A method and related apparatus for adaptive mapping of drilling physical electrical signals and formation hardness based on temporal deep learning

By using temporal deep learning methods, effective drilling sections are identified and signal correction is performed. The mapping relationship is adaptively corrected, which solves the problem of inaccurate formation hardness identification during drilling and realizes continuous formation hardness characterization and formation division.

CN123115645APending Publication Date: 2026-11-17QINGHAI GEOTECHNICAL ENG INVESTIGATION CONSULTING CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611235042.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-14
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing technologies struggle to effectively distinguish between changes in formation hardness and equipment disturbances during drilling, making it difficult to accurately identify continuous formation changes using fixed mapping relationships, especially in high-altitude areas where environmental changes have a significant impact.

Method used

By using a time-series deep learning approach, effective drilling sections are identified, load signal baseline correction and working condition standardization are performed, and combined with the validated adaptive correction mapping relationship of formation sections, continuous formation resistance characteristics are extracted to generate formation hardness characterization results that continuously correspond to the borehole depth.

Benefits of technology

It improves the consistency of formation hardness identification, can distinguish between local disturbances and continuous formation changes, and forms a drilling hardness profile that can be used for formation delineation and exploration data processing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123115645A_ABST
    Figure CN123115645A_ABST
Patent Text Reader

Abstract

This invention discloses a method, adaptive mapping device, adaptive mapping equipment, and computer-readable storage medium for adaptive mapping of drilling physical electrical signals and formation hardness based on temporal deep learning. The method acquires temporal operational data such as current, voltage, power, spindle speed, feed load, and drilling depth during the drilling process of the target borehole, establishing a correspondence between the operational data and the borehole depth position; identifies effective drilling sections, performs equipment operating baseline correction, operating condition standardization, and time-depth joint segmentation on the drilling load signal; utilizes a temporal deep learning network to extract the local drilling response and the continuous change relationship between adjacent sections, forming a temporal representation sequence of formation resistance; establishes a basic mapping relationship by combining formation verification data and drilling conditions, and performs adaptive correction using reference depth sections; finally, it generates a formation hardness profile during drilling and formation change indication results. This method can reduce the impact of equipment status and short-term operational disturbances on formation hardness identification.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the field of formation state identification technology, and more specifically, relates to a method for adaptive mapping of drilling physical electrical signals and formation hardness based on time-series deep learning, a device for adaptive mapping of drilling physical electrical signals and formation hardness, an adaptive mapping device, and a computer-readable storage medium. Background Technology

[0002] During geotechnical engineering exploration drilling, when the drill bit cuts, breaks, and penetrates strata of different hardness, the current, power, speed, and load of the drilling rig's rotary drive motor and feed drive mechanism will fluctuate accordingly with changes in stratum resistance. Therefore, using drilling physical electrical signals to identify stratum hardness can provide auxiliary basis for stratum division, abnormal stratum identification, and borehole data digitization.

[0003] Existing technologies typically establish a correlation between drilling signals and formation hardness using fixed thresholds, single-moment signal amplitude, or average power per unit depth. However, drilling electrical signals are affected not only by formation hardness but also by spindle speed, feed rate, drill string wear, equipment operating baseline, and environmental conditions. Especially in high-altitude areas, changes in temperature, air pressure, and equipment thermal state can easily cause different load responses in the same formation, making it difficult for fixed mapping relationships to distinguish between continuous formation changes and short-term drilling disturbances.

[0004] Therefore, how to identify effective drilling sections, perform baseline correction and working condition standardization on load signals, extract continuous formation resistance characteristics using time-series deep learning, and combine the verified formation section adaptive correction mapping relationship to form a formation hardness characterization result that continuously corresponds to the hole depth is a key issue of concern to those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, and computer-readable storage medium for adaptive mapping of drilling physical electrical signals and formation hardness based on time-series deep learning. By identifying effective drilling sections, baseline correction and working condition standardization of load signals are performed. Continuous formation resistance characteristics are extracted using time-series deep learning, and the mapping relationship of verified formation sections is adaptively corrected to form a formation hardness characterization result that continuously corresponds to the hole depth.

[0006] To address the aforementioned deficiencies or improvement needs of existing technologies, this invention provides a method for adaptive mapping of drilling physical electrical signals and formation hardness based on time-series deep learning, comprising: S1, acquire drilling time sequence data during the drilling process of the target borehole, and establish the correspondence between the drilling time sequence data and the borehole depth position based on the acquisition time and drilling depth to obtain the original drilling time sequence dataset; S2, Identify the effective drilling section based on the drilling depth change status, rotation status and feed status in the original drilling time series dataset, perform baseline correction on the drilling load signal in the effective drilling section based on the corresponding equipment operating baseline, and perform standardization processing and time series segmentation according to the drilling conditions to obtain the effective drilling time series sample. S3, extract time-series state information from the effective drilling time-series samples, input it into a time-series deep learning network, extract the local drilling response and the continuous change relationship between adjacent samples, and obtain the formation resistance time-series characterization sequence arranged along the hole depth; S4. Obtain formation hardness reference data corresponding to the depth segment with formation verification results, form a formation hardness reference sequence, align the formation resistance time series characterization sequence with the formation hardness reference sequence at depth, and establish a basic mapping relationship in combination with drilling condition information; use the basic mapping relationship to obtain the initial formation hardness characterization result of the target borehole, and correct the basic mapping relationship according to the deviation between the initial formation hardness characterization result corresponding to the verified reference depth segment in the target borehole and the actual formation hardness reference result, to obtain an adaptive mapping relationship and the corresponding formation hardness characterization sequence. S5, perform continuity discrimination on the formation hardness characterization sequence, distinguish between local drilling disturbances and continuous formation hardness changes, and generate a formation hardness profile during drilling and formation change indication results.

[0007] Optionally, in S1, the drilling timing operation data includes at least one of the following: the operating current, operating voltage, and active power of the rotary drive motor, the actual spindle speed, the feed drive load, and the drilling depth. The actual drilling footage is determined based on the changes in drilling depth corresponding to adjacent sampling times. The drilling time series data corresponding to each sampling time is mapped to the corresponding hole depth position to form the original drilling time series dataset indexed by sampling time and drilling depth.

