Intelligent analysis method and device for risk of blocking

Abstract

This invention discloses an intelligent analysis method and device for stuck-block risk. The method includes: real-time acquisition of drilling parameters; determining whether the operating condition is in a cyclic state within a predetermined time period before the current moment based on the drilling parameters; extracting features of the current time window and features of a reference time window; calculating the arithmetic mean of each drilling parameter within the current time window as the current feature; calculating the arithmetic mean of each drilling parameter within the reference time window as the reference feature; based on the calculated current feature and reference feature, continuously monitoring and analyzing torque trend anomalies of multiple drilling parameters and corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions; and generating stuck-block risk alarm information when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles. This invention aims to improve the efficiency and alarm accuracy of intelligent stuck-block risk analysis and reduce the false alarm rate of stuck-block risk.

Description

Technical Field

[0001] This invention relates to the fields of information technology and petroleum industry technology, and in particular to a method and apparatus for intelligent analysis of traffic jam risk. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention described herein. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] In oil and gas drilling engineering, drill string sticking is one of the core risks threatening drilling safety and efficiency. As oil and gas resource development extends to deeper formations, complex structures, and unconventional reservoirs, the environmental complexity and technical challenges faced by drilling operations have significantly increased. However, in actual drilling processes, drill string sticking frequently occurs due to variable geological structures, improper control of drilling parameters, or equipment malfunctions. If not handled promptly and effectively, it can even lead to secondary disasters such as work stoppages, equipment damage, and well control failures, threatening the lives and property of personnel on site.

[0004] Therefore, accurate alarms for complex stuck-hole accidents are an effective means of reducing losses. Traditional stuck-hole alarm technologies mainly rely on manual experience and parameter threshold monitoring, which has significant limitations. On the one hand, monitoring systems based on single-parameter thresholds such as drilling pressure, torque, and pump pressure are not sensitive enough to early abnormal signals and cannot effectively distinguish between normal drilling fluctuations and true signs of stuck-hole conditions, often resulting in frequent false alarms. Moreover, alarms are usually only triggered when the stuck-hole condition reaches a critical state, leaving operators with a short emergency response window. On the other hand, manual interpretation is difficult to meet the needs of 24-hour uninterrupted monitoring. Summary of the Invention

[0005] This invention provides a method for intelligent analysis of card blocking risks, which improves the efficiency and alarm accuracy of intelligent analysis of card blocking risks and reduces the false alarm rate of card blocking risks. The method includes:

[0006] Real-time acquisition of drilling parameters; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure;

[0007] Based on the drilling parameters, determine whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter being continuously greater than the first stroke speed threshold and the stand pressure being continuously greater than the first pressure threshold.

[0008] Extract features from the current time window and the baseline time window; calculate the arithmetic mean of each drilling parameter within the current time window as the current feature; calculate the arithmetic mean of each drilling parameter within the baseline time window as the baseline feature;

[0009] Based on the calculated current and baseline characteristics, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and their corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions.

[0010] When it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, a blockage risk alarm message is generated.

[0011] This invention also provides a smart card blocking risk analysis device to improve the efficiency and alarm accuracy of smart card blocking risk analysis and reduce the false alarm rate of card blocking risk. The device includes:

[0012] The drilling parameter acquisition module is used to acquire drilling parameters in real time; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure.

[0013] The cycle state determination module is used to determine whether the working condition is in a cycle state within a predetermined time period before the current moment based on the drilling parameters; the cycle state is defined as the pump stroke parameter being continuously greater than a first stroke speed threshold and the stand pressure being continuously greater than a first pressure threshold.

[0014] The feature extraction module is used to extract features of the current time window and features of the reference time window; calculate the arithmetic mean of each drilling parameter in the current time window as the current feature; calculate the arithmetic mean of each drilling parameter in the reference time window as the reference feature;

[0015] The continuous monitoring and analysis module is used to continuously monitor and analyze torque trend anomalies for multiple drilling parameters and corresponding preset thresholds based on calculated current and baseline characteristics, and to determine whether each drilling parameter meets the corresponding parameter conditions.

[0016] The alarm information generation module is used to generate a stuck risk alarm information when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles.

[0017] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned intelligent analysis method for card blocking risks.

[0018] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent analysis method for card blocking risks.

[0019] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described intelligent analysis method for card blocking risks.

[0020] In this embodiment of the invention, drilling parameters are acquired in real time; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure; based on the drilling parameters, it is determined whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter continuously exceeding a first stroke speed threshold and the standpipe pressure continuously exceeding a first pressure threshold; features of the current time window and features of the reference time window are extracted; the arithmetic mean of each drilling parameter within the current time window is calculated as the current feature; the arithmetic mean of each drilling parameter within the reference time window is calculated as the reference feature; based on the calculated current feature and reference feature, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions; when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, a jamming risk alarm is generated. This invention, through cyclic state operating condition analysis, eliminates interference from non-cyclic states, ensuring the stability of the monitoring environment and avoiding invalid analysis. It establishes a dual-time-window dynamic comparison mechanism, extracting data from the current window and the baseline window, calculating the arithmetic mean of parameters such as rotational speed and torque, and generating a feature set reflecting real-time changes and historical benchmarks. This enables early anomaly detection of jamming risks, solving the lag problem of traditional threshold monitoring. Furthermore, it establishes a multi-parameter collaborative verification system, jointly determining conditions such as torque mean exceeding the threshold, accompanying increase in vertical pressure, and rotational speed / drilling pressure fluctuation tolerance, automatically generating alarm information. This significantly improves the efficiency and accuracy of intelligent jamming risk analysis and reduces the false alarm rate of jamming risks. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0022] Figure 1 This is a flowchart illustrating an intelligent risk analysis method for blocking cards in an embodiment of the present invention;

[0023] Figure 2 This is a specific example diagram of a torque trend anomaly alarm process in an embodiment of the present invention;

[0024] Figure 3 This is a specific example diagram of an intelligent alarm model for abnormal torque trend and card risk in an embodiment of the present invention;

[0025] Figure 4 This is a specific example diagram illustrating a cyclic state condition verification in an embodiment of the present invention;

[0026] Figure 5 This is a specific example diagram of drilling parameter analysis in an embodiment of the present invention;

[0027] Figure 6 This is a specific example diagram of drilling parameter analysis in an embodiment of the present invention;

[0028] Figure 7 This is a schematic diagram of the structure of a smart card risk analysis device according to an embodiment of the present invention;

[0029] Figure 8 This is a schematic diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0031] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0032] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0033] The acquisition, storage, use, and processing of data in this application comply with relevant regulations. The information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation interfaces are provided for users to choose to authorize or refuse.

[0034] It should be noted that in the embodiments of this application, certain existing solutions in the industry, such as software, components, and models, may be mentioned. For example, some existing software tools, components, algorithm models, or solutions well-known in other technical fields may be cited. These should be considered exemplary, and their purpose is only to illustrate the feasibility of implementing the technical solution of this application. These mentions should be understood as typical examples, and their core purpose is to illustrate and verify the rationality and feasibility of implementing the technical solution proposed in this application. However, this does not mean that the applicant has already used or necessarily used the solution. Such citations do not imply that the applicant has actually adopted these existing solutions, or that it will necessarily adopt these methods in its technical implementation process in the future. In other words, these mentions are only illustrative in nature, helping to understand the connection and transcendence of the innovation points of this application with the prior art, and do not constitute an endorsement or reliance statement on a specific prior art product.

