A discrete-time-based underground anti-seepage structure leakage monitoring method and system

Abstract

The application discloses a discrete-time-based underground anti-seepage structure leakage monitoring method and system, relates to leakage detection, and comprises the following steps: collecting transient electromagnetic response data generated by an excitation signal; according to initial conductivity parameters and electrode position parameters of a monitoring area, a three-dimensional geophysical model of the monitoring area is established through a full-waveform inversion algorithm; electromagnetic anomaly data are obtained by using a finite element forward algorithm; according to temperature data, a distributed temperature field analysis method is used to calculate the spatial gradient and time change rate of temperature, and temperature anomaly data are obtained; according to pressure data, pressure anomaly data are determined according to the time sequence change characteristics of the pressure data; the electromagnetic anomaly data, the temperature anomaly data and the pressure anomaly data are fused by using a Bayesian algorithm to obtain fusion data; and the fusion data are input into a pre-trained machine learning model to obtain a leakage detection result. The application improves the dynamic monitoring precision in view of the low dynamic leakage monitoring precision of the underground anti-seepage structure.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of leakage detection, in particular to a discrete-time-based underground anti-seepage structure leakage monitoring method and system. BACKGROUND

[0002] With the acceleration of urbanization and the deepening of underground space development, underground anti-seepage structures have become a key component of modern construction engineering. According to statistics, the carbonation rate of concrete in building structures below the groundwater level increases by 300% due to leakage, and the risk of steel corrosion increases by 47%. Taking a typical deep foundation pit project as an example, when the depth of the underground continuous wall exceeds 30 meters, the leakage probability at the joint of the waterproof structure is as high as 18.6%, which seriously threatens the safety and durability of the structure. Therefore, it is of great significance to conduct high-precision dynamic leakage monitoring of underground anti-seepage structures.

[0003] However, the existing underground anti-seepage structure leakage monitoring technology has serious deficiencies in dynamic monitoring accuracy. The traditional natural potential method needs to re-deploy electrodes every time detection is performed, cannot achieve continuous dynamic monitoring, and has low sensitivity to small leaks, with a detection accuracy of only about 70%. Although the tracer method can locate the leakage path, it requires drilling and injecting tracers outside the anti-seepage structure, and can only detect large-scale leaks, and cannot capture the dynamic development process of the leak. More importantly, the existing technology lacks effective multi-source data fusion mechanisms: (1) Single physical field detection methods are easily disturbed by the environment, resulting in a false positive rate as high as 15-20%; (2) It is impossible to achieve simultaneous collection and comprehensive analysis of multi-physical field data such as electromagnetic field, temperature field, and pressure field; (3) Lack of dynamic data processing framework based on discrete time window, making it difficult to accurately extract abnormal features caused by leakage; (4) No effective background field separation mechanism is established, which cannot distinguish the signal difference between normal and leakage states. These problems result in the inability of existing technology to meet the high-precision, real-time dynamic monitoring needs of underground anti-seepage structures throughout their life cycle. SUMMARY

[0004] In view of the low dynamic leakage monitoring accuracy of underground anti-seepage structures, the present application provides a discrete-time-based underground anti-seepage structure leakage monitoring method and system, which actively detects and collects response data using a transient electromagnetic excitation source, and extracts electromagnetic anomalies, pressure and temperature anomaly data based on discrete time windows, and performs multi-source fusion, etc., thereby improving the dynamic monitoring accuracy.

[0005] One aspect of the present application provides a discrete-time-based underground anti-seepage structure leakage monitoring method, comprising: S1, collecting underground anti-seepage structure data including current data, temperature data and pressure data through a sensor array; S2, sending an excitation signal to the monitoring area through a signal excitation source, and collecting transient electromagnetic response data generated by the excitation signal through the sensor array; S3, setting a discrete time window, constructing a space-time data matrix according to the spatial coordinates and data collection time stamps of each sensor in the sensor array; performing space-time alignment on the underground anti-seepage structure data and the transient electromagnetic response data based on the space-time data matrix; S4, establishing a three-dimensional geophysical model of the monitoring area through a full waveform inversion algorithm according to the initial conductivity parameter and the electrode position parameter of the monitoring area; modeling the background field of the transient electromagnetic response data after S3 space-time alignment using a finite element forward algorithm based on the three-dimensional geophysical model, to obtain the background electromagnetic field distribution under the no-leakage state; performing difference operation on the transient electromagnetic response data after S3 space-time alignment and the background electromagnetic field distribution to obtain electromagnetic anomaly data; S5, calculating the spatial gradient and time change rate of temperature using a distributed temperature field analysis method according to the temperature data in the underground anti-seepage structure data after S3 space-time alignment, to obtain temperature anomaly data; S6, analyzing the pressure data in the underground anti-seepage structure data after S3 space-time alignment, and determining pressure anomaly data according to the time sequence variation characteristics of the pressure data; S7, fusing the electromagnetic anomaly data, the temperature anomaly data and the pressure anomaly data using a Bayesian algorithm to obtain fusion data; S8, inputting the fusion data into a pre-trained machine learning model to obtain a leakage detection result, wherein the leakage detection result includes a leakage probability, a leakage position and a leakage level.

[0006] In the present application, the underground anti-seepage structure refers to a structure system in underground engineering for preventing groundwater from permeating, including underground continuous wall, waterproof concrete structure, water stop curtain, impermeable membrane, etc. These structures are usually built with low-permeability materials, and their integrity is directly related to the safety of underground engineering. The monitoring object of the present scheme is the leakage defects that may occur in such anti-seepage structures.

[0007] The transient electromagnetic response data refers to the time-varying electromagnetic field response signal generated by the underground medium under the action of the excitation signal. When the bipolar square wave excitation signal is suddenly turned off, the induced eddy current in the underground conductive medium does not immediately disappear, but decays exponentially, and the secondary electromagnetic field generated by this decay process is the transient response.

[0008] The conductivity parameter represents the physical parameter of the material's conductivity, with the unit of Siemens per meter (S / m). In the present application, the initial conductivity parameter is the initial estimation of the electrical conductivity of each stratum in the monitoring area based on geological survey data, and the typical range is 0.01-0.1 S / m. Leakage will change the local electrical conductivity, so accurate modeling of the electrical conductivity distribution is the basis for leakage detection.

