A tunnel advance geological prediction monitoring method and related device

Abstract

The application discloses a tunnel advanced geological prediction monitoring method and related equipment, and relates to the technical field of intelligent monitoring. The method comprises the following steps: acquiring a time domain response of a transient electromagnetic signal; processing the time domain response of the transient electromagnetic signal by using an adaptive filtering algorithm to obtain processing data; generating a three-dimensional geological model according to the processing data by using a three-dimensional imaging algorithm; and predicting a geological condition based on an abnormal density function, a pattern recognition algorithm and the three-dimensional geological model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring, and more particularly, to a tunnel advanced geological prediction monitoring method and related equipment. BACKGROUND

[0002] With the continuous expansion of tunnel construction scale and the increase of tunnel projects under complex geological conditions, how to effectively predict the geology in front of the tunnel, reduce construction risks, and ensure project progress and safety has become a major challenge in current tunnel engineering. The existing tunnel advanced geological prediction technology mainly relies on manual observation, drilling detection and geological radar and other means. However, these traditional methods often face problems such as insufficient accuracy, limited detection range, low data processing efficiency, etc. under complex geological conditions, which are difficult to meet the needs of modern tunnel construction.

[0003] In order to at least solve part of the above problems, it is urgent to provide a tunnel advanced geological prediction monitoring method, which can further improve the accuracy and efficiency of geological prediction and help tunnel construction enterprises better cope with complex geological environments. SUMMARY

[0004] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiment section. The summary section of the present application does not mean to attempt to limit the key features and necessary technical features of the claimed technical solutions, nor to attempt to determine the protection scope of the claimed technical solutions.

[0005] In a first aspect, the present application provides a tunnel advanced geological prediction monitoring method, comprising:

[0006] Obtaining the time domain response of the transient electromagnetic signal;

[0007] Using an adaptive filtering algorithm to process the time domain response of the transient electromagnetic signal to obtain processed data;

[0008] Using a three-dimensional imaging algorithm to generate a three-dimensional geological model according to the processed data;

[0009] Based on the abnormal density function, the pattern recognition algorithm and the three-dimensional geological model, predicting the geological conditions.

[0010] In a feasible implementation, the time domain response of the transient electromagnetic signal is represented as:

[0011]

[0012]

[0013] In the formula, E(t, θ2, φ) is a time domain response of the transient electromagnetic signal, A(f, θ2, φ) is a frequency domain response of the transient electromagnetic signal, t is a current time, f is a frequency, θ2 is a reflected or refracted angle, φ is a depression angle, j is an imaginary unit, 2πft is a phase factor, d is an electromagnetic wave propagation depth, θ1 is an electromagnetic wave incidence angle, V1 is a propagation speed of the electromagnetic wave in a first medium, and V2 is a propagation speed of the electromagnetic wave in a second medium.

[0014] In an implementable embodiment, the method further comprises:

[0015] The frequency domain response of the transient electromagnetic signal is determined based on the following formula:

[0016]

[0017] In the formula, A0(f) is an amplitude response at a frequency f, α(f, θ2, φ) is an attenuation coefficient, the attenuation coefficient represents energy loss of the electromagnetic wave in the propagation process due to medium absorption and attenuation, the attenuation coefficient varies with the frequency and the antenna angle, and β(f, θ2, φ) is a phase offset, which represents a phase change of the electromagnetic wave in the propagation process due to different geological structures.

[0018] In an implementable embodiment, the time domain response of the transient electromagnetic signal is processed using an adaptive filter algorithm to obtain processed data, and the method comprises:

[0019] The adaptive filter is represented as:

[0020]

[0021] In the formula, is filtered processed data, w n is a weight coefficient of the adaptive filter, N is an order of the filter, t-n is a time of n sampling periods before the current time t, and E(t-n, θ2, φ) is a time domain response corresponding to the transient electromagnetic signal at the time t-n.

[0022] In an implementable embodiment, the method further comprises: the weight coefficient w n is determined based on the following formula:

[0023]

[0024] In the formula, and are weight values of the filter at the kth iteration and the k+1th iteration, respectively, μ is a learning rate, and Loss is a loss function.

[0025] Loss = L1 + L2 + L3 + L4

[0026] where D(t, θ2, φ) is the desired output signal, SNR(t) -1 is the inverse of the signal-to-noise ratio, λ1 is the weight coefficient of the signal-to-noise ratio suppression term, λ2 is the weight coefficient of the sparsity penalty term, λ3 is the weight coefficient of the time-domain smoothness penalty term, and T is the time series length.

[0027] In a possible implementation, the three-dimensional geological model is determined based on the following formula:

[0028]

[0029] where M(x, y, z) is the three-dimensional geological model, which is the geological structure at the point (x, y, z) in space, L is the total number of geological layers, l is the lth layer of geology, w l is the weight coefficient of the lth layer, B is the total number of frequency bands, f i is the center frequency of the ith frequency band, R(t, x, y, z, f i , l) is a time inversion operator that converts a time-domain signal into spatial geological model information, δ(·) is an instantaneous propagation impulse response, v l is the propagation velocity of an electromagnetic wave in the lth layer of geological medium at a frequency f i .