[0035] In oil and gas drilling engineering, stuck drill string is one of the core risks threatening drilling safety and efficiency. As oil and gas resource development extends to deeper formations, complex structures, and unconventional reservoirs, the environmental complexity and technical challenges faced by drilling operations have significantly increased. However, in actual drilling processes, stuck drill string frequently occurs due to variable geological structures, improper control of drilling parameters, or equipment malfunctions. If not handled promptly and effectively, this can lead to secondary disasters such as work stoppages, equipment damage, and well control failures, threatening the lives and property of personnel on site. Therefore, accurate warnings for complex stuck drill string incidents are an effective means of reducing losses. Traditional stuck drill string warning technologies mainly rely on manual experience and parameter threshold monitoring, which have significant limitations. On the one hand, monitoring systems based on single-parameter thresholds such as drilling pressure, torque, and pump pressure lack sensitivity to early abnormal signals and cannot effectively distinguish between normal drilling fluctuations and true signs of stuck drilling, often resulting in frequent false alarms. Furthermore, alarms are typically triggered only when the stuck drilling reaches a critical state, leaving operators with a short emergency response window. On the other hand, manual interpretation is insufficient to meet the demands of 24 / 7 uninterrupted monitoring. Therefore, establishing an intelligent alarm method for stuck drilling risk through torque trend anomaly monitoring, automating alarms, and improving alarm efficiency and accuracy, is particularly important for cost reduction, efficiency improvement, protecting operator safety, and enhancing drilling efficiency.

[0036] The key technologies of the intelligent alarm method for stuck drilling risk based on continuous monitoring and analysis of torque trend anomalies mainly lie in the real-time data acquisition and the establishment of the business model. In terms of real-time monitoring of stuck drilling alarms, specialized equipment such as integrated logging instruments can instantly collect and record various drilling parameters, and then efficiently store this data in a database.

[0037] By using the Python programming language, the system can read information from the database in real time and accurately obtain the latest data using a time-based sliding window. Based on this, in-depth analysis of this real-time data is conducted to monitor and analyze abnormal torque trends and promptly issue blocking alarms.

[0038] The construction of the business logic model for the intelligent alarm model of stuck hole risk based on continuous monitoring and analysis of abnormal torque trends is mainly based on the analysis and verification of a large amount of historical stuck hole data and the summary of expert experience. This new stuck hole alarm method is proposed. When downhole hazards such as formation collapse, severe sand accumulation, and drill bit mud bagging occur, the standing pressure and torque parameters will gradually increase due to annular blockage. When the hazards become severe to a certain extent, they will lead to stuck hole or even stuck drill. Therefore, by focusing on monitoring the changes in rotational speed, torque, standing pressure, and pump stroke, if the torque trend increases abnormally, or is accompanied by an increase in standing pressure, or is accompanied by abnormal torque points, a stuck hole risk alarm is issued under the condition that the rotational speed and pump stroke are basically stable. This achieves a fully automatic alarm monitoring task and provides a basis for complex alarms in the field.

[0039] Therefore, this invention provides an intelligent analysis method for stuck hole risk. The core objective of this invention is to provide an intelligent alarm method for stuck hole risk based on continuous monitoring and analysis of abnormal torque trends. Based on the engineering parameter data stream collected by the integrated logging tool, a real-time analysis and dynamic monitoring system is constructed to achieve automatic online identification of abnormal patterns, breaking through the time and space limitations of manual monitoring, establishing a 24 / 7 continuous alarm mechanism, and simultaneously reducing the false alarm rate of single thresholds. It also compresses the response time for handling complex downhole conditions from the "hours" of traditional operations to the "minutes," achieving an upgrade in drilling safety mode from passive response to proactive prevention. Specifically, this invention aims to improve the efficiency and accuracy of intelligent stuck hole risk analysis and reduce the false alarm rate of stuck hole risk. See [link to relevant documentation]. Figure 1 , Figure 1 This is a flowchart illustrating an intelligent risk analysis method for blocking cards according to an embodiment of the present invention. The method may include:

[0040] Step 101: Real-time acquisition of drilling parameters; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure;

[0041] Step 102: Based on the drilling parameters, determine whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameters being continuously greater than the first stroke speed threshold and the stand pressure being continuously greater than the first pressure threshold.

[0042] Step 103: Extract the features of the current time window and the features of the baseline time window; calculate the arithmetic mean of each drilling parameter in the current time window as the current feature; calculate the arithmetic mean of each drilling parameter in the baseline time window as the baseline feature;

[0043] Step 104: Based on the calculated current features and baseline features, perform continuous monitoring and analysis of torque trend anomalies on multiple drilling parameters and corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions.

[0044] Step 105: When it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, generate a stuck risk alarm message.

[0045] In this embodiment of the invention, drilling parameters are acquired in real time; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure; based on the drilling parameters, it is determined whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter continuously exceeding a first stroke speed threshold and the standpipe pressure continuously exceeding a first pressure threshold; features of the current time window and features of the reference time window are extracted; the arithmetic mean of each drilling parameter within the current time window is calculated as the current feature; the arithmetic mean of each drilling parameter within the reference time window is calculated as the reference feature; based on the calculated current feature and reference feature, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions; when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, a jamming risk alarm is generated. This invention, through cyclic state operating condition analysis, eliminates interference from non-cyclic states, ensuring the stability of the monitoring environment and avoiding invalid analysis. It establishes a dual-time-window dynamic comparison mechanism, extracting data from the current window and the baseline window, calculating the arithmetic mean of parameters such as rotational speed and torque, and generating a feature set reflecting real-time changes and historical benchmarks. This enables early anomaly detection of jamming risks, solving the lag problem of traditional threshold monitoring. Furthermore, it establishes a multi-parameter collaborative verification system, jointly determining conditions such as torque mean exceeding the threshold, accompanying increase in vertical pressure, and rotational speed / drilling pressure fluctuation tolerance, automatically generating alarm information. This significantly improves the efficiency and accuracy of intelligent jamming risk analysis and reduces the false alarm rate of jamming risks.

[0046] In practice, the first step is to collect drilling parameters in real time, including rotational speed, torque, stand pressure, pump pressure and drilling pressure.

[0047] In this embodiment, drilling parameters are collected in real time, including:

[0048] The system continuously acquires engineering parameter measurements of rotational speed, torque, stand pressure, pump pressure, and drilling pressure at a frequency of up to one second, and simultaneously records timestamps and well depth data.

[0049] A dynamic data stream is formed; this data stream is transmitted to the database for storage in real time in the form of a time series.

[0050] In the above embodiments, the real-time acquisition of drilling parameters is performed using a comprehensive logging tool, continuously acquiring measurements of key drilling parameters at a frequency of up to one second. The acquisition process simultaneously records timestamps and well depth data to ensure the integrity of the data's spatiotemporal attributes.