[0009] The electrode position parameter refers to the three-dimensional spatial coordinates of the power supply electrodes and the measurement electrodes arranged in the monitoring area and the electrode spacing information. In the present application, the electrodes are arranged in a matrix manner for exciting current and collecting potential response. Accurate determination of the electrode position (with an accuracy better than 0.1 m) is a prerequisite for ensuring the inversion accuracy.

[0010] The full waveform inversion algorithm is a geophysical inversion method that optimizes the theoretical model response and the measured waveform data to achieve the best fitting through iteration. In the present application, the algorithm simultaneously uses DC and AC data to invert the three-dimensional electrical conductivity distribution model by minimizing the objective function to provide a background model for identifying leakage anomalies.

[0011] The three-dimensional geophysical model describes the mathematical model of the spatial distribution of the physical properties of the underground medium in the monitoring area. In the present application, the model contains the three-dimensional distribution information of the electrical conductivity , the dielectric constant ε, and the magnetic permeability μ, and is discretely expressed through finite element meshing, which is the basis for numerical simulation of electromagnetic fields.

[0012] The finite element forward algorithm is a numerical calculation method for simulating the propagation of electromagnetic fields in complex media based on the finite element method for solving Maxwell's equations. In the present application, the algorithm calculates the electromagnetic field distribution under the action of the excitation signal according to the three-dimensional geophysical model to obtain the background field without leakage, which provides a reference benchmark for anomaly identification.

[0013] Further, S2 sends an excitation signal to the monitoring area through a signal excitation source and collects transient electromagnetic response data generated by the excitation signal through a sensor array, including: generating a bipolar square wave excitation signal; the bipolar square wave excitation signal is a square wave current signal with alternating positive and negative polarities. In the present application, the amplitude range is 0-±1000 V, the pulse width is adjustable from 0.1 ms to 1000 ms, and the frequency is set according to the detection depth requirement. The bipolar design can eliminate the effects of direct current bias and electrode polarization, and the wide frequency spectrum characteristics of the square wave are beneficial to simultaneously obtaining geoelectric information at different depths. According to the geological conditions of the monitoring area and the monitoring depth requirement, the frequency parameter of the bipolar square wave excitation signal is adjusted; a multi-channel parallel excitation mode is adopted to send the bipolar square wave excitation signal to multiple monitoring areas;

[0014] The transient electromagnetic response data of each monitoring area is collected by the sensor array, and the transient electromagnetic response data includes natural potential baseline DC data and transient response AC data. The natural potential baseline DC data is the steady-state natural potential distribution measured without applying artificial excitation, and reflects the static electric field characteristics of the underground medium. In this application, the DC data amplitude range is usually -100 mV to +100 mV, mainly generated by natural processes such as groundwater flow, oxidation-reduction reaction, and can be used to identify existing stable leakage channels. The transient response AC data is the secondary field signal measured after the excitation signal is turned off, which decays with time. In this application, the effective time window of AC data is 0.1 ms-100 ms, and the peak value can reach 200 mV. This data contains the electrical structure information of the underground medium, and is particularly sensitive to new leaks and dynamic changes in the leakage process, and is the core observation quantity of the transient electromagnetic method.

[0015] In particular, the conventional passive electrical method monitoring can only rely on the weak change of the natural electric field to judge the leakage, and the signal strength is low, easy to be disturbed, and the positioning accuracy is poor. The active excitation technology applies a controllable electromagnetic excitation signal to generate a primary field with sufficient strength, and when the primary field propagates in the underground medium, a secondary induced field is generated due to the electrical difference of the medium, and the underground anomaly body can be accurately detected by analyzing the total field response characteristics. The bipolar square wave as the excitation signal has unique advantages: the positive and negative pulses alternate to eliminate direct current bias and polarization effect, and the wide frequency spectrum characteristics of the square wave can simultaneously excite multiple frequency components, which is beneficial to obtain geoelectric information at different depths. This active detection mode improves the signal-to-noise ratio by 1-2 orders of magnitude, greatly improving the detection sensitivity and spatial resolution.

[0016] In this application, on the one hand, the frequency parameters of the bipolar square wave are flexibly adjusted to realize accurate control of the detection depth: low-frequency signals (0.1-10 Hz) have stronger penetration ability and can detect deep leaks (>30 m), while high-frequency signals (10-1000 Hz) have high resolution but fast decay, which is suitable for shallow fine detection (<10 m). This adaptive frequency adjustment based on geological conditions and monitoring needs ensures effective detection of leaks at different depths; on the other hand, a multi-channel parallel excitation mode is innovatively adopted, which breaks through the efficiency bottleneck of traditional single-point excitation: multiple excitation sources work simultaneously but use different coding modulation (such as orthogonal code division), and the receiving end can separate the responses of each channel through decoding, realizing synchronous monitoring of multiple areas without increasing the measurement time, and improving the monitoring efficiency by 4-8 times. Especially important is that the system simultaneously collects natural potential baseline DC data and transient response AC data, the DC data reflects the steady-state electric field distribution and can identify existing leakage channels, and the AC data contains dynamic information of the transient process and is extremely sensitive to new leaks and leakage development, and the combination of the two realizes complete monitoring of the whole life cycle of the leakage, providing rich raw data for subsequent full-waveform inversion and anomaly identification.

[0017] Furthermore, the amplitude range of the bipolar square wave excitation signal is 0-±1000V, and the pulse width range is 0.1ms-1000ms.

[0018] Further, S3, constructs a spatiotemporal data matrix; performs spatiotemporal alignment of underground anti-seepage structure data and transient electromagnetic response data based on the spatiotemporal data matrix, including: setting a discrete time window The time interval is 10s to 24h. Through time slicing, the continuous data stream is divided into discrete time segments. The discrete time segments are used as the basic time units for data fusion. According to the three-dimensional spatial coordinates of each sensor, and the data acquisition timestamp t, constructing a four-dimensional spatiotemporal data matrix , used to store the measurement values ​​of each sensor in each discrete time segment; for sensor data with different sampling frequencies, discrete time windows are used Based on the spatiotemporal data matrix, the sensor data are synchronized to the same time node through the interpolation algorithm; the time-synchronized sensor data are spatially aligned to obtain spatiotemporal aligned data. , the underground anti-seepage structure data and transient electromagnetic response data after time synchronization are converted into the corresponding spatial coordinates The time node t is mapped to the corresponding position of the spatiotemporal data matrix to achieve unified alignment of data in the time dimension and space dimension, and obtain spatiotemporal aligned data.

