Prediction method for shield to pass through karst cave in karst area

Abstract

The invention discloses a prediction method for a shield to pass through a karst cave in a karst area, and belongs to the technical field of karst cave prediction.The method comprises the steps that reflected waves of the karst area are collected through a detector in the working process of a shield tunneling machine, the instantaneous frequency, the instantaneous amplitude and the instantaneous phase of P waves and S waves are calculated, and changes of the frequency, the amplitude and the phase at each moment are reflected; the phase inversion coefficient, the amplitude change coefficient, the frequency change coefficient and the energy attenuation coefficient of the P wave and the amplitude change coefficient and the energy attenuation coefficient of the S wave are captured, and the response characteristics of the P wave and the S wave to the karst cave can be effectively reflected. And by combining the characteristic coefficients and the processing of the karst cave prediction model, the accuracy of karst cave prediction can be further improved, and a powerful guarantee is provided for shield construction safety.

Description

Technical Field

[0001] The invention relates to the technical field of karst cave prediction, and in particular to a method for predicting karst caves when a shield machine passes through a karst area. Background Art

[0002] With the continuous development of urban underground engineering construction, shield tunnel construction has become more and more common in infrastructure construction such as transportation and subways. However, during the shield construction process, encountering complex geological conditions such as karst areas and caves often brings safety hazards, increased construction difficulties and economic losses. Therefore, accurately predicting the distribution of caves in karst areas is of great significance to ensure the construction safety and efficiency of shield projects.

[0003] The karst area is a special geological structure formed by soluble rocks (such as limestone, dolomite, etc.) under the erosion of water, with obvious spatial changes and unevenness. The existence of caves will lead to the weakening of soil strength, settlement and landslide risks, while traditional geological exploration methods, such as drilling and geological radar, usually have problems such as high cost, long cycle, and difficulty in comprehensive coverage, which are difficult to meet the real-time and precision requirements of shield construction.

[0004] In recent years, geological information acquisition technology based on seismic reflection detection has gradually been used. The reflected wave signal collected by the detector is used to analyze the signal components of the reflected wave signal to obtain geological information. However, in the karst area, there are obvious spatial variations and unevenness. It is difficult to fully reflect the location of the cave from the signal components, resulting in the problem of low accuracy in cave prediction. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present invention provides: a method for predicting karst caves when a shield tunnel passes through a karst area, which solves the problem of low karst cave prediction accuracy in the prior art.

[0006] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is: a method for predicting karst caves when a shield tunnel passes through a karst area, comprising the following steps:

[0007] S1. Collect the reflected waves from the karst area when the shield machine is working through the detector;

[0008] S2, respectively calculate the instantaneous frequency, instantaneous amplitude and instantaneous phase of the P wave and S wave in the reflected wave;

[0009] S3, extracting the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient according to the instantaneous phase, instantaneous amplitude and instantaneous frequency at multiple consecutive moments in the P wave;

[0010] S4, extracting the amplitude variation coefficient and energy attenuation coefficient according to the instantaneous amplitudes at multiple moments in the S wave;

[0011] S5. According to the cave prediction model, the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P wave, as well as the amplitude variation coefficient and energy attenuation coefficient of the S wave are processed to obtain the cave prediction distance.

[0012] Further, extracting the phase reversal coefficient in S3 includes the following steps:

[0013] A1. In a plurality of consecutive moments, the instantaneous phase of the latter moment is subtracted from the instantaneous phase of the previous moment in two adjacent moments, and the absolute value is taken to obtain a phase difference, and the plurality of phase differences are added to obtain a phase difference addition result;

[0014] A2. In a plurality of consecutive moments, subtract the maximum instantaneous phase from the minimum instantaneous phase to obtain the maximum difference;

[0015] A3. Add the maximum difference and the phase difference addition result, and normalize them to obtain a phase reversal coefficient.

[0016] Further, the specific process of extracting the amplitude variation coefficient in S3 and S4 is as follows: in a plurality of consecutive moments, the instantaneous amplitude at the latter moment is subtracted from the instantaneous amplitude at the previous moment in two adjacent moments, and the absolute value is taken to obtain an amplitude difference, multiple amplitude differences are added to obtain an amplitude difference addition result, and the amplitude difference addition result is normalized to obtain an amplitude variation coefficient;

[0017] The specific process of extracting the frequency change coefficient in S3 is: in a plurality of consecutive moments, subtract the instantaneous frequency of the latter moment from the instantaneous frequency of the previous moment in two adjacent moments, and take the absolute value to obtain a frequency difference, add a plurality of frequency differences to obtain a frequency difference addition result, and normalize the frequency difference addition result to obtain the frequency change coefficient.

