An intelligent drilling rig operation system and a method for deviation correction control

Abstract

The present application relates to the field of mechanical automation, and in particular to a drilling rig intelligent operation system and a deviation correction control method. The system significantly shortens the time for identifying and disposing stuck drill by means of multi-dimensional signal fusion and dynamic risk assessment, and avoids the efficiency loss caused by traditional shutdown protection. The imaging and obstacle positioning technology is used to replace manual tripping inspection, thereby reducing the idle running time of the equipment and mechanical loss. The multi-physical field signal fusion technology breaks through the limitation of single sensor perception, and is beneficial to accurately identifying the spatial distribution of underground obstacles and the mutation characteristics of geological interface. The acoustic spectrum and thermal field distribution analysis can enhance the analysis capability of the drill bit-formation interaction dynamics, and provide multi-dimensional input for intelligent decision-making. In combination with the virtual-real interaction mechanism, the dynamic optimization of the control strategy is realized, so as to adapt to the demand changes of different formation conditions and construction stages.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mechanical automation, and in particular to a drilling rig intelligent operation system and a deviation correction control method. BACKGROUND

[0002] As the core equipment of foundation engineering construction, the spiral drilling equipment is widely used in the fields of building pile foundation construction and geological exploration. The traditional drilling rig operation highly depends on the experience of the operator for judgment. When encountering complex strata (such as hard rock strata and high cohesive soil layers), there are some technical bottlenecks. The existing equipment mostly adopts a single torque threshold alarm mechanism, which can only trigger the stop protection after the occurrence of the stuck drill pipe, lacks the early prediction ability for the gradual stuck drill pipe, causes the response lag of the stuck drill pipe, and requires repeated drilling inspection for manual processing, resulting in the decrease of the construction efficiency and the aggravation of the drill pipe loss. The conventional laser guiding system is limited by the straightness measurement accuracy, is easily disturbed by the bending of the drill pipe and the collapse of the hole wall during the deep hole operation, and is difficult to realize the millimeter-level trajectory correction. The deviation correction operation mostly depends on the trial-and-error method to adjust the drilling parameters, which easily causes the secondary deviation.

[0003] The existing monitoring system usually independently collects single-dimensional signals such as vibration and pressure, lacks the spatio-temporal correlation analysis of multi-physical field data, and is difficult to accurately identify the complex working condition characteristics such as the sudden change of the soil layer interface and the underground obstacles, and the working condition perception is one-sided. The existing intelligent drilling rig control system mostly adopts a fixed control strategy, and does not establish a dynamic interaction mechanism of the physical equipment and the virtual model, resulting in the lack of stratum adaptability of the deviation correction strategy and the inability to realize the continuous optimization of the construction process. SUMMARY

[0004] The present application aims to solve the problem that the single-dimensional signal used in the prior art is difficult to identify the complex working condition characteristics, resulting in the poor effect of the stuck drill pipe fault disposal and the deviation correction disposal strategy, and provides a drilling rig intelligent operation system and a deviation correction control method.

[0005] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows:

[0006] In a first aspect, the present application provides a drilling rig intelligent operation system, comprising:

[0007] The acquisition module is configured to acquire mechanical vibration signals, torque signals, spatial displacement signals, thermal field signals, acoustic signals and image signals in the drilling process.

[0008] The analysis module processes the signals obtained by the acquisition module to obtain the time sequence evolution law of torque-displacement, displacement stagnation characteristics, vibration spectrum, thermal field distribution map and acoustic time-frequency map, and fuses and processes the time sequence evolution law of torque-displacement, displacement stagnation characteristics, vibration spectrum, thermal field distribution map and acoustic time-frequency map through a dynamic filtering algorithm and a machine learning model to generate a drilling condition feature vector; a stuck drill risk grading mechanism is established in combination with a historical condition mode library to generate a stuck drill risk grade; a stratum type and an interface position are generated based on a mutation law of the vibration spectrum and an attenuation law of the thermal field distribution map and the acoustic time-frequency map; a three-dimensional model of the inside of the drill hole is constructed according to the image signals, and the spatial coordinates of a hard obstacle in the drilling path are located based on the energy reflection characteristics of the acoustic signals and the local temperature anomalies of the thermal field signals; a time sequence prediction model about the drilling trajectory is constructed based on a nonlinear relationship between the torque growth rate and the displacement stagnation length; and drilling trajectory deviation characteristics are identified;