[0008] Optionally, S2 includes: The effective drilling section is determined based on the combination of the states of continuously increasing drilling depth, continuous spindle rotation, and continuous feed drive load. Obtain the drilling load in the stable no-load operating state or the drill bit suspension and rotation state corresponding to the current effective drilling section, and determine the operating baseline of the equipment; The actual drilling load within the effective drilling section is compared with the equipment operating baseline to obtain the incremental load response generated by the interaction between the drill bit and the formation. The incremental load response is then standardized based on the actual spindle speed and the actual drilling speed.

[0009] Optionally, in step S2, the time-series segmentation of the standardized drilling load signal includes: A continuous time window is formed according to a preset time range, and the drilling depth range corresponding to each continuous time window is determined. When the drilling depth range does not meet the preset depth range condition, the corresponding continuous time window is adjusted according to the actual drilling depth change. The drilling load signals in each adjusted continuous time window are used to form the effective drilling time sequence sample according to the sampling order.

[0010] Optionally, in S3, the time-series state information includes drilling load level, drilling load fluctuation state, and penetration state; the time-series deep learning network includes a local time-series change extraction part and a continuous state association part. The local time-series change extraction section is used to perform time-series processing on the changes in drilling load and drilling footage within the same valid drilling time-series sample to obtain the local drilling response. The continuous state association section is used to perform association processing on multiple local drilling responses arranged in the drilling sequence, determine the continuous change relationship of drilling load and penetration state between adjacent drilling depth sections, and generate the formation resistance time series characterization based on the local drilling responses and the continuous change relationship.

[0011] Optionally, in step S4, the formation hardness reference data is derived from at least one of the following: core logging results corresponding to the drilling depth, description of soil and rock conditions, in-situ test results, and laboratory mechanical test results. The drilling condition information includes at least one of the following: spindle speed status, actual drilling speed status, drill string status, equipment operating baseline, and equipment operating environment status. When establishing the basic mapping relationship, the drilling condition information is used as the mapping condition between the formation resistance time series characterization and the formation hardness, so that the formation resistance time series characterization obtains the formation hardness characterization result according to the corresponding drilling condition.

[0012] Optionally, in step S4, the reference depth section in the target borehole verified by core logging, in-situ testing, or laboratory mechanical testing is determined as the correction anchor point. Based on the deviation between the initial formation hardness characterization result corresponding to the correction anchor point and the actual formation hardness reference result, at least one of the combined weights of the equipment operating baseline, formation hardness output scale, and time-series status information is corrected. When the state of the drill string changes, the location where the state of the drill string changes is taken as the starting point of the new mapping stage, and the basic mapping relationship of the subsequent drilling depth section is corrected in stages using the correction anchor point corresponding to the changed state of the drill string. Accordingly, in S5, when the change in the formation hardness characterization result exists only in a local drilling depth segment and subsequently returns to the hardness level before the change, the corresponding change is determined as a local drilling disturbance; when the formation hardness characterization result maintains the same direction of change in multiple consecutive drilling depth segments and meets the preset continuous condition, the corresponding drilling depth position is determined as the formation hardness change position.

[0013] This application also provides an adaptive mapping device for drilling physical electrical signals and formation hardness based on time-series deep learning, including: The data acquisition module is used to acquire drilling time sequence data during the drilling process of the target borehole, and establish the correspondence between the drilling time sequence data and the borehole depth position based on the acquisition time and drilling depth to obtain the original drilling time sequence dataset. The data processing module is used to identify effective drilling sections based on the drilling depth change status, rotation status and feed status in the original drilling time series dataset, perform baseline correction on the drilling load signal in the effective drilling section based on the corresponding equipment operating baseline, and perform standardization and time series segmentation according to the drilling conditions to obtain effective drilling time series samples. The time-series sample feature extraction module is used to extract time-series state information from the effective drilling time-series samples, and input it into the time-series deep learning network to extract the local drilling response and the continuous change relationship between adjacent samples, so as to obtain the formation resistance time-series characterization sequence arranged along the hole depth. The formation hardness acquisition module is used to acquire formation hardness reference data corresponding to depth segments with formation verification results, form a formation hardness reference sequence, align the formation resistance time series characterization sequence with the formation hardness reference sequence at depth, and establish a basic mapping relationship in conjunction with drilling condition information; use the basic mapping relationship to obtain the initial formation hardness characterization result of the target borehole, and correct the basic mapping relationship according to the deviation between the initial formation hardness characterization result corresponding to the verified reference depth segment in the target borehole and the actual formation hardness reference result, to obtain an adaptive mapping relationship and the corresponding formation hardness characterization sequence. The results output module is used to perform continuity discrimination on the formation hardness characterization sequence, distinguish between local drilling disturbances and continuous formation hardness changes, and generate drilling-while-drilling formation hardness profiles and formation change prompts.

[0014] This application also provides an adaptive mapping device, including: Memory, used to store computer programs; A processor is used to implement the steps of the adaptive mapping method between drilling physical electrical signals and formation hardness as described above when executing the computer program.

[0015] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the adaptive mapping method between drilling physical electrical signals and formation hardness as described above.

[0016] It has the following beneficial effects: By establishing the correspondence between drilling time-series operational data and hole depth position, identifying effective drilling sections, and performing baseline correction and operating condition standardization on load signals, the interference of equipment status and operational changes on signal representation can be reduced. Furthermore, by using time-series deep learning to extract continuous formation resistance characteristics and combining them with validated formation data to adaptively correct the mapping relationship, the consistency of formation hardness identification under different drilling conditions can be improved. By distinguishing between local disturbances and continuous formation changes through continuity discrimination, a drilling hardness profile that can be used for formation division and exploration data processing can be formed. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 A flowchart illustrating an adaptive mapping method for drilling physical electrical signals and formation hardness based on time-series deep learning, provided as an embodiment of this application. Figure 2 A schematic diagram of a drilling physical electrical signal and formation hardness adaptive mapping device based on time-series deep learning provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of the adaptive mapping device provided in the embodiments of this application. Detailed Implementation

[0019] The purpose of this application is to provide a method, device, and computer-readable storage medium for adaptive mapping of drilling physical electrical signals and formation hardness based on time-series deep learning. By identifying effective drilling sections, baseline correction and working condition standardization of load signals are performed. Continuous formation resistance characteristics are extracted using time-series deep learning, and the mapping relationship of verified formation sections is adaptively corrected to form a formation hardness characterization result that continuously corresponds to the hole depth.

