Near-bit formation detection method based on acoustic wave ahead-looking while drilling

Abstract

The application discloses a near-bit formation detection method based on while-drilling acoustic forward-looking, and belongs to the technical field of formation detection, and comprises the following steps: S1, acquiring a while-drilling acoustic signal generated by rock breaking of a drill bit in a drilling process, performing time-frequency analysis on the while-drilling acoustic signal, and determining a while-drilling acoustic source feature in combination with theoretical analysis; S2, performing independent component analysis on the while-drilling acoustic signal, and combining with ensemble empirical mode decomposition (CEEMD) and wavelet transform to identify effective while-drilling acoustic signals from complex background noise; and S3, establishing a geophysical model of a bad geological body containing a lithology boundary surface, a fault fracture zone, a karst cave and a water-rich formation, and obtaining a propagation rule and characteristic parameters of the while-drilling acoustic signal in the model by using a time-domain finite difference numerical simulation method. Through multi-algorithm collaborative processing, the while-drilling acoustic signal with high signal-to-noise ratio and obvious characteristics is extracted from the complex background noise, and the reliability and accuracy of signal processing are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of stratum exploration, and more particularly to a near-bit stratum exploration method based on acoustic wave look-ahead while drilling. BACKGROUND

[0002] The measurement-while-drilling technology is a widely used method in oil and gas exploration and geological drilling, which obtains physical signals near the drill bit or drill pipe during drilling to assist in judging the structure and properties of the stratum. As an important means, acoustic wave measurement while drilling can provide acoustic wave information of the stratum in front of the drill bit, so as to realize the pre-judgment of lithology changes and adverse geological bodies (such as fault fracture zone, karst cave, water-rich layer, etc.). However, the existing acoustic wave measurement while drilling method has the following main problems: complex noise is generated by rock breaking of the drill bit during drilling, including mechanical vibration, drilling pressure fluctuation, and drill pipe resonance, etc., so that the acoustic wave signal while drilling appears as low signal-to-noise ratio and unclear time-frequency characteristics at the receiving end. The traditional filtering or simple frequency domain analysis method is difficult to accurately extract the effective acoustic wave signal from the complex background, which affects the accuracy of stratum exploration. The existing technology usually cannot accurately determine the comprehensive characteristic parameters of the acoustic wave source while drilling, such as the main frequency, frequency band width, energy attenuation coefficient, and directivity, etc. by combining theoretical analysis, which leads to the lack of pertinence of signal processing and stratum imaging model, and affects the reliability of the imaging result. The traditional method relies on empirical formula or simple numerical simulation, and it is difficult to fully consider the influence of complex adverse geological bodies such as lithology boundary, fault fracture zone, karst cave, and water-rich layer, etc., and lacks high-precision acoustic wave propagation rule modeling and characteristic parameter extraction means. At the same time, the existing imaging method has limited training and prediction ability for large-scale and multi-type geological bodies, and it is difficult to realize high-precision real-time imaging of the stratum in front of the near-bit. SUMMARY

[0003] The present application aims to provide a near-bit stratum exploration method based on acoustic wave look-ahead while drilling, to solve the problems raised in the background art: complex noise is generated by rock breaking of the drill bit during drilling, including mechanical vibration, drilling pressure fluctuation, and drill pipe resonance, etc., so that the acoustic wave signal while drilling appears as low signal-to-noise ratio and unclear time-frequency characteristics at the receiving end. The traditional filtering or simple frequency domain analysis method is difficult to accurately extract the effective acoustic wave signal from the complex background, which affects the accuracy of stratum exploration. The existing technology usually cannot accurately determine the comprehensive characteristic parameters of the acoustic wave source while drilling, such as the main frequency, frequency band width, energy attenuation coefficient, and directivity, etc. by combining theoretical analysis, which leads to the lack of pertinence of signal processing and stratum imaging model, and affects the reliability of the imaging result. The traditional method relies on empirical formula or simple numerical simulation, and it is difficult to fully consider the influence of complex adverse geological bodies such as lithology boundary, fault fracture zone, karst cave, and water-rich layer, etc., and lacks high-precision acoustic wave propagation rule modeling and characteristic parameter extraction means. At the same time, the existing imaging method has limited training and prediction ability for large-scale and multi-type geological bodies, and it is difficult to realize high-precision real-time imaging of the stratum in front of the near-bit.

