Real-time evaluation method for health degree of tunnel supporting structure based on distributed optical fiber sensing

Abstract

The invention discloses a tunnel supporting structure health degree real-time evaluation method based on distributed optical fiber sensing, relates to the technical field of tunnel supporting structure health degree evaluation, and can realize real-time evaluation of tunnel supporting structure health degree, timely discover potential safety hazards and improve working efficiency. Key parts of the tunnel supporting structure can be fully covered, and the monitoring comprehensiveness and accuracy are improved; and the health condition of the tunnel supporting structure can be evaluated more accurately. The scheme is characterized in that a distributed optical fiber sensing network is arranged on the surface of a to-be-evaluated tunnel supporting structure; acquiring strain distribution data, a vibration frequency spectrum and temperature field data of the to-be-evaluated tunnel supporting structure in real time; constructing a health degree evaluation model; and inputting the strain distribution data, the vibration frequency spectrum and the temperature field data into a health degree evaluation model, and outputting a health degree index of the to-be-evaluated tunnel supporting structure. The method is used for real-time evaluation of the health degree of the tunnel supporting structure.

Description

Technical Field

[0001] The present invention relates to the technical field of the health assessment of tunnel support structures, and particularly to a real-time assessment method for the health of tunnel support structures based on distributed optical fiber sensing. Background Art

[0002] Tunnel engineering plays a crucial role in modern infrastructure construction and is widely used in multiple fields such as transportation, water conservancy, and energy. For example, in the transportation field, tunnels can effectively shorten the traffic distance and improve traffic conditions; in the water conservancy field, tunnels are used for water conveyance, water diversion, and flood discharge; in the energy field, tunnels are used for laying power transmission lines and oil and gas pipelines. However, the health status of tunnel support structures is directly related to the safety and service life of tunnels. Once structural damage or failure occurs, it will not only cause huge economic losses but also endanger the safety of personnel.

[0003] Traditional health monitoring methods for tunnel support structures mainly rely on manual inspection and a small number of point sensors. Manual inspection usually requires regularly dispatching professional personnel to enter the tunnel for inspection. This method is not only inefficient but also difficult to cover the entire area of the tunnel, easily missing potential safety hazards. In addition, manual inspection is also limited by environmental conditions and the technical level of inspectors, and it is difficult to guarantee the accuracy and reliability of inspection results. Point sensors (such as strain gauges, temperature sensors, etc.) can provide local monitoring data, but their coverage is limited and they cannot comprehensively reflect the overall health status of tunnel support structures. Moreover, the installation and maintenance costs of point sensors are relatively high, making it difficult to arrange them on a large scale. Summary of the Invention

[0004] The present invention provides a real-time assessment method for the health of tunnel support structures based on distributed optical fiber sensing, which can realize the real-time assessment of the health of tunnel support structures, timely discover potential safety hazards, and improve work efficiency; the distributed optical fiber sensing network can comprehensively cover the key parts of the tunnel support structure, improving the comprehensiveness and accuracy of monitoring; the health assessment model combines the design parameters, construction process, material properties, and historical monitoring data of the tunnel support structure, and can more accurately assess the health status of the tunnel support structure.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] The present invention provides a real-time assessment method for the health of tunnel support structures based on distributed optical fiber sensing, including:

[0007] Laying a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated.

[0008] Based on the distributed optical fiber sensing network, the strain distribution data, vibration frequency spectrum, and temperature field data of the tunnel support structure to be evaluated are collected in real time.

[0009] Construct a health assessment model:

[0010] H = f LSTM -Attention(X t |X t-1 ...X t-n )

[0011] In the formula, X t is the input feature vector at time t, including the strain gradient, frequency offset, and temperature change rate.

[0012] Input the strain distribution data, the vibration frequency spectrum, and the temperature field data into the health assessment model, and output the health index of the tunnel support structure to be evaluated.

[0013] Furthermore, for the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing, after collecting the strain distribution data, vibration frequency spectrum, and temperature field data of the tunnel support structure to be evaluated in real time through the distributed optical fiber sensing network, it further includes:

[0014] Preprocess the strain distribution data, the vibration frequency spectrum, and the temperature field data.

[0015] Furthermore, for the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing, the preprocessing of the strain distribution data, the vibration frequency spectrum, and the temperature field data includes:

[0016] Perform data compensation on the strain distribution data:

[0017]

[0018] In the formula, α is the temperature-strain coupling coefficient, T is the current temperature, and T0 is the reference temperature.

[0019] Decompose the vibration frequency spectrum.

[0020] Perform filtering, denoising, and standardization processing on the temperature field data, and extract the temperature change rate.