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0021] The following embodiment illustrates an adaptive mapping method for drilling physical electrical signals and formation hardness based on temporal deep learning provided in this application.

[0022] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an adaptive mapping method for drilling physical electrical signals and formation hardness based on temporal deep learning, provided in an embodiment of this application.

[0023] This embodiment is applied to borehole construction in geotechnical engineering exploration. The exploration site is at a high altitude with a large temperature difference between day and night. During continuous operation of the drilling rig, issues such as motor temperature rise, power supply fluctuations, and drill bit wear arise. The borehole construction utilizes an electrically driven rotary engineering drilling rig, equipped with a rotary drive motor, a feed drive mechanism, a spindle speed detection device, a drilling depth detection device, and an operational data acquisition unit. The operational data acquisition unit communicates with the drilling rig control system, enabling continuous reading of the rotary drive motor's operating current, operating voltage, and active power; reading the actual spindle speed, feed drive load, and drilling depth; and determining the actual drilling footage based on changes in drilling depth at adjacent sampling times.

[0024] To ensure accurate correspondence between drilling physical electrical signals and borehole depth, the drilling rig control system, operational data acquisition unit, and drilling depth detection device employ a unified time reference. Each sampled data point records the acquisition time, borehole number, drilling shift, current drill string number, and corresponding drilling depth. When a drill string is changed, the system synchronously records the change time and location, used to distinguish the data stages corresponding to different drill string states during subsequent mapping processes.

[0025] In this embodiment, the method may include: S1. Obtain the drilling time sequence data during the drilling process of the target borehole, and establish the correspondence between the drilling time sequence data and the borehole depth position based on the acquisition time and drilling depth to obtain the original drilling time sequence dataset.

[0026] After drilling begins, the data acquisition unit continuously samples and acquires the drilling timing data during the target borehole drilling process. In this embodiment, the drilling timing data includes the operating current, operating voltage, and active power of the rotary drive motor, the actual spindle speed, the feed drive load, and the drilling depth.

[0027] The operating current and active power of the rotary drive motor are used to reflect load changes during drill bit rotation cutting and formation breaking, while the operating voltage is used to determine whether changes in power supply status affect the current and power response. The actual spindle speed is used to characterize the drill bit rotation condition, the feed drive load is used to reflect the axial resistance encountered by the drill bit as it penetrates to the bottom of the hole, and the drilling depth is used to determine the hole depth position corresponding to each drilling physical electrical signal.

[0028] At each sampling moment, the system reads the current drilling depth and associates the operating current, operating voltage, active power, actual spindle speed, and feed drive load obtained at the same sampling moment with the current drilling depth. The system further calculates the drilling depth difference between adjacent sampling moments, thereby obtaining the actual drilling footage within the corresponding time period, and determines the actual drilling speed based on the actual drilling footage and the sampling time interval.

[0029] When the drilling depth remains constant, the system retains the corresponding sampled data, but temporarily marks this part of the data as no progress, so that it can be combined with the spindle rotation status and feed drive status to determine whether the drilling rig is in a drilling pause, suspended rotation, rod changing or other ineffective drilling status.

[0030] After the above processing, the drilling physical electrical signals at each sampling time have corresponding time and drilling depth indices, forming an original drilling time-series dataset with sampling time and drilling depth as dual indices. This original drilling time-series dataset is saved in drilling time order, while preserving the continuous change relationship of drilling depth, so that subsequent signal processing results can be accurately written back to the corresponding hole depth section.

[0031] To adapt to changes in equipment operating conditions at high altitudes, this embodiment also simultaneously records motor temperature, ambient temperature, and ambient air pressure. This environmental data is not directly used for fixed-ratio correction of ground hardness, but rather serves as the equipment's operating environment status to determine whether the equipment's operating baseline has changed due to temperature, air pressure, or continuous operating time.

[0032] Step S1 avoids depth mismatch caused by recording drilling physical electrical signals and drilling depth separately, and ensures that all kinds of electrical signals, rotation speed signals and feed signals can be mapped to the actual formation location, providing a data basis for subsequent differentiation of formation resistance changes and operation status changes.

[0033] S2. Identify the effective drilling section based on the drilling depth change status, rotation status and feed status in the original drilling time series dataset. Based on the corresponding equipment operating baseline, perform baseline correction on the drilling load signal in the effective drilling section, and perform standardization and time series segmentation according to the drilling conditions to obtain the effective drilling time series sample. In this step, the system reads the original drilling time series dataset formed in step S1 and identifies the effective drilling section based on the drilling depth change status, spindle rotation status, and feed drive status.

[0034] In this embodiment, when the drilling depth continuously increases during the continuous sampling period, the actual spindle speed remains higher than the value corresponding to the stop state, and the feed drive load is continuously present, the continuous sampling period is determined as the effective drilling section. This state indicates that the drill bit is continuously rotating and penetrating to the bottom of the hole. The rotation drive load and the feed drive load are mainly formed by the cutting, breaking, and penetration actions between the drill bit and the formation.

[0035] When the spindle is stopped, the system marks the corresponding data as a stopped state. When the spindle continues to rotate but the drilling depth does not increase, and the feed drive load is not continuously present, the system, based on the drilling rig operation record, marks the corresponding data as a drill bit suspended rotation state or a drilling paused state. When the drilling depth changes in the opposite direction, the system marks the corresponding data as a drill pipe lifting or retraction state. When the drilling depth stops increasing and is accompanied by continuous switching between rotation and feed states, the system marks the corresponding data as a drill pipe changing state. The data corresponding to the above-mentioned ineffective drilling states are retained in the original drilling time series dataset, but are not directly included in the formation hardness mapping process.