[0051] The acquired engineering parameters specifically include five core indicators: rotational speed, torque, stand pressure, pump stroke, and drilling pressure. Pump stroke parameters cover total pump stroke and sub-pump stroke speed data, while drilling pressure parameters reflect the axial load status of the downhole drilling tools. All acquired data forms a continuous dynamic data stream, which is structured based on a time series and sorted by millisecond-level timestamps before being transmitted in real-time to the target database for storage. Data storage employs a time-series database architecture to ensure efficient writing and compressed archiving of incremental data at the second-per-second level, providing low-latency data access capabilities for subsequent real-time monitoring. Well depth data, as a key location identifier, is indexed with the engineering parameters using timestamp alignment during storage, ensuring accurate matching of well depth trajectories during subsequent window analysis.

[0052] In this embodiment, the real-time acquired drilling parameter data includes a timestamp field recording the acquisition time and a well depth field indicating the current drill bit position. Rotation speed parameters reflect the drill string's rotational speed, torque parameters characterize the drill string's torsional load, standpipe pressure parameters indicate the pressure status of the circulation system, pump stroke parameters include the total pump stroke and the stroke rates of multiple sub-pumps, and drilling pressure parameters quantify the drill bit's axial pressure. New data points generated every second are immediately appended to the tail of the dynamic data stream, and time windows are divided using a stream processing engine.

[0053] Dynamic data streams are continuously written to the distributed database cluster, employing a time-partitioned storage strategy to achieve millisecond-level data persistence. The database storage layer provides a fast query interface based on time ranges for subsequent feature extraction modules, supporting millisecond-level response times for sliding windows. Well depth data is stored with strict time synchronization to engineering parameters, ensuring that well depth changes remain within controllable threshold ranges during subsequent dual-window analysis.

[0054] In specific implementation, after performing step 101: real-time acquisition of drilling parameters; the drilling parameters include rotational speed, torque, stand pressure, pump stroke and drilling pressure, step 102: based on the drilling parameters, determine whether the working condition is in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter being continuously greater than the first stroke speed threshold and the stand pressure being continuously greater than the first pressure threshold.

[0055] In one embodiment, determining whether the operating conditions are in a cyclic state within a predetermined time period prior to the current moment, based on the drilling parameters, includes:

[0056] Using the current moment as the reference point, trace back the first preset time interval as the verification period;

[0057] The verification period is divided into multiple sub-windows of equal length. For each sub-window, it is determined whether the corresponding pumping parameters are continuously greater than the first pumping speed threshold and whether the vertical pressure is continuously greater than the first pressure threshold.

[0058] If the pump parameters corresponding to more than a preset number of sub-windows are continuously greater than the first pump speed threshold and the vertical pressure is continuously greater than the first pressure threshold, determine whether the working condition is in a cyclic state within the predetermined time period before the current moment.

[0059] In the above embodiment, the current moment is used as the time reference point, and a continuous period of a predetermined time length is traced back as the verification interval. This verification interval is evenly divided into multiple sub-window units of fixed duration, and each sub-window unit independently performs state verification. For each sub-window unit, it is verified whether the following two conditions are continuously met: the measured value per second of at least one pumping parameter is continuously greater than a preset pumping speed threshold, and the measured value per second of the standing pressure parameter is continuously greater than a preset pressure threshold. Based on the verification results of all sub-window units, the total compliance rate is statistically calculated. If and only if the compliance rate of all sub-window units reaches or exceeds a preset proportion threshold, the current working condition is determined to be in a cyclic state; if any sub-window unit fails to meet the compliance rate requirement, it is determined to be a non-cyclic working condition, and the subsequent blockage risk analysis process is immediately terminated.

[0060] In practice, the verification of pump stroke parameters covers both total pump stroke and sub-pump stroke speed data, ensuring that the stroke speed condition is met if any pump stroke source is effective. Continuous monitoring of the vertical pressure parameter requires the pressure value to remain stable above the threshold throughout the entire process, avoiding intermittent fluctuations. The number and duration of sub-window units are dynamically adapted based on the total length of the verification interval to ensure that the time granularity meets statistical significance requirements. The setting of the compliance rate threshold must balance system sensitivity and fault tolerance to prevent misjudgments caused by occasional data anomalies. The status determination result directly affects the start and stop of the subsequent dual-window feature extraction function, forming a strict operating condition filtering mechanism.

[0061] In this embodiment, the determination of non-circulating operating conditions is directly associated with the termination command of the analysis process, and the system automatically releases computing resources and resets the monitoring status. Confirmation of circulating operating conditions triggers the initialization of the feature extraction module, providing access permission for subsequent torque trend analysis. This design ensures that the system performs stuck-out risk analysis only under physical conditions where drilling fluid circulation is stable, fundamentally eliminating interference from non-circulating states such as tripping out of the drill string and stopping the pump on torque monitoring.

[0062] In one embodiment, it also includes:

[0063] The collected drilling parameters are preprocessed; the preprocessing includes data cleaning, unit standardization, and missing value imputation.

[0064] Based on the drilling parameters, determine whether the operating conditions are in a cyclical state within a predetermined time period prior to the current moment, including:

[0065] Based on the pre-processed drilling parameters, determine whether the working conditions are in a cyclic state within the predetermined time period before the current moment.

[0066] In the above embodiments, a data cleaning operation is performed on the collected drilling parameters. Specifically, the sliding window method is used to detect abnormal measurement values, and data points that exceed the predetermined standard deviation range are marked as suspicious values.

[0067] When dealing with duplicate data, a differentiated strategy is implemented based on the degree of impact on the analysis results: duplicate values ​​with little impact on the analysis are directly removed, while outliers that may affect key judgments are treated as missing values.

[0068] When standardizing the data processing, the data units of different logging equipment are unified to the international standard system to ensure parameter comparability. Missing values ​​are repaired using linear interpolation to maintain the continuity of the time series. The processed data is then strictly aligned to timestamps before being written into the real-time database.

[0069] Based on the preprocessed drilling parameters, the specific implementation method of cyclic state verification is as follows:

[0070] Using the current time as the time reference point, a continuous period of predetermined time length is traced back as the verification interval. This verification interval is then evenly divided into multiple sub-window units of fixed duration.

[0071] For each sub-window unit, verify two continuous state conditions: the measured value per second of at least one pumping parameter is continuously greater than a preset pumping speed threshold, and the measured value per second of the vertical pressure parameter is continuously greater than a preset pressure threshold. Statistically analyze the compliance status of all sub-window units. The current operating condition is determined to be in a cyclic state only if the compliance rate of all sub-window units reaches or exceeds a preset percentage threshold.

[0072] If any sub-window cell fails to meet the compliance rate requirement, the subsequent analysis process will be terminated immediately and a non-cyclic status will be returned.