[0019] Further, S4, based on the initial conductivity parameters and electrode position parameters, a three-dimensional geophysical model of the monitoring area is established by full waveform inversion algorithm; the initial conductivity parameters of the monitoring area are obtained. , initial conductivity parameters Based on geological survey data, the typical value range is 0.01S / m-0.1S / m; for multi-layer geological structures, the initial conductivity value of each layer is set layer by layer; the electrode position parameters are obtained, including the three-dimensional spatial coordinates of the electrode and electrode spacing d, the electrodes are arranged in an m×n matrix with a spacing of d=2m-10m.

[0020] Extracting spontaneous potential baseline DC data from spatiotemporally aligned data and transient response AC data The DC data is low-pass filtered (cut-off frequency 1Hz) to eliminate high-frequency noise; the AC data is time-windowed to retain the effective attenuation segment of 0.1ms-100ms after the excitation signal is turned off; in particular, the conductivity distribution of the underground anti-seepage structure reflects the physical state of the medium. The full waveform inversion algorithm can reconstruct the true three-dimensional spatial distribution of the conductivity of the underground medium by simultaneously utilizing the natural potential baseline (DC) and transient response (AC) data. This method is based on the propagation law of electromagnetic field in conductive medium, and the medium parameters are obtained by solving the inverse problem. Unlike the traditional assumption of homogeneous medium, the non-uniformity of underground medium is considered in the application, which provides a reliable reference benchmark for subsequent anomaly identification.

[0021] The objective function is established: Wherein, is the measured data, is the model response, and λ is the regularization parameter (0.01-0.1); the conjugate gradient method is used for iterative optimization, and the iterative step size is adaptively adjusted: Wherein, k is the iteration number; when the relative change of the objective function of the adjacent two iterations is less than or the iteration number reaches 100, stop; output the three-dimensional conductivity distribution model , the spatial resolution reaches 0.5m×0.5m×0.5m;

[0022] Based on , tetrahedral elements are used for finite element meshing of the monitoring area, and the mesh size is adaptively adjusted according to the conductivity gradient: Wherein, represents the minimum mesh size allowed in meshing, h represents the local mesh size, represents the modulus value of the conductivity gradient vector; represents the maximum value of the conductivity gradient modulus in the monitoring area; the Maxwell equation set is solved in time domain: , Wherein, the conductivity term is introduced, E represents the electric field intensity, B represents the magnetic induction intensity, H represents the magnetic field intensity, D represents the electric displacement, and J represents the current density; the boundary conditions are set: the far-field boundary adopts the absorbing boundary condition, and the ground surface adopts the air-ground interface condition; a complete three-dimensional geophysical model containing the spatial distribution of conductivity σ, the distribution of dielectric constant ε and the distribution of magnetic permeability μ is established;

[0023] The excitation signal parameters are input: bipolar square wave, amplitude A, pulse width τ, frequency f; the finite element forward algorithm is used to solve the electromagnetic field propagation equation at each time step ; considering the reflection and refraction effect of the stratum interface, the interface continuity condition is used to process the multi-layer medium; the background electromagnetic field under the condition of no leakage is calculated, including the three components of electric field ; the measured transient electromagnetic response data and the background electromagnetic field are point-by-point differentiated: ;

[0024] In particular, the background electromagnetic field in the case of no leakage is calculated by a finite element forward algorithm , which contains the influence of normal geological structure on electromagnetic field. When leakage occurs, the leakage channel changes the local conductivity, generating additional abnormal electromagnetic field. The present application eliminates the "false anomaly" caused by geological structure, such as stratigraphic interface, fault, etc. natural electrical difference; improves the identification ability of weak leakage signal, even if the abnormal signal only accounts for 5%-10% of the total signal; realizes quantitative anomaly evaluation, directly obtains the amount of electromagnetic field change caused by leakage.

[0025] In addition, when solving the time-domain Maxwell equations by finite element method, the complete physical process of electromagnetic field is considered: the propagation of primary field in medium produced by excitation source; the secondary field response caused by medium conductivity difference; eddy current effect and diffusion process in transient process. This physical mechanism-based forward simulation more accurately describes the distribution characteristics of electromagnetic field in complex underground environment than empirical formula or simplified model, providing a high-fidelity background field model.

[0026] Finally, the present application, through the difference between the spatio-temporally aligned data and the accurate background field model, captures the dynamic process of leakage development, distinguishes transient interference and persistent anomaly, and the traditional method can only detect static anomaly at a certain moment, while the present application achieves dynamic monitoring of four-dimensional spatio-temporal anomaly.

[0027] Further, S5, obtaining temperature anomaly data, comprising: calculating the temperature spatial gradient of each monitoring point according to the temperature data in the spatio-temporally aligned data ; calculating the temperature time change rate of each monitoring point; marking the corresponding monitoring point as a temperature spatial anomaly point when the temperature spatial gradient modulus of the monitoring point is greater than a preset gradient threshold; marking the corresponding monitoring point as a temperature time-varying anomaly point when the temperature time change rate of the monitoring point is greater than a preset temperature rise threshold; according to the physical mechanism of local heat transfer anomaly caused by groundwater leakage, analyzing the temperature field distribution by solving the heat conduction equation to verify whether the temperature spatial anomaly point and the temperature identification anomaly point conform to the temperature field change characteristics caused by leakage; wherein the heat conduction equation is solved by: where, is the density, c is the specific heat capacity, k is the thermal conductivity, and q is the heat source term (introduced by leakage). Determine whether the detected anomaly conforms to the thermodynamic characteristics of leakage, and distinguish the leakage anomaly from other heat sources (such as geothermal, pipeline, etc.). For the anomaly points that pass the verification, determine them as temperature anomaly monitoring points; extract the temperature data , temperature spatial gradient​ and temperature time change rate , as temperature anomaly data.