[0036] After identifying the valid drilling sections, the system determines the equipment operating baseline corresponding to each valid drilling section. Before the borehole officially starts drilling, the operator controls the drill bit to be in a stable rotational state before it touches the bottom of the hole. The operation data acquisition unit records the operating current, active power, and feed drive load of the rotation drive motor during this stage, and forms the initial equipment operating baseline after the signal enters a stable state.

[0037] During drilling operations, after each rod change or before the drill bit is lowered back to the bottom of the hole, if the drill bit is in a stable suspended rotation phase, the system re-extracts the stable load state of that phase and compares it with the current motor temperature, continuous operating time, and the previous equipment operating baseline. When there is a continuous difference between the new stable load state and the previous equipment operating baseline, the equipment operating baseline is updated using the stable load state closest to the current effective drilling section.

[0038] The equipment operating baseline includes the reference current of the rotary drive motor, the reference active power of the rotary drive motor, and the reference load of the feed system. For each valid drilling sampling moment, the system compares the actual operating current with the reference current, the actual active power with the reference active power, and the actual feed drive load with the reference load of the feed system to obtain the incremental current response, incremental power response, and incremental feed load response.

[0039] The aforementioned incremental load response mainly represents the increased load component after the drill bit contacts the formation, relative to the equipment's no-load operating state. By separating the equipment's operating load from the actual drilling load, the impact of motor temperature rise, mechanical transmission resistance, and changes in the high-altitude operating environment on formation resistance identification can be reduced.

[0040] After baseline correction, the system standardizes the incremental load response based on the actual spindle speed and actual drilling speed. Under the same formation conditions, when the operator increases the spindle speed or changes the feed rate, the current, power, and feed load may change accordingly. The system uses the actual spindle speed and actual drilling speed as drilling condition parameters, converting the incremental load response into a standardized drilling load signal with a unified comparison basis according to the current rotation and penetration conditions.

[0041] During the standardization process, changes in spindle speed or drilling speed are not directly interpreted as changes in formation hardness. Instead, the deviation of the drilling load response from the current operating conditions is preserved. When the actual spindle speed is adjusted, but the standardized incremental load response and actual drilling footage do not change continuously, the system primarily attributes this change to the drilling operation adjustment. When the incremental load response continues to increase after standardization, while the actual drilling speed decreases, the system considers this combination as a candidate indication of increased formation resistance.

[0042] Subsequently, the system performs time-series segmentation on the standardized drilling load signal. First, continuous time windows are formed according to a preset time range. Each continuous time window contains standardized incremental current, standardized incremental power, standardized feed load, actual spindle speed, and actual drilling footage arranged in the sampling order.

[0043] The system determines the actual drilling depth range covered by each continuous time window based on the drilling depth corresponding to the start and end times of each continuous time window. When the drilling speed is too fast, causing the drilling depth range covered by a continuous time window to exceed the preset depth range condition, the system shortens the duration of that continuous time window. When the drilling speed is too slow, causing the drilling depth range covered by a continuous time window to be insufficient to form an effective layer segment, the system extends that continuous time window or merges adjacent continuous time windows.

[0044] After adjustment, each continuous time window corresponds to a continuous drilling depth segment with engineering comparative significance. The system arranges the drilling load signals within the adjusted continuous time window according to the sampling order to form a valid drilling time sequence sample. Adjacent valid drilling time sequence samples maintain a sequential connection according to the drilling order, and record their respective starting depth, ending depth, equipment operating baseline, and drilling condition information.

[0045] By combining constraints on time range and drilling depth range, we can avoid excessively large differences in formation thickness at different drilling speeds within the same time window, thus ensuring that each effective drilling time series sample is comparable in terms of both temporal and spatial continuity.

[0046] S3 extracts temporal state information from effective drilling time series samples and inputs it into a temporal deep learning network to extract the local drilling response and the continuous change relationship between adjacent samples, thus obtaining a time series characterization sequence of formation resistance arranged along the hole depth. The system takes the valid drilling time sequence sample formed in step S2 as input, and extracts the drilling load level, drilling load fluctuation state and penetration state from each valid drilling time sequence sample to form time sequence state information.

[0047] The drilling load level is determined based on the continuous state of standardized incremental current, standardized incremental power, and standardized feed load within the effective drilling time series sample. It is used to characterize the combined rotational resistance and penetration resistance experienced by the drill bit in the corresponding drilling depth segment.

[0048] The drilling load fluctuation state is determined based on the amplitude and duration of the load signal change within the time window, as well as the relationship between adjacent sampling points. It is used to distinguish different response forms such as stable load, periodic fluctuation, short-term impact, and continuous increase or decrease.

[0049] The penetration state is determined based on the actual drilling footage, actual drilling speed, and their relationship with time. When the drilling load increases and the actual drilling speed continuously decreases, it indicates that the drill bit penetration resistance tends to increase. When the drilling load decreases and the actual drilling speed continuously increases, it indicates that the drill bit penetration resistance tends to decrease. When the drilling load increases briefly but the drilling speed subsequently recovers, this state may be caused by localized particle or cuttings accumulation or instantaneous impact.

[0050] The system inputs the aforementioned temporal state information into the temporal deep learning network according to the original sampling order. The temporal deep learning network includes a local temporal change extraction part and a continuous state association part.

[0051] The local time-series change extraction section performs time-series processing on the changes in drilling load and drilling footage within the same valid drilling time-series sample. During the processing, the original sequence of each signal is maintained, enabling the network to identify combinations of local responses such as sudden increases in incremental current, continuous increases in incremental power, fluctuations in feed load, slight decreases in spindle speed, and reductions in actual drilling footage.

[0052] For spike signals that exist only in a small number of sampling times, the local time-series variation extraction part distinguishes the signal from continuous stable load changes based on the duration of the spike and the recovery state of the signals before and after it. For a state where the load increases continuously and is accompanied by a decrease in penetration rate within the same effective drilling time-series sample, the local time-series variation extraction part forms a local drilling response that reflects the increase in formation resistance.