[0073] In specific implementation, after step 102: determining whether the working condition is in a cyclic state within a predetermined time period before the current moment based on the drilling parameters; the cyclic state is defined as the pump stroke parameter continuously being greater than the first stroke speed threshold and the stand pressure continuously being greater than the first pressure threshold, step 103: extracting the features of the current time window and the features of the reference time window; calculating the arithmetic mean of each drilling parameter in the current time window as the current feature; calculating the arithmetic mean of each drilling parameter in the reference time window as the reference feature.

[0074] In one embodiment, the current time window is a time interval from the current moment back to a first predetermined duration; the reference time window is a time interval from the current moment back to a second predetermined duration to a third predetermined duration; and the well depth difference between the reference time window and the current time window is less than a predetermined depth tolerance.

[0075] In this embodiment, using the current moment as the time reference point, complete drilling parameter time-series data for a second predetermined duration continuous interval along the time axis in the shallow well section are extracted as the current time window. The arithmetic mean of the continuously acquired rotational speed measurement sequence within this window is calculated to generate a feature value characterizing the real-time rotational state and marked as the current average rotational speed. The same calculation rule is synchronously applied to the torque measurement sequence to generate a feature value reflecting the torsional load of the drill string and marked as the current average torque.

[0076] The same computational logic is used to process the standpressure measurement sequence, generating feature values ​​indicating the circulating system pressure and marking them as the current standpressure average. The arithmetic mean of the pump surge measurement sequence is calculated to generate feature values ​​characterizing drilling fluid pumping efficiency and marked as the current pump surge average. The mean of the drill bit pressure measurement sequence is calculated to generate feature values ​​quantifying the drill bit axial pressure and marked as the current drill bit pressure average. A time decay weighting mechanism is implemented in the calculation process, giving higher weight coefficients to measurement data near the end of the window.

[0077] The drilling parameter time series data of the continuous interval from the second predetermined time period to the third predetermined time period before the current time is extracted as the reference time window.

[0078] Before starting the calculation, the absolute difference between the well depth measurements at the start and end points of the window is verified to be less than a preset depth tolerance threshold. When the well depth difference meets the requirements, the arithmetic mean of the rotational speed parameter time series data within the benchmark window is calculated to generate a characteristic value representing the historical stable state and marked as the benchmark rotational speed mean. The same calculation rule is applied to the torque parameter time series data to generate the benchmark torque mean. Simultaneously, the arithmetic mean of the standpipe pressure parameter time series data, pump flushing parameter time series data, and drilling pressure parameter time series data are calculated independently to generate the benchmark standpipe pressure mean, benchmark pump flushing mean, and benchmark drilling pressure mean in sequence. The benchmark window calculation adopts the same attenuation weighting mechanism as the current window.

[0079] The well depth difference verification process is achieved by querying the well depth record corresponding to the timestamp. If the absolute difference exceeds the tolerance threshold, the system automatically shifts the reference window position along the time axis until the condition is met.

[0080] This design ensures that the geological strata corresponding to the two windows are homogeneous, eliminating the interference of well depth variations on parameter comparison. The feature output set contains the fully corresponding five-dimensional parameter averages. The current window features are named as follows: current rotation speed average, current torque average, current standpipe pressure average, current pump stroke average, and current drill pressure average. The baseline window features are named as follows: baseline rotation speed average, baseline torque average, baseline standpipe pressure average, baseline pump stroke average, and baseline drill pressure average.

[0081] In this embodiment, a specific point in time is taken as an example:

[0082] When obtaining the feature set for the current time window, the rotational speed data sequence within a specific three-minute interval is extracted and weighted to obtain the current average rotational speed; the torque sequence is processed simultaneously to obtain the current average torque. During the generation of the baseline window feature set, the starting and ending well depth difference within a five-minute interval is first verified. After confirming that the requirements are met, the baseline average rotational speed and baseline average torque are calculated. The dual-window feature sets are transmitted to subsequent analysis modules via a standardized interface.

[0083] In one embodiment, extracting features of the current time window includes:

[0084] Using the current moment as the time reference point, extract the drilling parameter time series data within the first predetermined time interval;

[0085] The arithmetic mean values ​​of the measured values ​​of rotational speed, torque, stand pressure, pump stroke, and drilling pressure in the time series data of drilling parameters collected within the interval are calculated to obtain the current average values ​​of rotational speed, torque, stand pressure, pump stroke, and drilling pressure, forming the characteristics of the current time window that reflects the real-time changes in operating conditions.

[0086] In the above embodiment, the current moment is used as the time analysis reference point, and complete drilling parameter time series data of a first predetermined duration continuous interval is extracted along the shallow well section of the time axis. The arithmetic mean calculation operation is performed on the rotational speed measurement value sequence collected per second within this interval to generate a feature value representing the real-time rotational state and mark it as the current rotational speed average. Simultaneously, the same calculation rule is performed on the torque measurement value sequence to generate a feature value reflecting the torsional load of the drill string and mark it as the current torque average. The same calculation logic is used to process the standpipe pressure measurement value sequence to generate a feature value indicating the circulating system pressure and mark it as the current standpipe pressure average. The arithmetic mean is calculated on the pump flush measurement value sequence to generate a feature value representing the drilling fluid pumping efficiency and mark it as the current pump flush average. The mean calculation is performed on the drill bit pressure measurement value sequence to generate a feature value quantifying the drill bit axial pressure and mark it as the current drill bit pressure average.

[0087] In one embodiment, extracting features of a baseline time window includes:

[0088] Extract drilling parameter time series data within a continuous interval from the second to the third predetermined time period before the current moment;

[0089] While ensuring that the difference between the measured well depth at the start and end points of the interval is less than the preset depth tolerance, the average reference rotational speed, average reference torque, average reference stand pressure, average reference pump stroke, and average reference drilling pressure of different drilling parameter time series data are calculated to form the characteristics of the reference time window that characterizes the historical stable state.

[0090] In the above embodiment, the drilling parameter time series data within the continuous time interval is extracted as the reference time window, with the second predetermined time period before the current time as the starting point and the third predetermined time period as the ending point.

[0091] Before feature calculation, the absolute difference between the well depth measurement value recorded at the start point and the well depth measurement value recorded at the end point of the window is verified to be less than a preset depth tolerance threshold. When the well depth difference meets the tolerance requirement, the arithmetic mean of the continuously collected rotational speed parameter time series data within the window is calculated to generate a benchmark rotational speed mean representing the historical stable state; the same calculation rule is applied to the torque parameter time series data to generate a benchmark torque mean; simultaneously, the arithmetic mean of the standpressure parameter time series data, pump flushing parameter time series data, and drilling pressure parameter time series data are calculated independently to generate benchmark standpressure mean, benchmark pump flushing mean, and benchmark drilling pressure mean in sequence. The above set of mean values ​​together constitutes the feature output of the benchmark time window, which fully reflects the parameter level of drilling operations in the historical stable stage.

[0092] During the calculation, measurement data near the end of the window are given higher weight, and the contribution of the data is dynamically adjusted through a preset time decay factor, so that the data at the end of the window has a stronger impact on the mean result. This weighting mechanism is completely consistent with the feature calculation of the current time window, ensuring the comparability of the two-window data.