[0009] The virtual simulation module establishes a drill pipe-geological environment coupled dynamics model, optimizes a treatment strategy through simulation deduction and feeds back the treatment strategy to the decision module; the equipment response under extreme conditions is preplayed to generate a safety protection strategy and feed back the safety protection strategy to the decision module;

[0010] The decision module determines whether to correct deviation according to the stuck drill risk grade; generates a treatment strategy and forms an adjustment instruction.

[0011] Through multi-dimensional signal fusion and dynamic risk assessment, the stuck drill identification and treatment response time is significantly shortened, and the efficiency loss caused by traditional shutdown protection is avoided; imaging and obstacle positioning technology is used to replace manual drilling inspection, and the equipment idle running time and mechanical wear are reduced. The multi-physical field signal fusion technology breaks through the limitation of single sensor perception, is beneficial to accurately identifying the spatial distribution of underground obstacles and the mutation characteristics of geological interfaces, and can enhance the analysis capability of the drill bit-stratum interaction dynamics to provide multi-dimensional input for intelligent decision-making. In combination with the virtual-real interactive mechanism, the dynamic optimization of the control strategy is realized to adapt to the demand changes of different stratum conditions and construction stages.

[0012] Further, the acquisition module comprises:

[0013] The vibration detection sensor acquires mechanical vibration signals including drill pipe axial vibration, radial vibration and circumferential vibration signals;

[0014] The laser displacement sensor and the inertial measurement unit are used to acquire the spatial displacement signals of the drill bit;

[0015] The thermal field detection unit is used to acquire the temperature field distribution data of the inside wall of the drill hole;

[0016] The voiceprint feature acquisition unit is used to acquire acoustic signals during the drilling process;

[0017] The imaging component is used to acquire image signals.

[0018] Further, the vibration frequency spectrum graph is obtained by wavelet packet decomposition on the axial vibration, radial vibration and circumferential vibration signals of the drill pipe, the energy ratio of the low frequency band of 0-200Hz and the high frequency band greater than 500Hz is extracted to calculate the frequency spectrum kurtosis, and the vibration frequency spectrum mutation rule is obtained;

[0019] The temperature field of the inner wall of the drill hole is regionally separated, the radial temperature gradient is calculated, and a thermal field distribution graph is obtained;

[0020] The acoustic time-frequency graph is extracted by the Mel frequency cepstrum coefficient, the formation resonance peak is calculated, the acoustic energy attenuation rate is calculated, and the attenuation rate change rule is obtained.

[0021] Further, a feature weight distribution model based on an attention mechanism is constructed to perform cross-dimension signal fusion on the vibration frequency spectrum energy, thermal field distribution and acoustic energy attenuation rate to generate a drill hole working condition feature vector.

[0022] Further, the dynamic weight range of the vibration frequency spectrum energy is 0.4-0.6, the dynamic weight range of the thermal field distribution is 0.3-0.5, and the dynamic weight range of the acoustic energy attenuation rate is 0.2-0.4.

[0023] Further, according to the vibration frequency spectrum mutation intensity, the thermal field abnormal area and the acoustic signal energy attenuation rate, a low-middle-high three-level sticking risk grading mechanism is established in combination with a historical working condition mode library.

[0024] Further, a convolutional neural network is used to perform joint feature learning on the vibration frequency spectrum graph, the thermal field distribution graph and the acoustic time-frequency graph to obtain the formation type and the interface position.

[0025] In a second aspect, the present application also provides a drilling operation deviation control method, which adopts the drilling rig intelligent operation system as described above, and comprises:

[0026] Real-time acquisition of mechanical vibration signals, torque signals, spatial displacement signals, thermal field signals and acoustic signals during the drilling operation process;

[0027] Temporal and spatial fusion processing is performed on the above signals to extract a working condition feature vector;

[0028] Sticking risk level is determined;

[0029] When the preset risk level is reached, an image signal is acquired to construct a three-dimensional model of the drill hole and determine the deviation of the drill hole trajectory;

[0030] An optimal scheme is obtained by simulating different treatment strategies in a virtual environment, and adjustment instructions are generated.

