Slurry pulse decoding method, device and equipment for directional drilling, medium and product

Abstract

The invention discloses a mud pulse decoding method, device and equipment for directional drilling, a medium and a product, and relates to the technical field of directional drilling, the method is based on a multi-channel pressure sensor, and a mud pulse signal is obtained; fusing the mud pulse signals by using a multi-sensor signal fusion technology to generate fused pulse signals; recognizing and filtering noise in the fused pulse signal through a self-adaptive noise elimination algorithm to obtain a noise filtering pulse signal; modulating and demodulating the noise filtering pulse signal to obtain an enhanced pulse signal; according to the mud transmission distance, the mud flowing pressure and the mud flowing speed which are monitored in real time, the pulse intensity of the enhanced pulse signal is adjusted, and a recovery pulse signal is determined; and carrying out decoding and error code correction on the recovery pulse signal to obtain a decoding result. A high-precision decoding result can be obtained, and the drilling operation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of directional drilling, and particularly to a mud pulse decoding method, device, equipment, medium and product for directional drilling. Background Art

[0002] During the process of directional drilling, a mud pulse telemetry system is a key communication tool for transmitting data collected by sensors below the drill bit to the surface. This technology transmits information through pressure fluctuations in the mud flow without the need for additional physical connection cables.

[0003] However, existing mud pulse decoding devices usually have some problems. For example, the flow of mud in a complex downhole environment can cause attenuation of the mud pulse signal. Especially during deep well and long-distance drilling, the receiving accuracy of the mud pulse signal of the mud pulse decoding device drops significantly. In addition, due to the complexity of the downhole environment, the mud pulse signal is easily interfered by factors such as noise, affecting the decoding accuracy of the mud pulse signal. At the same time, the existing technology cannot decode the mud pulse signal in real time, affecting the drilling operation efficiency.

[0004] Therefore, the problems and defects existing in the prior art are as follows:

[0005] (1) The long-distance transmission attenuation of the mud pulse signal makes it difficult for the signal to be effectively transmitted and decoded in a deep well.

[0006] (2) It is difficult to identify the mud pulse signal in a noisy environment. The mud pulse signal is easily submerged by downhole noise, and the decoding accuracy is low.

[0007] (3) The decoding speed is slow. During real-time drilling, signal processing lags behind, affecting the timeliness of drilling operations. Summary of the Invention

[0008] The purpose of the present application is to provide a mud pulse decoding method, device, equipment, medium and product for directional drilling, which can solve the problem that the prior art cannot decode the mud pulse signal in real time, resulting in low drilling operation efficiency.

[0009] To achieve the above purpose, the present application provides the following solutions:

[0010] In a first aspect, the present application provides a mud pulse decoding method for directional drilling, including:

[0011] In a second aspect, the present application provides a mud pulse decoding device for directional drilling, including:

[0012] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the mud pulse decoding method for directional drilling described above.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the mud pulse decoding method for directional drilling described above.

[0014] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the mud pulse decoding method for directional drilling described in any one of the above.

[0015] According to the specific embodiments provided by the present application, the following technical effects are disclosed:

[0016] The present application provides a mud pulse decoding method, device, equipment, medium and product for directional drilling. First, the present application obtains mud pulse signals based on multi-channel pressure sensors arranged at different positions in the drilling mud flow path, removes the random errors of the mud pulse signals obtained by a single multi-channel pressure sensor, and at the same time, through an adaptive noise cancellation algorithm, identifies and filters the noise in the fused pulse signals to obtain noise-filtered pulse signals, realizing signal compensation and enhancement of the mud pulse signals. Further, the multi-sensor signal fusion technology is used to fuse the mud pulse signals to generate fused pulse signals, effectively overcoming the problem of signal attenuation, so that accurate mud pulse signals can still be obtained even during long-distance transmission, facilitating subsequent high-precision decoding results. Further, through the adaptive noise cancellation algorithm, the interference noise in the fused pulse signals is eliminated to obtain noise-filtered pulse signals, and the noise-filtered pulse signals are modulated and demodulated to obtain enhanced pulse signals, and the enhanced pulse signals improve the anti-attenuation ability of the mud pulse signals. Then, according to the real-time monitored mud transmission distance, mud flow pressure and mud flow rate, the pulse intensity of the enhanced pulse signals is adjusted in a timely manner to obtain restored pulse signals, improving the timeliness of drilling operations; that is, the transmission and restoration strategies of the enhanced pulse signals are automatically adjusted according to the actual environment to make it more adaptable to various downhole complex working conditions and avoid affecting the decoding accuracy subsequently. Finally, the restored pulse signals are decoded and error-corrected in real time, where the error-correction function effectively reduces the error phenomenon in signal decoding, ensures high-precision decoding results, and improves the drilling operation efficiency. Description of the Drawings