[0093] If the well depth difference exceeds the tolerance threshold, the system automatically adjusts the reference window time range until the well depth consistency requirement is met, specifically through time axis shifting or window scaling. The well depth verification process ensures that the two windows correspond to the same geological strata, eliminating interference from well depth changes on parameter comparison.

[0094] In specific implementation, after performing step 103: extracting the features of the current time window and the features of the benchmark time window; calculating the arithmetic mean of each drilling parameter in the current time window as the current feature; and calculating the arithmetic mean of each drilling parameter in the benchmark time window as the benchmark feature, step 104: based on the calculated current feature and benchmark feature, performing continuous monitoring and analysis of torque trend anomalies on multiple drilling parameters and their corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions.

[0095] In one embodiment, the parameter conditions include one or any combination of the following: the arithmetic mean of torque increases by more than a torque threshold, the arithmetic mean of stand pressure increases by more than a stand pressure threshold, the arithmetic mean of rotational speed changes by less than a rotational speed tolerance threshold, the arithmetic mean of pump stroke changes by less than a pump stroke tolerance threshold, and the arithmetic mean of drilling pressure changes by less than a drilling pressure tolerance threshold.

[0096] In one embodiment, based on calculated current and baseline characteristics, continuous monitoring and analysis of torque trend anomalies is performed on multiple drilling parameters and corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions, including:

[0097] Continuous monitoring and analysis of torque trend anomalies were performed on multiple drilling parameters and corresponding preset thresholds to determine whether the following conditions were met:

[0098] The difference between the current arithmetic mean of torque and the baseline arithmetic mean of torque exceeds the torque change threshold;

[0099] The difference between the current arithmetic mean of vertical pressure and the benchmark arithmetic mean of vertical pressure exceeds the vertical pressure change threshold, or when the vertical pressure data is invalid, the difference between the current arithmetic mean of total pump stroke and the benchmark arithmetic mean of total pump stroke is less than the pump stroke tolerance threshold.

[0100] The absolute value of the difference between the current arithmetic mean of rotational speed and the reference arithmetic mean of rotational speed is less than the rotational speed tolerance threshold, or when the rotational speed is zero, the absolute value of the difference between the current arithmetic mean of drilling pressure and the reference arithmetic mean of drilling pressure is less than the drilling pressure tolerance threshold.

[0101] In the above embodiment, the absolute difference between the current average torque and the reference average torque is first calculated. When the difference exceeds the dynamically adjusted torque change threshold, it is determined that the torque has increased significantly. Simultaneously, the absolute difference between the current average vertical pressure and the reference average vertical pressure is calculated. When the difference exceeds the vertical pressure change threshold, it is determined that the vertical pressure has increased. If the vertical pressure sensor data is marked as invalid, the system automatically switches to the pump-flush replacement verification path. The determination is completed by comparing whether the absolute difference between the current average total pump-flush and the reference average total pump-flush is less than the pump-flush tolerance threshold.

[0102] The rotational speed stability verification step calculates the absolute difference between the current average rotational speed and the reference average rotational speed. When the difference is less than the rotational speed tolerance threshold, the rotational speed is determined to be stable. If the rotational speed measurement value continues to return to zero, the drilling pressure substitution verification path is activated, and the determination is completed by checking whether the absolute difference between the current average drilling pressure and the reference average drilling pressure is less than the drilling pressure tolerance threshold.

[0103] The above verification process must meet the time continuity constraint: within multiple consecutive detection cycles, the frequency of triggering verification conditions for all parameters must reach a preset proportional threshold.

[0104] Specifically, the system performs a full parameter verification once per second, requiring all conditions to be met at least four out of five consecutive tests. If a condition fails midway, the counting cycle is reset. The formation type parameter dynamically affects the threshold setting. For example, in drilling conditions classified as hard formations, the torque change threshold automatically increases by a specific percentage; while in mudstone formations, the sensitivity of the torque change threshold is correspondingly reduced.

[0105] When all conditions pass verification under continuous constraints, the system generates a structured early warning message, which includes a timestamp, well depth coordinates, drill bit position, and deviation values ​​of each parameter.

[0106] Alarm information is pushed to the driller's control console terminal via a real-time communication protocol, simultaneously triggering the audible and visual alarm devices. The system automatically enters a four-hour alarm cooling-off period, during which duplicate alarms of the same type are blocked; if the average torque value is detected to fall back to the benchmark level and remain stable for a preset duration during the cooling-off period, the cooling state is lifted early. A complete snapshot of operating data (including original measurements, characteristic averages, and verification results) is automatically stored in the historical case library, classifying the event level and labeling the formation lithology type according to the torque deviation value.

[0107] In specific implementation, after step 104: based on the calculated current features and benchmark features, perform continuous monitoring and analysis of torque trend anomalies on multiple drilling parameters and corresponding preset thresholds, and determine whether each drilling parameter meets the corresponding parameter conditions, proceed to step 105: when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, generate a jamming risk alarm message.

[0108] In one embodiment, when all conditions for multi-parameter joint verification meet the trigger frequency requirement within five consecutive detection cycles, a structured early warning message containing timestamps, well depth, drill bit position, and deviation values ​​of each parameter is generated and pushed to the operation terminal via a real-time communication protocol, triggering an audible and visual alarm. Simultaneously, a 4-hour alarm cooling-off period is initiated, during which repeated triggering of the same type of alarm signal is automatically blocked. If the arithmetic mean of torque is detected to fall back to the baseline level and remain stable for a predetermined duration during the cooling-off period, the cooling state is lifted in advance. At the same time, a snapshot of the current operating condition data is stored in the historical case library, and the event level is classified and the formation type is labeled according to the torque deviation value, providing learning samples for subsequent model optimization.

[0109] Two specific embodiments are given below to illustrate the specific application of the method of the present invention.

[0110] In the first specific embodiment:

[0111] This first specific embodiment achieves intelligent alarm for drilling sticking risk based on dynamic data monitoring and multi-parameter collaborative analysis. Firstly, drilling parameters such as rotational speed, torque, and pump pressure are collected in real time through industrial IoT devices, and the data is cleaned and standardized to ensure data quality. The system sets a continuous pump pressure threshold and time window, verifying the stability of drilling fluid circulation as a prerequisite for analysis, and only initiates subsequent detection processes when the operating condition is continuously in a circulating state. By establishing a dual-time-window comparison mechanism, the mean characteristics of parameters in the near 3-minute and baseline 8-minute intervals are extracted respectively, constructing a dynamic comparison model between the current trend and historical benchmarks.

[0112] During the multi-dimensional anomaly analysis phase, the system focuses on monitoring key signals where torque increases exceed thresholds (e.g., 3 kN·m) and are accompanied by pump pressure increases (e.g., 1.5 MPa). Simultaneously, it strictly limits the fluctuation tolerances of auxiliary parameters such as rotational speed and pump stroke (e.g., rotational speed changes less than 2.5 RPM), forming a multi-parameter coupled verification system. When all conditions are met, an intelligent alarm is triggered, and a 4-hour alarm cooldown period is initiated to prevent repeated alarms. Alarm information is pushed to the work terminal in real time. Through historical case database accumulation and machine learning optimization, the system continuously improves model threshold settings, ultimately forming a closed-loop alarm system encompassing data acquisition, feature extraction, intelligent decision-making, and feedback optimization, significantly enhancing drilling safety situational awareness capabilities.

