High-speed transmission while-drilling guide decision-making method and system based on machine learning

Abstract

The invention discloses a high-speed transmission while-drilling guide decision-making method and system based on machine learning, relates to the technical field of well drilling construction, and realizes an automatic analysis process from original microscopic data to adaptive values by utilizing machine learning means such as a microorganism adaptive value analysis model and a microelement adaptive value analysis model. The efficiency of data analysis is improved, and subjective errors and tedious workloads possibly brought by manual analysis are reduced. A machine learning model can learn rules from a large amount of historical data, complex relations among microbiological indexes, microelement indexes and stratum suitability can be mined more accurately, a foundation is laid for accurate calculation of adaptation values and making of reasonable guiding decisions, and the method has a good application prospect from cellular level microscopic data collection to quantum link transmission evaluation. And then drill bit guiding decision analysis and early warning are carried out, so that a set of all-around risk monitoring system is constructed.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling construction, and in particular to a high-speed transmission while-drilling guidance decision-making method and system based on machine learning. Background Art

[0002] As the exploration and development of resources such as oil and natural gas gradually expands to deep and complex formations, relying solely on traditional geological exploration methods and macroscopic formation information can no longer meet the requirements of precision drilling. Understanding the microscopic information of the formation at the cellular level, such as microbial activity and trace element distribution, is crucial for predicting formation stability, fluid properties, and potential reservoir characteristics. Therefore, a high-speed transmission while-drilling guidance decision-making method and system based on machine learning is needed.

[0003] The prior art, such as the invention patent with announcement number: CN115822557A, discloses a method, system, storage medium and electronic device for reconstructing a geosteering model while drilling, which includes: obtaining the azimuth logging data of each sector on each cross section of the wellbore; expanding the wellbore along the high side or north side of the wellbore to form a rectangle, mapping the azimuth logging data of each sector on each cross section of the wellbore into the rectangle, obtaining an imaging information image, and then calculating the formation dip of the formation where the wellbore is located; establishing a steering profile of the formation within the preset range of the wellbore, the steering profile includes the current formation dip of the formation where the wellbore is located; adjusting the current formation dip of the formation where the wellbore is located in the steering profile to the calculated formation dip of the formation where the wellbore is located. This can greatly improve the accuracy of the reconstruction of the steering model and play a good supporting role in the geological steering analysis and decision-making of complex oil and gas reservoirs.

[0004] In view of the above scheme, the inventors of the present application found that the above technology has at least the following technical problems: 1. The existing technology can often only rely on relatively macroscopic geological data, such as conventional lithology description, formation pressure test, etc. This will lead to insufficient understanding of the formation, and it is impossible to deeply understand the impact of microscopic factors such as microorganisms and trace elements on the drilling process. It may not be possible to predict the changes in formation porosity caused by certain microbial activities in advance, and then encounter unexpected formation fluid influx during the drilling process. There is a lack of clear acquisition time points and acquisition point setting mechanisms, and data acquisition may be untimely or irregular. This makes it impossible to adjust the drill bit guidance decision in time when facing rapid changes in the formation, such as sudden faults or abnormal flow of local formation fluids, resulting in reduced drilling efficiency and even accidents. There are no comprehensive analysis indicators such as microbial fitness values ​​and trace element fitness values. Different types of microscopic data may be scattered and difficult to integrate for guiding drill bit guidance. The correlation mining between the various data is not deep enough, and the data synergy cannot be fully utilized to optimize the drilling process.

[0005] 2. The existing technology does not consider the transmission quality assessment of quantum links and cross-media transmission mechanisms. In complex downhole environments, traditional data transmission methods are easily affected by factors such as electromagnetic interference, high temperature and high pressure, resulting in data transmission interruptions or errors. This will make the data received by the ground control center incomplete or inaccurate, which in turn affects the accuracy of the drill bit guidance decision. For downhole guidance decisions with high real-time requirements, the existing technology may not be able to meet the needs of high-speed data transmission. In the absence of a flexible switching mechanism such as quantum links and bioelectric signal transmission, once the data transmission speed cannot keep up with the drilling speed, data lag will occur, making it impossible for the drill bit guidance decision to be adjusted in time according to the latest downhole situation, increasing the risk of drilling.

[0006] 3. Existing technologies may be mainly based on experience or simple geological models. This decision-making method cannot accurately consider the complex effects of changes in microorganisms and trace elements on drill bit guidance. For example, when the interaction between microorganisms and trace elements affects the stability of the formation, it is impossible to make accurate adjustments to the drilling direction and speed, which can easily cause the drill bit to deviate from the optimal path or the drilling efficiency to be low. Existing technologies may be difficult to adapt to changes in the microscopic environment of the formation in a timely manner during the drilling process. When the microscopic characteristics of the formation change, it is impossible to respond quickly. If the drilling continues as planned, it may cause problems such as stuck drill and instability of the well wall. At the same time, there is a lack of a systematic early warning mechanism. When facing potential drilling risks, if the cell-level microscopic adaptation value exceeds the normal range, indicating that the formation is abnormal, it is impossible to issue a clear alarm to the relevant personnel and provide detailed information in a timely manner. This may result in the on-site staff being unable to take timely measures, thereby increasing the severity of the accident and the difficulty of handling it. Summary of the invention

[0007] In view of the above-mentioned technical deficiencies, the object of the present invention is to provide a high-speed transmission while-drilling guidance decision-making method and system based on machine learning.

[0008] In order to solve the above technical problems, the present invention adopts the following technical solutions: In the first aspect, the present invention provides a high-speed transmission downhole guidance decision-making method based on machine learning, including: Step 1, acquisition of cellular-level microscopic data: After the target drilling is started, a number of collection time points and collection points are set, and then the cellular-level microscopic data corresponding to each collection point is collected at each collection time point, and the cellular-level microscopic data includes microbial indicators and trace element indicators.

[0009] Step 2: Transmission of high-speed data across media: Analyze the quantum link transmission quality assessment value corresponding to each acquisition point at each acquisition time point of the target drilling, and then evaluate whether the quantum link transmission corresponding to each acquisition point at each acquisition time point of the target drilling needs to be switched to bioelectric signal transmission.