[0031] Further, the temporal and spatial fusion processing includes signal noise reduction and feature enhancement operations; the virtual environment simulation includes dynamic response prediction of geological conditions.

[0032] Further, the execution effect data of the adjustment instruction is fed back to the virtual simulation module to form a learning sample, and the decision weight parameter of the machine learning model is updated regularly.

[0033] To sum up, due to the adoption of the technical solutions described above, the present application has the following beneficial effects:

[0034] The traditional single torque threshold alarm is broken through, the dynamic identification and prevention and control processing of the progressive stuck risk are realized, the construction interruption and equipment damage caused by manual intervention are reduced, the accuracy of the dynamic deviation correction of the drilling trajectory is improved, and the straight trajectory tracking capability in the complex stratum is improved, the multi-physical field signals such as mechanical vibration, thermal field distribution and acoustic spectrum are integrated, which is beneficial to accurately identifying the soil interface mutation, underground obstacles and geological abnormal areas, the dynamic interaction mechanism of physical equipment and virtual model is constructed, the intelligent decision optimization of virtual-real linkage is formed, the adaptive optimization of the control strategy and the continuous improvement of the construction process are realized, and the closed-loop collaborative control system of“multi-source perception-intelligent analysis-prevention and control autonomous deviation correction-virtual simulation”is successfully constructed. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 It is a flowchart of a deviation correction control method for a drilling operation. DETAILED DESCRIPTION

[0036] To make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0037] In the description of the specific embodiments of the present application, the orientation or position relationship expression terms appearing in the description of the specific embodiments of the present application, such as“up”,“down”,“left”,“right”,“center”,“inner” and“outer”, are based on the orientation or position relationship expressed in the drawings, or are the orientation or position relationship used when the product / equipment / device of the present application is usually placed. These orientation or position relationship terms are only used to facilitate the description of the present application scheme or simplify the description in the specific embodiments, to facilitate the quick understanding of the scheme by the technicians, and are not intended to indicate or imply that the specific device / component / element must have a specific orientation, or be constructed and operated in a specific position relationship, so it cannot be understood as a limitation on the present application.

[0038] In addition, if the terms "horizontal", "vertical", "overhanging", "parallel" and the like appear, it does not mean that the corresponding device / component / element is absolutely horizontal or vertical or overhanging or parallel, but can be slightly inclined or deviated. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined. Alternatively, it can be simplified to understand that the corresponding device / component / element is arranged in the direction of "horizontal", "vertical", "overhanging", "parallel" and the like, and can have an error / deviation of ±10% relative to the corresponding direction, more preferably an error / deviation of ±8% or less, more preferably an error / deviation of ±6% or less, more preferably an error / deviation of ±5% or less, and more preferably an error / deviation of ±4% or less. As long as the corresponding device / component / element is within the error / deviation range, it can still achieve its role in the present application.

[0039] In addition, the terms "first", "second", "third" and the like in the terms are only used to distinguish the same or similar components for description, and should not be understood as emphasizing or implying the relative importance of the specific components.

[0040] In addition, in the description of the embodiments of the present application, "several", "a plurality of", "several" represent at least 2. It can be 2, 3, 4, 5, 6, 7, 8, 9, etc. Any case, it can even be more than 9.

[0041] In addition, in the description of the technical solutions of the present application, unless otherwise specified / limited / limited, the terms "arrangement", "installation", "connection", "connection", "provided with", "laid", "arrangement" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected, which can be welding, riveting, bolting, screwing and other commonly used connection means in the art. The connection can be mechanical connection, electrical connection or communication connection; it can be directly connected or indirectly connected through an intermediate medium; it can be the communication between two elements.