[0113] The following is a detailed explanation:

[0114] Step 1: Real-time data acquisition and preprocessing:

[0115] The system establishes a dynamic data stream by acquiring parameters such as rotational speed (RPM), torque (kN·m), standpipe pressure (MPa), total pump stroke (stroke / minute), drilling pressure (kN), and well depth (m) per second using a comprehensive logging tool. Data cleaning comprises three stages: first, a sliding window method (30-second window length) is used to detect outliers, marking data exceeding three times the standard deviation as suspicious; second, units are forcibly standardized (e.g., converting imperial units to SI units); and finally, linear interpolation is used to repair missing values, ensuring the continuity of the time series. The preprocessed data is then aligned with timestamps and stored in a real-time database.

[0116] Step 2: Dynamic verification under cyclic operating conditions:

[0117] The system uses the current time t as a baseline and backs 13 minutes (interval t-13, t) to verify whether the cyclic operating conditions are consistently met during this period: at least one pumping parameter (pumping speed 1 / 2 / 3) has a reading greater than 1 pump / minute per second, and the vertical pressure is consistently greater than 1 MPa. The verification uses a segmented scanning method, dividing the 13 minutes into 78 10-second sub-windows, requiring a pumping and vertical pressure compliance rate of ≥95% within each sub-window. If the compliance rate in any sub-window is insufficient, it is determined to be a non-cyclic operating condition, and subsequent analysis is terminated.

[0118] Step 3: Dual-time-window feature extraction:

[0119] 1. Current Trend Window: Extract data from the t-3, t interval (the most recent 3 minutes), and calculate the average rotational speed (RPM1), average torque (Tor1), average standpipe pressure (SPP1), average total pump pressure (Pump1), and average drilling pressure (WOB1). A decay-weighted method is used in the calculation, assigning higher weights to the most recent data (e.g., time decay factor α = 0.9).

[0120] 2. Baseline Trend Window: Extract data from the t-8 and t-3 intervals (from the first 5 minutes to the first 8 minutes), and calculate RPM2, Tor2, SPP2, Pump Total 2, and WOB2 using the same method. The selection criteria for the window are: to avoid near-end data that may be affected by previous anomalies, and to ensure that it has the same well depth as the current window (achieved by verifying that the well depth difference between the start and end points of the window is <0.5m).

[0121] Step 4: Verification of multi-parameter coupling criterion:

[0122] Four-dimensional joint validation is performed on the extracted features:

[0123] 1. Significantly increased torque:

[0124] The difference between the current arithmetic mean torque (Tor1) and the baseline arithmetic mean torque (Tor2) is as follows:

[0125] ΔTor=Tor1-Tor2≥3kN·m (The threshold is automatically floated according to the formation drillability classification. For example, in hard rock formations (such as granite and basalt), the threshold is floated up to 4kN·m to enhance the sensitivity to highly drillable formations).

[0126] 2. Increased vertical pressure:

[0127] The differences between the current arithmetic mean of standing pressure (SPP1) and the baseline arithmetic mean of standing pressure (SPP2) are as follows:

[0128] ΔSPP=SPP1-SPP2≥1.5MPa (If the vertical pressure sensor malfunctions (e.g., missing data, over-range), enable pump flushing parameter verification: the difference between the current total pump flushing arithmetic mean and the baseline value ΔPumptotal ≤3 flushes / minute).

[0129] 3. Speed ​​stability verification:

[0130] The absolute difference between the current arithmetic mean of rotational speeds (RPM1) and the reference value (RPM2) is as follows:

[0131] |ΔRPM|=|RPM1-RPM2|≤2.5RPM (When the rotation speed is reduced to zero (e.g., when drilling is stopped for maintenance), switch to drill pressure verification: the arithmetic mean fluctuation of drill pressure is |ΔWOB|=|WOB1-WOB2|≤10kN).

[0132] 4. Time-duration verification:

[0133] The above conditions must be triggered at least 4 times in 5 consecutive detection cycles (5 seconds) to avoid transient interference. Transient interference (such as sensor power surges or brief drill bit collisions) lasting ≤1 second will be filtered out; anomalies lasting ≥4 seconds are considered valid signals.

[0134] Step 5: Intelligent Alarm Decision and Suppression:

[0135] When all four-dimensional criteria are met, the system executes:

[0136] 1. Generate a warning message, including timestamp, well depth, drill bit position, and deviation values ​​of each parameter, and push it to the driller's terminal in real time via WebSocket protocol, triggering an audible and visual alarm.

[0137] 2. A 4-hour alarm cooling period is initiated, during which similar alarms are automatically disabled. If the torque value drops back to the reference level (ΔTor < 1 kN·m) and remains so for 2 minutes during the cooling period, the cooling will be deactivated prematurely.

[0138] 3. Store a complete snapshot of the operating conditions (including raw data and feature values) to the case library and mark the event level (classify alarms into levels I-III based on ΔTor values).

[0139] Step Six: Model Self-Optimization and Feedback Learning

[0140] The system performs offline optimizations weekly:

[0141] 1. Perform feature inversion on false positive / false negative cases, analyze the sensitivity of each threshold using the random forest algorithm, and dynamically optimize core thresholds such as ΔTor and ΔSPP.

[0142] 2. Based on the well depth-formation data clustering results, establish a threshold matrix for different formation types (e.g., use a lower torque threshold for mudstone layers and increase the standing pressure weight for sandstone layers).

[0143] 3. Through transfer learning, the optimized parameters are synchronized to other drilling platforms to form a knowledge-sharing network for multi-well collaboration.

[0144] In the second specific embodiment:

[0145] I. Dynamic Adaptive Window Adjustment Process:

[0146] 1. Real-time data fluctuation monitoring: Real-time acquisition of drilling parameters (torque, standpipe pressure, etc.).

[0147] Monitor the degree of fluctuation of parameters (such as changes in standard deviation or extreme values).

[0148] 2. Window size is dynamically adjusted. If parameter fluctuations exceed the preset fluctuation threshold, the window is shortened to a high-frequency monitoring mode (e.g., 1 minute). If the parameters are stable, the window is extended to a low-frequency monitoring mode (e.g., 5 minutes).

[0149] 3. Update the window time range to generate a new window time interval (e.g., [t-1, t] or [t-5, t]). Reacquire and process the real-time data within the window.

[0150] II. Trend Slope Analysis and Alarm Triggering Process:

[0151] 1. Parameter Trend Calculation: Perform linear regression analysis on the parameters (torque, vertical pressure) within the current window. Calculate the average value of the parameters (e.g., Tor1, SPP1) and the slope of the linear change (e.g., torque increase per minute).

[0152] 2. Joint judgment of alarm conditions: The difference between the average parameter values ​​of the current window and the historical windows meets the original threshold (e.g., Tor1-Tor2>3kN·m).