[0010] Step 3. Analysis of cellular-level microscopic adaptation values: According to the microbial indicators and trace element indicators corresponding to each collection point at each collection time point of the target drilling, the microbial adaptation values ​​and trace element adaptation values ​​corresponding to each collection time point are analyzed, and the cellular-level microscopic adaptation values ​​corresponding to each collection time point of the target drilling are analyzed.

[0011] Step 4: Analysis of steering decisions: Analyze the cellular-level microscopic adaptation values ​​corresponding to each acquisition time point of the target drilling, and then analyze the drill bit steering decisions corresponding to each acquisition time point of the target drilling, and initiate the drill bit steering decision warning.

[0012] Preferably, the setting of several acquisition time points and acquisition points is specifically carried out as follows: after the target drilling is started, the drilling speed and drilling depth corresponding to the target drilling at the current moment are obtained, and the drilling speed and drilling depth corresponding to the target drilling at the current moment are compared with the drilling speeds and drilling depths corresponding to each acquisition parameter collection in the database; if the drilling speed and drilling depth corresponding to the target drilling at the current moment are the same as the drilling speed and drilling depth corresponding to a certain acquisition parameter collection in the database, then the acquisition parameter collection in the database is recorded as the acquisition parameter collection corresponding to the target drilling at the current moment, the acquisition parameter collection includes the acquisition time interval and the acquisition point interval distance, and the target drilling at the current moment is set according to the corresponding acquisition time interval and the acquisition point interval distance.

[0013] Preferably, the microbial indicators include the number of microbial species, the rate of change of microbial number and the microbial diversity index, and the trace element indicators include the trace element concentration value, concentration change amplitude and concentration fluctuation period.

[0014] Preferably, the quantum link transmission quality evaluation value corresponding to each acquisition point in each acquisition time point of the target drilling is analyzed, and the specific analysis process is as follows: B1, the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point in each acquisition time point of the target drilling are obtained, and the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point in each acquisition time point of the target drilling are recorded as and Wherein, y represents the number corresponding to each collection time point, y=1,2...a, a is any integer greater than 2, g represents the number corresponding to each collection point, g=1,2...b, b is any integer greater than 2.

[0015] B2. Substitute the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point at each acquisition time point of the target drilling into the calculation formula:

[0016] The quantum link transmission quality evaluation value corresponding to the g-th acquisition point at the y-th acquisition time point of the target drilling is obtained. Among them, S′, H′ and K′ are the standard quantum entanglement fidelity, standard quantum bit error rate and standard quantum state coherence duration corresponding to the set drilling, respectively. are the weight factors corresponding to the set drilling quantum entanglement fidelity, the weight factors corresponding to the quantum bit error rate, and the weight factors corresponding to the quantum state coherence duration, μ1, μ2, and μ3 are the adjustment factors corresponding to the set drilling quantum entanglement fidelity, the adjustment factors corresponding to the quantum bit error rate, and the adjustment factors corresponding to the quantum state coherence duration, respectively, and e represents a natural constant.

[0017] Preferably, the evaluation of whether the quantum link transmission corresponding to each collection point at each collection time point of the target drilling needs to be switched to bioelectric signal transmission is performed as follows: C1. Compare the quantum link transmission quality evaluation value corresponding to each collection point at each collection time point of the target drilling with the quantum link transmission quality evaluation value corresponding to the set standard drilling. If the quantum link transmission quality evaluation value corresponding to a certain collection point at a certain collection time point of the target drilling is greater than or equal to the quantum link transmission quality evaluation value corresponding to the set standard drilling, then it is evaluated that the quantum link transmission corresponding to the collection point at the collection time point of the target drilling does not need to be switched to bioelectric signal transmission. If the quantum link transmission quality evaluation value corresponding to a certain collection point at a certain collection time point of the target drilling is less than the quantum link transmission quality evaluation value corresponding to the set standard drilling, then it is evaluated that the quantum link transmission corresponding to each collection point at the collection time point of the target drilling needs to be switched to bioelectric signal transmission.

[0018] C2. If the quantum link transmission corresponding to a certain collection point at a certain collection time point of the target drilling needs to be switched to bioelectric signal transmission, an instruction to switch to bioelectric signal transmission is sent to various relevant equipment underground, and the instruction is quickly issued to the signal conversion module corresponding to each collection point underground through the backup wired communication link. After receiving the instruction, the signal conversion module quickly completes the parameter configuration adjustment from the quantum link transmission mode to the bioelectric signal transmission mode. After completing the configuration adjustment, the underground collection point begins to convert the collected data into bioelectric signals through the bioelectric induction film and transmits it along the drill pipe. The corresponding bioelectric signal amplifier and decoder on the ground end immediately intervene to amplify and preliminarily decode and verify the bioelectric signal initially transmitted, until the quantum link transmission quality assessment value corresponding to the collection point at the collection time point of the target drilling is greater than or equal to the set quantum link transmission quality assessment value corresponding to the standard drilling, then the collection point at the collection time point of the target drilling is switched from switching to bioelectric signal transmission to switching back to quantum link transmission as needed.

[0019] Preferably, the analysis obtains the microbial fitness value and trace element fitness value corresponding to each collection point at each collection time point. The specific analysis process is as follows: D1. The number of microbial species, the rate of change of microbial number and the microbial diversity index corresponding to each collection point at each collection time point of the target drilling are input into the microbial fitness value analysis model, and the microbial fitness value corresponding to each collection point at each collection time point is output.

[0020] D2. Input the trace element concentration value, concentration change amplitude and concentration fluctuation period corresponding to each acquisition point at each acquisition time point of the target drilling into the trace element adaptation value analysis model, and output the trace element adaptation value corresponding to each acquisition point at each acquisition time point.