[0042] Embodiment 1

[0043] The drilling wisdom operation system provided by the present application comprises:

[0044] The acquisition module is used for acquiring mechanical vibration signals, torque signals, spatial displacement signals, thermal field signals, acoustic signals and image signals in the drilling process.

[0045] The analysis module processes the signals obtained by the acquisition module to obtain the time sequence evolution law of torque-displacement, displacement stagnation characteristics, vibration spectrum, thermal field distribution map and acoustic time-frequency map, and fuses and processes the dynamic filtering algorithm and the machine learning model to generate a drilling condition feature vector; a stuck drill risk grading mechanism is established in combination with a historical condition mode library to generate a stuck drill risk grade; a stratum type and interface position are generated based on the mutation law of the vibration spectrum and the attenuation law of the acoustic time-frequency map; a three-dimensional model of the inside of the drill hole is constructed according to the image signals, and the spatial coordinates of hard obstacles in the drilling path are located based on the energy reflection characteristics of the acoustic signals and the local temperature anomalies of the thermal field signals; a time sequence prediction model about the drilling trajectory is constructed based on the nonlinear relationship between the torque growth rate and the displacement stagnation time length; drilling trajectory deviation characteristics are identified;

[0046] The virtual simulation module establishes a drill pipe-geological environment coupling dynamics model, optimizes a treatment strategy through simulation and deduction, and feeds back to the decision module; the response of the equipment under extreme conditions is preplayed, a safety protection strategy is generated, and the safety protection strategy is fed back to the decision module;

[0047] The decision module determines whether to correct deviation according to the stuck drill risk grade; generates a treatment strategy and forms an adjustment instruction.

[0048] Specifically, the acquisition module includes:

[0049] The vibration detection sensor acquires mechanical vibration signals including drill pipe axial vibration, radial vibration and circumferential vibration signals;

[0050] The laser displacement sensor and the inertial measurement unit are used to acquire spatial displacement signals of the drill bit;

[0051] The thermal field detection unit is used to acquire temperature field distribution data of the inside wall of the drill hole;

[0052] The voiceprint feature acquisition unit is used to acquire acoustic signals during drilling;

[0053] The imaging component is used to acquire image signals.

[0054] Specifically, triaxial accelerometers are placed at key nodes of the drill pipe to collect axial, radial, and circumferential vibration signals in real time, capturing the dynamic interaction characteristics between the drill bit and the formation; a combination of laser displacement sensors and inertial measurement units is used to monitor the three-dimensional spatial displacement changes of the drill bit, combined with Kalman filtering algorithms to eliminate measurement errors caused by drill pipe deflection; an infrared thermal imager array is integrated behind the drill bit to acquire real-time data on the temperature field distribution of the borehole wall, and abnormal friction areas are identified by changes in thermal radiation intensity; an acoustic sensor group is deployed along the drill pipe to collect acoustic signals during the drilling process, and the acoustic spectrum characteristics of different formations are extracted by combining wavelet transform; the imaging component can use a retractable optical imaging assembly, which is easy to extend into the borehole and can also adapt to the low-light environment inside the borehole.

[0055] The vibration spectrum is obtained by wavelet packet decomposition of the axial, radial and circumferential vibration signals of the drill pipe. The energy ratio of the low frequency band of 0-200Hz and the high frequency band of greater than 500Hz is extracted to calculate the spectral kurtosis and obtain the vibration spectrum abrupt change law.

[0056] The temperature field inside the borehole wall is divided into regions, the radial temperature gradient is calculated, and a thermal field distribution map is obtained.

[0057] By extracting the formation resonance peak from the acoustic time-frequency diagram using the Mel spectrum cepstral coefficients, the acoustic energy attenuation rate is calculated, and the variation law of the attenuation rate is obtained.

[0058] The processing of the acquired signals also includes: for example, using an adaptive band-stop filter to suppress interference in specific frequency bands for mechanical noise in vibration signals; performing environmental noise compensation on acoustic signals to enhance the significance of formation characteristic frequencies; and eliminating signal delays caused by differences in sampling frequencies of different sensors through a timestamp synchronization mechanism to ensure the spatiotemporal consistency of vibration, displacement, thermal field and acoustic signals.