[0028] In particular, on the one hand, reflects the rate of change of temperature in three-dimensional space. An abnormal temperature gradient will be formed at the leakage channel: the horizontal gradient indicates the lateral expansion of the leakage path, and the vertical gradient reflects the vertical migration characteristics of the leakage. The spatial gradient is sensitive to the boundary of the leakage channel, and the peak position of |∇T| corresponds to the leakage boundary. The gradient direction indicates the direction of heat flow, which indirectly reflects the direction of water flow. The spatial continuity of the gradient anomaly can be used to track the leakage path.

[0029] On the other hand, reflects the rate of change of temperature with time, and a positive value indicates a temperature rise: it may be that the groundwater with higher temperature seeps in; a negative value indicates a temperature drop: it may be that the surface water with lower temperature seeps in; the change rate reflects the leakage intensity and water flow speed.

[0030] The present application uses temperature field change as an indirect indicator of leakage, provides a detection means independent of electromagnetic field, and enhances the reliability of the monitoring system.

[0031] Further, the sensor array includes a potential sensor, a temperature sensor, and a pressure sensor; the pressure sensor adopts a fiber Bragg grating sensor.

[0032] Further, S6, obtaining pressure anomaly data, includes: extracting the reflection wavelength data of the fiber Bragg grating sensor ; calculating the pressure change value according to the wavelength-pressure relationship , wherein, is the initial wavelength, is the wavelength change amount, and K is the stress sensitivity coefficient; performing time series analysis on the pressure change value , when the pressure change rate is greater than a preset change rate threshold, regarding the corresponding monitoring point as a pressure sudden change point; when the pressure change value is greater than a threshold range, regarding the corresponding monitoring point as an abnormal fluctuation point; regarding the pressure data corresponding to the monitoring points containing the pressure sudden change point and the abnormal fluctuation point as the pressure anomaly data.

[0033] In particular, the fiber Bragg grating pressure sensing technology has unique technical advantages in underground anti-seepage structure leakage monitoring. Its working principle is based on the optical properties of Bragg gratings: the fiber Bragg grating forms Bragg reflection through periodic refractive index modulation. When external pressure acts on the optical fiber, it causes changes in grating period and effective refractive index , resulting in reflection wavelength The wavelength coding measurement method is intrinsically safe, does not need power supply, and fundamentally avoids electrical safety hazards. In addition, the wavelength information is not affected by light source power fluctuations and transmission loss, ensuring long-term measurement stability. In practical applications, the wavelength resolution can reach 1pm, corresponding to a pressure resolution of 0.1kPa, fully meeting the detection requirements of small leaks. At the same time, the optical signal transmission is completely immune to electromagnetic interference, and is particularly suitable for the complex electromagnetic environment in which underground anti-seepage structures are located.

[0034] In the present application, on the one hand, by establishing an accurate pressure measurement model based on the linear relationship between wavelength and pressure , the quantitative detection of the change in pore water pressure caused by leakage is realized, and the calibration of the stress sensitivity coefficient K ensures the accuracy and repeatability of the measurement; on the other hand, by setting double abnormality criteria, comprehensive identification of different leakage modes is realized: the pressure sudden change point greater than the threshold value is used to identify dangerous leakage developing rapidly, such as sudden pressure change caused by sudden damage of the anti-seepage structure; the abnormal fluctuation point greater than the threshold value is used to detect the steady but abnormal pressure state, such as the persistent pressure deviation formed by the slow development of the leakage channel. This detection strategy combining the time derivative criterion with the amplitude criterion can not only capture transient pressure pulses, but also identify long-term pressure shifts.

[0035] Further, S7, obtaining fusion data, including: calculating the conditional probability of electromagnetic anomaly and leakage event, the conditional probability of temperature anomaly and leakage event, and the conditional probability of pressure anomaly and leakage event according to historical monitoring data; calculating the posterior probability P of multi-source data fusion based on Bayesian algorithm; setting the weight coefficients , and of the conditional probabilities according to the signal-to-noise ratios of the sensors; , , , wherein, are the signal-to-noise ratios of the potential sensor, the temperature sensor and the pressure sensor respectively; weighting the electromagnetic anomaly data, the temperature anomaly data and the pressure anomaly data according to the weight coefficients to obtain the comprehensive anomaly index; obtaining the fusion data according to the comprehensive anomaly index and the posterior probability P.

[0036] In particular, the Bayesian algorithm regards the detection results of different sensors as independent evidence, and calculates the posterior probability of the leakage event under the condition of multiple evidence by combining conditional probability and prior knowledge. This probability reasoning mechanism not only can handle the uncertainty of various sensor data, but also can quantitatively evaluate the contribution of each abnormal feature to the leakage judgment. Compared with simple threshold judgment or linear superposition, Bayesian fusion can make full use of the statistical rules contained in historical data, especially in the monitoring of underground anti-seepage structure, which is a complex environment. Single physical field detection is easily disturbed by various disturbances, and Bayesian fusion significantly improves the accuracy and robustness of leakage detection through cross verification of multi-source information.

[0037] In this application, on the one hand, by deeply mining historical monitoring data, a conditional probability model based on statistical learning is established: the conditional probability of electromagnetic anomaly and leakage event reflects the reliability of electromagnetic field change as a leakage indicator, the conditional probability of temperature anomaly and leakage event quantifies the correlation between temperature field disturbance and leakage, and the conditional probability of pressure anomaly and leakage event characterizes the probability that pressure change indicates leakage. The accurate estimation of these three conditional probabilities lays a solid foundation for subsequent probability reasoning; on the other hand, a dynamic weight distribution mechanism based on signal-to-noise ratio is innovatively introduced, which adjusts the weight of each sensor in the fusion decision according to its real-time signal quality through formula, sensors with high signal-to-noise ratio obtain greater weight, effectively suppressing the influence of data with serious noise pollution on the final judgment.