[0030] In a possible implementation, the geological condition is predicted based on the abnormal density function, the pattern recognition algorithm, and the three-dimensional geological model, and the prediction includes:

[0031] An abnormal area is determined based on the abnormal density function and the three-dimensional geological model, where the abnormal density function is:

[0032]

[0033] where ρ a (x, y, z) is the abnormal density value of the point (x, y, z) in the three-dimensional geological model, σ(·) is an activation function, is a Laplacian operator, μ M is the mean density of the three-dimensional geological model;

[0034] The abnormal area is identified based on the pattern recognition algorithm to predict the geological condition, where the pattern recognition algorithm includes a feature extraction operation, an abnormal point classification operation, and an abnormal type optimization operation.

[0035] In a second aspect, the application provides a tunnel advance geological prediction monitoring device, which includes:

[0036] An acquisition unit configured to acquire a time-domain response of a transient electromagnetic signal.

[0037] a processing unit configured to process the time domain response of the transient electromagnetic signal using an adaptive filtering algorithm to obtain processed data;

[0038] a generating unit configured to generate a three-dimensional geological model according to the processed data using a three-dimensional imaging algorithm;

[0039] an identifying unit configured to predict a geological condition based on an abnormal density function, a pattern recognition algorithm and the three-dimensional geological model.

[0040] In a third aspect, an electronic device is provided, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor is configured to implement the steps of the tunnel advanced geological prediction monitoring method according to any one of the first aspect when running the computer program stored in the memory.

[0041] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, wherein the computer program is executed by a processor to implement the tunnel advanced geological prediction monitoring method according to any one of the first aspect.

[0042] In summary, the embodiment of the present application can accurately predict the geological conditions by acquiring the time domain response of the transient electromagnetic signal, processing the transient electromagnetic signal using an adaptive filtering algorithm, and generating a three-dimensional geological model. Compared with traditional manual observation or drilling detection methods, the present scheme can process data under complex geological conditions, significantly improve the prediction accuracy, and reduce errors caused by geological complexity. Through the adaptive filtering algorithm, the time domain response of the transient electromagnetic signal is quickly processed, and a three-dimensional geological model is generated by combining the three-dimensional imaging algorithm, effectively accelerating the data processing process. Traditional geological prediction methods often have low processing efficiency due to the large amount of data, while the present scheme can achieve efficient data processing while ensuring data accuracy. The present scheme uses an anomaly density function and a pattern recognition algorithm to effectively identify abnormal geological regions that may exist in front of the tunnel. With the aid of the three-dimensional geological model, the complex geological environment in front of the tunnel can be accurately predicted, ensuring comprehensive control of the geological conditions during construction and reducing construction risks. In complex tunnel construction, the uncertainty of the geology is an important factor that leads to construction risks. The present scheme can effectively avoid potential geological risks through early prediction of the geological conditions, ensuring safety during construction and improving construction progress. The present scheme is based on intelligent monitoring technology and combines advanced algorithms such as adaptive filtering, three-dimensional imaging, and pattern recognition, breaking through the technical bottleneck of traditional geological prediction and providing a more intelligent and accurate prediction method for tunnel engineering. This innovative technical means can effectively intervene in the early stages of tunnel construction, ensuring the smooth progress of the project. By improving the accuracy and efficiency of geological prediction, construction companies can better cope with complex geological conditions in the early stages, reduce additional costs such as downtime and rework caused by geological problems, and thus reduce overall construction costs.

[0043] The tunnel advance geological prediction monitoring method of the present application, other advantages, objectives and features of the present application will be embodied in part through the following description, and part will be understood by those skilled in the art through research and practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0044] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for purposes of illustration only and are not considered a limitation of the present specification. Moreover, like reference numerals designate identical parts throughout the several views. In the drawings:

[0045] Figure 1 A tunnel advance geological prediction monitoring method flow chart is provided for the embodiment of the present application;

[0046] Figure 2 A tunnel advance geological prediction monitoring device structure diagram is provided for the embodiment of the present application;

[0047] Figure 3 A tunnel advanced geological prediction monitoring electronic equipment structure schematic diagram is provided for the embodiment of the present application. DETAILED DESCRIPTION

[0048] The terms "first", "second", "third", "fourth" and the like in the description and claims of the present application and in the above Summary are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of these terms herein is to be construed as interchangeable in order to distinguish similar elements. It is also to be understood that the description of the embodiments of the present application is intended to cover any alternatives, modifications, equivalents, and / or improvements of the embodiments of the present application which are within the scope of the present application as defined by the appended claims. In the following description of the embodiments of the present application, the terms "include" and "have" and their conjugates, are used functional descriptive purpose only and do not mean "consist only of" or "consisting only of". Therefore, the embodiments of the present application should not be limited to the embodiments of the present application described herein, but should be given the most broadest interpretation available under the jurisdiction.

[0049] Reference will now be made to the drawings, in which Figure 1 A tunnel advanced geological prediction monitoring method flowchart is provided for the embodiment of the present application, which can specifically include:

[0050] S110, acquiring a time domain response of a transient electromagnetic signal;

[0051] For example, in the geological detection in front of a tunnel, the transient electromagnetic method is a non-invasive and non-destructive detection technology. By measuring the transient electromagnetic response at different angles, different levels of information of the geological structure can be obtained. The multi-polarization antenna array adjusts the elevation and depression angles dynamically, so that the electromagnetic wave can be incident to the underground in a multi-angle and multi-polarization manner, thereby improving the data coverage and the resolution of the geological structure, and greatly increasing the detection accuracy of the geological structure. The multi-polarization antenna refers to an antenna system capable of working in multiple polarization states, and the polarization state usually refers to the direction of the electric field of the electromagnetic wave. For example, the vertical and horizontal polarizations of the electromagnetic wave can be used to detect the structures in different directions of the underground. The elevation and depression angles of the antenna determine the propagation direction of the electromagnetic wave, and adjusting these two parameters can detect the geology at different depths.

