Near-bit formation detection method, system and device, electronic equipment and medium

Abstract

The invention relates to the technical field of logging while drilling, and discloses a near-bit stratum detection method, system and device, electronic equipment and a medium, and the method comprises the steps: transmitting a seismic wave to a to-be-detected stratum in front of a drill bit through an underground vibroseis, and receiving a reflected wave signal of the to-be-detected stratum through a geophone; calculating the relative position of the stratum in front of the drill to the drill in real time according to the reflected wave signal; acquiring a first lithologic seismic wave characteristic parameter of the reflected wave signal and a second lithologic seismic wave characteristic parameter of a known typical stratum; matching the first lithologic characteristic wave characteristic parameter with the second lithologic seismic wave characteristic parameter, and determining the formation lithology and the geological structure of the formation to be detected; outputting the stratum information of the to-be-measured stratum including the distance data, the stratum lithology and the geological structure; the seismic waves are not affected by various complex geological environments, the stratum information of the stratum to be measured can be accurately obtained, the drilling risk is reduced, and the drilling efficiency and safety are improved.

Description

Background Art

[0002] The forward distance parameter while drilling is a key geological parameter used in geosteering drilling systems to predict formations in real time and provide drilling guidance information. The forward distance parameter while drilling is developed on the basis of traditional logging while drilling technology. It is a measurement method that can measure the formation information in front of the drill bit in real time during drilling. During the drilling process, the uncertainty of the geological body information in front of the drill bit is the main cause of drilling accidents, so it is particularly important to obtain the distance parameter of the geological body in front of the drill bit in real time. The forward distance parameter while drilling technology can not only predict the formation structure and formation characteristics to be measured in front of the drill bit during drilling; it can also predict the high-pressure layer, depleted oil layer and the top boundary of the complex salt layer in front of the drill bit to guide geological drilling stop; it can optimize the cementing casing design (casing shoe position) and adjust the drilling fluid density in real time to reduce the number of times the downhole drilling tool assembly goes out of the well; it can reduce drilling uncertainty, optimize development plans, and make early judgments and disposals for drilling risks.

[0003] In the process of oil drilling and geological exploration, accurate detection of formation information ahead of the drill bit is of great significance for optimizing drilling paths, preventing drilling risks, and improving drilling efficiency. Traditional measurement while drilling technologies mostly rely on electromagnetic or acoustic wave measurements. For example, the drill bit while drilling seismic (R-VSP) technology is used to obtain formation information ahead of the drill bit. The drill bit while drilling seismic (R-VSP) technology can detect geological structures within a range of hundreds to thousands of meters from the drill bit, which is helpful for geological predictions in a large range. Seismic wave data can provide continuous profiles of underground structures, which helps to identify complex structures such as geological faults and salt domes. However, the resolution of seismic signals while drilling is low, and it is impossible to guide drilling projects at "meter-level accuracy". The application effect is poor for deep wells, highly deviated wells, soft formations, etc.

[0004] Another example is the use of electromagnetic wave prospecting technology while drilling to obtain formation information ahead of the drill bit. The electromagnetic wave prospecting technology while drilling can provide high-resolution formation electrical information with a measurement accuracy of less than 1m, which helps to accurately identify the electrical characteristics of the formation and rock ahead of the drill bit. It has a wider adaptability to mud types and can work in mud systems with different conductivity. However, the detection depth of electromagnetic waves is relatively shallow. The maximum prospecting distance of mature tools is currently 30m. It is greatly affected by the formation conductivity and the electric field of the downhole instrument. The prospecting distance is unstable and is not suitable for formation environments with high resistivity and unclear electrical characteristics.

[0005] Another example is the use of acoustic foresight while drilling technology to obtain formation information ahead of the drill bit. The data collected by acoustic foresight while drilling technology can be used to determine porosity, pore pressure, rock mechanical parameters, gas layer identification, fracture evaluation, and seismic data time-depth relationship correction. However, acoustic foresight while drilling technology is still in the theoretical stage. The key factor restricting its development is that there is no effective method to increase the acoustic energy radiated ahead of the drill bit, which cannot meet the requirements of engineering foresight.

[0006] In summary, the current traditional measurement while drilling technology cannot adapt to the various complex geological environments during the drilling process and cannot obtain accurate formation information in front of the drill bit. Summary of the invention

[0007] In order to overcome the problem that traditional measurement while drilling technology cannot adapt to various complex geological environments during drilling and cannot obtain accurate formation information in front of the drill bit, the present invention provides a near-drill bit formation detection method, system, device, electronic equipment and medium.