[0018] Furthermore, the specific process of extracting the energy attenuation coefficient in S3 and S4 is: at multiple consecutive moments, square the instantaneous amplitude, accumulate the squared instantaneous amplitudes to obtain energy, and in the time length N, take the normalized value of the ratio of the maximum energy to the minimum energy as the energy attenuation coefficient, where N is a positive integer.

[0019] Further, the cave prediction model in S5 includes: an S-wave feature extraction unit, a P-wave feature extraction unit, a first Concat layer, a transposition operation layer, a multiplier M1, a Conv layer, a dual-channel feature enhancement unit and a fully connected layer;

[0020] The input end of the S-wave feature extraction unit is used to input the amplitude variation coefficient and energy attenuation coefficient of the S-wave; the input end of the P-wave feature extraction unit is used to input the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P-wave; the input end of the first Concat layer is respectively connected to the output end of the S-wave feature extraction unit and the output end of the P-wave feature extraction unit, and its output end is respectively connected to the input end of the transposition operation layer and the first input end of the multiplier M1; the second input end of the multiplier M1 is connected to the output end of the transposition operation layer, and its output end is connected to the input end of the Conv layer; the input end of the dual-channel feature enhancement unit is connected to the output end of the Conv layer, and its output end is connected to the input end of the fully connected layer; the output end of the fully connected layer serves as the output end of the cave prediction model.

[0021] Further, the S-wave feature extraction unit includes: an amplitude processing channel and an energy processing channel;

[0022] In the S-wave feature extraction unit, the amplitude processing channel is used to process the amplitude variation coefficient of the S-wave, and the energy processing channel is used to process the energy attenuation coefficient of the S-wave;

[0023] The P wave feature extraction unit includes: a phase processing channel, an amplitude processing channel, a frequency processing channel and an energy processing channel;

[0024] In the P wave feature extraction unit, the phase processing channel is used to process the phase reversal coefficient of the P wave, the amplitude processing channel is used to process the amplitude variation coefficient of the P wave, the frequency processing channel is used to process the frequency variation coefficient of the P wave, and the energy processing channel is used to process the energy attenuation coefficient of the P wave.

[0025] Further, the phase processing channel, the amplitude processing channel, the frequency processing channel and the energy processing channel each include: a Tanh activation layer, a Sigmoid activation layer and a multiplier M2;

[0026] The Tanh activation layer is used to assign weights and biases to the coefficients of the input phase processing channel, amplitude processing channel, frequency processing channel or energy processing channel to obtain a first eigenvalue; the Sigmoid activation layer is used to assign weights and biases to the coefficients of the input phase processing channel, amplitude processing channel, frequency processing channel or energy processing channel to obtain a second eigenvalue; the multiplier M2 is used to multiply the first eigenvalue and the second eigenvalue to obtain a channel output.

[0027] Furthermore, the first Concat layer is used to concatenate the output features of the S wave feature extraction unit and the output features of the P wave feature extraction unit to obtain a concatenated vector a, and the transposition operation layer is used to perform a transposition operation on the concatenated vector a to obtain an operation result a TThe multiplier M1 is used to convert the operation result a T Multiply it with the concatenated vector a to get the fusion matrix A, A = a T a, where T is the transpose operation.

[0028] Furthermore, the dual-channel feature enhancement unit includes: a GAP layer, a GMP layer, a mean feature enhancement layer, a significant feature enhancement layer and a second Concat layer;

[0029] The input ends of the GAP layer and the GMP layer are both used as input ends of the dual-channel feature enhancement unit;

[0030] The input end of the mean feature enhancement layer is connected to the output end of the GAP layer;

[0031] The input end of the salient feature enhancement layer is connected to the output end of the GMP layer;

[0032] The input end of the second Concat layer is connected to the output end of the mean feature enhancement layer and the output end of the significant feature enhancement layer respectively, and the output end thereof serves as the output end of the dual-channel feature enhancement unit.

