way coupling processing to obtain a dynamically updated digital twin.

[0039] Exemplarily, based on the tunnel device performance data and the tunnel environment state data, through the coupling of the tunnel device and the tunnel environment and the coupling of the tunnel environment and the tunnel device, a digital twin that meets two-way coupling and dynamic update is realized, and tunnel health assessment based on the interaction between the tunnel device and the tunnel environment is realized.

[0040] Specifically, based on the tunnel equipment performance data and the tunnel environment status data, through two-way coupling processing, a dynamically updated digital twin is obtained, including: coupling the tunnel equipment performance data with the boundary conditions of the tunnel environment affected by the equipment to determine the coupling data of the tunnel equipment to the tunnel environment; coupling the tunnel environment status data with the equipment monitoring threshold conditions to determine the coupling data of the tunnel environment to the tunnel equipment; and dynamically updating the data of the coupling data of the equipment to the tunnel environment and the coupling data of the tunnel environment to the equipment to obtain a dynamically updated digital twin.

[0041] In one embodiment, first, the ventilation equipment performance data (such as wind pressure, flow rate) is converted into the thermal-mechanical coupling boundary conditions of the surrounding rock-support system to simulate the dynamic influence of equipment operation on the tunnel temperature and humidity fields and stress fields, so as to determine the coupling data of the tunnel equipment to the tunnel environment.

[0042] Then, the surrounding rock displacement monitoring data is converted into the equipment working load coefficient, and the start-stop threshold of the drainage pump and the control strategy of the ventilation fan speed are dynamically adjusted to determine the coupling data of the tunnel environment to the tunnel equipment.

[0043] It should be noted that the selection of the coupling data can be reasonably adjusted according to the needs of the cableway health assessment. The higher the requirements for the health assessment, the more types of coupling data and the greater the amount of calculation.

[0044] Finally, a cross-scale model is constructed. At the macroscopic level, the finite element method is used to simulate the overall structural response, and at the microscopic level, the discrete element method is used to analyze the movement of rock mass particles. By designing a co-simulation engine, stress transfer, energy dissipation data interaction, and adaptive matching of time steps between the two-scale models are realized to obtain a dynamically updated digital twin.

[0045] Step 105: According to the dynamically updated digital twin, through the dynamic interaction of the tunnel data twin, determine the tunnel state-driven simulation data.

[0046] Exemplarily, through the dynamic interaction of the tunnel data twin, the present application determines the tunnel state-driven simulation data, realizes the multi-objective adaptive interaction of the tunnel state, and meets the tunnel state-driven simulation requirements based on the digital twin.

[0047] Specifically, according to the dynamically updated digital twin, through the dynamic interaction of the tunnel data twin, the tunnel state-driven simulation data is determined, specifically including: obtaining the real-time monitoring data stream of the tunnel, and performing grid threshold simulation processing on the real-time monitoring data stream of the tunnel to obtain dynamically adjusted tunnel simulation configuration parameters; based on the tunnel simulation configuration parameters, through dynamic federated learning-driven processing, determining the simulation configuration parameters; according to the simulation configuration parameters, through the tunnel multi-objective adaptive control strategy configuration, obtaining the tunnel hierarchical state determination strategy; embedding the tunnel hierarchical state determination strategy into the dynamically updated digital twin to determine the tunnel state-driven simulation data.

[0048] In one embodiment, first, perform sliding window sampling on the real-time monitoring data stream, generate dynamically adjusted tunnel simulation configuration parameters by combining grid threshold constraints, aggregate the simulation results of multiple nodes based on the federated learning framework, and optimize the global simulation model through parameter weight allocation to generate corrected simulation configuration parameters.

[0049] The real-time monitoring data stream is the surrounding rock displacement of 0.3 - 2.1 mm, the segment joint opening of 0.5 - 3.8 mm, the current fluctuation value of the ventilator of 12 - 18 A, and the environmental humidity of 70 - 95% RH. Perform grid threshold processing on the data stream, dynamically divide the high-precision simulation grid area according to the preset safety threshold of surrounding rock displacement of 1.8 mm and the early warning threshold of joint opening of 2.5 mm, and encrypt the grid density from the conventional 1 m×1 m to 0.2 m×0.2 m in the area where the displacement exceeds the limit, generating a set of tunnel simulation configuration parameters including local refinement parameters.