[0008] In a first aspect, in order to solve the above technical problems, the present invention provides a near-drill-bit formation detection method, comprising:

[0009] The seismic source in the well emits seismic waves of preset frequency and preset energy to the formation to be measured in front of the drill bit, and the seismic detector receives the reflected wave signal of the formation to be measured;

[0010] Calculate the relative position of the formation in front of the drill bit to the drill bit in real time based on the reflected wave signal;

[0011] Acquire a first lithology seismic wave characteristic parameter of a reflection wave signal and a second lithology seismic wave characteristic parameter of a known typical stratum;

[0012] Matching the characteristic parameters of the first lithology characteristic wave with the characteristic parameters of the second lithology seismic wave to determine the lithology and geological structure of the stratum to be measured;

[0013] The output includes stratigraphic information of the measured strata including distance data, stratigraphic lithology and geological structure.

[0014] In a second aspect, the present invention provides a near-drill-bit formation detection system, comprising:

[0015] A reflected wave signal receiving module is used to transmit seismic waves of a preset frequency and preset energy to the formation to be measured in front of the drill bit through a downhole controllable vibrator, and receive the reflected wave signal of the formation to be measured through a seismic detector;

[0016] A relative position determination module is used to calculate the relative position of the formation in front of the drill bit from the drill bit in real time based on the reflected wave signal;

[0017] A lithology seismic wave characteristic parameter acquisition module, used to acquire a first lithology seismic wave characteristic parameter of a reflection wave signal and a second lithology seismic wave characteristic parameter of a known typical stratum;

[0018] A formation identification module, used for matching the characteristic parameters of the first lithology characteristic wave with the characteristic parameters of the second lithology seismic wave to determine the formation lithology and geological structure of the formation to be measured;

[0019] The formation information output module is used to output the formation information of the formation to be measured, including distance data, formation lithology and geological structure.

[0020] In a third aspect, the present invention provides a near-drill bit formation detection device, comprising: a downhole controllable seismic source, a seismic detector and a terminal module; wherein the seismic detector and the downhole controllable seismic source are respectively connected to the terminal module, and the terminal module is used to execute a near-drill bit formation detection method as described above.

[0021] In a fourth aspect, the present invention provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor, and when the processor executes the program, the steps of a near-drill bit formation detection method as described above are implemented.

[0022] In a fifth aspect, the present invention provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the steps of a near-drill-bit formation detection method as described above.

[0023] The beneficial effects of the present invention are: by exciting seismic waves through a downhole controllable seismic source, and using a seismic detector to receive the reflected wave signal of the formation to be measured, the relative position of the formation in front of the drill bit from the drill bit is calculated using the reflected wave signal; and extracting the first lithology seismic wave characteristic parameter from the reflected wave signal, and matching it with the second lithology seismic wave characteristic parameter of the known typical formation, to obtain the formation information of the formation to be measured. The seismic waves of the present application are not affected by various complex geological environments, and the downhole controllable seismic source can excite seismic waves with controllable frequency and energy intensity, and the frequency and energy intensity of the forward exploration seismic waves are regulated according to actual engineering needs and geological conditions, thereby increasing the detection distance of the instrument and improving the signal-to-noise ratio of the received signal, which has the beneficial effect of improving the forward exploration capability of the drilling instrument, can accurately obtain the formation information of the formation to be measured, reduces drilling risks, and improves drilling efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0025] Figure 1 A schematic flow chart of a near-drill-bit formation detection method according to an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of a process for preprocessing a reflected wave signal;

[0027] Figure 3 This is the training flow chart of the lithology identification model;

[0028] Figure 4 A schematic structural diagram of a near-drill-bit formation detection system according to an embodiment of the present invention;

[0029] Figure 5 The present invention is a schematic structural diagram of a near-drill-bit formation detection device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following examples are provided to further explain and supplement the present invention and do not constitute any limitation to the present invention.

[0031] A near-drill-bit formation detection method, system, device, electronic device and medium according to an embodiment of the present invention will be described below in conjunction with the accompanying drawings.

[0032] like Figure 1 As shown, the present invention provides a near-drill-bit formation detection method, comprising:

[0033] S1. A seismic wave of a preset frequency and preset energy is emitted to a formation to be measured in front of the drill bit through a downhole controllable vibrator, and a reflected wave signal of the formation to be measured is received through a seismic detector.

[0034] S2. Calculate the relative position of the formation in front of the drill bit from the drill bit in real time based on the reflected wave signal.

[0035] S3. Acquire a first lithology seismic wave characteristic parameter of the reflected wave signal and a second lithology seismic wave characteristic parameter of a known typical stratum.