[0052] The speed and manner of electromagnetic wave propagation in different media are closely related to geological structures. Transient electromagnetic method measures the reflection signals at different depths to infer the underground structure. In different polarization states, the response of electromagnetic waves changes with the properties of underground media such as conductivity and dielectric constant. Therefore, through a multi-polarization antenna array, multi-dimensional electromagnetic signals can be captured simultaneously, and a more accurate geological model can be constructed.

[0053] S120, processing the time-domain response of the transient electromagnetic signal using an adaptive filtering algorithm to obtain processed data;

[0054] For example, the adaptive filtering algorithm is used to dynamically adjust the parameters of the filter to optimize the quality of the electromagnetic signal. This algorithm can automatically adapt to different geological conditions by adjusting the filtering parameters to suppress background noise and signal interference, thereby ensuring the accuracy of the measurement data in complex tunnel geological environments.

[0055] The adaptive filter learns through a feedback mechanism, which continuously adjusts the weight coefficients of the filter according to the characteristics of the input signal, so that the filter can better adapt to real-time input data. This adaptability can effectively handle various disturbances in complex background environments, such as noise from steel frames, cables, and external electromagnetic signals.

[0056] S130, generating a three-dimensional geological model based on the processed data using a three-dimensional imaging algorithm;

[0057] For example, in tunnel geological prediction, it is crucial to obtain the distribution of underground media through transient electromagnetic data. The three-dimensional imaging algorithm converts the measured transient electromagnetic signals into a three-dimensional geological structure model of the underground by inverting electromagnetic data. The reverse time migration algorithm is used to invert the time-domain signal to the spatial domain, thereby constructing a three-dimensional model of the underground geology. The basic idea of the reverse time migration algorithm is to "reverse" the time information of the transient electromagnetic signal back to the spatial information. Using the propagation and reflection characteristics of electromagnetic waves, the reflection signal is mapped back to the actual position underground through the inversion process. In this way, a three-dimensional image of the geological structure can be generated.

[0058] S140, predicting the geological conditions based on the abnormal density function, pattern recognition algorithm and three-dimensional geological model.

[0059] For example, after generating a three-dimensional geological model, detecting potential geological anomaly areas (such as cavities, faults, and fracture zones) is a key step in tunnel geological prediction. These abnormal areas usually exhibit discontinuity, density changes or other significant deviations in the model.

[0060] Pattern recognition algorithms are used to automate the detection and classification of these anomalous regions. By analyzing the local properties of the model, extracting features related to geological anomalies (e.g., density, gradient, etc.), pattern recognition algorithms can categorize and evaluate these anomalous regions, helping to predict potential risks ahead of the tunnel.

[0061] Pattern recognition algorithms identify anomalous regions in the geological model through a series of signal feature extraction, data analysis, and classification techniques, following this process:

[0062] Feature extraction: Extract features from the three-dimensional model that describe anomalous regions. Common features include density variations, structural gradients, spatial locations, etc. Classifier training: Train a classifier using existing geological data sets (such as historical geological exploration data). The classifier is used to classify points or regions in the three-dimensional model into different types of geological anomalies, such as cavities, faults, etc. Anomalous region identification: Scan the three-dimensional model using the trained classifier to identify anomalous points or regions.

[0063] The identified geological anomaly points are combined into complete anomalous regions, which may represent discontinuous structures such as cavities, faults, etc. in the geology. Pattern recognition algorithms can not only identify single types of anomalies, but also through joint analysis of multiple features, identify complex anomalous structures. Once the anomalous regions are identified, further geological analysis can be performed through simulation and evaluation to predict the geological conditions ahead of the tunnel.

[0064] In summary, the embodiment of the present application can accurately predict the geological conditions by obtaining the time-domain response of the transient electromagnetic signal, processing the transient electromagnetic signal using an adaptive filtering algorithm, and generating a three-dimensional geological model. Compared with traditional manual observation or drilling detection methods, the present scheme can process data under complex geological conditions, significantly improve the prediction accuracy, and reduce errors caused by geological complexity. Through the adaptive filtering algorithm, the time-domain response of the transient electromagnetic signal is quickly processed, and a three-dimensional geological model is generated by combining a three-dimensional imaging algorithm, effectively accelerating the data processing process. Traditional geological prediction methods often have low processing efficiency due to the large amount of data, while the present scheme can achieve efficient data processing while ensuring data accuracy. The present scheme uses an anomaly density function and a pattern recognition algorithm to effectively identify abnormal geological regions that may exist in front of the tunnel. With the aid of a three-dimensional geological model, the complex geological environment in front of the tunnel can be accurately predicted, ensuring comprehensive control of the geological conditions during construction and reducing construction risks. In complex tunnel construction, the uncertainty of the geology is an important factor that leads to construction risks. The present scheme can effectively avoid potential geological risks through early prediction of the geological conditions, ensuring safety during construction and improving construction progress. The present scheme is based on intelligent monitoring technology and combines advanced algorithms such as adaptive filtering, three-dimensional imaging, and pattern recognition, breaking through the technical bottleneck of traditional geological prediction and providing a more intelligent and accurate prediction method for tunnel engineering.