[0153] Auxiliary condition: The slope of the current window parameter exceeds the preset slope threshold (e.g., torque slope > 0.5 kN·m / min).

[0154] Triggering rule: The primary condition and the secondary condition must be met simultaneously.

[0155] 3. Alarm Information Output: If an alarm is triggered, send an "abnormal torque trend" message and store the data.

[0156] Do not send the same type of alarm repeatedly within 4 hours.

[0157] In this first specific embodiment, dynamic window adjustment logic is added to the database reading and preprocessing steps in the preprocessing stage; when establishing the current / standard torque trend database in the alarm model stage, the average value and slope are calculated simultaneously. When comparing trends, the difference in average value and the slope threshold are checked simultaneously.

[0158] This first specific embodiment has the following advantages:

[0159] 1. The dynamic window mechanism automatically adjusts the monitoring granularity based on real-time data fluctuations, balancing sensitivity and stability.

[0160] 2. Dual-dimensional trend analysis combines "static difference" (comparison of average values) and "dynamic trend" (slope change) to improve alarm accuracy.

[0161] The specific embodiment is described in detail below:

[0162] The second specific embodiment employs the following technical solution to construct an intelligent alarm model for continuous monitoring and analysis of abnormal torque trends, thereby mitigating card risk:

[0163] First, real-time data is read from the database and preprocessed. Then, based on business logic, an intelligent alarm model for continuous monitoring and analysis of torque trend anomalies is established to determine whether there is a jamming problem due to abnormal torque trends. If the alarm conditions for jamming due to abnormal torque trends are met, an alarm message for jamming due to abnormal torque trends is sent to the driller. A simplified diagram is shown below. Figure 2 As shown, Figure 2 Here is a specific example diagram of a torque trend anomaly alarm process in an embodiment of the present invention:

[0164] (a) Real-time data acquisition and preprocessing:

[0165] Ideally, the integrated logging tool collects field data in real time at a frequency of one second (or every few seconds) and stores it in a database. This alarm program monitors and analyzes the risk of stuck drill bit due to abnormal torque trends by extracting the latest data from the database. The required data includes time, well depth, drill bit position, rotational speed, torque, total pump stroke, standpipe pressure, and drill pressure, etc., and their data types are shown in Table 1. Table 1 shows a real-time data type table provided by an embodiment of the present invention:

[0166] Table 1

[0167]

[0168] During data acquisition and transmission, factors such as on-site equipment malfunctions and human error may lead to incomplete, abnormal, or duplicate data. To ensure data quality, the following processing strategies can be adopted:

[0169] 1. Handling Duplicate and Outlier Values: Duplicate values ​​and outliers with minimal impact on the results can be directly removed to simplify the dataset and improve analysis efficiency. Outliers that may affect the analysis results can be treated as missing values, and appropriate imputation methods can be used to maintain data continuity. Common imputation methods include weighted imputation, mean imputation, linear imputation, and nearest neighbor imputation.

[0170] 2. Data Unit Standardization: In view of the large variety of logging instruments and inconsistent data units, standardization and unification are carried out to ensure data consistency and comparability, thereby providing a reliable data foundation for subsequent analysis.

[0171] (II) Constructing an intelligent alarm method for card block risk based on continuous monitoring and analysis of abnormal torque trends:

[0172] For the abnormal torque trend blocking risk alarm model, the judgment method is to make judgments through business logic, replacing experts to perform real-time monitoring. Once the risk of blocking is detected, an alarm message is issued to warn.

[0173] Figure 3 This is a specific example diagram of an intelligent alarm model for abnormal torque trend and card risk in an embodiment of the present invention, as shown in the figure. Figure 3 As shown: The judgment order of the business model is slightly different from the above figure. The detailed business model process of the intelligent alarm model for card blocking risk based on continuous monitoring and analysis of abnormal torque trends is as follows:

[0174] 1. The operating conditions are always in a cyclical state:

[0175] Within the interval [t-13,t], the operating condition must always be in a cyclic state (i.e., pump speed 1, pump speed 2, or pump speed 3 must always be >1 and stand pressure SPP > 1MPa). This is to ensure that the drilling fluid flow and pressure are relatively stable under cyclic conditions, which helps to collect more stable and continuous torque data. If the operating conditions are not fixed, such as during tripping, running, or other non-cyclic states, the drilling fluid flow and pressure will fluctuate due to operational changes, which may mask or interfere with the judgment of torque anomalies. Furthermore, under cyclic conditions, the continuous flow of drilling fluid helps to reduce the impact of changes in drilling fluid properties (such as viscosity and density) on torque measurement. Therefore, this analysis can only be performed under consistently cyclic operating conditions.

[0176] 2. Perform torque trend anomaly analysis:

[0177] (1) Establish a "Current Torque Trend Database":

[0178] A sliding window analysis is performed from the current time t towards the shallow well section. The rotational speed, torque, total pump stroke, stand pressure, and drilling pressure are recorded from the current time t to 3 minutes prior (t-3). The arithmetic mean of these five data points is calculated, and the current arithmetic mean of rotational speed is denoted as RPM1, the current arithmetic mean of torque as Tor1, the current arithmetic mean of total pump stroke as Pumptotal1, the current arithmetic mean of stand pressure as SPP1, and the current arithmetic mean of drilling pressure as WOB1, forming the "current torque trend database".

[0179] (2) Establish a "standard torque trend database":

[0180] A sliding window analysis was performed from time t-3 towards the shallow well section. The rotational speed, torque, total pump stroke, stand pressure, and drilling pressure were recorded from time t-3 to the previous 8 minutes (time t-8). The arithmetic mean of these five data points was calculated, and the standard rotational speed arithmetic mean was denoted as RPM2, the standard torque arithmetic mean as Tor2, the standard total pump stroke arithmetic mean as Pumptotal2, the standard stand pressure arithmetic mean as SPP2, and the standard drilling pressure arithmetic mean as WOB2, forming a "standard torque trend database".

[0181] (3) Compare the magnitudes of the "current torque trend" and the "standard torque trend":

[0182] Monitor whether the following conditions exist within the interval [t-8,t]: current speed arithmetic mean RPM1 - standard speed arithmetic mean RPM2 < 2.5, current torque arithmetic mean Tor1 - standard torque arithmetic mean Tor2 > 3 kN.m, current total pump arithmetic mean Pumptotal1 - standard total pump arithmetic mean Pumptotal2 < 3, current stand pressure arithmetic mean SPP1 - standard stand pressure arithmetic mean SPP2 > 1.5 MPa, and current drill pressure arithmetic mean WOB1 - standard drill pressure arithmetic mean WOB2 < 10 kN. That is, RPM1 - RPM2 < 2.5, Tor1 - Tor2 > 3 kN.m, Pumptotal1 - Pumptotal2 < 3, SPP1 - SPP2 > 1.5 MPa, and WOB1 - WOB2 < 10 kN.

[0183] This setting is based on the fact that if the torque trend increases abnormally, or is accompanied by an increase in vertical pressure, or is accompanied by an abnormal point in the torque when the rotation speed and pump flow are basically stable, it indicates that the drill bit is prone to jamming at this position, indicating a high risk of drilling jamming.