[0036] S4. Match the characteristic parameters of the first lithology characteristic wave with the characteristic parameters of the second lithology seismic wave to determine the lithology and geological structure of the stratum to be measured.

[0037] S5. Output the stratigraphic information of the stratum to be measured including distance data, stratigraphic lithology and geological structure.

[0038] In this embodiment, seismic waves are excited by a downhole controllable seismic source, and a seismic detector is used to receive the reflected wave signal of the formation to be measured, so as to calculate the relative position of the formation in front of the drill bit from the drill bit by using the reflected wave signal; and the characteristic parameters of the first lithology seismic wave are extracted from the reflected wave signal, and matched with the characteristic parameters of the second lithology seismic wave of the known typical formation to obtain the stratigraphic information of the formation to be measured. The seismic waves of the present application are not affected by various complex geological environments, and the downhole controllable seismic source can excite seismic waves of controllable frequency and energy intensity, and the frequency and energy intensity of the forward exploration seismic waves are regulated according to actual engineering needs and geological conditions, thereby increasing the detection distance of the instrument and improving the signal-to-noise ratio of the received signal, which has the beneficial effect of improving the forward exploration capability of the drilling instrument, can accurately obtain the stratigraphic information of the formation to be measured, reduces drilling risks, and improves drilling efficiency and safety.

[0039] In this embodiment, a downhole controllable vibrator is deployed near the drill bit to emit seismic waves of specific intensity and frequency, and its propagation characteristics in the underground structure are used to obtain effective reflection waves from the strata ahead through seismic detectors, and the geological information of the strata ahead is analyzed in real time. This includes but is not limited to key parameters such as the distance, thickness, lithology, cracks, porosity, and fluid properties of the strata. Through high-precision data processing and analysis technology, accurate information on the strata ahead to be measured can be provided for drilling, helping to optimize drilling plans, reduce drilling risks, and improve drilling efficiency and safety.

[0040] In this embodiment, the preset frequency and preset energy are set according to actual conditions.

[0041] In this embodiment, the seismic detector can be a three-component array geophone. The three-component array geophone is a special geophone used in multi-wave exploration. Three mutually perpendicular sensors are installed inside to record the three components of the particle vibration velocity vector respectively. That is, the seismic detector can simultaneously receive vibrations in three directions (usually X, Y, and Z axes), which are:

[0042] X-axis amplitude: The amplitude that the seismic detector can receive in the X-axis direction, which represents a component in the horizontal direction.

[0043] Y-axis amplitude: Similar to the X-axis, the Y-axis is another component in the horizontal direction that can capture the amplitude in this direction.

[0044] Amplitude in the Z-axis direction: The Z-axis direction is usually the vertical direction, and the seismic detector can also receive and measure the amplitude in this direction.

[0045] Based on the above, the three-component seismic data is the amplitude in three directions (X, Y, Z axis), and it is the prior art that the seismic detector determines the three-component seismic data according to the reflected wave signal, so it will not be elaborated.

[0046] In this embodiment, after the formation information corresponding to the formation to be measured is obtained, it is only the predicted formation information, and the real formation information needs to be iteratively updated based on the real formation information measured by the while drilling measurement.

[0047] Optionally, extracting a first lithologic seismic wave characteristic parameter of the reflection wave signal includes:

[0048] The reflected wave signal is subjected to signal amplification, baseline correction, time synchronization, noise identification, filtering, denoising and signal extraction in sequence to determine the target reflected wave signal;

[0049] Extract the first lithology seismic wave characteristic parameter of the target reflection wave signal.

[0050] like Figure 2 As shown, the reflected wave signal needs to be processed in sequence: signal preprocessing (signal amplification, baseline correction, time synchronization), noise identification, filtering operation (filter design, filtering operation), effect evaluation and adjustment (denoising) and signal extraction. The specific process is as follows:

[0051] (1) Signal amplification, baseline correction, and time synchronization of reflection signals can enhance useful signals and suppress noise to improve the quality of seismic signals.

[0052] In this embodiment, noise identification is performed on the reflected signal to identify and distinguish background noise from effective signals to improve the signal-to-noise ratio of the signal.

[0053] Among them, methods such as spectrum analysis can be used to determine the frequency and intensity range where the noise in the reflected signal is mainly concentrated.

[0054] (2) Filtering the reflected signal can further purify the effective signal.

[0055] Among them, it is necessary to design a filter first, and then design an appropriate filter to remove the noise according to the result of noise identification, including low-pass, high-pass, band-pass or band-stop filters, or even more complex adaptive filters or multiple filtering schemes to specifically suppress noise within a specific frequency range.