[0065] In some examples, the time-domain response of the transient electromagnetic signal is represented as:

[0066]

[0067] d = v2tcos(θ2)cos(φ)

[0068] where E(t, θ2, φ) is the time-domain response of the transient electromagnetic signal, A(f, θ2, φ) is the frequency-domain response of the transient electromagnetic signal, t is the current time, f is the frequency, θ2 is the reflected or refracted angle, φ is the depression angle, j is the imaginary unit, 2πft is the phase factor describing the phase change of the signal at time t, d is the electromagnetic wave propagation depth, θ1 is the electromagnetic wave incidence angle, i.e., the angle at which the electromagnetic wave enters the medium interface, V1 is the propagation speed of the electromagnetic wave in the first medium, and V2 is the propagation speed of the electromagnetic wave in the second medium.

[0069] The time domain response of the electromagnetic signal can be transformed from the frequency domain signal by inverse Fourier transform. The frequency domain signal A(f, θ2, φ) is the response of the transient electromagnetic wave at a specific frequency f. By inverse Fourier transform, the frequency domain signal can be transformed into a time domain signal. Considering the reflection and refraction of electromagnetic waves, electromagnetic waves in different media will produce reflection and refraction due to the existence of medium interface, and then the propagation direction of the reflected electromagnetic wave can be described by Snell's law. The angle of the electromagnetic wave received by the antenna array is no longer a single elevation angle and depression angle, but is determined by the reflection or refraction angle.

[0070] Although the reflection and refraction angles of Snell's law mainly affect the propagation angle perpendicular to the interface normal direction (i.e. the change of the incident angle), the depression angle as the horizontal component of the electromagnetic wave determines another dimension of the electromagnetic wave propagation direction, which still affects the spatial distribution of the entire signal and data acquisition.

[0071] The elevation angle mainly describes the propagation path of the electromagnetic wave in the vertical direction, which affects the interaction (such as reflection, refraction) between the electromagnetic wave and the underground interface. The depression angle describes the propagation angle in the horizontal plane. Even if the propagation direction of the electromagnetic wave in different media changes due to Snell's law, the distribution in the horizontal plane still determines how the electromagnetic wave covers different spatial regions in the horizontal level.

[0072] The calculation formula of the depth d depends on the elevation angle and the depression angle. Even if the elevation angle changes due to reflection or refraction, the projection of the horizontal depression angle on the propagation depth is still effective, θ2 is the reflection or refraction angle adjusted by Snell's law, which affects the propagation in the vertical direction; φ still affects the propagation direction in the horizontal plane, and by adjusting the depression angle φ, the antenna can detect the change of the electromagnetic wave in the horizontal space, which is very important to improve the lateral resolution between the measurement points.

[0073] In practical applications, by jointly adjusting θ2 and φ, electromagnetic wave data acquisition at different depths and angles can be realized. The depression angle φ can control the horizontal propagation direction of the electromagnetic wave to ensure that the antenna array can cover a larger area in front of or beside the tunnel. Specifically, the detector adjusts φ point by point during measurement, so that the measurement density in the horizontal plane is higher, thereby increasing the lateral coverage of electromagnetic wave detection.

[0074] In some examples, further comprising:

[0075] The frequency domain response of the transient electromagnetic signal is determined based on the following formula:

[0076]

[0077] where A0(f) is the amplitude response at frequency f, which is the initial frequency-domain response of the signal without the influence of reflection or refraction, a(f, θ2, φ) is the attenuation coefficient, which represents the energy loss of the electromagnetic wave during propagation due to medium absorption and attenuation, the attenuation coefficient varies with frequency and antenna angle, β(f, θ2, φ) is the phase shift, which represents the phase change of the electromagnetic wave due to different geological structures during propagation.

[0078] For example, the angle θ2 changes the propagation path of the signal, affecting the energy distribution and phase shift of the signal. Due to the different propagation speeds and directions of waves at different angles on the reflecting surface or refracting medium, the attenuation a(f, θ2, φ) and the phase β(f, θ2, φ) are also adjusted accordingly.

[0079] The attenuation coefficient describes the energy loss of the wave during reflection or refraction. It is usually dependent on the dielectric properties of the material and the characteristics of the reflecting surface or refracting medium. The attenuation coefficient not only depends on the frequency f, but also depends on the incident angle θ2 and the depression angle φ, because the energy attenuation of the wave at different angles is different. For example, a larger incident angle will cause the attenuation of the wave penetrating the medium to increase, while a smaller reflection angle will cause the reflected wave to experience less energy loss.

[0080] The phase change represents the influence of reflection or refraction on the propagation phase of the wave. The wave will experience different phase shifts on different paths, and this shift is usually dependent on the propagation speed of the wave in the medium and the path length. For example, when the wave penetrates or reflects, it may experience different phase delays due to different electromagnetic properties of the medium or the lengthening of the path.

[0081] In some examples, the above-mentioned processing of the time-domain response of the transient electromagnetic signal using the adaptive filtering algorithm obtains processed data, including:

[0082] The adaptive filter is represented as:

[0083]

[0084] wherein, is the filtered processed data, representing the signal after the noise and interference are suppressed, w n is the weight coefficient of the adaptive filter, representing the influence of the filter on the signal at the past n time points, N is the order of the filter, t-n is the backtracking of the signal at the past n time points, the past signal is used to adjust the output signal at the current time point in the filtering process, represents the time point of the n sampling periods before the current time t, E(t-n, θ2, φ) is the time-domain response corresponding to the transient electromagnetic signal at t-n.