[0021] Furthermore, for the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing, after inputting the strain distribution data, the vibration frequency spectrum, and the temperature field data into the health assessment model and outputting the health index of the tunnel support structure to be evaluated, it further includes:

[0022] Based on the health index and its change trend, determine whether the health status of the tunnel support structure to be evaluated is normal:

[0023] When the health index is higher than or equal to the safety threshold, no warning signal is triggered.

[0024] When the health index is lower than the safety threshold, trigger the warning signal and generate a damage location map.

[0025] Furthermore, the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing is characterized in that a distributed optical fiber sensing network is arranged on the surface of the tunnel support structure to be evaluated, including:

[0026] The distributed optical fiber sensing network is arranged on the surface of the tunnel support structure to be evaluated in a spiral winding manner; wherein, the relationship between the adjacent optical fiber ring spacing D and the diameter R of the tunnel to be evaluated is: D ≤ 0.2R.

[0027] Furthermore, the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing, based on the distributed optical fiber sensing network, real-time collects the strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated, including:

[0028] Based on the distributed optical fiber sensing network, the strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated are real-time collected by optical time domain reflectometry or optical frequency domain reflectometry.

[0029] Furthermore, the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing is characterized in that a health assessment model is constructed, including:

[0030] Construct a health assessment model according to the design parameters, construction process, material properties and historical monitoring data of the tunnel support structure to be evaluated.

[0031] Furthermore, the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing decomposes the vibration frequency spectrum, including:

[0032] Use the improved EMD algorithm to separate the characteristic frequencies in the 0.1Hz - 50Hz frequency band of the vibration frequency spectrum.

[0033] Furthermore, the real-time health assessment method of the tunnel support structure based on distributed optical fiber sensing, the warning signal includes:

[0034] The warning signal includes but is not limited to audible and visual alarms, SMS notifications and email notifications.

[0035] According to one aspect of the present invention, there is provided a real-time evaluation system for the health of a tunnel support structure based on distributed optical fiber sensing, comprising:

[0036] One or more distributed optical fiber sensors for sensing changes in strain, temperature or stress of the tunnel support structure;

[0037] A signal acquisition device for receiving the signals of the distributed optical fiber sensors and performing preliminary processing;

[0038] A data processing unit for analyzing the signals and calculating the health parameters of the tunnel support structure;

[0039] A health evaluation module for generating a real-time health evaluation result according to the health parameters;

[0040] An alarm module for emitting an alarm signal when the health evaluation result reaches a preset threshold;

[0041] A data storage and display module for storing the health evaluation result and performing visual display.

[0042] The present invention provides a real-time evaluation method for the health of a tunnel support structure based on distributed optical fiber sensing, comprising: arranging a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated; collecting in real time strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated based on the distributed optical fiber sensing network; constructing a health evaluation model; inputting the strain distribution data, vibration frequency spectrum and temperature field data into the health evaluation model, and outputting the health index of the tunnel support structure to be evaluated. Compared with the prior art, the present invention can realize the real-time evaluation of the health of the tunnel support structure, timely discover potential safety hazards, and improve work efficiency; the distributed optical fiber sensing network can comprehensively cover the key parts of the tunnel support structure, improving the comprehensiveness and accuracy of monitoring; the health evaluation model combines the design parameters, construction process, material properties and historical monitoring data of the tunnel support structure, and can more accurately evaluate the health status of the tunnel support structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. The drawings are only for the purpose of showing the embodiments and are not considered as a limitation to the present invention.

[0044] Figure 1 It is a schematic flow chart of a real-time evaluation method for the health of a tunnel support structure based on distributed optical fiber sensing in an embodiment of the present invention;

[0045] Figure 2Schematic diagram of another real-time evaluation method for the health of tunnel support structures based on distributed optical fiber sensing in the embodiments of the present invention;

[0046] Figure 3 Frame diagram of a real-time evaluation system for the health of tunnel support structures based on distributed optical fiber sensing in the embodiments of the present invention;

[0047] Figure 4 Structure diagram of a computer device in a real-time evaluation system for the health of tunnel support structures based on distributed optical fiber sensing in the embodiments of the present invention. Detailed implementation manners

[0048] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs; the terms used in the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above drawings are intended to cover non-exclusive inclusion.

[0050] In the description of the embodiments of the present invention, technical terms such as "first" and "second" are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present invention, the meaning of "a plurality of" is more than two, unless otherwise specifically defined.

[0051] In the description of the embodiments of the present invention, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0052] In the description of the embodiments of the present invention, the term "a plurality of" refers to more than two (including two). Similarly, "a plurality of groups" refers to more than two groups (including two groups), and "a plurality of pieces" refers to more than two pieces (including two pieces).