[0056] In addition, the designed filter is applied to the data to perform the actual filtering operation. Digital signal processing software and algorithms are used to filter the data in the frequency domain or time domain through convolution, Fourier transform and other techniques.

[0057] (3) The reflected signal is denoised and the quality of the filtered signal can be evaluated to achieve the optimal filtering effect.

[0058] After filtering, the filtering effect needs to be evaluated to confirm whether the noise is effectively removed and whether the effective signal is not excessively attenuated or distorted. Compare the signal spectrum, waveform and other parameters before and after filtering. According to the evaluation results, adjust the filter parameters to achieve the best filtering effect.

[0059] (4) Signal extraction of reflection signals can extract effective reflection wave signals for further analysis and interpretation of lithological and stratigraphic characteristics.

[0060] Among them, after filtering, the background noise and interference signals are effectively removed, and the effective formation reflection wave signal can be more clearly identified. Further signal extraction facilitates the parsing and analysis of formation information.

[0061] In addition, the entire filtering process needs to comprehensively consider the characteristics of the signal, the nature of the noise, and the analysis objectives. Through iterative adjustment and optimization, the accurate extraction of effective signals can be ensured to provide a basis for subsequent geological interpretation.

[0062] Optionally, extracting a first lithologic seismic wave characteristic parameter of the target reflection wave signal includes:

[0063] Extract FFT amplitude spectrum, energy spectrum and complex cepstrum from the target reflected wave signal to determine the spectrum feature data;

[0064] Extract frequency-wavenumber spectrum and time-frequency analysis parameters from the target reflected wave signal to determine time-frequency characteristic data;

[0065] The first lithologic seismic wave characteristic parameters include frequency spectrum characteristic data and time-frequency characteristic data.

[0066] In this embodiment, the target reflection wave signal is converted into commonly used seismic wave data such as frequency spectrum characteristic data and time-frequency characteristic data, so as to better match the seismic wave data corresponding to known typical strata.

[0067] The spectral feature data include frequency domain feature data extracted from the reflected wave signal such as FFT amplitude spectrum, energy spectrum, and complex cepstrum, as follows:

[0068] (1) Through FFT transformation, the reflected wave signal is converted from the time domain to the frequency domain, and the amplitude spectrum and energy spectrum are extracted, thereby revealing the frequency content and energy distribution of the reflected wave signal, which is very important for identifying the formation interface and rock properties. The calculation formula is:

[0069]

[0070] Among them, x(n) is the reflected wave signal corresponding to the nth sampling point in the time domain, X(k) is the kth frequency component in the frequency domain, and N is the total number of sampling points.

[0071] By analyzing all frequency components X(k), the spectrum distribution, that is, the frequency content (amplitude spectrum) and energy distribution (energy spectrum) of the reflected wave signal, can be obtained.

[0072] (2) Complex cepstrum analysis can separate the reverberation components in seismic signals, help extract the periodic characteristics of reflection sequences, and is useful for identifying waveforms in multilayer media. The complex cepstrum is obtained by inverse Fourier transforming the logarithmic amplitude spectrum of the reflection wave signal. The formula is as follows:

[0073] c(n)=F -1 {log|X(k)|}

[0074] c(n) represents the complex cepstrum, F -1 represents the inverse Fourier transform.

[0075] In addition, the time-frequency characteristic data mainly include the frequency-wavenumber spectrum (fk spectrum), time-frequency analysis parameters (such as short-time Fourier transform STFT) and other time-frequency domain characteristic data extracted from the reflected wave signal, as follows:

[0076] (1) The frequency-wavenumber spectrum (fk spectrum) can be used to analyze the distribution of reflected wave signals in the frequency-wavenumber domain. It can be used to analyze the propagation characteristics of seismic waves in detail, such as wave velocity analysis and wave propagation direction determination. It is based on the two-dimensional Fourier transform. For the two-dimensional wave function u(t,x), its relationship with the corresponding frequency-wavenumber spectrum function U(f,k) is:

[0077]

[0078]

[0079] (2) Time-frequency analysis parameters, such as short-time Fourier transform (STFT) and other time-frequency analysis techniques, can be used to describe the time-frequency characteristics of the reflection wave signal and provide information on the changes in time and frequency of the seismic wave:

[0080] STFT(x)(τ,ω)=∫x(t)ω(t-τ)e -iωt dt

[0081] Among them, ω(t) is the window function, τ and ω are variables in the time and frequency domains respectively, and STFT(x)(τ, ω) represents the short-time Fourier transform function.