[0085] For example, given an input signal, the adaptive filter processes it to obtain a processed output signal. The output signal represents the filtered electromagnetic signal, with noise and interference effectively suppressed, resulting in significantly improved signal quality. The core of the adaptive signal processing algorithm lies in its ability to adaptively adjust filter parameters based on signal characteristics under different geological conditions. The specific adaptive adjustment strategy is as follows:

[0086] Noise detection: In complex geological environments, electromagnetic signals are often disturbed by background noise (such as steel frames, cables, external environmental electromagnetic fields, etc.). The adaptive filter can identify these noises by analyzing the frequency characteristics of the signal and reduce their impact by adjusting the weights.

[0087] Signal enhancement: The filter not only suppresses noise but also enhances useful signals through adaptive adjustment. By optimizing the loss function, the adaptive algorithm can amplify the useful parts of the electromagnetic signal, ensuring that geological information can still be effectively extracted in complex environments.

[0088] For example, N represents the order of the adaptive filter, i.e., the filter processes and weights the signals of the past N time points. In the adaptive filter, the signals of the past N time points are usually used to calculate the current output signal. It can be understood as the length of the historical data used by the filter. The larger this value, the more historical information the filter considers.

[0089] Specifically, N determines the complexity of the filter and the length of its memory for the input signal. For example, when N increases, the filter uses more past time signals to make estimates at the current time, which helps better suppress noise and interference, but may also increase computational complexity.

[0090] In some examples, it also includes:

[0091] The above weight coefficient w n is determined based on the following formula:

[0092]

[0093] wherein, and are the weight values of the filter at the kth and k+1th iterations, μ is the learning rate, and Loss is the loss function;

[0094] Loss = L1 + L2 + L3 + L4

[0095] wherein, D(t, θ2, φ) is the expected output signal, SNR(t) -1wherein, 1 / SNR is the inverse of signal-to-noise ratio, λ1 is a weight coefficient of the signal-to-noise ratio suppression term, λ2 is a weight coefficient of the sparsity penalty term, λ3 is a weight coefficient of the time-domain smoothness penalty term, and T is the length of the time series.

[0096] For example, in a complex geological environment, the signal is disturbed by multiple noises, and the sparsity and time-frequency characteristics of the signal are helpful to improve the signal quality. The defined loss function satisfies: the difference between the processed signal and the expected signal is minimized; the noise suppression term is increased to ensure that the noise component in the filtered signal is effectively weakened; the sparsity of the signal (i.e., the number of non-zero elements in the signal is small) can also be one of the optimization goals, which can preserve important information and remove unnecessary noise components; the time-frequency distribution characteristics of the electromagnetic signal need to be maintained during the filtering process to avoid distortion of the signal in the time-frequency domain.

[0097] The mean square error (MSE) of the first term measures the error square between the filtered signal and the expected signal; by minimizing this term, the filtered signal is closer to the expected signal. In the second term, λ1 is a weight coefficient for balancing the influence of the signal-to-noise ratio suppression term in the total loss function, and a larger λ1 will make the signal-to-noise ratio suppression more important; the inverse SNR(t) -1 , the signal-to-noise ratio (SNR) represents the ratio of signal strength to noise strength, and the inverse value indicates that the stronger the noise (the smaller the signal-to-noise ratio), the greater the weight of this term; therefore, in the time period with strong noise, the filter will pay more attention to suppressing noise; the square term of the filtered signal is multiplied by the signal-to-noise ratio SNR(t) -1 , which indicates that the stronger the signal strength, the stronger the demand for noise suppression. In the third term, λ2 is a weight coefficient for controlling the sparsity penalty term, and a larger λ2 value means that it is more inclined to preserve sparsity, making the signal as simple and clean as possible; is the L1 norm, which represents the sum of the absolute values of the signal, and this term is used to control the sparsity of the signal. By minimizing the L1 norm, most signal components can be made to approach 0, leaving only a few important signal components, achieving the requirement of sparsity. In the fourth term, λ3 is a weight coefficient for controlling the time-domain smoothness penalty term, and a larger λ3 value means that the signal is expected to change smoothly over time; the second derivative of the filtered signal represents the acceleration change of the signal over time. The larger the second derivative, the more intense the change of the signal over time. By minimizing this term, the signal can be made to change more smoothly over time; in order to ensure signal smoothness, the second derivative is squared, so that the signal will be more severely punished for intense changes.

[0098] In some examples, further comprising:

[0099] The three-dimensional geological model is determined based on the following formula:

[0100]

[0101] In the formula, M(x, y, z) is a three-dimensional geological model, representing the geological structure at the midpoint (x, y, z) in space; L is the total number of geological layers; l is the l-th geological layer; and w l Here, f represents the weighting coefficients for the l-th layer, B represents the total number of frequency bands, and f is the weighting coefficient for the l-th layer. i Let R(t, x, y, z, f) be the center frequency of the i-th frequency band. i δ(·) is the time-reversal operator, which converts the time-domain signal into spatial geological model information. This operator represents the propagation of an electromagnetic wave from time t. Through time reversal, it calculates the path of the wave propagating to location (x, y, z) in the geological model, and combines the frequency band and the characteristics of geological layer l for imaging. δ(·) is the instantaneous propagation impulse response, v l For electromagnetic waves in a geological medium of layer l, frequency f i The speed of propagation below.