[0053] The continuous state correlation component reads the local drilling responses corresponding to multiple adjacent valid drilling time series samples according to the drilling sequence, and performs correlation processing on the drilling load and penetration state between adjacent drilling depth sections. When the incremental load in adjacent samples continuously changes in the same direction, and the actual drilling speed shows a corresponding continuous changing trend, the continuous state correlation component retains this continuous changing relationship. When an abnormal response occurs in a valid drilling time series sample, but the samples before and after it recover to their original state, the continuous state correlation component reduces the impact of this abnormal response on the judgment of persistent formation resistance.

[0054] The local drilling response from the local time-series change extraction section and the continuous change relationship from the continuous state correlation section are used together to generate a time-series representation of formation resistance. Each time-series representation of formation resistance corresponds to a specific drilling depth segment, which is used to characterize the comprehensive drilling resistance of that depth segment under the current equipment operating baseline, spindle speed, actual drilling speed, and drill string status.

[0055] The system arranges the formation resistance time series representations according to the hole depth corresponding to each valid drilling time series sample, forming a formation resistance time series representation sequence continuously distributed along the hole depth. This sequence does not directly equate a single current value or power value with formation hardness, but comprehensively represents the load level, load change mode, and penetration efficiency formed during the interaction between the drill bit and the formation.

[0056] Step S3 allows for the differentiation between short-term impacts and continuous formation resistance changes by utilizing the temporal continuity of drilling physical electrical signals, thereby reducing the problem that single-point current thresholds or individual statistical values ​​are easily affected by operational disturbances.

[0057] S4. Obtain formation hardness reference data corresponding to the depth segment with formation verification results, form a formation hardness reference sequence, align the formation resistance time series characterization sequence with the formation hardness reference sequence at depth, and establish a basic mapping relationship in combination with drilling condition information; use the basic mapping relationship to obtain the initial formation hardness characterization result of the target borehole, and correct the basic mapping relationship according to the deviation between the initial formation hardness characterization result corresponding to the verified reference depth segment in the target borehole and the actual formation hardness reference result, to obtain an adaptive mapping relationship and the corresponding formation hardness characterization sequence. The system acquires formation hardness reference data corresponding to depth sections with formation verification results. In this embodiment, the formation hardness reference data is derived from at least one of the following: core logging results, soil and rock condition descriptions, in-situ test results, and laboratory mechanical test results.

[0058] Core logging results provide information on soil and rock names, weathering degree, integrity, and drilling depth range. Soil and rock condition descriptions provide information on soil compaction, plasticity, or rock hardness. In-situ test results provide information on the response of soil and rock at corresponding depths to penetration, probing, or wave propagation. Laboratory mechanical test results provide information on soil and rock sample strength, compressibility, or other test results reflecting their hardness.

[0059] The system converts various formation verification results into a formation hardness reference sequence that continuously corresponds to the drilling depth, based on a unified drilling depth benchmark. When a formation verification result corresponds to a depth segment with a certain thickness, the verification result is associated with the valid drilling time series samples within that depth segment. When the core sampling location or in-situ test location is not completely consistent with the boundary of the drilling time series samples, depth alignment is performed based on the sampling depth interval, test depth, and formation interface location to avoid incorrectly associating the verification result with adjacent formations.

[0060] During the historical borehole data preparation phase, the system performs depth alignment between the historical borehole formation resistance time series characterization sequence and the corresponding formation hardness reference sequence, and obtains drilling condition information for each depth segment. The drilling condition information includes at least one of the following: spindle speed status, actual drilling speed status, drill string status, equipment operating baseline, and equipment operating environment status.

[0061] The system uses drilling condition information as a mapping condition between the time series characterization of formation resistance and formation hardness to establish a basic mapping relationship. The basic mapping relationship does not determine hardness solely based on the numerical value of the time series characterization of formation resistance, but also considers the rotation conditions, penetration conditions, drill string status, and equipment operating status at the time the characterization is formed.

[0062] For example, similar incremental power responses may correspond to different drill bit cutting states at different spindle speeds, and similar incremental feed loads may correspond to different formation penetration resistances at different actual drilling speeds. By using drilling conditions as mapping conditions, the system can ensure that the formation resistance time series representation falls into the corresponding interpretation range according to the corresponding operating conditions, reducing hardness mapping deviations caused by changes in operating parameters.

[0063] After establishing the basic mapping relationship, the formation resistance time series characterization sequence and corresponding drilling condition information obtained in step S3 of the target borehole are input into the basic mapping relationship to obtain the initial formation hardness characterization results for each drilling depth section of the target borehole.

[0064] During the drilling process of the target borehole, as core logging, in-situ testing, or laboratory mechanical experiments are gradually completed, the system acquires one or more verified reference depth sections and designates these reference depth sections as calibration anchor points. Each calibration anchor point has corresponding initial formation hardness characterization results and actual formation hardness reference results.

[0065] The system compares the initial formation hardness characterization results corresponding to the correction anchor points with the actual formation hardness reference results to determine the direction of deviation, the degree of deviation, and whether the deviation is concentrated under specific drilling conditions.

[0066] When the initial formation hardness characterization results of multiple calibration anchor points are generally higher than the actual formation hardness reference results, and the current equipment operating baseline is higher than the operating baseline of similar drilling rigs in the past, the system corrects the equipment operating baseline for the current drilling stage to reduce the impact of increased equipment load on formation hardness results.

[0067] When the deviation between the initial formation hardness characterization result and the actual formation hardness reference result is basically consistent in direction under different drilling conditions, the system corrects the formation hardness output scale to match the output result with the formation hardness reference scale of the current project.

[0068] When deviations mainly occur in data segments corresponding to specific spindle speeds, actual drilling speeds, or drill bit states, the system adjusts the combined weights of drilling load levels, drilling load fluctuation states, and penetration states under that working condition. This ensures that time-series state information with a high degree of correlation to the cause of the deviation has a corresponding impact on hardness mapping, without modifying the overall mapping relationship under other working conditions.

[0069] After the above corrections are completed, an adaptive mapping relationship is formed that is applicable to the current equipment status, drilling conditions, and drill string status of the target borehole. The system uses the adaptive mapping relationship to reprocess the formation resistance time series characterization sequence of the target borehole to obtain a formation hardness characterization sequence that continuously corresponds to the drilling depth.