[0004] A near-bit formation detection method based on acoustic wave while drilling forward-looking, comprising the following steps:

[0005] S1, obtaining the acoustic wave while drilling signal generated by the rock breaking of the drill bit in the drilling process, performing time-frequency analysis on the acoustic wave while drilling signal, and determining the acoustic wave while drilling source characteristics in combination with theoretical analysis;

[0006] S2, performing independent component analysis on the acoustic wave while drilling signal, and combining with ensemble empirical mode decomposition (CEEMD) and wavelet transform to identify effective acoustic wave while drilling signals from complex background noise;

[0007] S3, establishing a geophysical model of adverse geological bodies including lithological boundary surface, fault fracture zone, karst cave and water-rich formation, and using the time-domain finite difference numerical simulation method to obtain the propagation law and characteristic parameters of the acoustic wave while drilling in the model;

[0008] S4, constructing an acoustic wave field characteristic sample library of adverse geological bodies based on the characteristic parameters, and training the sample library using a deep learning model to obtain an adverse geological body imaging model;

[0009] S5, inputting the obtained acoustic wave while drilling signal into the adverse geological body imaging model to obtain the imaging result of the formation structure in front of the drill bit.

[0010] Preferably, the determination of the acoustic wave while drilling source characteristics in S1 comprises the following steps:

[0011] The time-frequency distribution characteristics of the acoustic wave while drilling in different time intervals are obtained by performing time-frequency decomposition on the acoustic wave while drilling signal using short-time Fourier transform;

[0012] Based on the propagation theory of the acoustic wave while drilling, the spectrum distribution is model fitted and parameter inverted to extract the main frequency component, frequency band width, energy attenuation coefficient and directivity parameter of the acoustic wave while drilling source, so as to obtain a source characteristic parameter set representing the comprehensive characteristics of the acoustic wave while drilling source in time domain and frequency domain.

[0013] Preferably, the step of identifying effective acoustic wave while drilling signals from complex background noise in S2 is as follows:

[0014] S2.1, performing detrending and normalization processing on the acoustic wave while drilling signal, and setting a band-pass filter according to the acoustic wave while drilling source characteristic parameters (including main frequency component and frequency band width) determined in S1 to perform band-pass filtering on the acoustic wave while drilling signal, then frame and window the filtered signal according to a fixed frame length to obtain a frame signal set to be decomposed;

[0015] S2.2, applying a collection empirical mode decomposition (CEEMD) to the frame signal to decompose it into a plurality of intrinsic mode functions (IMFs) and a residual term, and calculating an instantaneous energy, an instantaneous frequency distribution, and a spectral centroid of each IMF for representing time-frequency energy concentration;

[0016] S2.3, performing a discrete wavelet transform on the IMFs, extracting different frequency band features according to a multi-scale decomposition manner, and performing denoising processing on wavelet coefficients by using a soft threshold method, and then reconstructing the denoised IMFs by inverse wavelet transform, and simultaneously calculating a multi-scale energy distribution and an energy proportion;

[0017] S2.4, sorting and filtering the IMFs according to the energy proportion, spectral matching degree with a seismic source main frequency band, instantaneous frequency stability, and kurtosis, and the like, based on the while-drilling acoustic wave source feature parameters and the IMF features, and retaining a plurality of candidate IMFs with high matching degrees with the while-drilling acoustic wave source features;

[0018] S2.5, constructing a matrix of the candidate IMFs in a multi-channel dimension, inputting the matrix into an independent component analysis (ICA) algorithm for blind source separation to obtain a plurality of independent components, and respectively calculating a cross-correlation coefficient with the while-drilling acoustic wave source features, an energy concentration degree of the independent components, a signal-to-noise ratio, and an instantaneous frequency consistency;