[0082] The length and dimension of the characteristic sequence commonly used in this embodiment depend on the purpose of data processing and the required resolution. For example, for frequency domain features, the characteristic sequence length of FFT amplitude spectrum and energy spectrum may be between 128 and 512 data sampling points. For more detailed features, such as phase spectrum or time-frequency features, different dimensionality selections may be available.

[0083] Optionally, the relative position of the formation in front of the drill bit from the drill bit is calculated in real time according to the reflected wave signal, including:

[0084] Obtain the propagation velocity of seismic waves in the stratum to be measured, and the two-way time from the time when the seismic wave is emitted from the downhole controllable vibrator to the time when the seismic detector receives the reflected wave signal;

[0085] Determine the distance between the drill bit and the formation to be measured based on the propagation velocity and the two-way time;

[0086] The three-component seismic data of the reflected wave signal are extracted, and the formation dip and azimuth of the formation to be measured are determined according to the three-component seismic data.

[0087] In this embodiment, the three-component seismic data includes a first amplitude generated in the X-axis direction, a second amplitude generated in the Y-axis direction, and a third amplitude generated in the Z-axis direction after the seismic wave reaches the stratum to be measured;

[0088] In this embodiment, the formation inclination of the formation to be measured is determined according to the first amplitude, the second amplitude and the third amplitude, and the formula is as follows:

[0089]

[0090] tan(θ) represents the formation inclination, A x , A y and A z They are the first amplitude, the second amplitude and the third amplitude respectively.

[0091] According to the first amplitude and the second amplitude, the azimuth of the formation to be measured is determined, and the formula is as follows:

[0092]

[0093] α represents the azimuth angle.

[0094] According to the propagation velocity and the two-way time, the distance between the drill bit and the formation to be measured is determined by the following formula:

[0095]

[0096] Among them, d is the distance, v is the propagation speed, and t is the round-trip time.

[0097] In this embodiment, when seismic waves radiate toward the stratum to be measured in front of the drill bit, if they encounter geological structures such as cracks, faults, and interfaces, the seismic waves are reflected or scattered back from the geological structures and received by the seismic detector. Based on this principle, by receiving and analyzing these reflected waves, the lithological characteristics and interface information of the stratum can be accurately detected.

[0098] Optionally, matching the characteristic parameters of the first lithology characteristic wave with the characteristic parameters of the second lithology seismic wave to determine the lithology and geological structure of the stratum to be measured includes:

[0099] Inputting the first lithology seismic wave characteristic parameter of the stratum to be measured into the lithology identification model;

[0100] Using the lithology recognition model, the first lithology seismic wave characteristic parameter of the stratum to be measured is matched with the second lithology seismic wave characteristic parameter of the known typical stratum to determine the target known typical stratum;

[0101] The lithology and geological structure corresponding to the target known typical strata are taken as the lithology and geological structure of the stratum to be measured.

[0102] In this embodiment, the use of machine learning and artificial intelligence technology can effectively learn and extract complex features in seismic data, and then predict the lithology of unknown formations, which is of great value in improving the accuracy of seismic data interpretation, reducing risks, and guiding oil and gas exploration and development activities.

[0103] Optionally, the training process of the lithology recognition model includes:

[0104] Obtain reflection wave signals, stratum lithology and geological structures corresponding to different known typical strata;

[0105] The training set and test set are constructed using the reflection wave signals, stratum lithology and geological structure corresponding to each known typical stratum, and both the training set and the test set are preprocessed by data cleaning, filtering, resampling, multiple wave removal and interference wave removal;

[0106] Extract the spectrum feature data and time-frequency feature data of the reflected wave signal in the training set, and use the spectrum feature data, time-frequency feature data, stratum lithology and geological structure corresponding to each known typical stratum in the training set as the target training set;

[0107] Extract the spectral feature data and time-frequency feature data of the reflected wave signal in the test set, and use the spectral feature data, time-frequency feature data, stratum lithology and geological structure corresponding to each known typical stratum in the test set as the target test set;

[0108] The target training set is input into the deep neural network model for training, and the trained deep neural network model is tested with the target test set to determine the lithology recognition model.

[0109] like Figure 3As shown, the typical stratigraphic lithology is selected as the known typical stratigraphic layer, and the typical seismic wave data (reflection wave signal, stratigraphic lithology and geological structure) encountered in the same work area and adjacent wells should be stored in advance as much as possible. The typical stratigraphic lithology may include sandstone, mudstone, shale, limestone, dolomite, granite, carbonate rock, igneous rock, coal seam, etc. In the case of unconditional acquisition of data in advance, sufficient typical rock seismic wave data in adjacent areas should be collected and stored.