[0059] Multi-sensor timestamp synchronization achieves signal alignment through Lagrange interpolation: ,in: Indicates the k-th sensor at The sampled value at time 10:00. Indicates the target time. This represents the time of the i-th known data point. This represents the time of the j-th known data point; n represents the interpolation order, which can be selected according to the actual situation, such as 3-5.

[0060] Based on the feature weight allocation mechanism, cross-dimensional correlation features such as vibration frequency spectrum characteristics, thermal radiation distribution patterns, and acoustic energy attenuation rules are extracted to generate high information density working condition representation vectors. For example, the extraction of vibration frequency spectrum characteristics is achieved by wavelet packet decomposition of three-axis acceleration signals, extraction of energy ratio of 0-200Hz low frequency band and >500Hz high frequency band, and identification of impact vibration anomalies by calculating the spectral kurtosis index. The thermal radiation distribution pattern uses the data input by the infrared thermal imager to segment the high temperature area of the borehole wall and calculate the radial temperature gradient to judge the heat diffusion anomaly. The feature extraction of acoustic energy attenuation is achieved by extracting the formation resonance peak through Mel frequency cepstral coefficient and calculating the acoustic energy attenuation rate.

[0061] The generated feature fusion vector obtained by dynamic weight allocation is:

[0062]

[0063] Among them: Dynamic weight of vibration frequency spectrum characteristics; Vibration spectrum kurtosis; Dynamic weight of thermal field distribution; Maximum radial temperature gradient; Dynamic weight of acoustic attenuation rate; Acoustic attenuation rate;

[0064] The dynamic weight allocation table is shown in Table 1:

[0065] Table 1 Dynamic weight allocation table

[0066]

[0067] The long short-term memory network is used to analyze the time sequence evolution rule of torque and displacement data, and to identify the composite anomaly mode of torque sudden increase accompanied by displacement stagnation. According to the vibration spectrum mutation intensity, the area of thermal anomaly region and the energy attenuation rate of acoustic signal, combined with the historical working condition mode library, a low-medium-high three-level risk grading mechanism of stuck drill pipe is established, and the stuck drill pipe risk assessment function is represented as .

[0068] Among them: Vibration spectrum kurtosis; Maximum kurtosis; Thermal anomaly area; Maximum thermal anomaly area; Acoustic attenuation rate; Maximum attenuation rate;

[0069] The risk level can be set as: R<0.4, determined as low risk; 0.4<R<0.7, determined as medium risk; R>0.7, determined as high risk.

[0070] As shown in Table 2:

[0071] Table 2 Drilling risk grading evaluation and parameter boundary

[0072]

[0073] The nonlinear relationship between the torque growth rate and the displacement stagnation time length is monitored through a sliding window mechanism to provide early warning of progressive sticking risk. A time series prediction model is constructed to predict the resistance change curve in the future drilling depth interval in combination with the current drilling pressure, rotation speed, and formation type. Multiple potential risk evolution paths are generated through Monte Carlo simulation to evaluate the sticking probability and trajectory deviation risk under different control strategies.

[0074] The trajectory dynamic correction calculates the azimuth angle deviation and deflection distance of the drill bit actual trajectory and target axis according to the displacement sensor data and the hole wall deformation characteristics output by the three-dimensional modeling module. A drill pipe-formation coupled dynamics model is constructed to minimize the trajectory deviation as the objective function, and the multi-degree-of-freedom adjustment instructions of the hydraulic actuator (including drilling pressure distribution, azimuth angle fine-tuning, and rotation speed adaptation) are optimized.