[0019] S2.6, selecting an independent component satisfying a requirement as an effective independent component according to the energy proportion, the cross-correlation coefficient with the while-drilling acoustic wave source feature template, the signal-to-noise ratio, and the instantaneous frequency consistency, and the like, of the independent components, performing wavelet domain denoising processing on the effective independent component, and then weighting and superimposing the effective independent component to obtain a reconstructed effective while-drilling acoustic wave signal;

[0020] Preferably, when the source feature parameters cannot be obtained, a preset empirical frequency band is used for band-pass filtering.

[0021] Preferably, the specific steps of S3 are as follows:

[0022] S3.1, establishing a geophysical model of a bad geological body according to lithology, fault fracture zones, karst caves, water-rich layers, and the like of a drilled formation;

[0023] S3.2, obtaining a propagation law of a while-drilling acoustic wave in the geophysical model by using a numerical simulation method;

[0024] S3.3, extracting acoustic wave propagation feature parameters, including a propagation time, an amplitude, an energy attenuation, and a spectral feature, from the simulation result;

[0025] S3.4, combining the feature parameters with corresponding geological type information to construct a bad geological body acoustic wave field feature sample library for subsequent imaging model training.

[0026] Preferably, the S4 specific steps are as follows:

[0027] S4.1, input the acoustic wave field characteristic sample library of adverse geologic body into the deep learning model for training the model to identify different types of adverse geologic body;

[0028] S4.2, construct a deep learning model including deep neural network, convolutional neural network or space-time Transformer, etc. for establishing the mapping relationship between the characteristic parameters and the geological types;

[0029] S4.3, define the loss function and optimize the model parameters through iteration to minimize the error between the prediction result and the true geological type label;

[0030] S4.4, after the training, an adverse geologic body imaging model is obtained, which can input the acoustic characteristics while drilling to predict the formation structure in front of the near-bit, realizing formation imaging.

[0031] Preferably, the S5 specific steps are as follows:

[0032] S5.1, input the effective acoustic characteristics while drilling obtained into the trained adverse geologic body imaging model to predict the formation type label in front of the near-bit;

[0033] S5.2, map the predicted formation type label to spatial distribution representation to form three-dimensional or two-dimensional imaging of the near-bit formation structure;

[0034] S5.3, set a decision threshold according to the imaging result to mark the key adverse geologic body area, realizing abnormal formation identification;

[0035] S5.4, output the formation type prediction result, spatial imaging result and marking result for guiding drilling operation or conducting geological analysis.

[0036] Preferably, the model fitting of the source characteristic parameters adopts least square fitting, genetic algorithm or particle swarm optimization algorithm, and the parameters include source main frequency component in the range of 100-5000 Hz, frequency band width in the range of 50-1000 Hz, energy attenuation coefficient in the range of 0.1-5 dB / m, and directivity parameter as the angle range related to the rotation direction of the drill bit.

[0037] Preferably, in the S2, the frame length of the frame after band-pass filtering and windowing is 50-500 ms, the sampling rate is 10-100 kHz, the windowing type is Hanning window or Hamming window, the CEEMD decomposition layer number is 5-10 layers, the wavelet denoising adopts Daubechies wavelet, the soft threshold is set according to 0.2-0.5 times of the channel noise energy, and the ICA separation matrix is realized by maximizing mutual information or minimizing high-order moment.

[0038] Preferably, the fault fracture zone, cave and water-rich layer in the adverse geologic body geophysical model are alternatively set as different stratum combinations, and the acoustic wave propagation law is simulated by a time domain finite difference method, and the characteristic parameters include propagation time, amplitude, spectral center frequency, instantaneous frequency and energy attenuation index.