[0050] Then, based on the dynamic federated learning framework, aggregate the simulation node data of the east and west construction sections of the tunnel, optimize the global model through the weight allocation algorithm, and configure the adaptive control strategy using the multi-objective optimization algorithm to balance the indicators of safety, energy consumption, and equipment life: in the ventilation system control, dynamically adjust the bearing vibration threshold from 6.0 mm / s to the range of 4.5 - 7.2 mm / s, while reducing the daily average energy consumption of the fan by 18%, and shortening the stress overrun alarm response time in the high-risk segment area to within 30 seconds. Based on this, generate the tunnel hierarchical state determination strategy, including a three-level response mechanism (normal monitoring, yellow early warning, red emergency response), and associate different levels of support resource scheduling plans.

[0051] Finally, embed the determination strategy into the digital twin managed by the blockchain, and drive the update of the simulation model through the dynamic interaction engine.

[0052] Step 106: Perform multi-level health index operations on the tunnel state-driven simulation data to obtain the tunnel health assessment score.

[0053] Exemplarily, the present application realizes tunnel health assessment based on the interaction between tunnel equipment and tunnel environment by performing multi-level health index operations on tunnel state-driven simulation data, improves the practicability and comprehensiveness of tunnel health assessment, and optimizes the data discretization process of tunnel health assessment.

[0054] Specifically, performing multi-level health index operations on tunnel state-driven simulation data to obtain a tunnel health assessment score includes: analyzing the health status of tunnel equipment in the tunnel state-driven simulation data to determine the first tunnel assessment parameter; assessing the tunnel environment risk in the tunnel state-driven simulation data to determine the second tunnel assessment parameter; and performing a two-way influence analysis on the first tunnel assessment parameter and the second tunnel assessment parameter to obtain a tunnel health assessment score.

[0055] In one embodiment, equipment operation parameters are extracted from the tunnel state-driven simulation data, and the equipment health index is calculated through degradation mode matching to generate the first tunnel assessment parameter.

[0056] Analyze the stress concentration degree and displacement change rate in the environmental simulation data, and combine with the risk probability model to generate the second tunnel assessment parameter; Construct a coupling influence matrix, fuse the two types of assessment parameters through a two-way weight distribution algorithm to generate a comprehensive tunnel health assessment score; generate a tunnel risk warning map through two-way coupling simulation, divide a 120m red high-risk section and a 350m yellow warning section, and generate an operation and maintenance work order based on the equipment health status. For the emergency condition of segment leakage risk superimposed with equipment aging, the system preferentially schedules maintenance resources to ensure timely disposal of high-risk areas.

[0057] Further, after performing multi-level health index operations on the tunnel state-driven simulation data to obtain a tunnel health assessment score, the method further includes: based on the tunnel health assessment score, determining the current tunnel maintenance requirements through maintenance strategy configuration; and obtaining a tunnel operation and maintenance priority ranking work order through operation and maintenance work order priority assessment according to the current tunnel maintenance requirements.

[0058] In one embodiment, first, divide the equipment aging level and environmental risk level according to the tunnel health assessment score to generate a maintenance strategy configuration plan.

[0059] Then, construct a multi-objective evaluation function based on maintenance cost, risk diffusion speed, and repair urgency to rank the work orders by priority.

[0060] Finally, according to the priority ranking, obtain a tunnel operation and maintenance priority ranking work order including the maintenance location, recommended measures, and execution time.

[0061] The above is the method embodiment proposed by this application. Based on the same inventive concept, the embodiments of this application also provide a tunnel health assessment device based on digital twin, and its structure is as Figure 2 shown.

[0062] Figure 2 This is a schematic diagram of the internal structure of a tunnel health assessment device based on digital twin provided by the embodiments of this application. As Figure 2 shown, the device includes: At least one processor 201; And a memory 202 communicatively connected to at least one processor; Wherein, the memory 202 stores instructions executable by at least one processor, and the instructions are executed by at least one processor 201 so that at least one processor 201 can: Obtain tunnel health monitoring data, and perform spatio-temporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel state data set; wherein, the structured tunnel state data set includes: structured tunnel equipment state data, structured tunnel environment state data; perform tunnel equipment physical drive analysis on the structured tunnel equipment state data to determine tunnel equipment performance data; perform finite element analysis on the structured tunnel environment state data to determine tunnel environment state data; based on the tunnel equipment performance data and the tunnel environment state data, through two-way coupling processing, to obtain a dynamically updated digital twin; according to the dynamically updated digital twin, through tunnel data twin dynamic interaction, determine tunnel state drive simulation data; perform multi-level health index operations on the tunnel state drive simulation data to obtain a tunnel health assessment score.