[0070] During drilling, when the drill bit is replaced, the wear condition of the drill string changes significantly, or the drill string assembly is adjusted, the system uses the location where the drill string condition changes as the starting point of the new mapping stage. Data before the change location is assigned to the previous drill string condition stage, and data after the change location is assigned to the new drill string condition stage.

[0071] The new mapping phase redefines the equipment operating baseline and uses correction anchor points corresponding to the changed drill string state to perform phased corrections on the basic mapping relationship for subsequent drilling depth sections. If the changed drill string state has not yet obtained an effective correction anchor point, the system first retains the initial results obtained based on the basic mapping relationship and marks the results of this phase as a state to be corrected, without directly using the correction parameters corresponding to the drill string state before the change.

[0072] By using the corrected anchor point to constrain the basic mapping relationship and dividing the mapping stages according to the state of the drill bit, we can avoid arbitrary changes in the mapping relationship without engineering evidence, and also avoid directly mixing the load responses before and after drill bit wear.

[0073] S5 performs continuity discrimination on the formation hardness characterization sequence, distinguishes between local drilling disturbances and continuous formation hardness changes, and generates a formation hardness profile during drilling and formation change indication results.

[0074] The system reads the formation hardness characterization sequence obtained in step S4 according to the drilling depth sequence and makes a continuous judgment on the hardness changes between adjacent drilling depth sections.

[0075] First, determine the direction and duration of changes in formation hardness characterization results between adjacent depth sections. When the hardness characterization result of a certain local drilling depth section suddenly increases or decreases, but subsequent depth sections recover to the hardness level before the change, the system identifies this change as a local drilling disturbance.

[0076] Local drilling disturbances may be caused by momentary collisions of the drill bit with local gravel, short-term accumulation of drill cuttings, localized spalling of the borehole wall, short-term changes in feed operation, or momentary fluctuations in the acquired signals. The system retains the anomaly record corresponding to this location, but does not directly identify it as a formation soft-hard interface.

[0077] When the formation hardness characterization results maintain a consistent change in the same direction across multiple consecutive drilling depths, and the continuous change relationship between drilling load level, penetration state, and adjacent samples all support this change, the system determines that the change meets the preset continuity condition and identifies the corresponding drilling depth location as the formation hardness change location.

[0078] When the hardness characterization result continuously increases and remains stable, the system outputs a change indication indicating the entry into a harder formation. When the hardness characterization result continuously decreases and remains stable, the system outputs a change indication indicating the entry into a softer formation. If the location of the hardness change basically corresponds to the stratigraphic interface in the core recording or the location of the change in in-situ testing, the reliability of the results for the corresponding section is improved.

[0079] After completing the continuity assessment, the system generates a formation hardness profile while drilling. The formation hardness profile while drilling uses the drilling depth as the longitudinal position reference, records the formation hardness characterization results corresponding to each drilling depth segment, and associates the data validity status, equipment operating baseline, drilling conditions, drill string status, and correction status of that segment.

[0080] The system also generates formation change alerts, including the location, direction, and duration of changes in formation hardness, as well as the corresponding data reliability status. For locations identified as localized drilling disturbances, the system generates separate local anomaly markers to allow drilling personnel to verify the changes in core samples, cuttings return data, and drilling operation records.

[0081] The results of the formation hardness profile and formation change indications during drilling can be output to the drilling site display terminal, enabling on-site technicians to view the changes in formation hardness during the drilling process; they can also be written into the borehole digital record file and associated with the borehole number, borehole coordinates, drilling reports, core logging results, and in-situ test results.

[0082] After drilling is completed, the formation hardness profile obtained during drilling can be used to assist in delineating formation interfaces, verifying borehole columnar sections, identifying localized weak or hard interlayers, and providing structured data for subsequent geotechnical engineering investigation data processing and report preparation. This hardness characterization result is used as supplementary data for the drilling process and does not replace legally required core logging, in-situ testing, and laboratory experiments.

[0083] This embodiment establishes a complete data processing chain consisting of drilling physical electrical signal acquisition, time-to-depth correspondence, effective drilling status identification, equipment operating baseline correction, drilling condition standardization, time-series sample construction, formation resistance time-series characterization, conditional base mapping, correction anchor point constraints, adaptive stage correction, and continuous hardness result output. Each step uses the data results generated in the previous stage as the processing basis, enabling the drilling physical electrical signals to form a mapping result that continuously corresponds to formation hardness, taking into account equipment status, drilling conditions, and changes in drill bit.

[0084] In summary, this embodiment establishes a correspondence between drilling time-series operational data and hole depth location, identifies effective drilling sections, and performs baseline correction and operating condition standardization on load signals, thereby reducing the interference of equipment status and operational changes on signal representation. Furthermore, by utilizing time-series deep learning to extract continuous formation resistance characteristics and combining them with validated formation data to adaptively correct the mapping relationship, the consistency of formation hardness identification under different drilling conditions can be improved. By distinguishing between local disturbances and continuous formation changes through continuity discrimination, a drilling hardness profile that can be used for formation division and exploration data processing can be formed.

[0085] The following describes an adaptive mapping device for drilling physical electrical signals and formation hardness based on temporal deep learning, provided in an embodiment of this application. The adaptive mapping device for drilling physical electrical signals and formation hardness based on temporal deep learning and the adaptive mapping method for drilling physical electrical signals and formation hardness based on temporal deep learning described below can be referred to in correspondence with each other.

[0086] Please refer to Figure 2 , Figure 2 This is a schematic diagram of a drilling physical electrical signal and formation hardness adaptive mapping device based on time-series deep learning, provided in an embodiment of this application.