[0017] Figure 1 It is a schematic flow chart of the mud pulse decoding method for directional drilling provided in the embodiments of the present application;

[0018] Figure 2 This is a schematic structural diagram of the mud pulse decoding device provided in the embodiment of the present application for directional drilling. Specific embodiments

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0020] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0021] As Figure 1 shown, the present application provides a mud pulse decoding method for directional drilling, including:

[0022] Step 101: Based on a multi-channel pressure sensor, obtain a mud pulse signal; the multi-channel pressure sensors are distributed at different positions on the drilling mud flow path.

[0023] Among them, there are multiple multi-channel pressure sensors, which are respectively arranged at different measurement points, covering key positions of the entire mud pipeline; each multi-channel pressure sensor real-time detects the pressure fluctuations in the mud, and captures the mud pulse signal through these fluctuation signals.

[0024] Step 102: Use multi-sensor signal fusion technology to fuse the mud pulse signals to generate a fused pulse signal.

[0025] Specifically, the multi-sensor signal fusion technology includes the weighted average method and the Kalman filter to ensure high-precision signal decoding even when the transmission distance increases.

[0026] Step 103: Identify and filter the noise in the fused pulse signal through an adaptive noise cancellation algorithm to obtain a noise-filtered pulse signal.

[0027] Among them, based on real-time modeling of the adaptive noise cancellation algorithm, identify the inherent noise in the mud flow during the drilling process, mainly including mechanical noise and vibration noise. And perform filtering processing on the noise interference, so as to remove the noise components that are not related to the mud pulse signal, and further improve the clarity of the mud pulse signal.

[0028] Step 104: Modulate and demodulate the noise-filtered pulse signal to obtain an enhanced pulse signal.

[0029] Step 105: Adjust the pulse intensity of the enhanced pulse signal according to the real-time monitored mud transmission distance, mud flow pressure, and mud flow velocity to determine a restored pulse signal.

[0030] Step 106: Decode and correct error codes of the restored pulse signal to obtain a decoding result.

[0031] In some embodiments, Step 105 specifically includes: determining the attenuation degree of the enhanced pulse signal according to the mud transmission distance and the mud flow velocity; adjusting the pulse intensity of the enhanced pulse signal based on a signal strength compensation algorithm and the attenuation degree to determine the restored pulse signal.

[0032] In some embodiments, Step 106 specifically includes Steps 201 - 202.

[0033] Step 201: Decode the restored pulse signal by using Fourier transform and digital signal processing techniques to determine a first decoding result.

[0034] Step 202: Correct error codes in the first decoding result to obtain the decoding result.

[0035] In some embodiments, Step 201 specifically includes: extracting spectral features of the restored pulse signal based on the Fourier transform; classifying the restored pulse signal based on the spectral features and a convolutional neural network to output different types of pulse signals; the different types of pulse signals include data signals, calibration signals, and status signals; decoding the different types of pulse signals by using the digital signal processing techniques to determine the first decoding result.

[0036] Among them, each multi-channel pressure sensor captures a mud pulse signal by recording pressure fluctuations formed during the mud fluid transmission process. These mud pulse signals are transmitted to a wellhead receiving device. Based on Fourier transform and a convolutional neural network, the mud pulse signals are classified to output different types of pulse signals. During subsequent decoding processes, the decoding accuracy is ensured.

[0037] Among them, when decoding the mud pulse signal, the present application applies fast Fourier transform and digital signal processing technology to accurately extract the spectral characteristics (such as frequency, amplitude, and phase) of the mud pulse signal. For example, for mud pulse signal data with a sampling frequency of 20 kHz, the signal is first transformed to the frequency domain through Fourier transform, and the frequency components of each signal type are screened out. Then, through digital signal processing technology, the frequency characteristics are further analyzed to extract the starting point and duration of the pulse, completing signal classification and feature extraction. During this process, the digital signal processing technology also performs noise reduction processing on the frequency characteristics, making the finally extracted signal clear and facilitating subsequent analysis and error correction.