[0102] For example, the reverse time migration algorithm is a high-precision algorithm commonly used in seismic exploration and electromagnetic data imaging. It reconstructs subsurface structural information by backpropagating electromagnetic signals measured on the ground. The core of 3D imaging is to construct a 3D subsurface structural model by using multi-band joint and multi-layer inversion methods to process processed transient electromagnetic signals. During imaging, electromagnetic waves of different frequency bands have different penetration depths; lower frequency bands are suitable for detecting deep geological structures, while higher frequency bands are suitable for detecting shallow structures. To improve imaging accuracy, electromagnetic data from multiple frequency bands are inverted to achieve multi-band joint imaging. Subsurface media often have multi-layered structures, with each layer having different conductivity and electromagnetic wave propagation characteristics. Therefore, in 3D imaging, the subsurface structure needs to be divided into multiple layers, and the inversion results of each layer are superimposed onto the final 3D model to achieve multi-layer inversion.

[0103] In some examples, the above-mentioned prediction of geological conditions based on anomaly density functions, pattern recognition algorithms, and the aforementioned 3D geological models includes:

[0104] Based on the above-mentioned anomaly density function and the above-mentioned three-dimensional geological model, the anomaly region is determined, wherein the above-mentioned anomaly density function is:

[0105]

[0106] In the formula, ρ a (x, y, z) represents the anomaly density value of point (x, y, z) in the three-dimensional geological model, reflecting whether the point is likely to belong to an anomalous area; σ(·) is the activation function (similar to the activation function in a neural network), used to normalize the calculation results, and can use functions such as Sigmoid or Tanh; Laplace operator, which is used to capture local variations in the model, especially in areas of rapid change (such as faults or cavities); μ M Mean density of the 3D geological model;

[0107] The above abnormal areas are identified based on the above pattern recognition algorithm to predict the above geological conditions, wherein the pattern recognition algorithm includes a feature extraction operation, an outlier classification operation and an outlier type optimization operation.

[0108] An exemplary Laplace operator is a tool for calculating the local variation of a 3D model, which can detect areas of rapid change in the model, such as faults or cavities, and its expression is:

[0109]

[0110] The above formula is the sum of the second derivatives of the model in three directions. If the Laplace value of a point is large, it indicates that there is a significant density change near the point, which may be an abnormal geological area.

[0111] Mean density μ M The expression is:

[0112]

[0113] Where V is the volume of the geological model.

[0114] First, calculate the abnormal density based on the 3D geological model. The goal of this step is to identify the local abnormal areas in the model. The calculation of the abnormal density function ρ a (x, y, z) will capture significant changes in the model by performing a Laplace operation on the second derivative of the model, including:

[0115] Calculate the Laplace operator of the 3D geological model M(x, y, z); Calculate the mean density to remove the effects of global uniformity; Calculate the abnormal density function.

[0116] Second, after detecting the abnormal density, perform a feature extraction operation on the abnormal areas to further input the pattern recognition algorithm for classification. The goal of feature extraction is to extract useful information from the abnormal areas that can represent the type of anomaly (such as faults, cavities, etc.), including: Extract shape features in the abnormal area, such as the size, shape, distribution of Laplace values, etc. of the region; Extract density distribution features, especially the density gradient and local density change rate in the abnormal area; Form a feature vector F(x, y, z) from these features as input for the next pattern recognition algorithm.

[0117] Then the outlier classification operation is performed, and the extracted features are classified using a pattern recognition algorithm. The specific algorithm can select a classifier such as a support vector machine (SVM), a random forest (Random Forest), or a neural network (Neural Networks). According to the feature vector, each outlier point is classified, including:

[0118] Training the classifier, training the classifier using prior data (historical geological data or simulation data), historical data set {F I , C I}, where F I is the feature vector of the Ith data point, and C I is the corresponding geological anomaly category (such as fault, cavity, etc.). The classifier f(F I ) is trained to learn the mapping relationship from the feature vector to the anomaly type C.

[0119] Applying the classifier, classifying the new three-dimensional geological model data. Using the trained classifier f(F(x, y, z), the feature vector of each point is classified to obtain the anomaly category (preliminary anomaly type) of each point, denoted as:

[0120] C(x, y, z) = f(F(x, y, z))

[0121] Finally, the anomaly type optimization operation is performed, and the classification result is optimized using a probability model. The maximum probability method is used to classify the points into the most likely anomaly type, including:

[0122] Using a Bayesian classifier or a neural network, the anomaly density p a (x, y, z) of each point (x, y, z) is calculated, which belongs to different categories P k (p a (x, y, z)), denoted as:

[0123] P k (p a (x, y, z)) = P(p a (x, y, z) | C k )

[0124] Where C k represents the kth anomaly category, and P k (p a (x, y, z)) represents the probability that the point (x, y, z) belongs to the category C k .

[0125] According to the maximum probability classification method, the anomaly of the point (x, y, z) is classified into the category with the maximum probability, denoted as:

[0126] C(x, y, z) = argmax k P k (k | ρ a (x, y, z))

[0127] where C(x, y, z) is the classification result at (x, y, z), indicating which type of geological anomaly this point belongs to; argmax k denotes finding the class k that maximizes the probability; P k (k | ρ a (x, y, z)) represents the probability distribution of the anomaly density value ρ a (x, y, z) belonging to class k; this probability is calculated by a pattern recognition algorithm, usually through a trained classifier (such as a neural network or random forest).

[0128] By calculating the anomaly density ρ a (x, y, z) of each point, and classifying these anomaly regions through a pattern recognition algorithm, the anomaly regions in the geological model can be divided into different categories. For example, faults may exhibit large amplitude density changes, while cavities may exhibit sudden density decreases. Through the probability model, determine which type of geological anomaly each point belongs to.