[0038] S8, constructing a machine learning model, using historical leakage monitoring data, simulating electromagnetic field distribution characteristics, temperature field distribution characteristics and pressure field distribution characteristics under different leakage states and different leakage scales, generating a training sample set to train the machine learning model;

[0039] input the fusion data into the trained machine learning model, the fusion data includes electromagnetic anomaly data, temperature anomaly data and pressure anomaly data weighted and fused according to the weight coefficient, and the leakage probability is obtained through the output layer of the machine learning model.

[0040] extract data points exceeding the preset abnormal threshold from the fusion data as abnormal data points, the abnormal data points include their corresponding spatial coordinates .

[0041] According to the spatial coordinate distribution of the abnormal data points, a three-dimensional coordinate clustering algorithm is used to determine the cluster center of the abnormal data points, and the cluster center is taken as the leakage center position .

[0042] a time-varying rate of the abnormal degree is calculated as the leakage rate based on the numerical change of the abnormal data points within a continuous time window;

[0043] a spatial distribution range of the abnormal data points is counted, and a minimum three-dimensional bounding box volume containing all the abnormal data points is calculated as the leakage influence range;

[0044] According to the leakage rate and the leakage influence range, when the leakage rate is less than a first rate threshold and the leakage influence range is less than a first range threshold, it is determined as a slight leakage; when the leakage rate or the leakage influence range exceeds a second rate threshold or a second range threshold, it is determined as a serious leakage; otherwise, it is determined as a moderate leakage.

[0045] Another aspect of the present application also provides a discrete-time dynamic grid-based underground anti-seepage structure leakage monitoring system, comprising: a sensor array comprising distributedly arranged potential sensors, temperature sensors and pressure sensors for collecting current data, temperature data and pressure data of a monitoring area; the pressure sensor adopts a fiber grating sensor; a signal excitation source for generating a bipolar square wave excitation signal and adjusting the frequency parameter according to the geological conditions of the monitoring area and the monitoring depth requirement, and sending the excitation signal to multiple monitoring areas in a multi-channel parallel excitation mode; a data acquisition module for acquiring underground anti-seepage structure data and transient electromagnetic response data generated by the excitation signal, the transient electromagnetic response data including natural potential baseline DC data and transient response AC data; a space-time alignment module for setting a discrete time window , constructing a four-dimensional space-time data matrix according to the spatial coordinates of each sensor in the sensor array and the data acquisition timestamp t, and performing space-time alignment on the sensor data of different sampling frequencies through an interpolation algorithm; a full waveform inversion module for minimizing the fitting error between the model response and the measured data through iterative optimization according to the initial conductivity parameter and the electrode position parameter, and constructing a three-dimensional conductivity distribution model ;

[0046] a background field modeling module for solving a time-domain Maxwell equation set through a finite element method based on the three-dimensional conductivity distribution model, establishing a three-dimensional geophysical model, and calculating a background electromagnetic field in a no-leakage state using a finite element forward algorithm ; an anomaly detection module for performing difference operation on the measured transient electromagnetic response data and the background electromagnetic field to obtain electromagnetic anomaly data ; calculating a temperature spatial gradient and a time-varying rate , when is greater than a gradient threshold and When the temperature rise is greater than the temperature rise threshold, corresponding temperature anomaly data is extracted; according to the wavelength-pressure relationship of the fiber grating The pressure change value is calculated, and when the pressure change rate is greater than the change rate threshold or the pressure change value is outside the threshold range, corresponding pressure anomaly data is extracted; a Bayesian fusion module calculates the conditional probability of each type of anomaly and leakage event according to historical monitoring data 、 and , based on the signal-to-noise ratio of each sensor, a weight coefficient is set , and a fusion data is generated through a Bayesian algorithm; a leakage detection module, which has a pre-trained machine learning model, is used to receive the fusion data and output a leakage detection result, including a leakage probability, a leakage location and a leakage level.

[0047] Compared with the prior art, the advantages of the present application are:

[0048] Through transient electromagnetic excitation source active detection technology, a bipolar square wave excitation signal with amplitude 0-±1000V and pulse width 0.1ms-1000ms adjustable is generated, a three-dimensional geophysical model is established by combining full waveform inversion algorithm, and background field difference operation is performed to accurately extract electromagnetic anomaly characteristics caused by leakage. Compared with the traditional passive detection method, the active detection method can detect a small leakage of 5cm², the detection sensitivity is improved to 0.1mV, and the early small leakage is accurately identified.

[0049] Based on a discrete time window , a four-dimensional spatiotemporal data matrix is constructed , and time slicing processing and interpolation algorithm are used to realize spatiotemporal alignment of sensor data with different sampling frequencies. In a unified spatiotemporal framework, electromagnetic anomaly data , temperature anomaly data (when is greater than 0.5℃ / h and exceeds the threshold) and pressure anomaly data (when exceeds the threshold) are extracted, and the dynamic tracking of the leakage development process is realized. Compared with the traditional single detection method, the present scheme can continuously monitor the dynamic evolution process of the leakage, capture the leakage rate change, and provide data support for leakage trend prediction.

[0050] The Bayesian algorithm is used to calculate the conditional probability of each type of anomaly and leakage event 、 and , and the weight coefficient is dynamically allocated according to the signal-to-noise ratio of the sensor , realize the probability fusion of electromagnetic, temperature, pressure three kinds of abnormal data. Through the pre-trained machine learning model for intelligent identification of leakage, output the leakage probability, position (positioning accuracy 0.5m) and grade. The multi-source data fusion mechanism effectively eliminates the environmental interference of single physical field detection, significantly improves the reliability of the monitoring system. BRIEF DESCRIPTION OF DRAWINGS

[0051] The present application will be further described in the form of exemplary embodiments, which will be described in detail through the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same numbers represent the same structures, wherein:

[0052] Figure 1 is an exemplary flow chart of a discrete-time-based underground anti-seepage structure leakage monitoring method according to some embodiments of the present application;

[0053] Figure 2 is an exemplary flow chart of generating electromagnetic anomaly data according to some embodiments of the present application;

[0054] Figure 3 is an exemplary flow chart of generating temperature anomaly data according to some embodiments of the present application;

[0055] Figure 4 is an exemplary flow chart of generating pressure anomaly data according to some embodiments of the present application. DETAILED DESCRIPTION

[0056] The method and system provided by the embodiments of the present application will be described in detail below in combination with the accompanying drawings.