[0063] Some embodiments of this application provide a non-volatile computer storage medium corresponding to Figure 1 for tunnel health assessment based on digital twin, storing computer-executable instructions, and the computer-executable instructions are set as: Obtain tunnel health monitoring data, and perform spatio-temporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel state data set; wherein, the structured tunnel state data set includes: structured tunnel equipment state data, structured tunnel environment state data; perform tunnel equipment physical drive analysis on the structured tunnel equipment state data to determine tunnel equipment performance data; perform finite element analysis on the structured tunnel environment state data to determine tunnel environment state data; based on the tunnel equipment performance data and the tunnel environment state data, through two-way coupling processing, to obtain a dynamically updated digital twin; according to the dynamically updated digital twin, through tunnel data twin dynamic interaction, determine tunnel state drive simulation data; perform multi-level health index operations on the tunnel state drive simulation data to obtain a tunnel health assessment score.

[0064] Each embodiment in this application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the Internet of Things devices and media, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0065] The systems and media provided by the embodiments of this application correspond one by one to the methods. Therefore, the systems and media also have beneficial technical effects similar to those of their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be elaborated here.

[0066] Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0067] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0068] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, causing a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process Figure 1 one process or a plurality of processes and / or boxes Figure 1 steps for implementing the functions specified in one box or a plurality of boxes.

[0070] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0071] The memory may include non-permanent memory in the computer-readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0072] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0073] It should also be noted that the term "comprises", "comprising", or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, commodity, or device that comprises a list of elements does not include only those elements but also other elements not expressly listed, or elements that are inherent to such process, method, commodity, or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity, or device that comprises the element.

[0074] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and variations can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A tunnel health assessment method based on digital twins, characterized in that: The method comprises: Acquire tunnel health monitoring data, and perform spatiotemporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel status data set; wherein the structured tunnel status data set includes: structured tunnel equipment status data and structured tunnel environment status data; Performing tunnel equipment physical drive analysis on the structured tunnel equipment status data to determine tunnel equipment performance data; Performing finite element analysis on the structured tunnel environment state data to determine the tunnel environment state data; Based on the tunnel equipment performance data and the tunnel environment status data, a dynamically updated digital twin is obtained through bidirectional coupling processing; Determining tunnel state driving simulation data based on the dynamically updated digital twin through dynamic interaction of the tunnel data twin; A multi-level health index operation is performed on the tunnel state driving simulation data to obtain a tunnel health assessment score.

2. According to a tunnel health assessment method based on digital twins according to claim 1, it is characterized in that: The tunnel health monitoring data is subjected to spatiotemporal alignment processing to obtain a structured tunnel status data set, specifically including: The tunnel health monitoring data is cleaned to obtain pure tunnel health monitoring data; wherein the data cleaning includes: 3 Abnormal distribution determination and wavelet noise reduction processing; Performing timestamp alignment processing on the tunnel health monitoring clean data to determine time-synchronized tunnel detection data; Performing data space registration processing on the tunnel health monitoring clean data to determine spatially aligned tunnel detection data; Based on the time-synchronized tunnel detection data and the space-aligned tunnel detection data, the structured tunnel state data set is obtained through dual-end state feature extraction; wherein the dual-end state feature extraction includes: device-end abnormal feature extraction and environment-end strain gradient analysis.

3. The tunnel health assessment method based on digital twin according to claim 1 is characterized in that: Performing tunnel equipment physical drive analysis on the structured tunnel equipment status data to determine tunnel equipment performance data, specifically including: Acquire the physical equation of the tunnel equipment, and construct the physical initial drive of the tunnel equipment through historical fault analysis based on the structured tunnel equipment state data and the physical equation of the equipment; Performing LSTM data driven correction on the physical initial drive of the tunnel device to determine the physical drive of the tunnel device; The tunnel device performance data is determined by calculating the actual performance of the tunnel device according to the physical drive of the tunnel device.