[0021] Preferably, the cell-level microscopic fitness values ​​corresponding to each acquisition time point of the target drilling are analyzed, and the specific analysis process is as follows: the microbial fitness values ​​and trace element fitness values ​​corresponding to each acquisition time point of the target drilling are recorded as and Substitute into the calculation formula:

[0022] The cell-level microscopic adaptation value Φ corresponding to each acquisition time point of the target drilling is obtained y , where Z′ and X′ are the standard microbial fitness value and standard trace element fitness value corresponding to the set drilling, Ψ1 and Ψ2 are the weight factors corresponding to the set drilling microbial fitness value and trace element fitness value, respectively. are the microbial fitness value differences and trace element fitness value differences corresponding to each collection point and adjacent collection time points at each collection time point of the target drilling, respectively; Z″ and X″ are the standard microbial fitness value differences and standard trace element fitness value differences corresponding to the set drilling collection point and adjacent collection time points, respectively; and e represents a natural constant.

[0023] Preferably, the drill bit steering decision corresponding to each acquisition time point of the target drilling is analyzed, and the specific analysis process is as follows: E1. The cellular-level microscopic adaptation value corresponding to each acquisition time point of the target drilling is compared with the cellular-level microscopic adaptation value interval corresponding to the set standard drilling. If the cellular-level microscopic adaptation value corresponding to a certain acquisition time point of the target drilling is within the cellular-level microscopic adaptation value interval corresponding to the set standard drilling, it indicates that the drill bit steering decision corresponding to the acquisition time point of the target drilling is to adjust the drill bit steering parameters. If the cellular-level microscopic adaptation value corresponding to a certain acquisition time point of the target drilling is not within the cellular-level microscopic adaptation value interval corresponding to the set standard drilling, it indicates that the drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling, and an early warning prompt is given.

[0024] E2. If the drill bit steering decision corresponding to a certain acquisition time point of the target drilling is to adjust the drill bit steering parameters, the cellular-level microscopic adaptation value corresponding to the acquisition time point of the target drilling is compared with the cellular-level microscopic adaptation value interval corresponding to each drill bit steering decision parameter in the database. If the cellular-level microscopic adaptation value corresponding to the acquisition time point of the target drilling is within the cellular-level microscopic adaptation value interval corresponding to a certain drill bit steering decision parameter in the database, the drill bit steering decision parameter in the database is used as the drill bit steering decision parameter corresponding to the acquisition time point of the target drilling. In this way, the drill bit steering decision parameters corresponding to each acquisition time point of the target drilling are adjusted.

[0025] Preferably, the drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling, and an early warning prompt is given. The specific early warning process is as follows: if the drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling, a strong alarm is issued through the sound and light alarm device at the ground control center at the drilling site, the red warning light flashes, and the high-decibel buzzer sounds. At the same time, the abnormal acquisition time point information, the specific data of the adaptation value, and the accompanying text description are displayed in a striking pop-up window on the large screen of the control center. The text description includes: suspend drilling, beware of well wall collapse, and with the help of the specially developed drilling project management APP, the early warning information is pushed to the mobile phones of project managers, geological engineers, and personnel in various positions in drilling supervision in real time.

[0026] In a second aspect, the present invention provides a high-speed transmission downhole guidance decision-making system based on machine learning, including: a cellular-level microscopic data acquisition module: used to set a number of collection time points and collection points after the target drilling is started, and then collect the cellular-level microscopic data corresponding to each collection point at each collection time point, and the cellular-level microscopic data includes microbial indicators and trace element indicators.

[0027] Cross-medium high-speed data transmission module: used to analyze the quantum link transmission quality evaluation value corresponding to each acquisition point at each acquisition time point of the target drilling, and then evaluate whether the quantum link transmission corresponding to each acquisition point at each acquisition time point of the target drilling needs to be switched to bioelectric signal transmission.

[0028] Cell-level microscopic fitness value analysis module: used to analyze the microbial fitness value and trace element fitness value corresponding to each collection point at each collection time point of the target drilling according to the microbial indicators and trace element indicators corresponding to each collection point at each collection time point of the target drilling, and analyze the cell-level microscopic fitness value corresponding to each collection time point of the target drilling.

[0029] Steering decision analysis module: used to analyze the cellular-level microscopic adaptation values ​​corresponding to each acquisition time point of the target drilling, and then analyze the drill bit steering decision corresponding to each acquisition time point of the target drilling, and initiate the drill bit steering decision warning.

[0030] The beneficial effects of the present invention are as follows: 1. In the embodiment of the present invention, machine learning methods such as microbial fitness value analysis model and trace element fitness value analysis model are used to realize the automated analysis process from original microscopic data to fitness value. This not only improves the efficiency of data analysis, but also reduces the subjective errors and tedious workload that may be caused by manual analysis. The machine learning model can learn rules from a large amount of historical data, and more accurately dig out the complex relationship between microbial indicators, trace element indicators and formation adaptability, laying the foundation for accurately calculating fitness values ​​and making reasonable guidance decisions. From cell-level microscopic data collection to quantum link transmission evaluation, and then to drill bit guidance decision analysis and early warning, a comprehensive risk monitoring system is constructed. It can detect potential formation risks, data transmission risks and drilling operation risks in advance, and take corresponding measures for prevention and control, which significantly reduces the probability of various accidents during drilling, such as stuck drill, well wall collapse, drill bit damage, etc., and improves the safety and stability of the entire drilling project.

[0031] 2. The embodiment of the present invention systematically collects cell-level microscopic data, covering microbial indicators and trace element indicators, and analyzes the cell-level microscopic fitness value, which provides a detailed basis for the drill bit guidance decision based on the actual microscopic environmental conditions downhole. This data-driven approach enables the drill bit guidance decision to accurately match the formation characteristics, which helps to maintain an efficient and stable drilling process. During the drilling process, the formation conditions may change at any time. By continuously acquiring data with the help of multiple collection time points and collection points, and dynamically adjusting the drill bit guidance decision based on real-time cell-level microscopic fitness value analysis, it can quickly adapt to various microscopic changes in the formation. Whether the microbial community structure changes due to underground fluid activity, or the trace element distribution fluctuates due to changes in geological structures, it can be captured in time and reflected in the guidance decision to ensure that the drill bit is always in a relatively optimal drilling state and improve the drilling success rate.