[0057] As Figure 1As shown, underground anti-seepage structure data containing current data, temperature data and pressure data are collected by the sensor array; an excitation signal is sent to the monitoring area by a signal excitation source, and transient electromagnetic response data generated by the excitation signal are collected by the sensor array; a discrete time window is set, and a space-time data matrix is constructed according to the spatial coordinates and data collection time stamps of each sensor in the sensor array; the underground anti-seepage structure data and the transient electromagnetic response data are space-time aligned based on the space-time data matrix; a three-dimensional geophysical model of the monitoring area is established by a full waveform inversion algorithm according to the initial conductivity parameters and electrode position parameters of the monitoring area; based on the three-dimensional geophysical model, a background field modeling is performed on the variable electromagnetic response data by using a finite element forward algorithm to obtain the background electromagnetic field distribution under the condition of no leakage; difference operation is performed on the transient electromagnetic response data and the background electromagnetic field distribution to obtain electromagnetic anomaly data; according to the temperature data, a distributed temperature field analysis method is used to calculate the spatial gradient and time change rate of temperature to obtain temperature anomaly data; the pressure data are analyzed, and the pressure anomaly data are determined according to the time sequence variation characteristics of the pressure data; the electromagnetic anomaly data, the temperature anomaly data and the pressure anomaly data are fused by using a Bayesian algorithm to obtain fusion data; the fusion data are input into a pre-trained machine learning model to obtain a leakage detection result, which includes a leakage probability, a leakage position and a leakage level.

[0058] S1, in a certain underground station anti-seepage structure monitoring project, a sensor array containing potential sensors, temperature sensors and fiber grating pressure sensors is constructed.

[0059] The potential sensor is made of composite electrode material, with a sensitivity of 0.1 mV, and can detect micro-leakage current signals in a range of 5 cm². According to the distributed matrix deployment with a density of 4 per square meter, the high-risk areas such as underground continuous wall joints and anti-seepage structure weak points are covered. The sensor integrates an active noise cancellation circuit, effectively suppressing 50Hz power frequency interference, and the signal-to-noise ratio is improved to more than 60dB.

[0060] The temperature sensor adopts a MEMS temperature chip with a temperature resolution of 0.1℃ and a response time of less than 1 second. The sensor shell reaches IP68 waterproof level, is equipped with a waterproof and breathable membrane, and can work for a long time at a depth of 200 meters below the water level.

[0061] Based on the wavelength-stress sensitivity characteristics of fiber Bragg grating technology, precise pressure measurement is realized, with a range of 0~5MPa and a resolution of 0.1kPa. A series topology structure is adopted, and a single optical fiber can be connected with 64 measuring points. The material and structure are optimized for corrosion resistance, the optical fiber is wrapped with special acid and alkali resistant coating material, and a sealed packaging structure is adopted, which can work stably in a leakage water environment with pH3~11 for more than 10 years.

[0062] S2, the signal excitation source generates a bipolar square wave excitation signal, the amplitude is adjustable in the range of 0±1000V, the pulse width can be programmed to set between 0.1ms and 1000ms. According to the geological conditions of the monitoring area (such as the soil resistivity is 50Ω·m), the excitation signal amplitude is set to 500V, the pulse width is 10ms, and the frequency is 25Hz.

[0063] Using multi-channel parallel excitation mode, the monitoring area is divided into 4 sub-regions, and excitation signals with different parameters are sent at the same time. The transient electromagnetic response data of each sub-region is synchronously collected by the potential sensor array, including the natural potential baseline DC data (amplitude range-100mV~+100mV) and the transient response AC data (decay time 0.1ms~100ms).

[0064] S3, set the discrete time window Δt=60s, and divide the 24-hour continuous monitoring data into 1440 discrete time segments by time slicing processing. A four-dimensional spatiotemporal data matrix is constructed , in which the spatial coordinate accuracy is 0.1m and the time accuracy is 1s.

[0065] For sensors with different sampling frequencies (potential sensor 1kHz, temperature sensor 1Hz, pressure sensor 10Hz), a cubic spline interpolation algorithm is used to synchronize all data to the 60s time node. Finally, a spatiotemporal alignment data set is obtained, each data point contains position information , time stamp t and corresponding measurement value.

[0066] As Figure 2 described, S4, input the initial conductivity parameters of the monitoring area (based on geological survey data), and the electrode position parameters are 32 electrodes distributed in an 8×4 matrix. Extract the DC data (average value-50mV) and AC data (peak value 200mV) in the spatiotemporal alignment data.

[0067] Through the full waveform inversion algorithm, a three-dimensional conductivity distribution model is constructed after 50 iterations of optimization, and the model grid size is 0.5m×0.5m×0.5m. Based on the model, the background electromagnetic field is calculated by finite element forward calculation.

[0068] The measured transient electromagnetic response data and the background field are subjected to difference operation, and when ΔE>10mV, it is determined as an electromagnetic anomaly. In this embodiment, 3 electromagnetic anomaly areas are detected, with anomaly values of 15mV, 22mV and 18mV respectively.

[0069] As Figure 3 shown, S5, extract temperature data from the spatiotemporal alignment data The temperature spatial gradient and time rate of change of each monitoring point are calculated. The temperature rise threshold is set to 0.5℃ / h, and the gradient threshold is set to 0.2℃ / m.

[0070] During the monitoring process, it is found that the temperature time rate of change of two monitoring points is 0.8℃ / h and 1.2℃ / h respectively, which exceeds the temperature rise threshold; at the same time, the temperature spatial gradient modulus of these two points is 0.3℃ / m and 0.5℃ / m respectively, which exceeds the gradient threshold. The data of these two monitoring points are taken as temperature anomaly data.

[0071] As shown in Figure 4 S6, the reflection wavelength data of the fiber grating sensor is extracted, and the initial wavelength , the stress sensitivity coefficient K=1.2pm / kPa. When the wavelength change is detected, the pressure change value ΔP=2kPa is calculated.