[0039] Compared with the prior art, the present application has the following advantages:

[0040] (1) The present application combines multi-algorithm collaborative processing such as collection empirical mode decomposition (CEEMD), wavelet transform and independent component analysis (ICA) to extract the while-drilling acoustic signal with high signal-to-noise ratio and obvious characteristics from complex background noise, thereby improving the reliability and accuracy of signal processing.

[0041] (2) The present application accurately obtains the main frequency component, frequency band width, energy attenuation coefficient and directivity parameter of the while-drilling acoustic wave source through short-time Fourier transform, model fitting and parameter inversion, so that the signal processing and stratum imaging are targeted, and the accuracy of stratum identification is enhanced.

[0042] (3) The present application establishes an adverse geologic body geophysical model containing lithology boundary, fault fracture zone, cave and water-rich layer, and extracts acoustic wave propagation characteristic parameters by using time domain finite difference numerical simulation, thereby realizing accurate characterization of the acoustic wave behavior of complex geologic body.

[0043] (4) The present application trains a deep learning model based on the acoustic wave field characteristic sample library, realizes automatic identification and prediction of different types of adverse geologic body, can quickly map the while-drilling acoustic wave characteristics to the two-dimensional or three-dimensional imaging results of the stratum structure in front of the near-bit, and supports real-time decision-making of drilling operation.

[0044] (5) The present application marks the key adverse geologic body region and identifies abnormal stratum, can early warn the potential geologic risk, optimizes the drilling strategy, reduces drilling accidents and drill bit wear, and improves the safety and economic benefit of drilling operation. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 The flow chart of the near-bit stratum detection method based on while-drilling acoustic wave forward-looking of the present application. DETAILED DESCRIPTION

[0046] The technical solutions of the present application will be described clearly and completely below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0047] Please refer toFigure 1 The near-bit formation detection method based on the while-drilling acoustic forward-looking comprises the following steps:

[0048] S1, obtaining the while-drilling acoustic signal generated by the rock breaking of the drill bit in the drilling process, performing time-frequency analysis on the while-drilling acoustic signal, and determining the while-drilling acoustic source characteristics in combination with theoretical analysis;

[0049] The determination of the while-drilling acoustic source characteristics in S1 comprises the following steps:

[0050] The frequency spectrum distribution characteristics of the while-drilling acoustic signal in different time intervals are obtained by performing time-frequency decomposition on the while-drilling acoustic signal using short-time Fourier transform; when performing short-time Fourier transform (STFT) time-frequency analysis on the while-drilling acoustic signal, the time window length of the STFT is 10-50 ms, the overlap rate is 50%-80%, and the frequency resolution is 5-50 Hz;

[0051] The frequency spectrum distribution is model fitted and parameter inverted based on the while-drilling acoustic propagation theory; the model fitting method comprises least square fitting or genetic algorithm optimization to obtain the source characteristic parameters with the smallest fitting error; the main frequency component, frequency band width, energy attenuation coefficient, and directivity parameter of the while-drilling acoustic source are extracted, so as to obtain the source characteristic parameter set representing the comprehensive characteristics of the while-drilling acoustic source in the time domain and the frequency domain.

[0052] The while-drilling acoustic source characteristic parameters are extracted from the fitting model, comprising:

[0053] The main frequency component f0, whose typical range is 500-5000 Hz;

[0054] The frequency band width Δf, whose typical range is 200-2000 Hz;

[0055] The energy attenuation coefficient α, whose typical range is 0.05-0.5 dB / m;

[0056] The directivity parameter θ, whose typical range is ±30°, is used to represent the directional energy distribution of the source;

[0057] S2, performing independent component analysis on the while-drilling acoustic signal, and combining the ensemble empirical mode decomposition (CEEMD) and wavelet transform to identify the effective while-drilling acoustic signal from the complex background noise;

[0058] S3, establishing a geophysical model of adverse geological bodies including lithological boundaries, fault fracture zones, karst caves, and water-rich formations, and using the time-domain finite difference numerical simulation method to obtain the propagation law and characteristic parameters of the while-drilling acoustic signal in the model;

[0059] S4, constructing a bad geological body acoustic field characteristic sample library based on the characteristic parameters, and training the sample library by using a deep learning model to obtain a bad geological body imaging model;

[0060] S5, inputting the acquired acoustic signal while drilling into the bad geological body imaging model to obtain an imaging result of a formation structure in front of a drill bit.