[0129] When multiple anomaly points are continuously distributed, they collectively form an anomaly region (such as a cavity or a fault). Therefore, the density function is first calculated at each point, and then the combination of multiple anomaly points forms an anomaly region, which can be composed by density changes. The pattern recognition algorithm analyzes and classifies the features of each point (such as density, shape, position, etc.), and identifies whether the point belongs to a certain type of geological anomaly (such as a cavity, a fault, etc.). Each point is independently classified, and then through the classification results of these points, the anomaly region can be further identified. For example, when multiple consecutive points are all classified as "cavity", the region composed of these points is a cavity region.

[0130] Once the anomaly region is identified, geological analysis can predict the geological conditions in front of the tunnel through simulation and evaluation, including:

[0131] First, a detailed analysis of the geometric and physical properties of these regions is needed, including:

[0132] The shape and size of the anomaly region, for example, whether it is a long strip-shaped fault, a circular or irregular-shaped cavity.

[0133] The spatial distribution of the region, by analyzing the location and distribution pattern of the anomaly region, it can be inferred whether these anomalies are isolated or have strong correlation with the surrounding geological structure.

[0134] Abnormal distribution of density or electrical conductivity, based on the physical properties of the region in the 3D model, such as fluctuations in electrical conductivity, to determine the type of geological material and its stability within the region.

[0135] Secondly, the identified abnormal regions are compared with existing geological databases or historical data, by comparing these abnormalities with similar structures in history, better understanding the nature of these abnormalities, including:

[0136] Historical tunnel engineering failure cases, by comparing abnormal regions with areas that have experienced collapse or other accidents in history, to determine whether these abnormalities have potential destructive.

[0137] Similar geological environment precedents, comparing the region with the same type of geological structure, further inferring the nature of the abnormal region and its possible stability.

[0138] Then, after identifying and analyzing abnormal regions, using physical models for simulation is a key step in predicting the geological conditions in front of the tunnel, by simulating the behavior of abnormal regions under different scenarios, predicting the potential changes of the region during tunnel excavation, simulation methods include:

[0139] Numerical simulation, using finite element method (FEM) or finite difference method (FDM) to simulate the abnormal region, simulate the influence of tunnel construction on the abnormal region, including stress, strain distribution.

[0140] Seismic wave simulation, simulating the influence of vibration on abnormal regions during tunnel construction, evaluating whether the abnormal region will experience structural instability or local collapse during construction.

[0141] Fluid dynamics simulation, if the abnormal region has aquifer, simulate the flow of water and its influence on geological structure, to judge the potential problems such as water seepage, corrosion in the region during construction.

[0142] Then, through the above-mentioned model simulation and historical data analysis, further evaluate the risk of identified abnormal regions to tunnel construction, including:

[0143] Collapse risk, evaluate the possibility of collapse of the region during tunnel excavation or construction, especially for the identified cavities and fault regions.

[0144] Groundwater leakage, simulate and evaluate whether there are hydrological related problems in the abnormal region, such as groundwater leakage, water inrush, etc., which may cause foundation instability or other hidden dangers during construction.

[0145] Explosive gas risk, in some geological environment, the abnormal region may be rich in gas, by monitoring and evaluating the gas content of the abnormal region, to determine whether there is a risk of sudden gas leakage or explosion.

[0146] Finally, after completing the above analysis and simulation, a comprehensive prediction of the geological conditions in front of the tunnel is made, including:

[0147] Short-term prediction, based on the structural characteristics of the current abnormal area, assesses the geological risks that may be encountered in the short term in front of the tunnel during construction, such as measures to deal with the abnormal area when the tunneling machine encounters it.

[0148] Long-term prediction, considering the impact of the abnormal area on the long-term safety of the entire tunnel, assesses whether the abnormal area will have a long-term impact after the tunnel is completed, such as the stability of the tunnel, maintenance requirements, etc.

[0149] Referring to Figure 2 A tunnel advanced geological prediction monitoring device structure schematic diagram provided by the embodiment of the present application comprises:

[0150] The acquisition unit 21 is configured to acquire the time-domain response of the transient electromagnetic signal.

[0151] The processing unit 22 is configured to process the time-domain response of the transient electromagnetic signal using an adaptive filtering algorithm to obtain processing data.

[0152] The generation unit 23 is configured to generate a three-dimensional geological model according to the processing data using a three-dimensional imaging algorithm.

[0153] The identification unit 24 is configured to predict the geological conditions based on the abnormal density function, the pattern recognition algorithm, and the three-dimensional geological model.

[0154] Referring to Figure 3 The embodiment of the present application also provides an electronic device 300, which comprises a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor, and the processor 320 implements the steps of any method of the tunnel advanced geological prediction monitoring method described above when executing the computer program 311.

[0155] Since the electronic device introduced in the embodiment is the device used in the tunnel advanced geological prediction monitoring device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device of the embodiment and its various forms, so the electronic device how to implement the method in the embodiment of the present application is not introduced in detail, as long as the device used by those skilled in the art to implement the method in the embodiment of the present application belongs to the scope of the present application.

[0156] In the specific implementation process, the computer program 311 can implement any embodiment in the first aspect when executed by the processor.

[0157] It should be noted that in the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0158] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-readable storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) containing computer-readable program code.

[0159] The embodiments of the present application are described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in one or more blocks.

[0160] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in one or more blocks.

[0161] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in one or more blocks.