[0110] After collecting the seismic wave data, it is necessary to construct a training set and a test set. The training set and the test set can be allocated in a ratio of 4:1 or 3:1 to ensure that there is enough data to train the deep neural network model, and the validation set can evaluate the generalization ability of the model.

[0111] Then, the seismic wave data in the training set and the test set need to be preprocessed, including data cleaning, filtering, resampling, removing multiple waves and removing interference waves, where:

[0112] Data cleaning: This step involves checking the consistency of seismic wave data, including identifying and handling outliers, invalid values, and missing values. This can be done by comparing the reflected wave signals received by different triplicate array detectors or using statistical methods. Data cleaning ensures the reliability and consistency of the data, laying the foundation for accurate analysis.

[0113] Filtering: Filtering is a key step in the preprocessing of seismic wave data. Its purpose is to remove noise that is not related to the reflection signal of the geological structure. Types of filtering can include: ① High-pass filtering: remove noise components with frequencies below a certain threshold, such as slow seismic waves and microseismic noise. ② Low-pass filtering: remove high-frequency noise, such as circuit noise or high-frequency vibrations generated by electronic equipment. ③ Band-pass filtering: combine high-pass and low-pass filtering to retain only data within a specific frequency band. The frequency range of the band-pass filter needs to be optimized based on the characteristics of the target signal and the results of the field environment test. Generally, for seismic wave data, it may be between 10Hz and several hundred Hz.

[0114] Resampling: Seismic wave data may need to be resampled to meet the needs of subsequent processing steps. If the original sampling rate is too high, the sampling rate can be reduced to reduce the amount of data and improve processing efficiency. Conversely, if the original data sampling rate is not enough to capture the reflected wave signal reflected by the target formation, the sampling rate may need to be increased.

[0115] Multiple wave removal and interference wave removal: Seismic wave data preprocessing requires the removal of multiple waves and interference waves. These are usually caused by multiple reflections of waves in underground structures, which will interfere with the identification of the main reflection signal. After the above noise removal, signal enhancement technology is applied to improve the signal-to-noise ratio of the effective seismic reflection signal.

[0116] Secondly, after the seismic wave data has been preprocessed as described above, the spectrum feature data and time-frequency feature data are extracted from the reflection wave signals in the training set and the test set. The specific algorithm has been explained above and will not be repeated here.

[0117] Finally, the target training set and target test set of typical stratum lithologies are obtained and input into the deep neural network for training to obtain a lithology recognition model. The lithology recognition model can then be used to obtain the target known typical strata that match the strata to be tested.

[0118] In this embodiment, when training the model, it is necessary to select appropriate initialization parameters, including learning rate, loss function, optimization algorithm, etc., and adjust the length of the input feature vector according to the characteristics of the seismic waves in the target training set and the requirements of the intelligent model. The length may affect the training efficiency and recognition accuracy of the model. A large number of model training and comparative tests are performed to optimize the algorithm parameters and verify the accuracy of the model.

[0119] In this embodiment, different types of machine learning algorithms can be selected, such as traditional methods such as BP neural network, support vector machine, random forest, or modern intelligent algorithms such as convolutional neural network, deep learning, transfer learning, etc. A variety of seismic wave features can be used as input data for the algorithm, and a variety of intelligent lithology recognition algorithms can be combined to improve the accuracy of recognition through model fusion. Statistical analysis methods are used to evaluate and refine the final lithology recognition results to improve the reliability of the lithology judgment of the formation to be tested in front of the drill bit.

[0120] like Figure 4 As shown, the present invention provides a near-drill-bit formation detection system, comprising:

[0121] A reflected wave signal receiving module is used to transmit seismic waves of a preset frequency and preset energy to the formation to be measured in front of the drill bit through a downhole controllable vibrator, and receive the reflected wave signal of the formation to be measured through a seismic detector;

[0122] A relative position determination module is used to calculate the relative position of the formation in front of the drill bit from the drill bit in real time based on the reflected wave signal;

[0123] A lithology seismic wave characteristic parameter acquisition module, used to acquire a first lithology seismic wave characteristic parameter of a reflection wave signal and a second lithology seismic wave characteristic parameter of a known typical stratum;

[0124] A formation identification module, used for matching the characteristic parameters of the first lithology characteristic wave with the characteristic parameters of the second lithology seismic wave to determine the formation lithology and geological structure of the formation to be measured;

[0125] The formation information output module is used to output the formation information of the formation to be measured, including distance data, formation lithology and geological structure.