[0053] In the description of the embodiments of the present invention, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the embodiments of the present invention.

[0054] In the description of the embodiments of the present invention, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to the specific circumstances.

[0055] Embodiment 1

[0056] The embodiment of the present invention provides a real-time evaluation method for the health of a tunnel support structure based on distributed optical fiber sensing, such as Figure 1 As shown, including:

[0057] S101. Deploy a distributed fiber optic sensor network on the surface of the tunnel support structure to be evaluated.

[0058] Among them, tunnel support structure refers to the structural system used to support surrounding rock, maintain tunnel stability and prevent collapse during tunnel construction and operation. It is a key part of tunnel engineering and is directly related to the safety, stability and service life of the tunnel. Health monitoring of tunnel support structure is an important means to ensure the safe operation of the tunnel.

[0059] Distributed Fiber Optic Sensing Network (DFOSN) is an intelligent monitoring system that uses optical fiber as a continuous sensing medium and utilizes the light scattering effect to achieve full-space, real-time, and continuous physical quantity (such as strain, temperature, vibration, sound waves, etc.) perception and positioning. Its core feature is that it converts the entire optical fiber into a distributed sensor, which can achieve continuous measurement with centimeter-level spatial resolution within the length of the optical fiber without relying on discrete sensing units.

[0060] Specifically, before deploying the distributed optical fiber sensing network, it is necessary to understand the specific conditions of the tunnel support structure, including the length of the tunnel, cross-sectional shape, support form, and geological conditions, etc. Then, according to the specific conditions of the above tunnel support structure, design a reasonable deployment plan for the distributed optical fiber sensing network to ensure the comprehensiveness and accuracy of the monitoring data. It should be noted that: the deployment of the distributed optical fiber sensing network needs to be carried out strictly in accordance with the designed deployment plan to ensure the installation quality of the sensors. After the deployment of the distributed optical fiber sensing network is completed, it is necessary to debug and calibrate the distributed optical fiber sensing network to ensure the accuracy and reliability of the monitoring data.

[0061] S102. Real-time collect the strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated based on the distributed optical fiber sensing network.

[0062] Among them, the strain distribution data is a set of spatially continuous strain values continuously collected by the distributed optical fiber sensing network along the surface or inside of the measured structure (such as tunnel support, pipeline, bridge, etc.), which reflects the spatial distribution law of the mechanical response of the structure under the action of factors such as load, temperature, and deformation. Its core value lies in upgrading the traditional "point-type" strain measurement to "field-type" global perception. The strain distribution data is an important basis for evaluating the health status of the tunnel support structure. Through the distributed optical fiber sensing network, real-time and continuous monitoring of the strain distribution of the tunnel support structure can be achieved. By analyzing the strain distribution data, potential safety hazards can be detected in a timely manner, the health status of the structure can be evaluated, and a scientific basis can be provided for the safe operation of the tunnel support structure.

[0063] The vibration frequency spectrum is a frequency-energy distribution map obtained by performing Fourier transform or wavelet analysis on the vibration signal of the tunnel support structure, which is used to reveal the natural frequency, damping characteristics, external excitation frequency and frequency shift caused by damage of the tunnel support structure. The vibration frequency spectrum can identify the characteristic frequencies of dynamic events such as blasting shock, mechanical vibration, and surrounding rock loosening, and provide a highly sensitive criterion in the frequency domain dimension for the safety warning of the tunnel support structure. The vibration frequency spectrum is an important tool for analyzing vibration signals. By obtaining and analyzing the vibration frequency spectrum, the dynamic characteristics of the tunnel support structure can be deeply understood, and potential faults or abnormalities can be identified.

[0064] The temperature field data is a set of spatially continuous temperature values continuously collected by the distributed optical fiber sensing network along the surface or inside of the tunnel support structure, which reflects the temperature gradient distribution and thermodynamic state of the tunnel support structure caused by factors such as environmental heat sources, material heat conduction, and internal losses. Its core value lies in revealing the coupling relationship between temperature and structural mechanical behavior (such as thermal stress, material expansion), and providing a direct basis for leakage detection, fire warning, and energy loss assessment.

[0065] S103. Build a health assessment model:

[0066] H = f LSTM -Attention(X t |X t-1 ...X t-n )

[0067] Wherein, X t is the input feature vector at time t, including strain gradient, frequency offset, and temperature change rate.

[0068] Specifically, constructing a health assessment model is a systematic process involving multiple steps such as data collection, feature extraction, model selection, and model training.

[0069] S104. Input the strain distribution data, vibration frequency spectrum, and temperature field data into the health assessment model to output the health index of the tunnel support structure to be evaluated.