[0162] The embodiments of the present application also provide a computer program product, which includes computer software instructions, when the computer software instructions run on a processing device, so that the processing device executes Figure 1The flow of the tunnel advanced geological prediction monitoring method in the corresponding embodiment.

[0163] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the flow or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that the computer can store or be integrated into a data storage device such as a server, data center, etc. containing one or more available media sets. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)) and the like.

[0164] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0165] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are only schematic. The division of units is only a logical function division. Actual implementation can have another division manner. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0166] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0167] In addition, each of the function units in each of the embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0168] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in each of the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0169] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit the same; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

[0170] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0171] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application also intends to include these modifications and variations.

Claims

1. A method for monitoring tunnel advance geological prediction, characterized in that, The method comprises: acquiring a time domain response of a transient electromagnetic signal; processing the time domain response of the transient electromagnetic signal using an adaptive filtering algorithm to obtain processed data; generating a three-dimensional geological model according to the processed data using a three-dimensional imaging algorithm; predicting a geological condition based on an abnormal density function, a pattern recognition algorithm and the three-dimensional geological model; The prediction of the geological condition based on the abnormal density function, the pattern recognition algorithm and the three-dimensional geological model comprises: determining an abnormal area based on the abnormal density function and the three-dimensional geological model, wherein the abnormal density function is: wherein, is an abnormal density value of a point in a three-dimensional geological model, is an activation function, is a Laplacian operator, is a three-dimensional geological model, is a mean density of the three-dimensional geological model; identifying the abnormal area based on the pattern recognition algorithm to predict the geological condition, wherein the pattern recognition algorithm comprises a feature extraction operation, an abnormal point classification operation and an abnormal type optimization operation.

2. The tunnel advance geological prediction monitoring method according to claim 1, characterized in that, The time domain response of the transient electromagnetic signal is represented as: wherein is the time domain response of the transient electromagnetic signal, is the frequency domain response of the transient electromagnetic signal, is the current time, is the frequency, is the reflected or refracted angle, is the depression angle, is the imaginary unit, is the phase factor, is the electromagnetic wave propagation depth, is the electromagnetic wave incidence angle, is the electromagnetic wave propagation speed in the first medium, is the electromagnetic wave propagation speed in the second medium.

3. The tunnel advance geological prediction monitoring method according to claim 2, characterized in that, Further comprising: determining a frequency domain response of the transient electromagnetic signal based on the following formula: wherein, is the amplitude response at frequency is the attenuation coefficient, which represents the energy loss of the electromagnetic wave due to medium absorption and attenuation during propagation, which varies with frequency and antenna angle, is the phase shift, which represents the phase change of the electromagnetic wave due to different geological structures during propagation.​ 4. The tunnel advance geological prediction monitoring method according to claim 2, characterized in that, The processing of the time domain response of the transient electromagnetic signal using the adaptive filtering algorithm to obtain the processed data comprises: The adaptive filter is represented as: In the formula, is the processed data after filtering, is the weight coefficient of the adaptive filter, is the order of the filter, is the current time is the time of the previous sampling period, is the time domain response corresponding to the transient electromagnetic signal at the time .

5. The tunnel advance geological prediction monitoring method according to claim 4, characterized in that, Further comprising: the weight coefficients are determined based on the following equation: In the formula, and The filters are respectively in the th... Second and third The weight value at the next iteration For learning rate, The loss function; wherein is a desired output signal, is an inverse signal-to-noise ratio, is a signal-to-noise ratio suppression term weight coefficient, is a sparsity penalty term weight coefficient, is a time-domain smoothness penalty term weight coefficient, is a time series length.

6. The tunnel advance geological prediction monitoring method according to claim 5, characterized in that, Further comprising: The three-dimensional geological model is determined based on the following formula: In the formula, is a three-dimensional geological model, which is a geological structure at a point in space, is the total number of geological layers, is the geological of the layer, is the weight coefficient of the layer, is the total number of frequency bands, is the center frequency of the frequency band, is the filtered post-processing data of the center frequency of the frequency band, is a time reversal operator, which converts a time domain signal into spatial geological model information, is an instantaneous propagation impulse response, is the propagation velocity of an electromagnetic wave in a layer geological medium at a frequency .​ 7. A tunnel advance geological prediction monitoring device, characterized in that, comprising: an acquisition unit configured to acquire a time domain response of a transient electromagnetic signal; a processing unit configured to process the time domain response of the transient electromagnetic signal using an adaptive filtering algorithm to obtain processed data; a generation unit configured to generate a three-dimensional geological model according to the processed data using a three-dimensional imaging algorithm; an identification unit configured to predict a geological condition based on an abnormal density function, a pattern recognition algorithm and the three-dimensional geological model; The prediction of the geological condition based on the abnormal density function, the pattern recognition algorithm and the three-dimensional geological model comprises: determining an abnormal area based on the abnormal density function and the three-dimensional geological model, wherein the abnormal density function is: wherein is an anomalous density value of a point in a three-dimensional geological model, is an activation function, is a Laplacian operator, is a three-dimensional geological model, is a mean density of the three-dimensional geological model; identifying the abnormal area based on the pattern recognition algorithm to predict the geological condition, wherein the pattern recognition algorithm comprises a feature extraction operation, an abnormal point classification operation and an abnormal type optimization operation.

8. An electronic device comprising: A memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the tunnel advance geological prediction monitoring method according to any one of claims 1-6 when executing the computer program stored in the memory.

9. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to implement the tunnel advance geological prediction monitoring method according to any one of claims 1-6.

Images