[0126] Optionally, the lithology seismic wave characteristic parameters are obtained, specifically for:

[0127] The reflected wave signal is subjected to signal amplification, baseline correction, time synchronization, noise identification, filtering, denoising and signal extraction in sequence to determine the target reflected wave signal;

[0128] Extract the first lithology seismic wave characteristic parameter of the target reflection wave signal.

[0129] Optionally, the lithology seismic wave characteristic parameters are obtained, specifically for:

[0130] Extract FFT amplitude spectrum, energy spectrum and complex cepstrum from the target reflected wave signal to determine the spectrum feature data;

[0131] Extract frequency-wavenumber spectrum and time-frequency analysis parameters from the target reflected wave signal to determine time-frequency characteristic data;

[0132] The first lithologic seismic wave characteristic parameters include frequency spectrum characteristic data and time-frequency characteristic data.

[0133] Optionally, the relative position determination module is specifically used to:

[0134] Obtain the propagation velocity of seismic waves in the stratum to be measured, and the two-way time from the time when the seismic wave is emitted from the downhole controllable vibrator to the time when the seismic detector receives the reflected wave signal;

[0135] Determine the distance between the drill bit and the formation to be measured based on the propagation velocity and the two-way time;

[0136] The three-component seismic data of the reflected wave signal are extracted, and the formation dip and azimuth of the formation to be measured are determined according to the three-component seismic data.

[0137] Optionally, the formation identification module is specifically used to:

[0138] Inputting the first lithology seismic wave characteristic parameter of the stratum to be measured into the lithology identification model;

[0139] Using the lithology recognition model, the first lithology seismic wave characteristic parameter of the stratum to be measured is matched with the second lithology seismic wave characteristic parameter of the known typical stratum to determine the target known typical stratum;

[0140] The lithology and geological structure corresponding to the target known typical strata are taken as the lithology and geological structure of the stratum to be measured.

[0141] Optionally, the system also includes a model training module, specifically used to:

[0142] Obtain reflection wave signals, stratum lithology and geological structures corresponding to different known typical strata;

[0143] The training set and test set are constructed using the reflection wave signals, stratum lithology and geological structure corresponding to each known typical stratum, and both the training set and the test set are preprocessed by data cleaning, filtering, resampling, multiple wave removal and interference wave removal;

[0144] Extract the spectrum feature data and time-frequency feature data of the reflected wave signal in the training set, and use the spectrum feature data, time-frequency feature data, stratum lithology and geological structure corresponding to each known typical stratum in the training set as the target training set;

[0145] Extract the spectral feature data and time-frequency feature data of the reflected wave signal in the test set, and use the spectral feature data, time-frequency feature data, stratum lithology and geological structure corresponding to each known typical stratum in the test set as the target test set;

[0146] The target training set is input into the deep neural network model for training, and the trained deep neural network model is tested with the target test set to determine the lithology recognition model.

[0147] like Figure 5 As shown, the present invention provides a near-drill bit formation detection device, including: a downhole controllable seismic source O, a seismic detector R and a terminal module (not shown); wherein the seismic detector R and the downhole controllable seismic source O are respectively connected to the terminal module, and the terminal module is used to execute any one of the near-drill bit formation detection methods in the above embodiments.

[0148] in addition, Figure 5 In the figure, A and B are both strata, and C is the stratigraphic interface between the two strata.

[0149] An embodiment of the present invention also provides a computing device, including a memory, a processor, and a program stored in the memory and running on a manager. When the manager executes the program, some or all steps of the above-mentioned near-drill-bit formation detection method are implemented.

[0150] Among them, the computing device can be a computer, and correspondingly, its program is computer software. The above-mentioned parameters and steps in the computing device of the present invention can refer to the parameters and steps in the embodiment of a near-drill bit formation detection method mentioned above, and will not be repeated here.

[0151] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. Computer-readable storage media can be, for example, but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above.

[0152] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0153] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for detecting formations near a drill bit, characterized in that: include: The seismic source in the well emits seismic waves of preset frequency and preset energy to the formation to be measured in front of the drill bit, and the seismic detector receives the reflected wave signal of the formation to be measured; Calculate the relative position of the formation in front of the drill bit to the drill bit in real time according to the reflected wave signal; Acquire a first lithology seismic wave characteristic parameter of the reflected wave signal and a second lithology seismic wave characteristic parameter of a known typical stratum; Matching the characteristic parameters of the first lithology characteristic wave with the characteristic parameters of the second lithology seismic wave to determine the lithology and geological structure of the stratum to be measured; The output includes the distance data, formation lithology and geological structure of the formation to be measured.