[0070] It should be noted here that for the detailed description of each step in this embodiment, reference can be made to other embodiments correspondingly, and details will not be elaborated here.

[0071] The embodiment of the present invention provides a real-time health assessment method for tunnel support structures based on distributed optical fiber sensing, including: arranging a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated; collecting the strain distribution data, vibration frequency spectrum, and temperature field data of the tunnel support structure to be evaluated in real time based on the distributed optical fiber sensing network; constructing a health assessment model; inputting the strain distribution data, vibration frequency spectrum, and temperature field data into the health assessment model to output the health index of the tunnel support structure to be evaluated. Compared with the prior art, the embodiment of the present invention can realize the real-time assessment of the health of the tunnel support structure, timely discover potential safety hazards, and improve work efficiency; the distributed optical fiber sensing network can comprehensively cover the key parts of the tunnel support structure, improving the comprehensiveness and accuracy of monitoring; the health assessment model combines the design parameters, construction process, material properties, and historical monitoring data of the tunnel support structure, and can more accurately evaluate the health status of the tunnel support structure.

[0072] Embodiment 2

[0073] The embodiment of the present invention provides a real-time health assessment method for tunnel support structures based on distributed optical fiber sensing, as Figure 2 shown, including:

[0074] S201. Arrange a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated.

[0075] Specifically, arrange the distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated in a spiral winding manner, wherein the relationship between the distance D between adjacent optical fiber rings and the diameter R of the tunnel to be evaluated is: D ≤ 0.2R.

[0076] Among them, φ-OFDR (Phase-Sensitive Optical Frequency Domain Reflectometry) distributed optical fiber is selected, with a spatial resolution of ≤1 m and a strain accuracy of ±2 με , and a temperature accuracy of ±0.1 °C. It should be noted here that: in key areas (such as fault zones and water seepage areas), the layout needs to be densified, for example: the spacing is ≤0.5 m.

[0077] S202. Based on the distributed optical fiber sensing network, the strain distribution data, vibration frequency spectrum, and temperature field data of the tunnel support structure to be evaluated are collected in real time.

[0078] Specifically, based on the distributed optical fiber sensing network, the strain distribution data, vibration frequency spectrum, and temperature field data of the tunnel support structure to be evaluated are collected in real time through optical time domain reflectometry or optical frequency domain reflectometry.

[0079] Among them, optical time domain reflectometry (OTDR) is a technology used to measure the optical signal transmission characteristics in an optical fiber link. By analyzing the propagation and reflection of optical pulses in the optical fiber, it can provide detailed information about the optical fiber link, such as optical fiber length, loss, splice location, break point, etc. Optical time domain reflectometry is an advanced optical fiber monitoring technology that can achieve real-time and continuous monitoring of optical fiber links and distributed optical fiber sensor networks. Through reasonable system design and signal processing methods, it can provide high-spatial-resolution monitoring data and provide reliable solutions for fields such as optical fiber communication, optical fiber sensor networks, and intelligent structure monitoring.

[0080] Optical frequency domain reflectometry (OFDR) is a high-precision optical fiber sensing technology used to measure the optical signal transmission characteristics in an optical fiber link. Compared with optical time domain reflectometry (OTDR), OFDR provides higher spatial resolution and measurement accuracy, and is especially suitable for scenarios that require high-precision monitoring.

[0081] S203. Preprocess the strain distribution data, the vibration frequency spectrum, and the temperature field data.

[0082] S2031. Perform data compensation on the strain distribution data:

[0083]

[0084] In the formula, α is the temperature-strain coupling coefficient, T is the current temperature, and T0 is the reference temperature.

[0085] S2032. Decompose the vibration frequency spectrum.

[0086] Specifically, the improved EMD algorithm is used to isolate the characteristic frequencies in the frequency band of 0.1 Hz - 50 Hz in the vibration frequency spectrum. Among them, Empirical Mode Decomposition (EMD) is an adaptive time-frequency analysis method widely used in the field of signal processing. The EMD algorithm can decompose complex signals into several Intrinsic Mode Functions (IMFs), thus revealing the internal characteristics of the signals. However, there are some problems with the traditional EMD algorithm, such as endpoint effects, mode mixing, and low computational efficiency. To overcome these problems, researchers have proposed a variety of improved EMD algorithms:

[0087] The first one: EEMD (Ensemble Empirical Mode Decomposition) is an improved EMD algorithm. By adding white noise to the original signal, repeating the EMD decomposition multiple times, and then taking the average value, it can reduce mode mixing and improve the stability of the decomposition.

[0088] The second one: CEEMD (Complete Ensemble Empirical Mode Decomposition) is a further improvement of EEMD. By considering the positive and negative symmetry when adding white noise, it can further reduce mode mixing and improve the accuracy of the decomposition.