[0038] In some embodiments, step 202 specifically includes: using redundant coding to detect and repair the error codes in the first decoding result to obtain the decoding result.

[0039] Among them, during the error correction process, redundant coding technologies such as Hamming Code are used to automatically detect and repair error codes in the decoded signal data. For example, for a certain pulse signal data detected, assuming it contains 7-bit coding (such as 1011011), where the redundant bits are used to check the parity of each data bit. When a bit does not conform to the parity check rule, the system will automatically locate the error code and correct it according to the Hamming Code rule to restore the correct mud pulse signal (such as 1011111). Through this automatic detection and correction process, the system ensures the integrity and high reliability of data transmission, and can guarantee the accuracy of decoding even in the downhole environment affected by interference.

[0040] The present application has the following advantages:

[0041] 1. It improves the anti-attenuation ability of the mud pulse signal. Through multi-channel signal reception and multi-sensor signal fusion technology, the transmission intensity and integrity of the mud pulse signal are greatly enhanced, effectively reducing the attenuation problem of the mud pulse signal during long-distance transmission, and ensuring high-precision signal decoding.

[0042] 2. It significantly reduces noise interference. By using an adaptive noise cancellation algorithm, it can model and identify the noise characteristics during the drilling process in real time, dynamically filter mechanical and vibration noise interference, greatly improving the clarity of the mud pulse signal, and ensuring that the mud pulse signal can be accurately transmitted and decoded.

[0043] 3. It improves the decoding efficiency and accuracy. By using an improved high-speed decoding algorithm and parallel digital signal processing technology, real-time high-speed decoding of the mud pulse signal is achieved, significantly improving the efficiency and accuracy of mud pulse decoding, and meeting the requirements for real-time data transmission and processing during directional drilling.

[0044] 4. Enhanced error correction ability: By introducing advanced error detection and correction mechanisms, it can automatically detect and correct errors in the signal during the decoding process, ensuring the accuracy of the decoded data, reducing the error rate problem in long-distance transmission, and improving the overall stability.

[0045] Referring to Figure 2 , the multi-channel signal receiving module 1 is connected to the signal processing module 2 and is used to receive the mud pulse signals of the multi-channel pressure sensors; the multi-channel pressure sensors are arranged at different positions on the mud flow path of the drilling mud; the signal processing module 2 is connected to the main control module 3, and the signal processing module 3 is used to fuse the mud pulse signals through multi-sensor signal fusion technology to obtain a fused pulse signal and send the fused pulse signal to the main control module 3; the main control module 3 is connected to the decoding processing module 4 and the error correction module 5; the main control module 3 is used to input the fused signal into the decoding processing module 4 to obtain a first decoding result; the decoding processing module 4 is used to output the first decoding result to the main control module 3; the main control module 3 is also used to output the first decoding result to the error correction module 5; the error correction module 5 is used to correct the errors in the first decoding result and output a decoding result.

[0046] In practical applications, the multi-channel signal receiving module 1 installs a plurality of high-precision multi-channel pressure sensors on the mud flow path of the drilling equipment.

[0047] Among them, the signal processing module 2 uses a multi-sensor signal fusion algorithm to synchronously process the signals from each multi-channel pressure sensor. By comparing and fusing multiple signal sources, it enhances the detection accuracy of the pulse signal and avoids the problem of signal loss caused by attenuation or noise of a single sensor.

[0048] In some embodiments, the decoding processing module 4 includes a noise filtering module 41, a pulse signal enhancement module 42, a signal recovery module 43, and a decoding module 44; the noise filtering module 41 is connected to the pulse signal enhancement module 42; the noise filtering module 41 is used to identify and filter the noise in the fused pulse signal through an adaptive noise cancellation algorithm to obtain a noise-filtered pulse signal.

[0049] Specifically, traditional decoding algorithms usually process data serially, with a relatively slow speed in processing a single signal, and are particularly prone to delays in a multi-channel high-frequency data environment. In contrast, the present application utilizes the acoustic filtering module 41, pulse signal enhancement module 42, signal recovery module 43, and decoding module 44 in the decoding processing module 4 to process mud pulse signals of different channels in parallel, ensuring that each mud pulse signal channel can be decoded in real time. Taking the data of a certain oil well as an example, which includes data signals, calibration signals, and status signals, through parallel processing technology, the system can process multiple signal sources at the same time, improving the decoding efficiency and the response speed of the overall system.