[0087] In this embodiment, the device may include: The data acquisition module 100 is used to acquire drilling time sequence data during the drilling process of the target borehole, and establish the correspondence between the drilling time sequence data and the borehole depth position based on the acquisition time and drilling depth to obtain the original drilling time sequence dataset. The data processing module 200 is used to identify effective drilling sections based on the drilling depth change status, rotation status and feed status in the original drilling time series dataset. Based on the corresponding equipment operating baseline, the drilling load signal in the effective drilling section is baseline corrected, and the drilling conditions are standardized and time-series segmented to obtain effective drilling time series samples. The time-series sample feature extraction module 300 is used to extract time-series state information from effective drilling time-series samples and input it into a time-series deep learning network to extract the local drilling response and the continuous change relationship between adjacent samples, thereby obtaining a time-series characterization sequence of formation resistance arranged along the hole depth. The formation hardness acquisition module 400 is used to acquire formation hardness reference data corresponding to depth segments with formation verification results, form a formation hardness reference sequence, align the formation resistance time series characterization sequence with the formation hardness reference sequence at depth, and establish a basic mapping relationship in combination with drilling condition information; use the basic mapping relationship to obtain the initial formation hardness characterization result of the target borehole, and correct the basic mapping relationship according to the deviation between the initial formation hardness characterization result corresponding to the verified reference depth segment in the target borehole and the actual formation hardness reference result, to obtain an adaptive mapping relationship and the corresponding formation hardness characterization sequence. The output module 500 is used to determine the continuity of the formation hardness characterization sequence, distinguish between local drilling disturbances and continuous formation hardness changes, and generate a formation hardness profile during drilling and formation change prompts.

[0088] This application also provides an adaptive mapping device; please refer to [reference needed]. Figure 3 , Figure 3This is a schematic diagram of the structure of the adaptive mapping device provided in the embodiments of this application. The adaptive mapping device may include: Memory, used to store computer programs; The processor, when executing a computer program, can implement the steps of any of the above-described methods for adaptive mapping of drilling physical electrical signals and formation hardness based on time-series deep learning.

[0089] like Figure 3 The diagram shows the structural composition of an adaptive mapping device, which may include a processor 10, a memory 11, a communication interface 12, and a communication bus 13. The processor 10, memory 11, and communication interface 12 communicate with each other through the communication bus 13.

[0090] In this embodiment, the processor 10 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic devices.

[0091] The processor 10 can call the program stored in the memory 11. Specifically, the processor 10 can execute the operations in the embodiment of the abnormal IP identification method.

[0092] The memory 11 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment, the memory 11 stores at least a program for implementing the following functions: S1. Obtain the drilling time sequence data during the drilling process of the target borehole, and establish the correspondence between the drilling time sequence data and the borehole depth position based on the acquisition time and drilling depth to obtain the original drilling time sequence dataset. S2. Identify the effective drilling section based on the drilling depth change status, rotation status and feed status in the original drilling time series dataset. Based on the corresponding equipment operating baseline, perform baseline correction on the drilling load signal in the effective drilling section, and perform standardization and time series segmentation according to the drilling conditions to obtain the effective drilling time series sample. S3 extracts temporal state information from effective drilling time series samples and inputs it into a temporal deep learning network to extract the local drilling response and the continuous change relationship between adjacent samples, thus obtaining a time series characterization sequence of formation resistance arranged along the hole depth. S4. Obtain formation hardness reference data corresponding to the depth segment with formation verification results, form a formation hardness reference sequence, align the formation resistance time series characterization sequence with the formation hardness reference sequence at depth, and establish a basic mapping relationship in combination with drilling condition information; use the basic mapping relationship to obtain the initial formation hardness characterization result of the target borehole, and correct the basic mapping relationship according to the deviation between the initial formation hardness characterization result corresponding to the verified reference depth segment in the target borehole and the actual formation hardness reference result, to obtain an adaptive mapping relationship and the corresponding formation hardness characterization sequence. S5 performs continuity discrimination on the formation hardness characterization sequence, distinguishes between local drilling disturbances and continuous formation hardness changes, and generates a formation hardness profile during drilling and formation change indication results.

[0093] In one possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0094] In addition, memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0095] Communication interface 12 can be an interface for the communication module, used to connect with other devices or systems.

[0096] Of course, it should be noted that, Figure 3 The structure shown does not constitute a limitation on the adaptive mapping device in the embodiments of this application. In practical applications, the adaptive mapping device may include more than Figure 3 More or fewer components as shown, or combinations of certain components.

[0097] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps of any of the above-described methods for adaptive mapping of drilling physical electrical signals and formation hardness based on time-series deep learning.

[0098] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] For a description of the computer-readable storage medium provided in this application, please refer to the above method embodiments; further details will not be repeated here.

[0100] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0101] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0102] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0103] The foregoing has provided a detailed description of the adaptive mapping method, device, and computer-readable storage medium for drilling physical electrical signals and formation hardness based on temporal deep learning, as well as the specific examples used to illustrate the principles and implementation methods of this application. The descriptions of these embodiments are merely illustrative of the method and its core concepts. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the scope of protection of the claims.

Claims

1. A method for adaptive mapping of drilling physical electrical signals and formation hardness based on temporal deep learning, characterized in that, include: S1, acquire drilling time sequence data during the drilling process of the target borehole, and establish the correspondence between the drilling time sequence data and the borehole depth position based on the acquisition time and drilling depth to obtain the original drilling time sequence dataset; S2, Identify the effective drilling section based on the drilling depth change status, rotation status and feed status in the original drilling time series dataset, perform baseline correction on the drilling load signal in the effective drilling section based on the corresponding equipment operating baseline, and perform standardization processing and time series segmentation according to the drilling conditions to obtain the effective drilling time series sample. S3, extract time-series state information from the effective drilling time-series samples, input it into a time-series deep learning network, extract the local drilling response and the continuous change relationship between adjacent samples, and obtain the formation resistance time-series characterization sequence arranged along the hole depth; S4. Obtain formation hardness reference data corresponding to the depth section with formation verification results, form a formation hardness reference sequence, align the formation resistance time series characterization sequence with the formation hardness reference sequence at depth, and establish a basic mapping relationship in combination with drilling condition information. The initial formation hardness characterization result of the target borehole is obtained by using the basic mapping relationship. Based on the deviation between the initial formation hardness characterization result corresponding to the verified reference depth segment in the target borehole and the actual formation hardness reference result, the basic mapping relationship is corrected to obtain the adaptive mapping relationship and the corresponding formation hardness characterization sequence. S5, perform continuity discrimination on the formation hardness characterization sequence, distinguish between local drilling disturbances and continuous formation hardness changes, and generate a formation hardness profile during drilling and formation change indication results.