[0089] The third one: The improvement of the endpoint effect of EMD is to perform mirror extension at both ends of the signal, making the signal transition smoothly at both ends, and performing polynomial fitting at both ends of the signal to smooth the endpoints of the signal.

[0090] The fourth one: The improvement of the adaptive filtering of EMD uses adaptive filtering methods, such as wavelet transform or adaptive filters, which can effectively remove noise and improve computational efficiency.

[0091] The improved EMD algorithm overcomes the deficiencies of the traditional EMD algorithm through various methods, such as endpoint effects, mode mixing, and low computational efficiency. EEMD and CEEMD effectively reduce mode mixing and improve the stability and accuracy of the decomposition by adding white noise and positive and negative symmetric noise. The improvement method of the endpoint effect reduces endpoint errors and improves the accuracy of the decomposition result through mirror extension or polynomial fitting. The adaptive filtering method improves computational efficiency, removes noise, and improves the accuracy of the decomposition result through wavelet transform or adaptive filters. These improvement methods perform well in practical applications and are suitable for the analysis and processing of various complex signals.

[0092] S2033. Filter, denoise, and standardize the temperature field data, and extract the temperature change rate.

[0093] Among them, by filtering, denoising, and normalizing the temperature field data, the quality and reliability of the data can be effectively improved. Extracting the temperature change rate can further analyze the dynamic change of temperature and provide important features for subsequent health assessment.

[0094] Specifically, the purpose of filtering is to remove high-frequency noise in the signal and retain useful low-frequency signals. Common filtering methods include low-pass filters, high-pass filters, and band-pass filters. The purpose of denoising is to remove random noise in the signal and improve the signal-to-noise ratio. Common methods include wavelet denoising and Kalman filtering. The purpose of normalization is to convert the data to a unified scale for subsequent analysis. Common methods include normalization and Z-score normalization.

[0095] S204. Construct a health assessment model:

[0096] H = f LSTM -Attention(X t |X t-1 ...X t-n )

[0097] In the formula, X t is the input feature vector at time t, including strain gradient, frequency offset, and temperature change rate.

[0098] Specifically, constructing a health assessment model based on the design parameters, construction process, material properties, and historical monitoring data of the tunnel support structure to be evaluated is divided into the following steps:

[0099] (1) Data collection and collation: Collect design parameters (such as structural form, material parameters, and design standards, etc.), construction process (such as construction method, construction quality, and construction records, etc.), material properties (such as material strength, material durability, and material aging characteristics), and historical monitoring data (such as strain data, vibration data, and temperature data).

[0100] (2) Feature extraction and selection: Extract useful features from the collected data, and these features will be used as the input of the health assessment model. Common features include: strain gradient, frequency offset, temperature change rate, material property indicators, and construction quality indicators, etc. Select the features with the strongest correlation with health to improve the accuracy and efficiency of the model. Methods such as correlation analysis and principal component analysis (PCA) can be used for feature selection.

[0101] (3) Construction of the health assessment model: Data-driven methods construct an assessment model by learning patterns in historical data. Common methods include: support vector machines, neural networks, random forests, and deep learning.

[0102] (4) Model training and validation: Use historical data to train the health assessment model, and adjust the model parameters to improve the accuracy and generalization ability of the model. Use independent test data to verify the accuracy and generalization ability of the model to ensure its reliability in practical applications.

[0103] S205. Input the strain distribution data, vibration frequency spectrum, and temperature field data into the health assessment model to output the health index of the tunnel support structure to be evaluated.

[0104] Among them, the health index (HI) is a quantitative indicator used to evaluate the current health status of the tunnel support structure. It provides a standardized value by comprehensively considering multiple key parameters (such as strain distribution, vibration frequency spectrum, and temperature field, etc.) to reflect the health status of the structure.

[0105] S206. According to the health index and its change trend, judge whether the health status of the tunnel support structure to be evaluated is normal:

[0106] S2061. When the health index is higher than or equal to the safety threshold, no warning signal is triggered.

[0107] S2062. When the health index is lower than the safety threshold, trigger a warning signal and generate a damage location map.

[0108] Among them, the safety threshold is a key indicator used to judge whether the tunnel support structure is in a safe state. When the health index is higher than or equal to the safety threshold, the tunnel support structure is generally considered to be in a safe state; while when the health index is lower than the safety threshold, it may indicate potential safety hazards and corresponding measures need to be taken. Specifically, the setting of the safety threshold is usually based on the following aspects: design standards, historical data, risk assessment, industry experience, and expert opinions, etc.