[0033] Furthermore, the mean feature enhancement layer is used to enhance the mean feature output by the GAP layer;

[0034] The significant feature enhancement layer is used to enhance the maximum value feature output by the GMP layer.

[0035] The beneficial effects of the present invention are as follows: the present invention collects the reflected waves in the karst area through the detector during the operation of the shield machine, calculates the instantaneous frequency, instantaneous amplitude and instantaneous phase of the P wave and the S wave respectively, and reflects the changes in frequency, amplitude and phase at each moment. In the cave, the P wave shows obvious frequency reduction and phase reversal. The reason is that the interior of the cave is usually filled with air or water, forming a significant acoustic impedance difference with the surrounding rocks. This difference leads to a high reflection coefficient, so that the signal intensity returned from the cave boundary is relatively large. At the same time, the S wave can only propagate in the solid, and when encountering a fluid-filled cave, a strong energy conversion and attenuation will occur. Therefore, capturing the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P wave, as well as the amplitude variation coefficient and energy attenuation coefficient of the S wave, can effectively reflect the response characteristics of the P wave and the S wave to the cave. Combining these characteristic coefficients with the processing of the cave prediction model can further improve the accuracy of the cave prediction and provide a strong guarantee for the safety of shield construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of a method for predicting caves when a shield tunnel passes through a karst area;

[0037] Figure 2This is a schematic diagram of the structure of the cave prediction model;

[0038] Figure 3 It is a structural schematic diagram of the S wave feature extraction unit;

[0039] Figure 4 It is a structural schematic diagram of a P wave feature extraction unit;

[0040] Figure 5 It is a structural schematic diagram of a phase processing channel, an amplitude processing channel, a frequency processing channel or an energy processing channel. DETAILED DESCRIPTION

[0041] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0042] like Figure 1 As shown, a method for predicting a karst cave when a shield machine passes through a karst area comprises the following steps:

[0043] S1. Collect the reflected waves from the karst area when the shield machine is working through the detector;

[0044] S2, respectively calculate the instantaneous frequency, instantaneous amplitude and instantaneous phase of the P wave and S wave in the reflected wave;

[0045] S3, extracting the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient according to the instantaneous phase, instantaneous amplitude and instantaneous frequency at multiple consecutive moments in the P wave;

[0046] S4, extracting the amplitude variation coefficient and energy attenuation coefficient according to the instantaneous amplitudes at multiple moments in the S wave;

[0047] S5. According to the cave prediction model, the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P wave, as well as the amplitude variation coefficient and energy attenuation coefficient of the S wave are processed to obtain the cave prediction distance.

[0048] Extracting the phase reversal coefficient in S3 comprises the following steps:

[0049] A1. In a plurality of consecutive moments, the instantaneous phase of the latter moment is subtracted from the instantaneous phase of the previous moment in two adjacent moments, and the absolute value is taken to obtain a phase difference, and the plurality of phase differences are added to obtain a phase difference addition result;

[0050] A2. In a plurality of consecutive moments, subtract the maximum instantaneous phase from the minimum instantaneous phase to obtain the maximum difference;

[0051] A3. Add the maximum difference and the phase difference addition result, and normalize them to obtain a phase reversal coefficient.

[0052] In this embodiment, the calculation formula of the phase reversal coefficient is: Among them, α t is the phase reversal coefficient at the tth moment in the P wave, arctan is the inverse tangent function, P τ is the instantaneous phase of the P wave at the τth moment, P τ-1 is the instantaneous phase of the P wave at the τ-1th moment, max is the maximum value, min is the minimum value, || is the absolute value, t s is the starting time, t is the current time, and τ is the superimposed variable.

[0053] In the presence of a cave, the P wave will experience an obvious phase reversal when passing through the cave boundary. By comparing the phases at adjacent moments, the phase change can be accurately identified, thus reflecting the presence of a cave.

[0054] The specific process of extracting the amplitude variation coefficient in S3 and S4 is as follows: in a plurality of consecutive moments, the instantaneous amplitude of the latter moment is subtracted from the instantaneous amplitude of the previous moment in two adjacent moments, and the absolute value is taken to obtain the amplitude difference, the plurality of amplitude differences are added to obtain the amplitude difference addition result, and the amplitude difference addition result is normalized to obtain the amplitude variation coefficient.