2. The method according to claim 1, characterized in that The step of obtaining the first lithologic seismic wave characteristic parameter of the reflected wave signal comprises: The reflected wave signal is sequentially subjected to signal amplification, baseline correction, time synchronization, noise identification, filtering, denoising and signal extraction to determine the target reflected wave signal; A first lithologic seismic wave characteristic parameter of the target reflected wave signal is extracted.

3. The method according to claim 2, characterized in that The step of extracting the first lithologic seismic wave characteristic parameter of the target reflected wave signal comprises: Extracting FFT amplitude spectrum, energy spectrum and complex cepstrum from the target reflected wave signal to determine spectrum feature data; Extracting frequency-wavenumber spectrum and time-frequency analysis parameters from the target reflected wave signal to determine time-frequency characteristic data; The first lithologic seismic wave characteristic parameter includes the frequency spectrum characteristic data and the time-frequency characteristic data.

4. The method according to claim 1, characterized in that The real-time calculation of the relative position of the formation in front of the drill bit from the drill bit according to the reflected wave signal includes: Obtain the propagation velocity of seismic waves in the stratum to be measured, and the two-way time from the time when the seismic wave is emitted from the downhole controllable vibrator to the time when the seismic detector receives the reflected wave signal; Determining the distance between the drill bit and the formation to be measured according to the propagation velocity and the round-trip time; The three-component seismic data of the reflected wave signal are extracted, and the formation dip and azimuth of the to-be-measured formation are determined according to the three-component seismic data.

5. The method according to any one of claims 1 to 4, characterized in that: The matching of the first lithology characteristic wave characteristic parameter with the second lithology seismic wave characteristic parameter to determine the stratum lithology and geological structure of the stratum to be measured comprises: Inputting the first lithology seismic wave characteristic parameter of the stratum to be measured into the lithology identification model; Using the lithology identification model, the first lithology seismic wave characteristic parameter of the stratum to be measured is matched with the second lithology seismic wave characteristic parameter of a known typical stratum to determine a target known typical stratum; The stratum lithology and geological structure corresponding to the target known typical stratum are used as the stratum lithology and geological structure of the stratum to be measured.

6. The method according to claim 5, characterized in that The training process of the lithology identification model includes: Obtain reflection wave signals, stratum lithology and geological structures corresponding to different known typical strata; The training set and the test set are constructed by using the reflection wave signals, stratum lithology and geological structure corresponding to each known typical stratum, and the training set and the test set are preprocessed; Extract the spectrum feature data and time-frequency feature data of the reflected wave signal in the training set, and use the spectrum feature data, time-frequency feature data, stratum lithology and geological structure corresponding to each known typical stratum in the training set as the target training set; Extract the spectral feature data and time-frequency feature data of the reflected wave signal in the test set, and use the spectral feature data, time-frequency feature data, stratum lithology and geological structure corresponding to each known typical stratum in the test set as the target test set; The target training set is input into the deep neural network model for training, and the trained deep neural network model is tested by the target test set to determine the lithology recognition model.

7. A near-drill-bit formation detection system, characterized in that: include: A reflected wave signal receiving module is used to transmit seismic waves of a preset frequency and preset energy to the formation to be measured in front of the drill bit through a downhole controllable vibrator, and receive the reflected wave signal of the formation to be measured through a seismic detector; A relative position determination module, used for calculating the relative position of the formation in front of the drill bit from the drill bit in real time according to the reflected wave signal; A lithology seismic wave characteristic parameter acquisition module, used to acquire a first lithology seismic wave characteristic parameter of the reflection wave signal and a second lithology seismic wave characteristic parameter of a known typical stratum; A formation identification module, used for matching the characteristic parameters of the first lithology characteristic wave with the characteristic parameters of the second lithology seismic wave to determine the formation lithology and geological structure of the formation to be measured; The formation information output module is used to output the formation information of the formation to be measured including the distance data, formation lithology and geological structure.

8. A near-drill-bit formation detection device, characterized in that: include: A downhole controllable vibrator, a seismic detector and a terminal module; wherein the seismic detector and the downhole controllable vibrator are respectively connected to the terminal module, and the terminal module is used to execute a near-drill bit formation detection method as described in any one of claims 1-6.

9. A computing device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the near-drill-bit formation detection method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on the terminal device, the terminal device executes the steps of the near-drill-bit formation detection method as described in any one of claims 1-6.

Images