2. The adaptive mapping method for drilling physical electrical signals and formation hardness according to claim 1, characterized in that, In S1, the drilling timing operation data includes at least one of the following: the operating current, operating voltage and active power of the rotary drive motor, the actual spindle speed, the feed drive load and the drilling depth. The actual drilling footage is determined based on the changes in drilling depth corresponding to adjacent sampling times. The drilling time series data corresponding to each sampling time is mapped to the corresponding hole depth position to form the original drilling time series dataset indexed by sampling time and drilling depth.

3. The adaptive mapping method for drilling physical electrical signals and formation hardness according to claim 1, characterized in that, S2 includes: The effective drilling section is determined based on the combination of the states of continuously increasing drilling depth, continuous spindle rotation, and continuous feed drive load. Obtain the drilling load in the stable no-load operating state or the drill bit suspension and rotation state corresponding to the current effective drilling section, and determine the operating baseline of the equipment; The actual drilling load within the effective drilling section is compared with the equipment operating baseline to obtain the incremental load response generated by the interaction between the drill bit and the formation. The incremental load response is then standardized based on the actual spindle speed and the actual drilling speed.

4. The adaptive mapping method for drilling physical electrical signals and formation hardness according to claim 3, characterized in that, In step S2, the time-series segmentation of the standardized drilling load signal includes: A continuous time window is formed according to a preset time range, and the drilling depth range corresponding to each continuous time window is determined. When the drilling depth range does not meet the preset depth range condition, the corresponding continuous time window is adjusted according to the actual drilling depth change. The drilling load signals in each adjusted continuous time window are used to form the effective drilling time sequence sample according to the sampling order.

5. The adaptive mapping method for drilling physical electrical signals and formation hardness according to claim 1, characterized in that, In S3, the temporal state information includes drilling load level, drilling load fluctuation state, and penetration state; the temporal deep learning network includes a local temporal change extraction part and a continuous state association part. The local time-series change extraction section is used to perform time-series processing on the changes in drilling load and drilling footage within the same valid drilling time-series sample to obtain the local drilling response. The continuous state association section is used to perform association processing on multiple local drilling responses arranged in the drilling sequence, determine the continuous change relationship of drilling load and penetration state between adjacent drilling depth sections, and generate the formation resistance time series characterization based on the local drilling responses and the continuous change relationship.

6. The adaptive mapping method for drilling physical electrical signals and formation hardness according to claim 1, characterized in that, In S4, the formation hardness reference data comes from at least one of the following: core logging results corresponding to the drilling depth, description of soil and rock conditions, in-situ test results, and laboratory mechanical test results. The drilling condition information includes at least one of the following: spindle speed status, actual drilling speed status, drill string status, equipment operating baseline, and equipment operating environment status. When establishing the basic mapping relationship, the drilling condition information is used as the mapping condition between the formation resistance time series characterization and the formation hardness, so that the formation resistance time series characterization obtains the formation hardness characterization result according to the corresponding drilling condition.

7. The adaptive mapping method for drilling physical electrical signals and formation hardness according to claim 6, characterized in that, In S4, the reference depth section in the target borehole verified by core logging, in-situ testing or laboratory mechanical testing is determined as the correction anchor point. Based on the deviation between the initial formation hardness characterization result and the actual formation hardness reference result corresponding to the correction anchor point, at least one of the combined weights of the equipment operating baseline, formation hardness output scale and time-series status information is corrected. When the state of the drill string changes, the location where the state of the drill string changes is taken as the starting point of the new mapping stage, and the basic mapping relationship of the subsequent drilling depth section is corrected in stages using the correction anchor point corresponding to the changed state of the drill string. Accordingly, in S5, when the change in the formation hardness characterization result exists only in a local drilling depth segment and subsequently returns to the hardness level before the change, the corresponding change is determined as a local drilling disturbance; when the formation hardness characterization result maintains the same direction of change in multiple consecutive drilling depth segments and meets the preset continuous condition, the corresponding drilling depth position is determined as the formation hardness change position.

8. A device for adaptive mapping of drilling physical electrical signals and formation hardness based on temporal deep learning, characterized in that, include: The data acquisition module is used to acquire drilling time sequence data during the drilling process of the target borehole, and establish the correspondence between the drilling time sequence data and the borehole depth position based on the acquisition time and drilling depth to obtain the original drilling time sequence dataset. The data processing module is used to identify effective drilling sections based on the drilling depth change status, rotation status and feed status in the original drilling time series dataset, perform baseline correction on the drilling load signal in the effective drilling section based on the corresponding equipment operating baseline, and perform standardization and time series segmentation according to the drilling conditions to obtain effective drilling time series samples. The time-series sample feature extraction module is used to extract time-series state information from the effective drilling time-series samples, and input it into the time-series deep learning network to extract the local drilling response and the continuous change relationship between adjacent samples, so as to obtain the formation resistance time-series characterization sequence arranged along the hole depth. The formation hardness acquisition module is used to acquire formation hardness reference data corresponding to the depth section with formation verification results, form a formation hardness reference sequence, align the formation resistance time series characterization sequence with the formation hardness reference sequence at depth, and establish a basic mapping relationship in combination with drilling condition information. The initial formation hardness characterization result of the target borehole is obtained by using the basic mapping relationship. Based on the deviation between the initial formation hardness characterization result corresponding to the verified reference depth segment in the target borehole and the actual formation hardness reference result, the basic mapping relationship is corrected to obtain the adaptive mapping relationship and the corresponding formation hardness characterization sequence. The results output module is used to perform continuity discrimination on the formation hardness characterization sequence, distinguish between local drilling disturbances and continuous formation hardness changes, and generate drilling-while-drilling formation hardness profiles and formation change prompts.

9. An adaptive mapping device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the adaptive mapping method for drilling physical electrical signals and formation hardness as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the adaptive mapping method for drilling physical electrical signals and formation hardness as described in any one of claims 1 to 7.