[0055] In this embodiment, the calculation formula of the amplitude variation coefficient is: Among them, β t is the amplitude variation coefficient at the tth moment, F τ is the instantaneous amplitude at the τth moment, F τ-1 is the instantaneous amplitude at the τ-1th moment, || is the absolute value operation, t s is the starting time, t is the current time, τ is the superposition variable, and arctan is the inverse tangent function.

[0056] When P-waves and S-waves encounter a cave, the sudden change in acoustic impedance will cause the amplitude of the wave to change significantly. P-waves will produce strong reflections at the cave boundary, causing the amplitude to increase sharply; while S-waves will undergo strong energy conversion and attenuation when encountering a fluid-filled cave, causing the amplitude to decrease sharply. The present invention calculates the amplitude differences at consecutive moments, accumulates and normalizes these differences, and obtains an indicator that can quantitatively describe the degree of amplitude change.

[0057] The specific process of extracting the frequency change coefficient in S3 is: in a plurality of consecutive moments, subtract the instantaneous frequency of the latter moment from the instantaneous frequency of the previous moment in two adjacent moments, and take the absolute value to obtain a frequency difference, add a plurality of frequency differences to obtain a frequency difference addition result, and normalize the frequency difference addition result to obtain the frequency change coefficient.

[0058] In this embodiment, the calculation formula of the frequency variation coefficient is: Among them, γ t is the frequency change coefficient at time t, f τ is the instantaneous frequency at the τth moment, f τ-1 is the instantaneous frequency at the τ-1th moment, || is the absolute value operation, t s is the starting time, t is the current time, τ is the superposition variable, and arctan is the inverse tangent function.

[0059] When a P wave passes through a cave, since the interior of the cave is usually filled with air or water, there is a significant acoustic impedance difference with the surrounding rocks. This difference causes a significant decrease in the frequency of the P wave. By calculating the instantaneous frequency changes at consecutive moments, this frequency reduction phenomenon can be effectively captured, and the frequency change coefficient can be extracted as a key indicator.

[0060] The specific process of extracting the energy attenuation coefficient in S3 and S4 is as follows: in a plurality of consecutive moments, square the instantaneous amplitude, accumulate the squared instantaneous amplitude to obtain energy, and in a time length N, take the normalized value of the ratio of the maximum energy to the minimum energy as the energy attenuation coefficient, where N is a positive integer.

[0061] In this embodiment, the calculation formula of the energy attenuation coefficient is: Among them, θ t is the energy attenuation coefficient at the tth moment, max is the maximum value, min is the maximum value, F τ is the instantaneous amplitude at the τth moment, t s is the starting time, t is the current time, τ is the superposition variable, E t is the energy at the tth moment, E t-i is the energy at the ti moment, E t-N is the energy at the tNth moment, i is a positive integer, N is the time length, N is a positive integer, and arctan is the inverse tangent function.

[0062] When P-waves and S-waves propagate to the cave area, the energy of the waves will be significantly attenuated due to the significant difference in acoustic impedance. Specifically, P-waves will maintain high energy at the cave boundary due to strong reflection, while S-waves will experience significant energy loss when encountering fluid-filled caves. This energy change feature can be quantified by calculating the energy attenuation coefficient at continuous moments, which can effectively reflect the existence and characteristics of the cave.

[0063] like Figure 2 As shown, the cave prediction model in S5 includes: an S-wave feature extraction unit, a P-wave feature extraction unit, a first Concat layer, a transposition operation layer, a multiplier M1, a Conv layer, a dual-channel feature enhancement unit and a fully connected layer;

[0064] The input end of the S-wave feature extraction unit is used to input the amplitude variation coefficient and energy attenuation coefficient of the S-wave; the input end of the P-wave feature extraction unit is used to input the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P-wave; the input end of the first Concat layer is respectively connected to the output end of the S-wave feature extraction unit and the output end of the P-wave feature extraction unit, and its output end is respectively connected to the input end of the transposition operation layer and the first input end of the multiplier M1; the second input end of the multiplier M1 is connected to the output end of the transposition operation layer, and its output end is connected to the input end of the Conv layer; the input end of the dual-channel feature enhancement unit is connected to the output end of the Conv layer, and its output end is connected to the input end of the fully connected layer; the output end of the fully connected layer serves as the output end of the cave prediction model.