[0061] The S2 of identifying effective acoustic signals while drilling from complex background noise comprises the following steps:

[0062] S2.1 signal preprocessing

[0063] The acoustic signals while drilling are subjected to detrending and normalization processing;

[0064] The signals are divided into frames according to a frame length , a Hamming window or a Hanning window is used for windowing, a frame overlap rate is , and a sampling rate is ;

[0065] A band-pass filter is set according to the source characteristic parameters determined in S1, and the filtering range covers half of the ± frequency bandwidth of the main frequency component.

[0066] S2.2 ensemble empirical mode decomposition (CEEMD)

[0067] The frame signals are subjected to CEEMD decomposition to obtain a plurality of IMFs and a residual term;

[0068] The CEEMD noise amplitude is times the standard deviation of the original signal, and the iteration number is .

[0069] S2.3 wavelet transform denoising

[0070] The IMFs are subjected to discrete wavelet transform (multi-scale decomposition layers are 3-6 layers), and a Daubechies or Symlets wavelet is used as a wavelet base;

[0071] The wavelet coefficients are subjected to soft threshold value method denoising, and the threshold value formula is:

[0072]

[0073] Wherein: denotes the noise standard deviation of the IMF signal; denotes the IMF signal length.

[0074] Inverse wavelet transform is used to reconstruct the denoised IMFs, and multi-scale energy distribution and energy proportion are calculated.

[0075] S2.4 IMF screening

[0076] IMFs are sorted and filtered by the following indicators:

[0077] Energy proportion:

[0078]

[0079] Where: Ei represents the energy of the i-th IMF; E represents the sum of all IMF energies.

[0080] Spectrum matching degree:

[0081]

[0082] Where:

[0083] Sj represents the spectrum of the j-th IMF;

[0084]

[0085]

[0086] Instantaneous frequency stability:

[0087]

[0088] Where: σfi represents the standard deviation of the instantaneous frequency of the i-th IMF.

[0089] Kurtosis:

[0090]

[0091] Where: Kj represents the kurtosis of the j-th IMF.

[0092] IMFs that meet the above conditions are selected as candidate IMFs.

[0093] S2.5 Independent Component Analysis (ICA)

[0094] The candidate IMFs are constructed into a matrix in the multi-channel dimension , input into the ICA algorithm for blind source separation, calculate the separation matrix and iterate and optimize until convergence;

[0095] Select independent components that meet the following conditions as valid independent components:

[0096] Energy proportion:​​​​​​​

[0097] Cross-correlation coefficient with source signature template

[0098] Signal-to-noise ratio

[0099] Instantaneous frequency consistency

[0100] S2.6 Effective signal reconstruction

[0101] After wavelet domain denoising processing of the independent components meeting the conditions, the final effective while-drilling acoustic signal is obtained by energy proportion weighted superposition :

[0102]

[0103] Wherein: represents the reconstructed effective while-drilling acoustic signal; represents the th independent component signal; represents the weighting coefficient, which is set according to the energy proportion of each independent component; represents the th independent component energy; represents the number of effective independent components; represents the wavelet domain denoising function.

[0104] The specific steps of S3 are as follows:

[0105] S3.1 Establishment of adverse geologic body model

[0106] A geophysical model of adverse geologic body containing lithology interface, fault fracture zone, karst cave and water-rich stratum is constructed;

[0107] The model parameters include lithology density , elastic modulus , Poisson's ratio , fault thickness , karst cave radius , water-rich layer porosity, etc., which are used to describe the physical properties of the stratum.