[0075] The virtual simulation module can perform digital twin modeling and optimization. A flexible body model of the drill pipe is established based on the finite element method, and a stratified formation mechanics parameter database is generated in combination with geological exploration data. The sensor data of the physical system and the virtual model state are synchronized in real time to simulate the drill bit-formation interaction force, drill pipe bending stress distribution, and hole wall stability evolution. Multiple correction schemes (such as different drilling pressure gradients and correction angle combinations) are executed in parallel in the virtual environment to evaluate the trajectory convergence speed and energy consumption under each scheme. The actual execution effect of the optimal strategy is fed back to the virtual model to correct the estimated values of the formation mechanics parameters, improving the model prediction accuracy. Historical construction data (including formation characteristics, correction strategies, and execution effects) are stored to optimize the decision weights of the control strategy through reinforcement learning algorithms. The virtual simulation module can also establish safety protection and abnormal response to pre-visualize the equipment response under extreme working conditions in the virtual environment, generate safety protection strategies in advance, and generate emergency protection instructions (such as gradual pressure reduction and drilling) for sudden conditions such as hole wall collapse and drill tool abnormal vibration to reduce the risk of equipment damage under abnormal working conditions.

[0076] According to the drilling trajectory deviation characteristics, the drill pipe can be adjusted by a multi-degree-of-freedom hydraulic actuator, and the drilling pressure, rotation speed, and azimuth angle can be dynamically adjusted through model predictive control algorithms to achieve sub-degree-level precision trajectory dynamic correction. For large-angle deflection conditions, an adaptive control strategy can be used to dynamically adjust the hydraulic system parameters to suppress the overshoot oscillation and secondary deflection risk during correction.

[0077] The stratum type (such as clay, rock stratum, gravel layer) and the interface position can be obtained by using a convolutional neural network to jointly learn features of vibration spectrograms, thermal field distribution maps and acoustic time-frequency maps. Based on the energy reflection characteristics of acoustic signals and the local temperature anomalies of the thermal field, the spatial coordinates of hard obstacles (such as boulders, concrete blocks) in the drilling path are located.

[0078] The drilling operation deviation control method of the drilling rig intelligent operation system of the embodiment is described with reference to Figure 1 The method comprises the following steps:

[0079] Real-time acquisition of mechanical vibration signals, torque signals, spatial displacement signals, thermal field signals and acoustic signals during drilling operation;

[0080] Temporal and spatial fusion processing is performed on the above signals to extract working condition feature vectors;

[0081] Judging the risk level of sticking;

[0082] When the preset risk level is reached, image signals are acquired to construct a three-dimensional model of the inside of the drill hole, and the deviation of the drill hole trajectory is determined;

[0083] The optimal scheme is obtained by simulating different treatment strategies in a virtual environment, and adjustment instructions are generated.

[0084] When the preset risk level is reached, refer to Table 2 for processing. When the high-risk sticking early warning is triggered, the telescopic high-definition camera is pushed to the sticking position, and the active light source is turned on to adapt to the low-illumination environment inside the drill hole; based on binocular vision and structured light scanning technology, obstacle point cloud data is obtained, the obstacle type (such as rock block, metal foreign matter) is distinguished by semantic segmentation algorithm, and its geometric size and embedding depth are calculated; the preset processing scheme (such as adjusting the drill bit speed to impact and break, starting lateral vibration to assist in escaping) is matched according to the obstacle type, and the strategy feasibility is verified through a virtual simulation module.

[0085] Low-risk and medium-risk refer to Table 2 for disposal.