[0065] The present invention sets an S-wave feature extraction unit to process the amplitude variation coefficient and energy attenuation coefficient of the S-wave, sets a P-wave feature extraction unit to process the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P-wave, adopts the first Concat layer to realize the splicing of P-wave and S-wave features, and then adopts the transposition operation layer to perform the transposition operation. At the multiplier M1, a fusion matrix A is constructed to realize the conversion from one-dimensional data to two-dimensional data. The Conv layer is adopted to perform convolution processing, and the dual-channel feature enhancement unit is adopted to enhance different features. The fully connected layer calculates the cave prediction distance according to the features output by the dual-channel feature enhancement unit.

[0066] like Figure 3 As shown, the S wave feature extraction unit includes: an amplitude processing channel and an energy processing channel;

[0067] In the S-wave feature extraction unit, the amplitude processing channel is used to process the amplitude variation coefficient of the S-wave, and the energy processing channel is used to process the energy attenuation coefficient of the S-wave;

[0068] like Figure 4As shown, the P wave feature extraction unit includes: a phase processing channel, an amplitude processing channel, a frequency processing channel and an energy processing channel;

[0069] In the P wave feature extraction unit, the phase processing channel is used to process the phase reversal coefficient of the P wave, the amplitude processing channel is used to process the amplitude variation coefficient of the P wave, the frequency processing channel is used to process the frequency variation coefficient of the P wave, and the energy processing channel is used to process the energy attenuation coefficient of the P wave.

[0070] like Figure 5 As shown, the phase processing channel, amplitude processing channel, frequency processing channel and energy processing channel all include: a Tanh activation layer, a Sigmoid activation layer and a multiplier M2;

[0071] The Tanh activation layer is used to assign weights and biases to the coefficients of the input phase processing channel, amplitude processing channel, frequency processing channel or energy processing channel to obtain a first eigenvalue; the Sigmoid activation layer is used to assign weights and biases to the coefficients of the input phase processing channel, amplitude processing channel, frequency processing channel or energy processing channel to obtain a second eigenvalue; the multiplier M2 is used to multiply the first eigenvalue and the second eigenvalue to obtain a channel output.

[0072] In the S-wave feature extraction unit, there are two channels that process two coefficients respectively. In the P-wave feature extraction unit, there are four channels that process four coefficients respectively. In each channel, two different activation functions, Tanh and Sigmoid, are used to enhance the nonlinear expression capability of the model and better fit the complex data distribution. The eigenvalues ​​processed by different activation functions are multiplied by multiplier M2 to achieve effective feature fusion and capture higher-order feature combinations.

[0073] The first Concat layer is used to concatenate the output features of the S wave feature extraction unit and the output features of the P wave feature extraction unit to obtain a concatenated vector a, and the transposition operation layer is used to perform a transposition operation on the concatenated vector a to obtain an operation result a T The multiplier M1 is used to convert the operation result a T Multiply it with the concatenated vector a to get the fusion matrix A, A = a T a, where T is the transpose operation.

[0074] The dual-channel feature enhancement unit includes: a GAP layer, a GMP layer, a mean feature enhancement layer, a significant feature enhancement layer and a second Concat layer;

[0075] The input ends of the GAP layer and the GMP layer are both used as input ends of the dual-channel feature enhancement unit;

[0076] The input end of the mean feature enhancement layer is connected to the output end of the GAP layer;

[0077] The input end of the salient feature enhancement layer is connected to the output end of the GMP layer;

[0078] The input end of the second Concat layer is connected to the output end of the mean feature enhancement layer and the output end of the significant feature enhancement layer respectively, and the output end thereof serves as the output end of the dual-channel feature enhancement unit.

[0079] The GAP layer is a global average pooling layer, and the GMP layer is a global maximum pooling layer.

[0080] The mean feature enhancement layer is used to enhance the mean feature output by the GAP layer;

[0081] The significant feature enhancement layer is used to enhance the maximum value feature output by the GMP layer.

[0082] The present invention can capture the global average and maximum features at the same time through the parallel GAP and GMP layers, providing a more comprehensive feature representation. Secondly, the mean and significant feature enhancement layers are connected to the outputs of the GAP and GMP layers respectively, which can further strengthen and refine different types of features. The introduction of the second Concat layer realizes the effective fusion of features, combining the enhanced mean and significant features to produce a richer feature representation.

[0083] In this embodiment, the expressions of the mean feature enhancement layer and the significant feature enhancement layer are both: X=BN(x)·(1+BN(x)), where X is the enhanced feature, BN is the BN layer, and x is the feature to be enhanced.