[0108] Note: These parameters are used to describe the spatial distribution and physical properties of the adverse geologic body, and the specific values can be set according to the drilling site measurement or geological data.

[0109] S3.2 While-drilling acoustic wave numerical simulation

[0110] The propagation of while-drilling acoustic wave in the model is simulated by using the finite difference time domain (FDTD) method, and the basic update formula is:

[0111]

[0112] wherein: denotes the displacement of the th grid node at the th time step; denotes the time step length; denotes the density of the th grid node; denotes the elastic modulus of the th grid node; denotes the spatial derivative operator.

[0113] S3.3 Feature parameter extraction

[0114] After obtaining the acoustic wave propagation field while drilling, the following set of feature parameters are extracted:

[0115]

[0116] wherein: denotes the travel time of the acoustic wave to reach the peak value; denotes the peak amplitude; denotes the energy attenuation coefficient, wherein is the source amplitude, is the amplitude at the propagation distance denotes the central frequency or spectral feature parameter of the acoustic wave.

[0117] S3.4 Construction of acoustic wave field feature sample library of adverse geological bodies

[0118] The feature parameters extracted in S3.3 are combined with the corresponding geological body type labels to form the acoustic wave field feature sample library of adverse geological bodies:

[0119]

[0120] wherein: denotes the acoustic wave field feature sample library of adverse geological bodies; denotes the number of samples; denotes the set of feature parameters of the th sample; denotes the geological type label corresponding to the th sample.

[0121] The specific steps of the S4 are as follows:

[0122] S4.1 Sample input

[0123] The acoustic wave field feature sample library of adverse geological bodies constructed in S3.4 is inputted into the model: ​​Input the deep learning model;

[0124] wherein: represents the acoustic feature parameter set (propagation time, amplitude, energy attenuation, spectral feature, etc.) of the th sample; represents the adverse geological body type label corresponding to the th sample; represents the total number of samples.

[0125] S4.2 Model structure

[0126] Use a deep neural network (DNN), convolutional neural network (CNN), or spatio-temporal Transformer model Train the sample, and the model output is the predicted geological body type:

[0127]

[0128] wherein: represents the deep learning model, is a set of trainable parameters; represents the predicted geological body type of the th sample.

[0129] S4.3 Loss function and training optimization

[0130] Define the loss function to measure the deviation between the predicted result and the true label, for example, cross-entropy loss:

[0131]

[0132] wherein: represents the total number of geological body categories; represents the true label (0 or 1) of the th sample in category ; represents the predicted probability of the model output in category .

[0133] Update by gradient descent or Adam optimization algorithm, until converges or reaches the preset number of iterations.

[0134] S4.4 Imaging model output

[0135] After training, the adverse geological body imaging model is obtained:

[0136]

[0137] wherein: denotes the trained bad geology imaging model; denotes the optimized parameters obtained by training; the acoustic features while drilling can be input to predict the formation structure near the drill bit, realizing formation imaging.

[0138] The specific steps of S5 are as follows:

[0139] S5.1 Feature input

[0140] The acquired effective acoustic feature vector while drilling is input into the trained bad geology imaging model :

[0141]

[0142] wherein: denotes the acoustic feature parameters while drilling, including propagation time, peak amplitude, energy attenuation coefficient, and spectral features; denotes the trained bad geology imaging model; denotes the formation type label near the drill bit predicted by the model.

[0143] S5.2 Imaging inference

[0144] The is converted into a spatial distribution representation of the formation structure in front of the drill bit :

[0145]

[0146] wherein: denotes the spatial coordinate formation imaging result; denotes a function based on model output for spatial interpolation or mapping.

[0147] S5.3 Visualization and analysis

[0148] The is visualized as a three-dimensional formation model or a two-dimensional profile for determining the location and range of bad geology;

[0149] Thresholds can be combined to mark key bad geology:

[0150]

[0151] wherein: denotes a marking matrix, 1 represents a bad geology area, and 0 represents a normal formation; denotes a formation type determination threshold, which is determined according to experience or model training.