[0032] 3. The embodiment of the present invention takes into account the impact of the complex underground environment on data transmission, innovatively analyzes the transmission quality of the quantum link, and can flexibly switch to bioelectric signal transmission according to the situation, ensuring that the cell-level microscopic data can be stably and quickly transmitted to the ground. When the quantum link has good performance, it can use its advantages of high bandwidth and high efficiency to transmit data. When the quantum link is interfered with or of poor quality, it switches to bioelectric signal transmission in a timely manner, which is relatively more resistant to interference, to avoid decision delays or errors caused by data transmission interruptions or errors, and provides reliable data support for the entire drilling guidance decision system. Under the protection of the quantum link transmission quality assessment and switching mechanism, the possibility of data loss is minimized. Key cell-level microscopic data such as microbial indicators and trace element indicators collected underground are crucial for accurately judging the formation conditions. Stable data transmission ensures that these data are fully delivered to the ground control center, so that subsequent adaptation value analysis, guidance decision-making and other links can be based on comprehensive and accurate data, improving the scientificity and reliability of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 The present invention is a flowchart of the steps for implementing the method.

[0035] Figure 2 This is a schematic diagram of the connection of the system modules of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Embodiments of the present invention Figure 1 As shown, a high-speed transmission downhole guidance decision-making method based on machine learning includes: step one, acquisition of cellular-level microscopic data: after the target drilling is started, a number of collection time points and collection points are set, and then the cellular-level microscopic data corresponding to each collection point is collected at each collection time point, and the cellular-level microscopic data includes microbial indicators and trace element indicators.

[0038] In a specific embodiment, the setting of several acquisition time points and acquisition points is specifically performed as follows: after the target drilling is started, the drilling speed and drilling depth corresponding to the target drilling at the current moment are obtained, and the drilling speed and drilling depth corresponding to the target drilling at the current moment are compared with the drilling speeds and drilling depths corresponding to each acquisition parameter collection in the database; if the drilling speed and drilling depth corresponding to the target drilling at the current moment are the same as the drilling speed and drilling depth corresponding to a certain acquisition parameter collection in the database, the acquisition parameter collection in the database is recorded as the acquisition parameter collection corresponding to the target drilling at the current moment, the acquisition parameter collection includes an acquisition time interval and an acquisition point interval distance, and the target drilling at the current moment is set according to the corresponding acquisition time interval and acquisition point interval distance.

[0039] In another specific embodiment, the microbial indicators include the number of microbial species, the rate of change of microbial number and the microbial diversity index, and the trace element indicators include the trace element concentration value, concentration change amplitude and concentration fluctuation period.

[0040] It should be noted that microfluidic chips are installed at each collection point and collection time point, and high-throughput screening platforms such as microfluidic chips are used to set up a large number of tiny reaction units on the chip, each of which can detect specific gene markers or metabolites of microorganisms. In this way, a large number of microorganisms can be quickly screened, different types of microorganisms can be identified, and the microbial samples can be properly stained and detected by flow cytometry. Flow cytometry can quickly count single microbial cells and distinguish different types of microorganisms based on parameters such as cell size, shape and fluorescence characteristics. By collecting samples at different time points for analysis, the rate of change of microbial numbers can be obtained, and the 16SrRNA gene in the microbial samples can be sequenced. This is a gene that is commonly found in bacteria and archaea, and its sequence is species-specific. By analyzing the diversity of 16SrRNA gene sequences, the diversity of microbial communities can be reflected. By comparing the diversity index at different collection points and time points, the changes in the structure of microbial communities can be understood. This method can comprehensively evaluate microbial diversity and is a common method in microbial ecology research.

[0041] It should also be noted that formation fluid or rock samples containing trace elements are collected underground, and after pretreatment, the samples are detected by ICP-MS equipment. ICP-MS can simultaneously measure the concentration of multiple trace elements and has the characteristics of high sensitivity and low detection limit. It ionizes the sample, analyzes the ions using a mass spectrometer, determines the type of element according to the mass-to-charge ratio of the ions, and quantifies the element concentration by detecting the intensity of the ions. This technology can accurately measure the concentration of trace elements and is suitable for trace element detection in various complex geological samples. Trace element sensors are installed at various collection points underground. These sensors can monitor the concentration changes of trace elements in real time based on electrochemical principles or optical principles. Through long-term continuous monitoring, the change curve of trace element concentration is recorded, and then the concentration change amplitude and fluctuation period are analyzed using data analysis software. This method can obtain dynamic change information of trace element concentration in real time, which is very effective for timely detection of abnormal changes in trace elements in formations.

[0042] Step 2: Transmission of high-speed data across media: Analyze the quantum link transmission quality assessment value corresponding to each acquisition point at each acquisition time point of the target drilling, and then evaluate whether the quantum link transmission corresponding to each acquisition point at each acquisition time point of the target drilling needs to be switched to bioelectric signal transmission.

[0043] In a specific embodiment, the quantum link transmission quality evaluation value corresponding to each acquisition point in each acquisition time point of the target drilling is analyzed, and the specific analysis process is as follows: B1, the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point in each acquisition time point of the target drilling are obtained, and the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point in each acquisition time point of the target drilling are recorded as and Wherein, y represents the number corresponding to each collection time point, y=1,2...a, a is any integer greater than 2, g represents the number corresponding to each collection point, g=1,2...b, b is any integer greater than 2.

[0044] It should be noted that, using an integrated quantum state analyzer, the output end of the downhole quantum transmission link is connected to the quantum state analyzer, and the device automatically runs the measurement program to estimate the quantum entanglement fidelity. The quantum state analyzer can quickly measure a specific quantum bit system through a simple interface setting, and then directly output the estimated value of the quantum entanglement fidelity. In the quantum communication hardware system, the quantum bit transmission device has its own error detection module. The module can monitor the errors in the quantum bit transmission process in real time. At the downhole equipment end, by viewing the error counts recorded by these built-in modules and the total number of quantum bits transmitted, it is possible to perform error monitoring while the quantum bit is being transmitted, and the error information can be transmitted to the ground control center through a simple data interface. By calculating the ratio of the recorded error counts and the total number of quantum bits transmitted, the quantum bit error rate is obtained, and a quantum state coherence time monitoring instrument is set. The quantum state coherence time monitoring instrument is usually based on the optical or electrical coherence detection principle. Connect it to the quantum system. In the downhole environment, when the quantum state passes through the transmission link, the quantum state coherence time monitoring instrument can automatically measure and display the quantum state coherence.