[0109] Among them, the warning signal is an important means to notify relevant personnel of potential risks or abnormal situations. The form of the warning signal can be various to ensure that the information can be conveyed to relevant personnel in a timely and accurate manner. The warning signal includes but is not limited to audible and visual alarms, SMS notifications, and email notifications. Specifically:

[0110] (1) Audible and visual alarm: Remind relevant personnel of potential dangers or abnormal situations through the combination of sound and light, which has real-time and intuitiveness.

[0111] (2) SMS notification: Send the warning information to the mobile phones of relevant personnel by sending text messages, which has convenience and wide coverage.

[0112] (3) Email notification: The early warning information is sent to the email boxes of relevant personnel by sending emails, which has the characteristics of detail and recordability.

[0113] Among them, the Damage Locating Map is a tool for visualizing and locating structural damage. It combines strain distribution data, vibration frequency spectra, and temperature field data with the geometric model of the tunnel support structure to generate a map that intuitively shows the location and degree of damage.

[0114] It should be noted here that: For the detailed description of each step of this embodiment, reference can be made to other embodiments correspondingly, and it will not be elaborated here.

[0115] The present invention provides a real-time health assessment system for tunnel support structures based on distributed optical fiber sensing, including:

[0116] One or more distributed optical fiber sensors for sensing changes in strain, temperature, or stress of the tunnel support structure;

[0117] A signal acquisition device for receiving the signals of the distributed optical fiber sensors and performing preliminary processing;

[0118] A data processing unit for analyzing the signals and calculating the health parameters of the tunnel support structure;

[0119] A health assessment module for generating a real-time health assessment result based on the health parameters;

[0120] An alarm module for sending an alarm signal when the health assessment result reaches a preset threshold;

[0121] A data storage and display module for storing the health assessment result and performing visual display.

[0122] In one embodiment, the purpose of this system is to monitor the health status of the tunnel support structure in real time through distributed optical fiber sensing technology, evaluate its safety, and prevent potential structural failure risks. The system consists of a sensor network, a data acquisition and transmission module, a data processing and analysis module, a health assessment model, and a real-time monitoring and alarm system.

[0123] Sensor selection:

[0124] A combination of distributed fiber Bragg grating sensors (FBG) and distributed temperature sensors (DTS) is adopted. FBG is used to monitor the strain change of the support structure, and DTS is used to monitor the temperature change. FBG sensors have the characteristics of high precision and strong anti-interference ability, and are suitable for monitoring the small strain changes of the support structure; DTS sensors can provide continuous temperature distribution information to help identify potential heat sources or abnormal temperature changes.

[0125] Sensor arrangement:

[0126] Sensors are arranged at key positions of the tunnel support structure, including the crown, side walls, invert, etc. Each group of sensors covers a certain length of the support structure to ensure the comprehensiveness of the monitoring range. The spacing between sensors is determined according to the size of the tunnel and the design requirements of the support structure, generally ranging from 0.5 meters to 1 meter.

[0127] Data acquisition module:

[0128] The data acquisition module is responsible for obtaining signals from fiber optic sensors and converting them into processable electrical signals. High-precision optical signal demodulation equipment is used to ensure the accuracy and stability of signal acquisition.

[0129] Data transmission:

[0130] Data is transmitted to the data processing center through optical fibers. Optical fiber communication technology is adopted during the transmission process to ensure the high speed and high reliability of data transmission. At the same time, the system supports wireless transmission as a backup solution to cope with the situation of optical fiber communication interruption.

[0131] Data preprocessing:

[0132] The raw data collected is preprocessed, including operations such as denoising and filtering, to eliminate the influence of environmental noise and interference signals and improve the data quality.

[0133] Feature extraction:

[0134] Feature parameters related to the health of the support structure, such as strain change rate, temperature gradient, vibration frequency, etc., are extracted from the preprocessed data. These feature parameters can reflect the mechanical state and thermodynamic state of the support structure.

[0135] Data fusion:

[0136] Data from different types of sensors is fused, combining various information such as strain, temperature, and vibration to improve the comprehensiveness and accuracy of health assessment.

[0137] Evaluation indicators:

[0138] Health assessment indicators include the strain distribution uniformity of the support structure, the degree of temperature anomaly, the vibration frequency change rate, etc. These indicators can comprehensively reflect the health state of the support structure.

[0139] Model establishment:

[0140] Adopt machine learning methods such as Support Vector Machine (SVM), Artificial Neural Network (ANN), etc. to establish a health assessment model. The model training is based on historical monitoring data and manually labeled health status data to ensure the accuracy and reliability of the assessment.

[0141] Real-time assessment:

[0142] According to the feature parameters collected in real time, calculate the health score of the support structure through the health assessment model. The score range is from 0 to 100, and the lower the score, the worse the structural health.