[0152] S5.4 Output for application

[0153] Output 、 and Results for guiding drilling operation or geological analysis;

[0154] Through the output, real-time monitoring and early warning of the formation structure near the front of the drill bit can be achieved.

[0155] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above examples, and the above examples and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for near-bit formation detection based on acoustic look-ahead while drilling, characterized in that, The method comprises the following steps: S1, acquiring a while-drilling acoustic signal generated by rock breaking of a drill bit in a drilling process, performing time-frequency analysis on the while-drilling acoustic signal, and determining a while-drilling acoustic source feature in combination with theoretical analysis; S2, performing independent component analysis on the while-drilling acoustic signal, identifying effective while-drilling acoustic signals from complex background noise in combination with ensemble empirical mode decomposition (CEEMD) and wavelet transform; S3, establishing a geophysical model of a bad geological body including a lithology boundary, a fault fracture zone, a karst cave and a water-rich stratum, and obtaining propagation rules and characteristic parameters of while-drilling acoustic waves in the model by using a time-domain finite difference numerical simulation method; S4, constructing a while-drilling acoustic field feature sample library based on the characteristic parameters, and training the sample library by using a deep learning model to obtain a bad geological body imaging model; S5, inputting the acquired while-drilling acoustic feature into the bad geological body imaging model to obtain imaging results of a formation structure in front of the drill bit; The step of determining the while-drilling acoustic source feature in S1 comprises the following steps: obtaining frequency spectrum distribution characteristics of while-drilling acoustic waves in different time intervals by performing time-frequency decomposition on the while-drilling acoustic signal by using short-time Fourier transform; model fitting and parameter inversion are performed on the frequency spectrum distribution based on a while-drilling acoustic wave propagation theory, main frequency components, frequency band width, energy attenuation coefficients and directivity parameters of the while-drilling acoustic source are extracted, the directivity parameters are angle ranges related to a drill bit rotation direction, thereby a source feature parameter set representing comprehensive characteristics of the while-drilling acoustic source in time domain and frequency domain is obtained, and model fitting of the source feature parameter is performed by using least square fitting, genetic algorithm or particle swarm optimization algorithm to obtain source feature parameters with minimum fitting error; The step of identifying effective while-drilling acoustic signals from complex background noise in S2 comprises the following steps: S2.1, performing detrending and normalization processing on the while-drilling acoustic signal, setting a band-pass filter according to the while-drilling acoustic source feature parameters determined in S1, performing band-pass filtering on the while-drilling acoustic signal, then framing and windowing the filtered signal according to a fixed frame length to obtain a frame signal set to be decomposed; S2.2, applying ensemble empirical mode decomposition (CEEMD) to the frame signal to decompose it into a plurality of intrinsic mode functions (IMFs) and a residual term, and calculating instantaneous energy, instantaneous frequency distribution and spectral centroid of each IMF for representing time-frequency energy concentration; S2.3, performing discrete wavelet transform on the IMF, extracting different frequency band features according to a multi-scale decomposition mode, performing denoising processing on wavelet coefficients by using a soft threshold method, and reconstructing the denoised IMF by inverse wavelet transform, while calculating multi-scale energy distribution and energy proportion; S2.4, according to the while-drilling acoustic source feature parameters in S1 and in combination with IMF features, sorting and screening the IMFs according to energy proportion, spectral matching degree with a source main frequency band, instantaneous frequency stability and kurtosis index, and retaining a plurality of candidate IMFs with high matching degree with the while-drilling acoustic source feature. S2.5, the candidate IMF is constituted into a matrix in the multi-channel dimension, an independent component analysis (ICA) algorithm is inputted to perform blind source separation, a plurality of independent components are obtained, and a cross-correlation coefficient with the while-drilling acoustic wave source feature template, an energy proportion of the independent component, a signal-to-noise ratio, and an instantaneous frequency consistency are respectively calculated in S1; S2.6, according to the energy proportion of the independent component, the cross-correlation coefficient with the while-drilling acoustic wave source feature template, the signal-to-noise ratio of the independent component, and the instantaneous frequency consistency criterion, an independent component meeting the requirement is selected as an effective independent component, a wavelet domain denoising processing is performed on the effective independent component, and a weighted superposition is performed to obtain a reconstructed effective while-drilling acoustic wave signal.