[0045] B2. Substitute the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point at each acquisition time point of the target drilling into the calculation formula:

[0046] The quantum link transmission quality evaluation value corresponding to the g-th acquisition point at the y-th acquisition time point of the target drilling is obtained. Among them, S′, H′ and K′ are the standard quantum entanglement fidelity, standard quantum bit error rate and standard quantum state coherence duration corresponding to the set drilling, respectively. are the weight factors corresponding to the set drilling quantum entanglement fidelity, the weight factors corresponding to the quantum bit error rate, and the weight factors corresponding to the quantum state coherence duration, μ1, μ2, and μ3 are the adjustment factors corresponding to the set drilling quantum entanglement fidelity, the adjustment factors corresponding to the quantum bit error rate, and the adjustment factors corresponding to the quantum state coherence duration, respectively, and e represents a natural constant.

[0047] It should be noted that Both are greater than 0 and less than 1.

[0048] It should also be noted that through the summary of a large amount of research data and experimental data. The standard quantum entanglement fidelity, standard quantum bit error rate, and standard quantum state coherence duration corresponding to drilling are set according to professional institutions and research institutions. At the same time, based on the professional knowledge and research basis of experts in the field, they are discussed and confirmed with industry organizations or professional institutions. Experts set the weight factors corresponding to the drilling quantum entanglement fidelity, the weight factors corresponding to the quantum bit error rate, and the weight factors corresponding to the quantum state coherence duration based on their own experience and knowledge, and set the adjustment factors corresponding to the drilling quantum entanglement fidelity, the adjustment factors corresponding to the quantum bit error rate, and the adjustment factors corresponding to the quantum state coherence duration.

[0049] In another specific embodiment, the evaluation of whether the quantum link transmission corresponding to each collection point at each collection time point of the target drilling needs to be switched to bioelectric signal transmission is performed as follows: C1. Compare the quantum link transmission quality evaluation value corresponding to each collection point at each collection time point of the target drilling with the quantum link transmission quality evaluation value corresponding to the set standard drilling. If the quantum link transmission quality evaluation value corresponding to a certain collection point at a certain collection time point of the target drilling is greater than or equal to the quantum link transmission quality evaluation value corresponding to the set standard drilling, then it is evaluated that the quantum link transmission corresponding to the collection point at the collection time point of the target drilling does not need to be switched to bioelectric signal transmission. If the quantum link transmission quality evaluation value corresponding to a certain collection point at a certain collection time point of the target drilling is less than the quantum link transmission quality evaluation value corresponding to the set standard drilling, then it is evaluated that the quantum link transmission corresponding to each collection point at the collection time point of the target drilling needs to be switched to bioelectric signal transmission.

[0050] C2. If the quantum link transmission corresponding to a certain collection point at a certain collection time point of the target drilling needs to be switched to bioelectric signal transmission, an instruction to switch to bioelectric signal transmission is sent to various relevant equipment underground, and the instruction is quickly issued to the signal conversion module corresponding to each collection point underground through the backup wired communication link. After receiving the instruction, the signal conversion module quickly completes the parameter configuration adjustment from the quantum link transmission mode to the bioelectric signal transmission mode. After completing the configuration adjustment, the underground collection point begins to convert the collected data into bioelectric signals through the bioelectric induction film and transmits it along the drill pipe. The corresponding bioelectric signal amplifier and decoder on the ground end immediately intervene to amplify and preliminarily decode and verify the bioelectric signal initially transmitted, until the quantum link transmission quality assessment value corresponding to the collection point at the collection time point of the target drilling is greater than or equal to the set quantum link transmission quality assessment value corresponding to the standard drilling, then the collection point at the collection time point of the target drilling is switched from switching to bioelectric signal transmission to switching back to quantum link transmission as needed.

[0051] It should be noted that quantum communication technology is combined with biological information transmission channels. Genetically edited microorganisms are used to carry quantum bit information in their bodies. These microorganisms can swim autonomously in the formation fluid and transmit key downhole data to the ground receiving station like a "messenger"; at the same time, with the help of quantum entanglement characteristics, an ultra-high-speed entanglement link is built between the microorganism and the ground base station to achieve instant and lossless transmission of information, breaking the shackles of traditional wireless transmission being shielded by formations and signal attenuation, and attaching a bioelectric induction film to the surface of the drill pipe. The weak energy generated by the operation of downhole equipment and changes in formation stress is converted into bioelectric signals by the film and transmitted to the ground at high speed along the drill pipe. The ground end uses bioelectric signal amplifiers and decoders to accurately restore the original data. This bioelectricity-based transmission method serves as a supplement to quantum communication, ensuring that data transmission is uninterrupted under extreme working conditions and when quantum communication fails partially.

[0052] Step 3. Analysis of cellular-level microscopic adaptation values: According to the microbial indicators and trace element indicators corresponding to each collection point at each collection time point of the target drilling, the microbial adaptation values ​​and trace element adaptation values ​​corresponding to each collection time point are analyzed, and the cellular-level microscopic adaptation values ​​corresponding to each collection time point of the target drilling are analyzed.

[0053] In a specific embodiment, the analysis obtains the microbial fitness value and trace element fitness value corresponding to each collection point at each collection time point. The specific analysis process is as follows: D1. The number of microbial species, the rate of change of microbial number and the microbial diversity index corresponding to each collection point at each collection time point of the target drilling are input into the microbial fitness value analysis model, and the microbial fitness value corresponding to each collection point at each collection time point is output.

[0054] It should be noted that the analysis process of the microbial fitness value corresponding to each collection point at each collection time point is as follows: the number of microbial species, the change rate of microbial number and the microbial diversity index corresponding to each collection point at each collection time point of the target drilling are normalized, and the number of microbial species, the change rate of microbial number and the microbial diversity index corresponding to each collection point at each collection time point of the target drilling after processing are recorded as and Substitute into the analysis formula Get the microbial fitness value corresponding to each collection point at each collection time point κ1, κ2, and κ3 are the weight factors corresponding to the number of drilling microbial species, the weight factor corresponding to the rate of change of microbial number, and the weight factor corresponding to the microbial diversity index, respectively.