[0084] The present invention adopts BN layer processing for the features to be enhanced, and applies attention (1+BN(x)) according to the BN layer result to achieve adaptive adjustment of the attention of important features.

[0085] In this embodiment, the cave prediction model is trained using the gradient descent method. When constructing training samples, the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P wave, the amplitude variation coefficient and energy attenuation coefficient of the S wave are used as samples, and the cave distance is used as a label.

[0086] The present invention collects reflected waves in the karst area through a detector during the operation of the shield machine, and calculates the instantaneous frequency, instantaneous amplitude and instantaneous phase of the P wave and the S wave respectively, reflecting the changes in frequency, amplitude and phase at each moment. In the cave, the P wave shows obvious frequency reduction and phase reversal. The reason is that the interior of the cave is usually filled with air or water, forming a significant acoustic impedance difference with the surrounding rocks. This difference leads to a high reflection coefficient, so that the signal intensity returned from the cave boundary is relatively large. At the same time, the S wave can only propagate in solids, and when encountering a fluid-filled cave, strong energy conversion and attenuation will occur. Therefore, capturing the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P wave, as well as the amplitude variation coefficient and energy attenuation coefficient of the S wave, can effectively reflect the response characteristics of the P wave and the S wave to the cave. Combining these characteristic coefficients with the processing of the cave prediction model can further improve the accuracy of cave prediction and provide a strong guarantee for the safety of shield construction.

[0087] When predicting caves, the present invention abandons the analysis of signal components, focuses on the response characteristics of P waves and S waves to caves, and then uses a cave prediction model to predict the cave prediction distance, thereby improving the accuracy of cave prediction.

[0088] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting caves in a karst area when a shield machine passes through it, characterized in that: The following steps are involved: S1. Collect the reflected waves from the karst area when the shield machine is working through the detector; S2, respectively calculate the instantaneous frequency, instantaneous amplitude and instantaneous phase of the P wave and S wave in the reflected wave; S3, extracting the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient according to the instantaneous phase, instantaneous amplitude and instantaneous frequency at multiple consecutive moments in the P wave; S4, extracting the amplitude variation coefficient and energy attenuation coefficient according to the instantaneous amplitudes at multiple moments in the S wave; S5. According to the cave prediction model, the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P wave, as well as the amplitude variation coefficient and energy attenuation coefficient of the S wave are processed to obtain the cave prediction distance.

2. The method for predicting caves in a karst area when a shield machine passes through according to claim 1 is characterized in that: Extracting the phase reversal coefficient in S3 comprises the following steps: A1. In a plurality of consecutive moments, the instantaneous phase of the latter moment is subtracted from the instantaneous phase of the previous moment in two adjacent moments, and the absolute value is taken to obtain a phase difference, and the plurality of phase differences are added to obtain a phase difference addition result; A2. In a plurality of consecutive moments, subtract the maximum instantaneous phase from the minimum instantaneous phase to obtain the maximum difference; A3. Add the maximum difference and the phase difference addition result, and normalize them to obtain a phase reversal coefficient.

3. The method for predicting a karst cave when a shield machine passes through a karst area according to claim 1, characterized in that: The specific process of extracting the amplitude variation coefficient in S3 and S4 is as follows: in a plurality of consecutive moments, the instantaneous amplitude at the latter moment is subtracted from the instantaneous amplitude at the previous moment between two adjacent moments, and the absolute value is taken to obtain an amplitude difference, multiple amplitude differences are added to obtain an amplitude difference addition result, and the amplitude difference addition result is normalized to obtain an amplitude variation coefficient; The specific process of extracting the frequency change coefficient in S3 is: in a plurality of consecutive moments, subtract the instantaneous frequency of the latter moment from the instantaneous frequency of the previous moment in two adjacent moments, and take the absolute value to obtain a frequency difference, add a plurality of frequency differences to obtain a frequency difference addition result, and normalize the frequency difference addition result to obtain the frequency change coefficient.

4. The method for predicting a karst cave when a shield machine passes through a karst area according to claim 1, characterized in that: The specific process of extracting the energy attenuation coefficient in S3 and S4 is as follows: in a plurality of consecutive moments, square the instantaneous amplitude, accumulate the squared instantaneous amplitude to obtain energy, and in a time length N, take the normalized value of the ratio of the maximum energy to the minimum energy as the energy attenuation coefficient, where N is a positive integer.