[0086] The above is only a preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A drilling rig smart operation system, characterized in that, The system comprises: a collection module for collecting mechanical vibration signals, torque signals, spatial displacement signals, thermal field signals, acoustic signals and image signals during drilling; The analysis module processes the signals obtained by the acquisition module to obtain the time sequence evolution law of torque-displacement, displacement stagnation characteristics, vibration spectrum, thermal field distribution and acoustic time-frequency diagram, and fuses and processes the dynamic filtering algorithm and the machine learning model to generate a drilling condition feature vector, constructs a feature weight distribution model based on an attention mechanism to perform cross-dimension signal fusion on vibration spectrum energy, thermal field distribution and acoustic energy attenuation rate to generate a drilling condition feature vector; a drilling risk grading mechanism is established according to the vibration spectrum mutation intensity, the thermal field abnormal area and the acoustic signal energy attenuation rate in combination with a historical working condition mode library, and a drilling risk grade is generated, and a drilling risk evaluation function is represented as wherein: a dynamic weight representing vibration spectrum characteristics; a dynamic weight representing thermal field distribution; a dynamic weight representing acoustic attenuation rate; a vibration spectrum kurtosis; a maximum kurtosis; a thermal anomaly area; a maximum thermal anomaly area; an acoustic attenuation rate; a maximum attenuation rate; a stratum type and an interface position are generated based on the mutation law of the vibration spectrum, the distribution law of the thermal field and the attenuation law of the acoustic time-frequency diagram; a three-dimensional model of the inside of the drilling hole is constructed according to the image signals, and the spatial coordinates of the hard obstacles in the drilling path are located based on the energy reflection characteristics of the acoustic signals and the local temperature anomalies of the thermal field signals; a time sequence prediction model about the drilling trajectory is constructed based on the nonlinear relationship between the torque growth rate and the displacement stagnation time length, and the drilling trajectory deviation characteristics are identified; a virtual simulation module for establishing a drill pipe-geological environment coupling dynamics model, deducing and feeding back an optimized treatment strategy to the decision module through simulation, and generating a safety protection strategy and feeding it back to the decision module to simulate the response of equipment under extreme conditions; a decision module for determining whether to correct deviation according to the risk level of stuck pipe, generating a treatment strategy and forming an adjustment instruction.

2. The drilling intelligence system of claim 1, wherein, The collection module comprises: a vibration detection sensor for collecting mechanical vibration signals including drill pipe axial vibration, radial vibration and circumferential vibration signals; a laser displacement sensor and an inertial measurement unit for collecting spatial displacement signals of the drill bit; a thermal field detection unit for collecting temperature field distribution data of the inner wall of the borehole; an acoustic feature collection unit for collecting acoustic signals during drilling; an imaging component for collecting image signals.

3. The system of claim 2, wherein, Wavelet packet decomposition is performed on the drill pipe axial vibration, radial vibration and circumferential vibration signals to obtain vibration frequency spectrum, and the energy ratio of the low frequency band of 0-200Hz and the high frequency band of more than 500Hz is extracted to calculate the frequency spectrum kurtosis, and the vibration frequency spectrum mutation rule is obtained; The temperature field of the inner wall of the borehole is regionally separated, the radial temperature gradient is calculated, and the thermal field distribution map is obtained; The acoustic time-frequency map is extracted by Mel frequency cepstrum coefficient to calculate the energy attenuation rate of the acoustic wave, and the attenuation rate change rule is obtained.

4. The system of claim 3, wherein, The dynamic weight range of the vibration spectrum energy is 0.4-0.6, the dynamic weight range of the thermal field distribution is 0.3-0.5, and the dynamic weight range of the acoustic energy attenuation rate is 0.2-0.

4.

5. The system of claim 3, wherein, According to the vibration spectrum mutation intensity, the thermal field abnormal area and the acoustic signal energy attenuation rate, a low-medium-high three-level stuck pipe risk grading mechanism is established in combination with the historical working condition mode library.

6. The system of any one of claims 1-5, wherein, Convolutional neural network is used for joint feature learning of the vibration spectrum, thermal field distribution and acoustic time-frequency map to obtain the formation type and its interface position.

7. A method of deviation control for a drilling operation, characterized by, The system comprises: real-time collection of mechanical vibration signals, torque signals, spatial displacement signals, thermal field signals and acoustic signals during drilling; spatiotemporal fusion processing of the above signals to extract working condition feature vectors; determination of the risk level of stuck pipe; when the preset risk level is reached, an image signal is acquired to construct a three-dimensional model of the inside of the borehole and determine the deviation of the borehole trajectory; simulation of different treatment strategies in a virtual environment to obtain an optimal scheme and generate an adjustment instruction.

8. A method of deviation control for a drilling operation according to claim 7 wherein, The spatiotemporal fusion processing includes signal noise reduction and feature enhancement operations; the virtual environment simulation includes dynamic response prediction of geological conditions.

9. The method of deviation control for a drilling operation of claim 7, wherein, The execution effect data of the adjustment instruction is fed back to the virtual simulation module to form a learning sample, and the decision weight parameters of the machine learning model are updated regularly.

Images