[0055] It should be noted that κ1, κ2, and κ3 are all greater than 0 and less than 1.

[0056] It should also be noted that, based on the expertise and research of experts in the field, and after discussion and confirmation with industry organizations or professional institutions, the experts set the weight factors corresponding to the number of drilling microbial species, the weight factors corresponding to the rate of change of microbial numbers, and the weight factors corresponding to the microbial diversity index based on their own experience and knowledge.

[0057] D2. Input the trace element concentration value, concentration change amplitude and concentration fluctuation period corresponding to each acquisition point at each acquisition time point of the target drilling into the trace element adaptation value analysis model, and output the trace element adaptation value corresponding to each acquisition point at each acquisition time point.

[0058] It should be noted that the analysis process of the trace element fitness values ​​corresponding to each collection point at each collection time is obtained by analysis according to the analysis process of the microbial fitness values ​​corresponding to each collection point at each collection time as described above.

[0059] In another specific embodiment, the cell-level microscopic fitness values ​​corresponding to each acquisition time point of the target drilling are analyzed, and the specific analysis process is as follows: the microbial fitness values ​​and trace element fitness values ​​corresponding to each acquisition time point of the target drilling are recorded as and Substitute into the calculation formula: The cell-level microscopic adaptation value Φ corresponding to each acquisition time point of the target drilling is obtained y , where Z′ and X′ are the standard microbial fitness value and standard trace element fitness value corresponding to the set drilling, Ψ1 and Ψ2 are the weight factors corresponding to the set drilling microbial fitness value and trace element fitness value, respectively. are the microbial fitness value differences and trace element fitness value differences corresponding to each collection point and adjacent collection time points at each collection time point of the target drilling, respectively; Z″ and X″ are the standard microbial fitness value differences and standard trace element fitness value differences corresponding to the set drilling collection point and adjacent collection time points, respectively; and e represents a natural constant.

[0060] It should be noted that Ψ1 and Ψ2 are both greater than 0 and less than 1.

[0061] It should also be noted that through the summary of a large amount of research data and experimental data. The standard microbial fitness value and standard trace element fitness value corresponding to drilling are set according to professional institutions and research institutions. At the same time, based on the professional knowledge and research basis of experts in the field, they are discussed and confirmed with industry organizations or professional institutions. Experts set the weight factors corresponding to the drilling microbial fitness value and the weight factors corresponding to the trace element fitness value based on their own experience and knowledge, and set the standard microbial fitness value difference and standard trace element fitness value difference corresponding to the drilling collection point and the adjacent collection time point.

[0062] Step 4: Analysis of steering decisions: Analyze the cellular-level microscopic adaptation values ​​corresponding to each acquisition time point of the target drilling, and then analyze the drill bit steering decisions corresponding to each acquisition time point of the target drilling, and initiate the drill bit steering decision warning.

[0063] In a specific embodiment, the drill bit steering decision corresponding to each acquisition time point of the target drilling is analyzed, and the specific analysis process is as follows: E1. The cellular-level microscopic adaptation value corresponding to each acquisition time point of the target drilling is compared with the cellular-level microscopic adaptation value interval corresponding to the set standard drilling. If the cellular-level microscopic adaptation value corresponding to a certain acquisition time point of the target drilling is within the cellular-level microscopic adaptation value interval corresponding to the set standard drilling, it indicates that the drill bit steering decision corresponding to the acquisition time point of the target drilling is to adjust the drill bit steering parameters. If the cellular-level microscopic adaptation value corresponding to a certain acquisition time point of the target drilling is not within the cellular-level microscopic adaptation value interval corresponding to the set standard drilling, it indicates that the drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling, and an early warning prompt is given.

[0064] E2. If the drill bit steering decision corresponding to a certain acquisition time point of the target drilling is to adjust the drill bit steering parameters, the cellular-level microscopic adaptation value corresponding to the acquisition time point of the target drilling is compared with the cellular-level microscopic adaptation value interval corresponding to each drill bit steering decision parameter in the database. If the cellular-level microscopic adaptation value corresponding to the acquisition time point of the target drilling is within the cellular-level microscopic adaptation value interval corresponding to a certain drill bit steering decision parameter in the database, the drill bit steering decision parameter in the database is used as the drill bit steering decision parameter corresponding to the acquisition time point of the target drilling. In this way, the drill bit steering decision parameters corresponding to each acquisition time point of the target drilling are adjusted.

[0065] It should be noted that the drill bit steering decision parameters include vertical drilling angle, horizontal drilling direction, azimuth adjustment, drilling speed, drilling fluid density adjustment and drill bit tilt posture.

[0066] In another specific embodiment, the drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling, and an early warning prompt is performed. The specific early warning process is as follows: if the drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling, a strong alarm is issued through an audio-visual alarm device at the ground control center at the drilling site, and the red warning light flashes and a high-decibel buzzer sounds. At the same time, the abnormal acquisition time point information, the specific data of the adaptation value, and a text description are displayed in a striking pop-up window on the large screen of the control center. The text description includes: suspend drilling and beware of well wall collapse. With the help of a specially developed drilling engineering management APP, the early warning information is pushed in real time to the mobile phones of project managers, geological engineers, and personnel in various positions in drilling supervision.

[0067] Embodiments of the present invention Figure 2As shown, a high-speed transmission downhole steering decision system based on machine learning includes: a cellular-level microscopic data acquisition module, a cross-medium high-speed data transmission module, a cellular-level microscopic adaptation value analysis module, a steering decision analysis module and a database.

[0068] It should be noted that the database is used to store the drilling speed and drilling depth corresponding to each set of acquisition parameters, and the database is also used to store the cellular-level microscopic adaptation value interval corresponding to each drill bit steering decision parameter.