[0050] In practical applications, through an integrated adaptive noise filter, the inherent noise characteristics generated during mud flow are analyzed in real time. The integrated adaptive noise filter includes a high-pass filter and a Kalman filter. The high-pass filter is used to eliminate low-frequency mud flow noise, and at the same time, in combination with the Kalman filter, adaptive adjustment is performed on high-frequency mechanical vibration noise.

[0051] Specifically, each multi-channel pressure sensor serves as an independent signal source, generating mud pulse signal data containing noise. The weighted average result of the fusion pulse signals for multiple signal sources is calculated, where the weights represent the credibility of each signal source. The weights can be calculated through the process of updating the predicted value and the observed value of the state estimation of the Kalman filter. The role of the Kalman filter: In the state estimation of mud flow, the sensor observation value (i.e., the fusion pulse signal) is combined with the output of the prediction model, thereby optimizing the state estimation of mud flow.

[0052] Exemplarily, the mud pulse signal at time K is taken as the observed value. The dynamic state of the mud flow process is regarded as the state of the dynamic system. Here, the state of the dynamic system refers to specific physical parameters during the mud flow process, such as pressure fluctuations, flow velocity states, or spectral characteristics of pulse signals. These states of the dynamic system are closely related to the mud pulse signals collected in real time. That is to say, the Kalman filter optimizes the state estimation of the dynamic system by processing the mud pulse signals collected by downhole multi-channel pressure sensors and through fusing signals and weights. The specific process is as follows.

[0053] The basic equations of the Kalman filter include a prediction equation and an update equation.

[0054] The prediction equation is used to predict the dynamic state of the mud flow process, and the dynamic state of the mud flow process is referred to as the state estimation of the dynamic system (i.e., the predicted value of the state estimation).

[0055] The prediction equation is

[0056] Where, is the predicted value of the state estimate at time k based on the predicted value of the state estimate at time k-1. A is the state transition matrix, B is the control input matrix, and u k-1 is the control input vector at time k-1; is the predicted value of the state estimate at time k-1.

[0057] Prediction error covariance:

[0058] P k|k-1 = AP k-1|k-1 A T + Q.

[0059] where P k|k-1 is the prediction error covariance matrix, representing the predicted error covariance at time k-1 for time k. P k-1|k-1 represents the estimated error covariance matrix of the state at time k-1, and Q is the process noise covariance matrix; A T is the transpose of the state transition matrix.

[0060] The Kalman gain can be used as a weight coefficient to balance the predicted value of the state assessment at the current time and the mud pulse signal (observed value) at the current time.

[0061] K k = P k|K-1 C T (CP k|k-1 C T + R) -1

[0062] where K k is the Kalman gain, C is the observation matrix, and R is the covariance of the noise;

[0063] Using to determine the predicted value of the state estimate at time k after filtering (such as the smoothed signal of the pressure fluctuation).

[0064] where is the predicted value of the state estimate at time k after filtering, and z k is the mud pulse signal (observed value) at time k;

[0065] The calculation formula for the error covariance P k|k is P k|k = (I - K k C)P k|k-1 , where I is the identity matrix; P k|k-1 is the covariance matrix of the error. Among them, the identity matrix maintains the consistency of the matrix dimension.

[0066] S102. The filter can learn the characteristics of the noise and dynamically adjust the filtering parameters, so that in the complex downhole noise environment, it can extract the effective mud pulse signal to the greatest extent while eliminating the interference signal.

[0067] The pulse signal enhancement module 42 is connected to the signal recovery module 43; the pulse signal enhancement module 42 is used to modulate and demodulate the noise-filtered pulse signal to obtain an enhanced pulse signal.

[0068] The signal recovery module 43 is connected to the decoding module 44; the signal recovery module 43 is used to adjust the pulse intensity of the enhanced pulse signal according to the real-time monitored mud transmission distance and mud flow rate to determine the recovered pulse signal.

[0069] The decoding module 44 is connected to the signal recovery module 43; the decoding module 44 is used to decode the recovered pulse signal to obtain the first decoding result.