4. The tunnel health assessment method based on digital twin according to claim 1 is characterized in that: Performing finite element analysis on the structured tunnel environment state data to determine the tunnel environment state data specifically includes: Performing tunnel grid division on the structured tunnel environment state data to obtain tunnel grid data; Based on the tunnel grid data, determining key risk areas through tunnel environmental state balance analysis; Perform FEM prediction update on the key risk area to obtain the tunnel environment status data.

5. The tunnel health assessment method based on digital twin according to claim 1 is characterized in that: Based on the tunnel equipment performance data and the tunnel environment status data, a dynamically updated digital twin is obtained through bidirectional coupling processing, specifically including: Performing coupling of the tunnel equipment performance data with the tunnel environment boundary condition of the equipment, so as to determine the coupling data of the tunnel equipment to the tunnel environment; Performing equipment monitoring threshold condition coupling on the tunnel environment status data to determine coupling data of the tunnel environment to the tunnel equipment; The coupling data of the device to the tunnel environment and the coupling data of the tunnel environment to the tunnel device are dynamically updated to obtain a dynamically updated digital twin.

6. The tunnel health assessment method based on digital twin according to claim 1 is characterized in that: According to the dynamically updated digital twin, tunnel state driving simulation data is determined through dynamic interaction of the tunnel data twin, specifically including: Acquire a tunnel real-time monitoring data stream, and perform grid threshold simulation processing on the tunnel real-time monitoring data stream to obtain dynamically adjusted tunnel simulation configuration parameters; Based on the tunnel simulation configuration parameters, determining the simulation configuration parameters through dynamic federated learning driven processing; According to the simulation configuration parameters, a tunnel level state determination strategy is obtained through tunnel multi-objective adaptive control strategy configuration; The tunnel level state determination strategy is embedded into the dynamically updated digital twin to determine the tunnel state driving simulation data.

7. The tunnel health assessment method based on digital twin according to claim 1 is characterized in that: A multi-level health index operation is performed on the tunnel state driving simulation data to obtain a tunnel health assessment score, specifically including: Performing tunnel equipment health status analysis on the tunnel state driving simulation data to determine a first tunnel evaluation parameter; Performing tunnel environment risk assessment on the tunnel state driving simulation data to determine a second tunnel assessment parameter; A bidirectional parameter impact analysis is performed on the first tunnel assessment parameter and the second tunnel assessment parameter to obtain the tunnel health assessment score.

8. The tunnel health assessment method based on digital twin according to claim 1 is characterized in that: After performing multi-level health index calculations on the tunnel state driving simulation data to obtain a tunnel health assessment score, the method further includes: Based on the tunnel health assessment score, determining the current tunnel maintenance requirements through maintenance strategy configuration; According to the current tunnel maintenance demand, a tunnel operation and maintenance priority sorting work order is obtained through an operation and maintenance work order priority evaluation.

9. A tunnel health assessment device based on digital twins, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Acquire tunnel health monitoring data, and perform spatiotemporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel status data set; wherein the structured tunnel status data set includes: structured tunnel equipment status data, structured tunnel environment status data; Performing tunnel equipment physical drive analysis on the structured tunnel equipment status data to determine tunnel equipment performance data; Performing finite element analysis on the structured tunnel environment state data to determine the tunnel environment state data; Based on the tunnel equipment performance data and the tunnel environment status data, a dynamically updated digital twin is obtained through bidirectional coupling processing; Determining tunnel state driving simulation data based on the dynamically updated digital twin through dynamic interaction of the tunnel data twin; A multi-level health index operation is performed on the tunnel state driving simulation data to obtain a tunnel health assessment score.

10. A non-volatile computer storage medium for tunnel health assessment based on digital twins, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Acquire tunnel health monitoring data, and perform spatiotemporal alignment processing on the tunnel health monitoring data to obtain a structured tunnel status data set; The structured tunnel status data set includes: structured tunnel equipment status data, structured tunnel environment status data; Performing tunnel equipment physical drive analysis on the structured tunnel equipment status data to determine tunnel equipment performance data; Performing finite element analysis on the structured tunnel environment state data to determine the tunnel environment state data; Based on the tunnel equipment performance data and the tunnel environment status data, a dynamically updated digital twin is obtained through bidirectional coupling processing; Determining tunnel state driving simulation data based on the dynamically updated digital twin through dynamic interaction of the tunnel data twin; A multi-level health index operation is performed on the tunnel state driving simulation data to obtain a tunnel health assessment score.

Images