[0143] Monitoring interface:

[0144] Develop an intuitive monitoring interface to display in real time information such as the health score of the support structure, the change trend of feature parameters, and the sensor status. The interface supports multi-dimensional data visualization, facilitating operators to quickly grasp the structural status.

[0145] Alarm system:

[0146] When the health score is lower than the preset threshold (such as 70 points), the system automatically triggers the alarm mechanism. The alarm information is sent to relevant personnel through various methods such as audible and visual alarms, text message notifications, and email notifications to ensure timely response measures are taken.

[0147] Hardware framework:

[0148] Sensor network: Distributed Fiber Bragg Grating Sensors (FBG) and Distributed Temperature Sensors (DTS)

[0149] Data acquisition module: High-precision optical signal demodulation equipment

[0150] Data transmission module: Optical fiber communication equipment and wireless transmission equipment

[0151] Data processing and storage equipment: High-performance servers and database systems

[0152] Monitoring and alarm equipment: Display terminals and alarm devices

[0153] Software framework:

[0154] Data acquisition software: Responsible for the acquisition and preliminary processing of sensor signals

[0155] Data processing and analysis software: Includes functional modules such as data preprocessing, feature extraction, and data fusion. Health assessment software: Health assessment model based on machine learning

[0156] Real-time monitoring and alarm software: Provides an intuitive monitoring interface and alarm function

[0157] System design:

[0158] According to the scale of the tunnel and the characteristics of the support structure, design the sensor layout plan, data acquisition and transmission plan, data processing and analysis plan, and health assessment model.

[0159] Sensor installation:

[0160] Install fiber optic sensors at key parts of the tunnel support structure to ensure the stability of the sensors and the comprehensiveness of the monitoring range.

[0161] System integration:

[0162] Integrate the hardware devices and software systems to ensure the collaborative work among modules. Conduct system debugging to optimize the data acquisition, processing, and evaluation processes.

[0163] System testing:

[0164] Conduct system testing in the actual tunnel environment to verify the accuracy and reliability of the system. Collect test data to optimize the health assessment model.

[0165] System operation and maintenance:

[0166] After the system is put into operation, conduct regular maintenance and updates to ensure the long-term stable operation of the system. According to the actual operation data, further optimize the health assessment model and system functions.

[0167] Sensor parameters:

[0168] Fiber Bragg Grating sensor (FBG): Measurement range: -1000 to +1000 microstrain; Resolution: 0.1 microstrain; Sampling frequency: 1Hz

[0169] Distributed Temperature Sensor (DTS): Measurement range: -50 to +150 °C; Resolution: 0.1 °C; Sampling frequency: 1Hz;

[0170] Data processing parameters:

[0171] Data acquisition frequency: 1Hz;

[0172] Data transmission rate: 100Mbps;

[0173] Data storage capacity: 1TB, support for expansion;

[0174] Data processing delay: less than 1 second;

[0175] Health assessment parameters:

[0176] Health score range: 0 to 100 points;

[0177] Alarm threshold: 70 points;

[0178] Evaluation period: Real-time evaluation, update frequency 1Hz.

[0179] An embodiment of the present invention provides a method for real-time evaluation of the health of a tunnel support structure based on distributed optical fiber sensing, including: arranging a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated; collecting strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated in real time based on the distributed optical fiber sensing network; constructing a health evaluation model; inputting the strain distribution data, vibration frequency spectrum and temperature field data into the health evaluation model, and outputting the health index of the tunnel support structure to be evaluated. Compared with the prior art, the embodiment of the present invention can realize the real-time evaluation of the health of the tunnel support structure, timely discover potential safety hazards, and improve work efficiency; the distributed optical fiber sensing network can comprehensively cover the key parts of the tunnel support structure, improving the comprehensiveness and accuracy of monitoring; the health evaluation model combines the design parameters, construction process, material properties and historical monitoring data of the tunnel support structure, and can more accurately evaluate the health status of the tunnel support structure.

[0180] At the same time, the embodiment of the present invention preprocesses the strain distribution data, vibration frequency spectrum and temperature field data, improves the quality and reliability of the data, and further improves the accuracy of health evaluation.

[0181] In addition, the embodiment of the present invention judges whether the health status of the tunnel support structure to be evaluated is normal according to the health index and its change trend. When the health index is lower than the safety threshold, a warning signal is triggered and a damage location map is generated. It can timely issue a warning signal according to the value and change trend of the health index, remind relevant personnel to take measures, effectively prevent the occurrence of safety accidents of the tunnel support structure, and ensure the safe operation of the tunnel.