[0070] Among them, the pulse signal enhancement module 42 enhances the original mud pulse signal by using signal modulation and demodulation techniques, specifically adopting amplitude modulation AM or frequency modulation FM techniques; by modulating the signal, the pulse information is transmitted in a stronger signal form to increase its anti-attenuation ability.

[0071] Among them, the signal recovery module 43 automatically adjusts the recovery strategy of the enhanced pulse signal according to the environmental parameters including transmission distance, mud flow rate, and pressure change at the receiving end, optimizes the intensity and shape of the enhanced pulse signal to ensure that the signal is still clearly distinguishable after long-distance transmission.

[0072] Among them, the decoding module 44 relies on a parallel signal processor, and multiple processing units process the signals of different channels in parallel to ensure that the signal decoding can be carried out in real time; digital signal processing technology is used to classify and extract the mud pulse signal, including the starting point, duration, and pulse amplitude characteristics of the pulse.

[0073] Among them, the error correction module 5 monitors the possible errors in the decoding process in real time and uses redundant coding techniques, such as Hamming code. The Hamming code introduces parity bits in the pulse signal to help the system detect and correct errors in the decoding process.

[0074] This application ensures that mud pulse signals can be accurately and quickly decoded in complex drilling environments through the collaborative work of multiple modules. First, the multi-channel signal receiving module 1 arranges multiple multi-channel pressure sensors at different positions in the drilling mud flow path. Each multi-channel pressure sensor receives mud pulse signals from different positions, avoiding the problem of signal attenuation caused by a single sensor being too far away or environmental interference, thus ensuring the integrity and diversity of the signals. Next, the signal processing module 2 uses multi-sensor signal fusion technology to integrate the mud pulse signals from different channels, reduces the signal loss of a single sensor through data fusion algorithms, and effectively improves the anti-interference ability of the mud pulse signals by analyzing the correlation of the signals in each channel. With such settings, even for long-distance transmission, a high decoding accuracy can be maintained, ensuring that the mud pulse signals will not be overly attenuated during transmission. Then, the noise filtering module 41 performs real-time modeling based on the adaptive noise cancellation algorithm to identify the inherent mechanical noise and vibration noise in the mud flow during drilling. And it filters out the noise interference, thereby removing the noise components unrelated to the pulse signals and further enhancing the signal clarity. This real-time noise modeling and filtering algorithm can effectively cope with the complex noise environment during drilling. When the mud pulse signal passes through the noise filter, the pulse signal enhancement module 42 modulates and demodulates the noise-filtered pulse signal to obtain an enhanced pulse signal, improving the anti-attenuation ability of the noise-filtered pulse signal. This enables the noise-filtered pulse signal to maintain a high signal strength during long-distance transmission and ensures that the noise-filtered pulse signal will not be significantly attenuated due to complex interference in the mud flow. As the signal is enhanced, the signal recovery module 43 automatically adjusts the intensity of the enhanced pulse signal according to parameters such as the drilling depth, transmission distance, and mud flow rate. And by real-time monitoring the mud flow conditions and signal attenuation status, it dynamically adjusts the intensity of the enhanced pulse signal to ensure that the enhanced pulse signal can always be maintained within the most appropriate intensity range, thereby effectively restoring the original characteristics of the mud pulse signal. Finally, the recovered pulse signal after signal recovery is decoded in real-time by the decoding module 44. The decoding module 44 combines parallel signal processing technology and digital signal processing technology to achieve fast and accurate decoding of the pulse signal. At the same time, the error correction module 5 detects the error codes generated during the decoding process and automatically corrects them using redundant information to ensure that the decoded signal is accurate and error-free, greatly improving the reliability and stability of the decoding.

[0075] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the above method is implemented.

[0076] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program which, when executed by a processor, implements the above method.

[0077] In an exemplary embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the above method.

[0078] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0079] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRdM), magnetoresistive random access memories (MRdM), ferroelectric random access memories (FRdM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memories (RdM) or external cache memories, etc. By way of illustration and not limitation, RdM can be in various forms, such as static random access memories (SRdM) or dynamic random access memories (DRdM), etc.

[0080] In each of the embodiments provided in the present application, the database involved may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on a blockchain, etc., without limitation. In each of the embodiments provided in the present application, the processor involved may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without limitation.