[0069] Cell-level microscopic data acquisition module: used to set several collection time points and collection points after the target drilling is started, and then collect the cell-level microscopic data corresponding to each collection point at each collection time point. The cell-level microscopic data includes microbial indicators and trace element indicators.

[0070] Cross-medium high-speed data transmission module: used to analyze the quantum link transmission quality evaluation value corresponding to each acquisition point at each acquisition time point of the target drilling, and then evaluate whether the quantum link transmission corresponding to each acquisition point at each acquisition time point of the target drilling needs to be switched to bioelectric signal transmission.

[0071] Cell-level microscopic fitness value analysis module: used to analyze the microbial fitness value and trace element fitness value corresponding to each collection point at each collection time point of the target drilling according to the microbial indicators and trace element indicators corresponding to each collection point at each collection time point of the target drilling, and analyze the cell-level microscopic fitness value corresponding to each collection time point of the target drilling.

[0072] Steering decision analysis module: used to analyze the cellular-level microscopic adaptation values ​​corresponding to each acquisition time point of the target drilling, and then analyze the drill bit steering decision corresponding to each acquisition time point of the target drilling, and initiate the drill bit steering decision warning.

[0073] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they shall all fall within the protection scope of the present invention.

Claims

1. A high-speed transmission while drilling guidance decision-making method based on machine learning, characterized in that: include: Step 1: Acquisition of cell-level microscopic data: After the target drilling is started, several collection time points and collection points are set, and then the cell-level microscopic data corresponding to each collection point is collected at each collection time point. The cell-level microscopic data includes microbial indicators and trace element indicators; Step 2: Transmission of high-speed data across media: Analyze the quantum link transmission quality evaluation value corresponding to each acquisition point at each acquisition time point of the target drilling, and then evaluate whether the quantum link transmission corresponding to each acquisition point at each acquisition time point of the target drilling needs to be switched to bioelectric signal transmission; Step 3: Analysis of cell-level microscopic fitness values: According to the microbial indicators and trace element indicators corresponding to each collection point at each collection time point of the target drilling, the microbial fitness values ​​and trace element fitness values ​​corresponding to each collection point at each collection time point are analyzed, and the cell-level microscopic fitness values ​​corresponding to each collection time point of the target drilling are analyzed; Step 4: Analysis of steering decisions: Analyze the cellular-level microscopic adaptation values ​​corresponding to each acquisition time point of the target drilling, and then analyze the drill bit steering decisions corresponding to each acquisition time point of the target drilling, and initiate the drill bit steering decision warning.

2. A high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 1, characterized in that: The specific setting process of setting several collection time points and collection points is as follows: After the target drilling is started, the drilling speed and drilling depth corresponding to the target drilling at the current moment are obtained, and the drilling speed and drilling depth corresponding to the target drilling at the current moment are compared with the drilling speeds and drilling depths corresponding to each acquisition parameter set in the database. If the drilling speed and drilling depth corresponding to the target drilling at the current moment are the same as the drilling speed and drilling depth corresponding to a certain acquisition parameter set in the database, the acquisition parameter set in the database is recorded as the acquisition parameter set corresponding to the target drilling at the current moment. The acquisition parameter set includes an acquisition time interval and an acquisition point interval distance, and the target drilling at the current moment is set according to the corresponding acquisition time interval and acquisition point interval distance.

3. A high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 2, characterized in that: The microbial indicators include the number of microbial species, the rate of change of microbial number and the microbial diversity index; the trace element indicators include the trace element concentration value, concentration change amplitude and concentration fluctuation period.

4. A high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 3, characterized in that: The specific analysis process of analyzing the quantum link transmission quality evaluation value corresponding to each acquisition point at each acquisition time point of the target drilling is as follows: B1. Obtain the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point at each acquisition time point of the target drilling, and record the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point at each acquisition time point of the target drilling as and Wherein, y represents the number corresponding to each acquisition time point, y=1,2...a, a is any integer greater than 2, g represents the number corresponding to each acquisition point, g=1,2...b, b is any integer greater than 2; B2. Substitute the quantum entanglement fidelity, quantum bit error rate and quantum state coherence duration corresponding to each acquisition point at each acquisition time point of the target drilling into the calculation formula: The quantum link transmission quality evaluation value corresponding to the g-th acquisition point at the y-th acquisition time point of the target drilling is obtained. Among them, S′, H′ and K′ are the standard quantum entanglement fidelity, standard quantum bit error rate and standard quantum state coherence duration corresponding to the set drilling, respectively. are the weight factors corresponding to the set drilling quantum entanglement fidelity, the weight factors corresponding to the quantum bit error rate, and the weight factors corresponding to the quantum state coherence duration, μ1, μ2, and μ3 are the adjustment factors corresponding to the set drilling quantum entanglement fidelity, the adjustment factors corresponding to the quantum bit error rate, and the adjustment factors corresponding to the quantum state coherence duration, respectively, and e represents a natural constant.

5. The high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 4, characterized in that: The specific evaluation process of evaluating whether the quantum link transmission corresponding to each collection point at each collection time point of the target drilling needs to be switched to bioelectric signal transmission is as follows: C1. Compare the quantum link transmission quality evaluation value corresponding to each collection point at each collection time point of the target drilling with the quantum link transmission quality evaluation value corresponding to the set standard drilling. If the quantum link transmission quality evaluation value corresponding to a certain collection point at a certain collection time point of the target drilling is greater than or equal to the quantum link transmission quality evaluation value corresponding to the set standard drilling, then it is evaluated that the quantum link transmission corresponding to the collection point at the collection time point of the target drilling does not need to be switched to bioelectric signal transmission. If the quantum link transmission quality evaluation value corresponding to a certain collection point at a certain collection time point of the target drilling is less than the quantum link transmission quality evaluation value corresponding to the set standard drilling, then it is evaluated that the quantum link transmission corresponding to each collection point at the collection time point of the target drilling needs to be switched to bioelectric signal transmission; C2. If the quantum link transmission corresponding to a certain collection point at a certain collection time point of the target drilling needs to be switched to bioelectric signal transmission, an instruction to switch to bioelectric signal transmission is sent to various relevant equipment underground, and the instruction is quickly issued to the signal conversion module corresponding to each collection point underground through the backup wired communication link. After receiving the instruction, the signal conversion module quickly completes the parameter configuration adjustment from the quantum link transmission mode to the bioelectric signal transmission mode. After completing the configuration adjustment, the underground collection point begins to convert the collected data into bioelectric signals through the bioelectric induction film and transmits it along the drill pipe. The corresponding bioelectric signal amplifier and decoder on the ground end immediately intervene to amplify and preliminarily decode and verify the bioelectric signal initially transmitted, until the quantum link transmission quality assessment value corresponding to the collection point at the collection time point of the target drilling is greater than or equal to the set quantum link transmission quality assessment value corresponding to the standard drilling, then the collection point at the collection time point of the target drilling is switched from switching to bioelectric signal transmission to switching back to quantum link transmission as needed.