5. The method for predicting a karst cave when a shield machine passes through a karst area according to claim 1, characterized in that: The cave prediction model in S5 includes: an S-wave feature extraction unit, a P-wave feature extraction unit, a first Concat layer, a transposition operation layer, a multiplier M1, a Conv layer, a dual-channel feature enhancement unit and a fully connected layer; The input end of the S-wave feature extraction unit is used to input the amplitude variation coefficient and energy attenuation coefficient of the S-wave; the input end of the P-wave feature extraction unit is used to input the phase reversal coefficient, amplitude variation coefficient, frequency variation coefficient and energy attenuation coefficient of the P-wave; the input end of the first Concat layer is respectively connected to the output end of the S-wave feature extraction unit and the output end of the P-wave feature extraction unit, and its output end is respectively connected to the input end of the transposition operation layer and the first input end of the multiplier M1; the second input end of the multiplier M1 is connected to the output end of the transposition operation layer, and its output end is connected to the input end of the Conv layer; the input end of the dual-channel feature enhancement unit is connected to the output end of the Conv layer, and its output end is connected to the input end of the fully connected layer; the output end of the fully connected layer serves as the output end of the cave prediction model.

6. The method for predicting a karst cave when a shield machine passes through a karst area according to claim 5, characterized in that: The S wave feature extraction unit includes: an amplitude processing channel and an energy processing channel; In the S-wave feature extraction unit, the amplitude processing channel is used to process the amplitude variation coefficient of the S-wave, and the energy processing channel is used to process the energy attenuation coefficient of the S-wave; The P wave feature extraction unit includes: a phase processing channel, an amplitude processing channel, a frequency processing channel and an energy processing channel; In the P wave feature extraction unit, the phase processing channel is used to process the phase reversal coefficient of the P wave, the amplitude processing channel is used to process the amplitude variation coefficient of the P wave, the frequency processing channel is used to process the frequency variation coefficient of the P wave, and the energy processing channel is used to process the energy attenuation coefficient of the P wave.

7. The method for predicting a karst cave when a shield machine passes through a karst area according to claim 6, characterized in that: The phase processing channel, amplitude processing channel, frequency processing channel and energy processing channel all include: a Tanh activation layer, a Sigmoid activation layer and a multiplier M2; The Tanh activation layer is used to assign weights and biases to the coefficients of the input phase processing channel, amplitude processing channel, frequency processing channel or energy processing channel to obtain a first eigenvalue; the Sigmoid activation layer is used to assign weights and biases to the coefficients of the input phase processing channel, amplitude processing channel, frequency processing channel or energy processing channel to obtain a second eigenvalue; the multiplier M2 is used to multiply the first eigenvalue and the second eigenvalue to obtain a channel output.

8. The method for predicting caves in a karst area when a shield machine passes through according to claim 5 is characterized in that: The first Concat layer is used to concatenate the output features of the S wave feature extraction unit and the output features of the P wave feature extraction unit to obtain a concatenated vector a, and the transposition operation layer is used to perform a transposition operation on the concatenated vector a to obtain an operation result a T The multiplier M1 is used to convert the operation result a T Multiply it with the concatenated vector a to get the fusion matrix A, A = a T a, where T is the transpose operation.

9. The method for predicting caves in a karst area when a shield machine passes through according to claim 5, characterized in that: The dual-channel feature enhancement unit includes: a GAP layer, a GMP layer, a mean feature enhancement layer, a significant feature enhancement layer and a second Concat layer; The input ends of the GAP layer and the GMP layer are both used as input ends of the dual-channel feature enhancement unit; The input end of the mean feature enhancement layer is connected to the output end of the GAP layer; The input end of the salient feature enhancement layer is connected to the output end of the GMP layer; The input end of the second Concat layer is connected to the output end of the mean feature enhancement layer and the output end of the significant feature enhancement layer respectively, and the output end thereof serves as the output end of the dual-channel feature enhancement unit.

10. The method for predicting caves in a karst area when a shield machine passes through according to claim 9, characterized in that: The mean feature enhancement layer is used to enhance the mean feature output by the GAP layer; The significant feature enhancement layer is used to enhance the maximum value feature output by the GMP layer.

Images