[0081] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0082] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A mud pulse decoding method for directional drilling, characterized in that: include: Obtain mud pulse signals based on multi-channel pressure sensors; The multi-channel pressure sensors are distributed at different positions of the drilling mud flow path; The mud pulse signal is fused by using a multi-sensor signal fusion technology to generate a fused pulse signal; Identifying and filtering the noise in the fused pulse signal through an adaptive noise elimination algorithm to obtain a noise-filtered pulse signal; Modulating and demodulating the noise filtered pulse signal to obtain an enhanced pulse signal; According to the real-time monitored mud transmission distance, mud flow pressure and mud flow rate, the pulse intensity of the enhanced pulse signal is adjusted to determine the restored pulse signal; The restored pulse signal is decoded and error corrected to obtain a decoding result.

2. The mud pulse decoding method for directional drilling according to claim 1, characterized in that: According to the real-time monitored mud transmission distance, mud flow pressure and mud flow rate, the pulse intensity of the enhanced pulse signal is adjusted to determine the restored pulse signal, specifically including: determining the attenuation of the enhanced pulse signal according to the mud transmission distance and the mud flow rate; Based on a signal strength compensation algorithm and the attenuation degree, the pulse strength of the enhanced pulse signal is adjusted to determine the restored pulse signal.

3. The mud pulse decoding method for directional drilling according to claim 1, characterized in that: Decoding and error correction are performed on the recovered pulse signal to obtain a decoding result, specifically including: Decoding the recovered pulse signal using Fourier transform and digital signal processing technology to determine a first decoding result; Error correction is performed on the bit errors in the first decoding result to obtain the decoding result.

4. The mud pulse decoding method for directional drilling according to claim 3, characterized in that: Decoding the recovered pulse signal using Fourier transform and digital signal processing technology to determine a first decoding result specifically includes: Based on the Fourier transform, extracting the frequency spectrum characteristics of the restored pulse signal; Based on the frequency spectrum characteristics and the convolutional neural network, the recovered pulse signal is classified to output different types of pulse signals; the different types of pulse signals include data signals, calibration signals and status signals; The different types of pulse signals are decoded by the digital signal processing technology to determine the first decoding result.

5. The mud pulse decoding method for directional drilling according to claim 3, characterized in that: Performing error correction on the bit errors in the first decoding result to obtain the decoding result specifically includes: Redundant coding is used to detect and repair bit errors in the first decoding result to obtain a decoding result.

6. A mud pulse decoding device for directional drilling, characterized in that: The method applied to any one of claims 1 to 5, wherein the mud pulse decoding device for directional drilling comprises: A multi-channel signal receiving module, connected to the signal processing module, for receiving mud pulse signals from a multi-channel pressure sensor; the multi-channel pressure sensor is arranged at different positions of the drilling mud flow path; The signal processing module is connected to the main control module, and is used to fuse the mud pulse signal through multi-sensor signal fusion technology to obtain a fused pulse signal, and send the fused pulse signal to the main control module; The main control module is connected to the decoding processing module and the error correction module; the main control module is used to input the fused signal into the decoding processing module to obtain a first decoding result; The decoding processing module is used to output the first decoding result to the main control module; The main control module is further used to output the first decoding result to the error correction module; the error correction module is used to perform error correction on the errors in the first decoding result and output the decoding result.

7. The mud pulse decoding device for directional drilling according to claim 6, characterized in that: The decoding processing module includes a noise filtering module, a pulse signal enhancement module, a signal recovery module and a decoding module; The noise filtering module is connected to the pulse signal enhancement module; The noise filtering module is used to identify and filter the noise in the fused pulse signal through an adaptive noise elimination algorithm to obtain a noise filtered pulse signal; The pulse signal enhancement module is connected to the signal recovery module; the pulse signal enhancement module is used to modulate and demodulate the noise filtered pulse signal to obtain an enhanced pulse signal; The signal recovery module is connected to the decoding module; The signal recovery module is used to adjust the pulse intensity of the enhanced pulse signal according to the mud transmission distance and mud flow rate monitored in real time, and determine the recovery pulse signal; The decoding module is connected to the signal recovery module; the decoding module is used to decode the recovered pulse signal to obtain the first decoding result.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the mud pulse decoding method for directional drilling according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the mud pulse decoding method for directional drilling described in any one of claims 1 to 5 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the mud pulse decoding method for directional drilling described in any one of claims 1 to 5 is implemented.

Images