[0072] The pressure change rate threshold is set to 0.5kPa / min, and the pressure change threshold is set to 1.5kPa. Monitoring finds that the pressure change rate of one measuring point reaches 0.8kPa / min, and the pressure change value is 2kPa. The data of this point is taken as pressure anomaly data.

[0073] S7, based on the historical monitoring data statistics, the following are calculated: (the conditional probability of electromagnetic anomaly and leakage), (the conditional probability of temperature anomaly and leakage), (the conditional probability of pressure anomaly and leakage).

[0074] According to the signal-to-noise ratio (SNR) of the sensor , , , the weight coefficient is calculated: , , .

[0075] The posterior probability P=0.92 of multi-source data fusion is calculated by Bayesian algorithm. The electromagnetic anomaly data (22mV), temperature anomaly data (1.2℃ / h) and pressure anomaly data (2kPa) are weighted according to the weight coefficient, and the comprehensive anomaly index is 18.5. The fusion data is generated combined with the posterior probability.

[0076] S8, the fusion data is input into the pre-trained deep learning model (including 3 convolutional layers and 2 fully connected layers), and the model outputs the leakage probability . According to the spatial distribution of abnormal data, the leakage center position is determined to be (x=125.3m, y=48.7m, z=-15.2m) by three-dimensional coordinate clustering algorithm.

[0077] The calculated leakage rate was 0.15 L / min, and the leakage affected area was 2.5 m². According to the preset grading standard (mild: <0.1 L / min and <1 m²; moderate: 0.1-0.5 L / min or 1-5 m²; severe: >0.5 L / min or >5 m²), it was determined to be a moderate leakage.

[0078] In practical applications, the present embodiment transmits monitoring data in real time through a 4G / Wi-Fi dual-mode network, and the data compression rate reaches 85%. After running for 6 months, the system successfully detects 5 leakage points, with a detection accuracy of 98.2% and a false positive rate of only 1.8%. The positioning accuracy of the leakage location is better than 0.5 m. Through the intelligent push system, the average response time of maintenance personnel is shortened from 4 hours to 30 minutes, effectively ensuring the safe operation of underground anti-seepage structures.

[0079] The above describes the present application and its embodiments in a schematic manner, which is not restrictive, and the present application can be realized in other specific forms without departing from the spirit or essential characteristics of the present application. The embodiments shown in the drawings are only one of the embodiments of the present application, and the actual structure is not limited thereto. Therefore, if a person skilled in the art is inspired by it, without departing from the spirit of the present application, similar structural forms and embodiments can be designed without creative design, which should belong to the protection scope of the present application. In addition, the word "comprising" does not exclude other elements or steps, and the word "one" before the element does not exclude the inclusion of "multiple" elements. The words "first", "second" and the like are used to indicate names, and do not mean any specific order.

Claims

1. A method for monitoring leakage of underground anti-seepage structures based on discrete time, characterized in that: include: S1, collecting underground anti-seepage structure data including current data, temperature data and pressure data through a sensor array; S2, sending an excitation signal to the monitoring area through a signal excitation source, and collecting transient electromagnetic response data generated by the excitation signal through a sensor array; S3, set a discrete time window and construct a spatiotemporal data matrix based on the spatial coordinates and data acquisition timestamps of each sensor in the sensor array; Perform spatiotemporal alignment of underground anti-seepage structure data and transient electromagnetic response data based on spatiotemporal data matrix; S4, establishing a three-dimensional geophysical model of the monitoring area using a full waveform inversion algorithm based on the initial conductivity parameters and electrode position parameters of the monitoring area; Based on the three-dimensional geophysical model, the finite element forward algorithm is used to model the background field of the transient electromagnetic response data after S3 time and space alignment to obtain the background electromagnetic field distribution under the no leakage state; Performing a differential operation on the transient electromagnetic response data and the background electromagnetic field distribution after the time-space alignment in step S3 to obtain electromagnetic anomaly data; S5, based on the temperature data in the underground anti-seepage structure data after the time-space alignment in S3, the distributed temperature field analysis method is used to calculate the spatial gradient and time change rate of the temperature to obtain the temperature anomaly data; S6, analyzing the pressure data in the underground anti-seepage structure data after the spatiotemporal alignment in S3, and determining the pressure anomaly data according to the temporal variation characteristics of the pressure data; S7, using a Bayesian algorithm to fuse the electromagnetic anomaly data, the temperature anomaly data, and the pressure anomaly data to obtain fused data; S8, inputting the fused data into a pre-trained machine learning model to obtain leakage detection results, which include leakage probability, leakage location, and leakage level; Among them, the electromagnetic anomaly data obtained include: Obtain the initial conductivity parameters of the monitoring area and electrode position parameters; initial conductivity parameters is the initial estimated value of the conductivity of each layer in the monitoring area; Extract the natural potential baseline DC data and transient response AC data from the time-space aligned data as input data for the full waveform inversion algorithm; The full waveform inversion algorithm is used to iteratively optimize the initial conductivity parameters. , minimize the fitting error between the model response and the natural potential baseline DC data and transient response AC data, and construct a three-dimensional conductivity distribution model ; Based on the three-dimensional conductivity distribution model and electrode location parameters, the monitoring area is meshed using the finite element method, and the time-domain Maxwell equations are solved to establish a three-dimensional geophysical model containing the spatial distribution information of conductivity; Using a three-dimensional geophysical model, the finite element forward algorithm simulates the electromagnetic field response after applying the excitation signal under the current conductivity distribution conditions, and calculates the background electromagnetic field under the non-leakage state. ; Align the measured transient electromagnetic response data in time and space Background electromagnetic field Perform a difference operation: , get the electromagnetic anomaly data caused by leakage .

2. The method for monitoring underground anti-seepage structure leakage based on discrete time according to claim 1, characterized in that: S2, collects transient electromagnetic response data generated by the excitation signal, including: Generate a bipolar square wave excitation signal; Adjust the frequency parameters of the bipolar square wave excitation signal according to the geological conditions of the monitoring area and the monitoring depth requirements; Adopting multi-channel parallel excitation mode, bipolar square wave excitation signals are sent to multiple monitoring areas; The transient electromagnetic response data of each monitoring area is collected through the sensor array. The transient electromagnetic response data includes natural potential baseline DC data and transient response AC data.