[0182] The present invention also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it realizes the steps of the above-mentioned method for real-time evaluation of the health of a tunnel support structure based on distributed optical fiber sensing.

[0183] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes the steps of the above-mentioned method for real-time evaluation of the health of a tunnel support structure based on distributed optical fiber sensing.

[0184] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in this application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be obtained in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0185] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention. In particular, as long as there is no structural conflict, the technical features mentioned in each embodiment can be combined in any way. The present invention is not limited to the specific embodiments disclosed in the text, but includes all technical solutions falling within the scope of the claims.

Claims

1. A real-time evaluation method for the health of tunnel support structures based on distributed optical fiber sensing, characterized in that Including: Deploy a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated; Based on the distributed optical fiber sensing network, collect the strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated in real time; Construct a health assessment model: H = f LSTM - Attention(X t | X t-1 ... X t-n ) where X t is the input feature vector at time t, including the strain gradient, the frequency offset, and the temperature change rate; Input the strain distribution data, the vibration frequency spectrum and the temperature field data into the health assessment model, and output the health index of the tunnel support structure to be evaluated.

2. The real-time evaluation method for the health degree of a tunnel support structure based on distributed optical fiber sensing according to claim 1, characterized in that After collecting the strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated in real time through the distributed optical fiber sensing network, it further includes: Preprocess the strain distribution data, the vibration frequency spectrum and the temperature field data.

3. The real-time evaluation method for the health degree of a tunnel support structure based on distributed optical fiber sensing according to claim 2, characterized in that, Preprocessing the strain distribution data, the vibration frequency spectrum and the temperature field data includes: Perform data compensation on the strain distribution data: where α is the temperature-strain coupling coefficient, T is the current temperature, and T0 is the reference temperature; Decompose the vibration frequency spectrum; Perform filtering, denoising and normalization processing on the temperature field data, and extract the temperature change rate.

4. The real-time evaluation method for the health of a tunnel support structure based on distributed optical fiber sensing according to claim 1, characterized in that After inputting the strain distribution data, the vibration frequency spectrum and the temperature field data into the health assessment model and outputting the health index of the tunnel support structure to be evaluated, it further includes: Judge whether the health condition of the tunnel support structure to be evaluated is normal according to the health index and its change trend: When the health index is higher than or equal to the safety threshold, no warning signal is triggered; When the health index is lower than the safety threshold, trigger the warning signal and generate a damage location map.

5. The real-time evaluation method for the health degree of a tunnel support structure based on distributed optical fiber sensing according to claim 1, characterized in that Deploying a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated includes: Deploy a distributed optical fiber sensing network on the surface of the tunnel support structure to be evaluated in a spiral winding manner; wherein, the relationship between the adjacent optical fiber ring spacing D and the diameter R of the tunnel to be evaluated is: D ≤ 0.2R.

6. The real-time evaluation method for the health of a tunnel support structure based on distributed optical fiber sensing according to claim 1, characterized in that Based on the distributed optical fiber sensing network, collecting the strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated in real time includes: Based on the distributed optical fiber sensing network, collect the strain distribution data, vibration frequency spectrum and temperature field data of the tunnel support structure to be evaluated in real time through optical time domain reflectometry or optical frequency domain reflectometry.

7. The real-time evaluation method for the health degree of the tunnel support structure based on distributed optical fiber sensing according to claim 1, wherein, Constructing a health assessment model includes: Construct a health assessment model according to the design parameters, construction process, material properties and historical monitoring data of the tunnel support structure to be evaluated.

8. The real-time evaluation method for the health degree of the tunnel support structure based on distributed optical fiber sensing according to claim 3, characterized in that Decomposing the vibration frequency spectrum includes: Use the improved EMD algorithm to separate the characteristic frequencies in the frequency band of 0.1 Hz - 50 Hz in the vibration frequency spectrum.

9. The real-time evaluation method for the health degree of a tunnel support structure based on distributed optical fiber sensing according to claim 4, characterized in that The warning signal includes: The warning signal includes but is not limited to audible and visual alarms, SMS notifications and email notifications.

10. A real-time evaluation system for the health of a tunnel support structure based on distributed optical fiber sensing, characterized in that, Including: One or more distributed optical fiber sensors for sensing changes in strain, temperature or stress of the tunnel support structure; A signal acquisition device for receiving the signals of the distributed optical fiber sensors and performing preliminary processing; A data processing unit for analyzing the signals and calculating the health parameters of the tunnel support structure; A health assessment module for generating a real-time health assessment result based on the health parameter; An alarm module for emitting an alarm signal when the health assessment result reaches a preset threshold; A data storage and display module for storing the health assessment result and visualizing it.

Images