6. A high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 5, characterized in that: The analysis obtained the microbial fitness value and trace element fitness value corresponding to each collection point at each collection time point. The specific analysis process is as follows: D1. Input the number of microbial species, the rate of change of microbial number and the microbial diversity index corresponding to each collection point at each collection time point of the target drilling into the microbial fitness value analysis model, and output the microbial fitness value corresponding to each collection point at each collection time point; D2. Input the trace element concentration value, concentration change amplitude and concentration fluctuation period corresponding to each acquisition point at each acquisition time point of the target drilling into the trace element adaptation value analysis model, and output the trace element adaptation value corresponding to each acquisition point at each acquisition time point.

7. A high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 6, characterized in that: The cell-level microscopic adaptation values ​​corresponding to each acquisition time point of the target drilling are analyzed, and the specific analysis process is as follows: The microbial fitness value and trace element fitness value corresponding to each sampling point at each sampling time point of the target drilling are recorded as and Substitute into the calculation formula: The cell-level microscopic adaptation value Φ corresponding to each acquisition time point of the target drilling is obtained y , where Z′ and X′ are the standard microbial fitness value and standard trace element fitness value corresponding to the set drilling, Ψ1 and Ψ2 are the weight factors corresponding to the set drilling microbial fitness value and trace element fitness value, respectively. are the microbial fitness value differences and trace element fitness value differences corresponding to each collection point and adjacent collection time points at each collection time point of the target drilling, respectively; Z″ and X″ are the standard microbial fitness value differences and standard trace element fitness value differences corresponding to the set drilling collection point and adjacent collection time points, respectively; and e represents a natural constant.

8. The high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 7, characterized in that: The drill bit steering decision corresponding to each acquisition time point of the target drilling is analyzed, and the specific analysis process is as follows: E1. Compare the cell-level microscopic adaptation value corresponding to each acquisition time point of the target drilling with the cell-level microscopic adaptation value interval corresponding to the set standard drilling. If the cell-level microscopic adaptation value corresponding to a certain acquisition time point of the target drilling is within the cell-level microscopic adaptation value interval corresponding to the set standard drilling, it indicates that the drill bit steering decision corresponding to the acquisition time point of the target drilling is to adjust the drill bit steering parameters. If the cell-level microscopic adaptation value corresponding to a certain acquisition time point of the target drilling is not within the cell-level microscopic adaptation value interval corresponding to the set standard drilling, it indicates that the drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling, and an early warning prompt is given; E2. If the drill bit steering decision corresponding to a certain acquisition time point of the target drilling is to adjust the drill bit steering parameters, the cellular-level microscopic adaptation value corresponding to the acquisition time point of the target drilling is compared with the cellular-level microscopic adaptation value interval corresponding to each drill bit steering decision parameter in the database. If the cellular-level microscopic adaptation value corresponding to the acquisition time point of the target drilling is within the cellular-level microscopic adaptation value interval corresponding to a certain drill bit steering decision parameter in the database, the drill bit steering decision parameter in the database is used as the drill bit steering decision parameter corresponding to the acquisition time point of the target drilling. In this way, the drill bit steering decision parameters corresponding to each acquisition time point of the target drilling are adjusted.

9. A high-speed transmission while drilling guidance decision-making method based on machine learning as claimed in claim 8, characterized in that: The drill bit steering decision corresponding to the acquisition time point of the target drilling is to suspend drilling and issue an early warning prompt. The specific early warning process is as follows: If the drill bit steering decision corresponding to the target drilling acquisition time point is to suspend drilling, a strong alarm will be issued through the sound and light alarm device at the ground control center at the drilling site, with the red warning light flashing and the high-decibel buzzer sounding. At the same time, the abnormal acquisition time point information, the specific data of the adaptation value, and the accompanying text description will be displayed in a striking pop-up window on the large screen of the control center. The text description includes: suspend drilling and beware of well wall collapse. With the help of the specially developed drilling project management APP, the early warning information will be pushed to the mobile phones of project managers, geological engineers, and drilling supervisors in real time.

10. A high-speed transmission while drilling steering decision system based on machine learning that executes the high-speed transmission while drilling steering decision method based on machine learning according to any one of claims 1 to 9, characterized in that: include: Cell-level microscopic data acquisition module: used to set a number of collection time points and collection points after the target drilling is started, and then collect the cell-level microscopic data corresponding to each collection point at each collection time point. The cell-level microscopic data includes microbial indicators and trace element indicators; Cross-medium high-speed data transmission module: used to analyze the quantum link transmission quality evaluation value corresponding to each acquisition point at each acquisition time point of the target drilling, and then evaluate whether the quantum link transmission corresponding to each acquisition point at each acquisition time point of the target drilling needs to be switched to bioelectric signal transmission; Cell-level microscopic fitness value analysis module: used to analyze the microbial fitness value and trace element fitness value corresponding to each collection point at each collection time point of the target drilling according to the microbial indicators and trace element indicators corresponding to each collection point at each collection time point of the target drilling, and analyze the cell-level microscopic fitness value corresponding to each collection time point of the target drilling; Steering decision analysis module: used to analyze the cellular-level microscopic adaptation values ​​corresponding to each acquisition time point of the target drilling, and then analyze the drill bit steering decision corresponding to each acquisition time point of the target drilling, and initiate the drill bit steering decision warning.

Images