3. The method for monitoring leakage of underground anti-seepage structures based on discrete time according to claim 2, characterized in that: The amplitude range of the bipolar square wave excitation signal is 0-±1000V, and the pulse width range is 0.1ms-1000ms.

4. The method for monitoring underground anti-seepage structure leakage based on discrete time according to claim 1, characterized in that: S3, constructs a spatiotemporal data matrix, including: Set the discrete time window ,Through time slicing processing, the continuous data stream is divided into discrete time segments; According to the three-dimensional space coordinates of each sensor and the data acquisition timestamp t, constructing a four-dimensional spatiotemporal data matrix , used to store the measurement values ​​of each sensor in each discrete time segment; For sensor data with different sampling frequencies, discrete time windows are used As a benchmark, the sensor data are synchronized to the same time node through the interpolation algorithm; The time-synchronized sensor data are spatially aligned to obtain spatiotemporally aligned data.

5. The method for monitoring leakage of underground anti-seepage structures based on discrete time according to claim 1, characterized in that: S5, obtain temperature anomaly data, including: Temperature data in spatiotemporal alignment data , calculate the temperature spatial gradient of each monitoring point ; Calculate the temperature time change rate of each monitoring point ; When the spatial gradient modulus of the temperature at the monitoring point When the gradient is greater than the preset threshold, the corresponding monitoring point is marked as a temperature spatial anomaly point; When the temperature change rate of the monitoring point When the temperature rise is greater than the preset threshold, the corresponding monitoring point will be marked as a temperature time-varying abnormal point; Based on the physical mechanism of local heat transfer anomalies caused by groundwater leakage, the temperature field distribution is analyzed by solving the heat conduction equation to verify whether the temperature spatial anomaly points and temperature identification anomaly points conform to the temperature field change characteristics caused by leakage; For abnormal points that have passed the verification, the corresponding monitoring points are determined as temperature abnormality monitoring points; Extract temperature data corresponding to temperature anomaly monitoring points , temperature spatial gradient and temperature-time change rate , as temperature anomaly data.

6. The method for monitoring leakage of underground anti-seepage structures based on discrete time according to claim 1, characterized in that: The sensor array includes a potential sensor, a temperature sensor, and a pressure sensor; The pressure sensor uses a fiber grating sensor.

7. The method for monitoring leakage of underground anti-seepage structures based on discrete time according to claim 6, characterized in that: S6, obtains abnormal pressure data, including: Extracting reflected wavelength data from fiber Bragg grating sensors ; According to the wavelength-pressure relationship Calculate pressure change ,in, is the initial wavelength, is the wavelength variation, K is the stress sensitivity coefficient; Pressure change value Perform timing analysis, when the pressure change rate When the change rate is greater than the preset threshold, the corresponding monitoring point is regarded as a pressure mutation point; When the pressure changes When it is greater than the threshold range, the corresponding monitoring point is regarded as an abnormal fluctuation point; The pressure data corresponding to the monitoring points containing pressure mutation points and abnormal fluctuation points are regarded as pressure abnormality data.

8. The method for monitoring leakage of underground anti-seepage structures based on discrete time according to claim 1, characterized in that: S7, obtain fused data, including: Calculate the conditional probability of electromagnetic anomalies and leakage events based on historical monitoring data , the conditional probability of temperature anomaly and leakage event , and the conditional probability of pressure anomaly and leakage events ; Based on the Bayesian algorithm, calculate the posterior probability P of multi-source data fusion; Set the conditional probability based on the signal-to-noise ratio of each sensor 、 and The weight coefficient ; The electromagnetic anomaly data, temperature anomaly data and pressure anomaly data are calculated based on the weight coefficients. Perform weighted calculation to obtain comprehensive abnormality indicators; According to the comprehensive abnormality index and posterior probability P, the fused data is obtained.

9. A leakage monitoring system for underground anti-seepage structures based on discrete-time dynamic grids, characterized in that: include: A sensor array, including distributed potential sensors, temperature sensors, and pressure sensors, is used to collect current data, temperature data, and pressure data in the monitoring area; The pressure sensor uses a fiber Bragg grating sensor; The signal excitation source is used to generate a bipolar square wave excitation signal, adjust the frequency parameters according to the geological conditions and monitoring depth requirements of the monitoring area, and use a multi-channel parallel excitation mode to send excitation signals to multiple monitoring areas; The data acquisition module collects underground anti-seepage structure data and transient electromagnetic response data generated by the excitation signal. The transient electromagnetic response data includes natural potential baseline DC data and transient response AC data. Spatiotemporal alignment module, setting discrete time windows , according to the spatial coordinates of each sensor in the sensor array and the data acquisition time stamp t to construct a four-dimensional spatiotemporal data matrix and align sensor data with different sampling frequencies in time and space through interpolation algorithms; Full waveform inversion module, based on the initial conductivity parameters and electrode position parameters, and minimize the fitting error between the model response and the measured data through iterative optimization to construct a three-dimensional conductivity distribution model ; The background field modeling module uses the finite element method to solve the time-domain Maxwell equations based on the three-dimensional conductivity distribution model, establishes a three-dimensional geophysical model, and uses the finite element forward algorithm to calculate the background electromagnetic field under the non-leakage state. ; The abnormality detection module converts the measured transient electromagnetic response data and background electromagnetic fields Perform differential calculations to obtain electromagnetic anomaly data ; Calculate the spatial temperature gradient and time rate of change ,when Greater than the gradient threshold and When the temperature rise threshold is greater than the threshold, the corresponding temperature anomaly data is extracted; according to the wavelength-pressure relationship of the fiber Bragg grating Calculate the pressure change value, when the pressure change rate Greater than the rate of change threshold or pressure change value When the threshold value is exceeded, the corresponding abnormal pressure data is extracted; Bayesian fusion module, which calculates the conditional probability of various anomalies and leakage events based on historical monitoring data 、 and , set the weight coefficient based on the signal-to-noise ratio of each sensor , generate fusion data through Bayesian algorithm; The leakage detection module has a built-in pre-trained machine learning model that receives fused data and outputs leakage detection results, which include leakage probability, leakage location, and leakage level.

Images