2. The near-bit formation detection method based on acoustic wave while-drilling look-ahead of claim 1, wherein, When the source feature parameter cannot be obtained, a preset empirical frequency band is used for band-pass filtering.

3. The near-bit formation detection method based on acoustic wave while-drilling look-ahead of claim 1, wherein, The specific steps of S3 are as follows: S3.1, a geophysical model of the adverse geological body is established according to the lithology, fault fracture zone, karst cave, and water-rich layer characteristics of the drilled stratum; S3.2, in the geophysical model, a numerical simulation method is used to obtain the propagation law of the while-drilling acoustic wave; S3.3, acoustic wave propagation feature parameters, including propagation time, amplitude, energy attenuation, and spectral features, are extracted from the simulation results; S3.4, the feature parameters are combined with corresponding geological type information to construct an adverse geological body acoustic wave field feature sample library for subsequent imaging model training.

4. The near-bit formation investigation method based on acoustic while drilling look-ahead of claim 3, wherein, The specific steps of S4 are as follows: S4.1, the adverse geological body acoustic wave field feature sample library is inputted into a deep learning model for training the model to identify different types of adverse geological bodies; S4.2, a deep learning model is constructed, including a deep neural network, a convolutional neural network, or a space-time Transformer, to establish a mapping relationship between the feature parameters and the geological types; S4.3, a loss function is defined and the model parameters are iteratively optimized to minimize the error between the prediction result and the true geological type label; S4.4, after the training is completed, an adverse geological body imaging model is obtained, which can input the while-drilling acoustic wave features to predict the stratum structure near the front of the drill bit, realizing stratum imaging.

5. The near-bit formation investigation method based on acoustic wave while-drilling look-ahead of claim 4, wherein, The specific steps of S5 are as follows: S5.1, the obtained effective while-drilling acoustic wave features are inputted into the trained adverse geological body imaging model to predict the stratum type label near the front of the drill bit; S5.2, the predicted stratum type label is mapped to a spatial distribution representation to form a three-dimensional or two-dimensional imaging of the stratum structure near the drill bit; S5.3, according to the imaging result, a determination threshold is set to mark the key adverse geological body area, realizing abnormal stratum identification; S5.4, the stratum type prediction result, spatial imaging result, and marking result are outputted to guide the drilling operation or conduct geological analysis.

6. The near-bit formation detection method based on acoustic wave while-drilling look-ahead of claim 1, wherein, The source feature parameter range includes a source main frequency component in the range of 100-5000 Hz, a frequency band width in the range of 50-1000 Hz, and an energy attenuation coefficient in the range of 0.1-5 dB / m.

7. The near-bit formation detection method based on acoustic wave while-drilling look-ahead of claim 1, wherein, The frame length of the band-pass filtered frame in S2 is 50-500 ms, the sampling rate is 10-100 kHz, the window type is Hanning window or Blackman window, the decomposition layer number of ensemble empirical mode decomposition is 5-10 layers, the wavelet denoising adopts Daubechies wavelet, the soft threshold is set according to 0.2-0.5 times of the channel noise energy, and the ICA separation matrix is realized by maximizing mutual information or minimizing high-order moments.

8. The near-bit formation investigation method based on acoustic wave while-drilling look-ahead of claim 3, wherein, The fault fracture zone, karst cave and water-rich layer in the geophysical model of the adverse geological body can be alternatively set as different stratum combinations, and the sound wave propagation law is simulated by a time domain finite difference method, and the sound wave propagation characteristic parameters include propagation time, amplitude, spectral center frequency, instantaneous frequency and energy attenuation index.

Images