[0184] 3. When conditions 1 and 2 are met simultaneously, the alarm time, well depth at the alarm time, drill bit position, and other data will be provided to the front end for display, and a stuck-out risk alarm will be issued. The alarm message will be described as "Abnormal torque trend, be aware of the risk of stuck-out." Furthermore, it is required that once this type of stuck-out risk alarm is issued, it will not be issued again within 4 hours.

[0185] (III) Storage and display of card blocking alarm information:

[0186] The alarm information is stored in the blockage case database. The backend developers develop a query interface, and the frontend calls the interface to display the alarm information on the page, which facilitates engineering technicians to formulate targeted drilling disposal measures.

[0187] Here is an application example of the second specific embodiment:

[0188] (1) Figure 4 This is a specific example diagram of a cyclic state condition verification in an embodiment of the present invention, as shown below. Figure 4 As shown, the limited operating conditions are always in a cyclical state:

[0189] Using the current time, 2024-07-03 16:15:32, as a marker, looking back over the 13-minute period from 2024-07-03 16:02:32 to 2024-07-03 16:15:32, if pump1 = 83 > 1 or pump2 = 83 > 1 and the stand pressure SPP > 1 MPa, then the drilling fluid is in circulation condition.

[0190] (2) Figure 5 This is a specific example diagram of drilling parameter analysis in an embodiment of the present invention, such as... Figure 5 As shown, establish a "Current Torque Trend Database":

[0191] Using the current time, 2024-07-03 16:15:32, as a marker, review the 3-minute period from 2024-07-03 16:12:32 to 2024-07-03 16:15:32, and record the speed, torque, total pump speed, and stand pressure data within this interval. The arithmetic mean of speed RPM1 is calculated to be 69, the arithmetic mean of torque Tor1 is 27.6, the arithmetic mean of total pump speed PumpTotal1 is 166, the arithmetic mean of stand pressure SPP1 is 31.2, and the arithmetic mean of drill pressure WOB1 is 0.

[0192] (3) Figure 6 This is a specific example diagram of drilling parameter analysis in an embodiment of the present invention, such as... Figure 6 As shown, a "standard torque trend database" is established:

[0193] Using 2024-07-03 16:12:32 as the marker, review the 8-minute period from 2024-07-03 16:07:32 to 2024-07-03 16:12:32, and record the speed, torque, total pump speed, and stand pressure data within this interval. The arithmetic mean of speed RPM2 is calculated to be 70, the arithmetic mean of torque Tor2 is 17.9, the arithmetic mean of total pump speed PumpTotal2 is 166, the arithmetic mean of stand pressure SPP2 is 27.7, and the arithmetic mean of drill pressure WOB2 is 0.

[0194] (4) Compare the magnitudes of the "current torque trend" and the "standard torque trend":

[0195] Comparing the "Current Torque Trend" with the "Standard Torque Trend," the arithmetic mean of the current speed (RPM1) minus the arithmetic mean of the standard speed (RPM2) within the monitoring period from 16:07:32 to 16:15:32 on 2024-07-03 is: 69 - 70 = -1 < 2.5; the arithmetic mean of the current torque (Tor1) minus the arithmetic mean of the standard torque (Tor2) is: 27.6 - 17.9 = 9.7 > 3 kN.m; and the arithmetic mean of the current total pump charge (PumpTotal1) minus the arithmetic mean of the standard total pump charge (Pu) is: The total drill bit pressure (MPP2) is calculated as follows: MPP1 - MPP2 = 166 - 166 = 0 < 3. The arithmetic mean of current standpipe pressure (SPP1) - the arithmetic mean of standard standpipe pressure (SPP2) = 31.2 - 27.7 = 3.5 > 1.5 MPa. The arithmetic mean of current drilling pressure (WOB1) - the arithmetic mean of standard drilling pressure (WOB2) = 0 - 0 = 0 < 10 kN. Therefore, RPM1 - RPM2 < 2.5, Tor1 - Tor2 > 3 kN.m, total drill bit pressure (Pump1) - total drill bit pressure (Pump2) < 3, SPP1 - SPP2 > 1.5 MPa, and WOB1 - WOB2 < 10 kN. This indicates that under relatively stable rotational speed and pump stroke conditions, the torque trend is abnormally increasing, accompanied by an increase in standpipe pressure. The drill bit is prone to sticking at this position, indicating a high risk of drilling sticking, and a sticking risk warning is issued.

[0196] (5) Send a card blocking alarm message:

[0197] The alarm interface is shown in Table 2, which is an alarm interface display table provided by an embodiment of the present invention:

[0198] Table 2

[0199]

[0200] The embodiments of the present invention have the following technical effects:

[0201] 1. Improved accuracy and timeliness of alarms: The intelligent alarm method for stuck drill risk based on continuous monitoring and analysis of abnormal torque trends, through the fusion of mechanism models and data analysis, can monitor torque change trends in real time. Once an abnormal increase or fluctuation is detected, an alarm can be issued immediately, giving operators enough time to take measures to avoid accidents such as stuck drill and secondary accidents, reduce long downtime caused by stuck drill, thereby reducing the additional time and costs incurred in handling accidents and ensuring the safety of drilling operations.

[0202] 2. Enhanced Model Intelligence and Automation: Real-time data acquisition using integrated logging tools and intelligent algorithms for data processing enables comprehensive, 24 / 7 monitoring of the drilling process. This intelligent monitoring method not only reduces reliance on manual labor and alleviates the workload of operators, but also provides timely guidance to help them adjust drilling optimization measures, thereby reducing the probability of accidents and ultimately improving drilling efficiency.

[0203] Of course, it is understood that there may be other variations of the above detailed process, and all such variations should fall within the protection scope of this invention.

[0204] In this embodiment of the invention, drilling parameters are acquired in real time; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure; based on the drilling parameters, it is determined whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter continuously exceeding a first stroke speed threshold and the standpipe pressure continuously exceeding a first pressure threshold; features of the current time window and features of the reference time window are extracted; the arithmetic mean of each drilling parameter within the current time window is calculated as the current feature; the arithmetic mean of each drilling parameter within the reference time window is calculated as the reference feature; based on the calculated current feature and reference feature, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions; when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, a jamming risk alarm is generated. This invention, through cyclic state operating condition analysis, eliminates interference from non-cyclic states, ensuring the stability of the monitoring environment and avoiding invalid analysis. It establishes a dual-time-window dynamic comparison mechanism, extracting data from the current window and the baseline window, calculating the arithmetic mean of parameters such as rotational speed and torque, and generating a feature set reflecting real-time changes and historical benchmarks. This enables early anomaly detection of jamming risks, solving the lag problem of traditional threshold monitoring. Furthermore, it establishes a multi-parameter collaborative verification system, jointly determining conditions such as torque mean exceeding the threshold, accompanying increase in vertical pressure, and rotational speed / drilling pressure fluctuation tolerance, automatically generating alarm information. This significantly improves the efficiency and accuracy of intelligent jamming risk analysis and reduces the false alarm rate of jamming risks.

[0205] This invention also provides a smart card blocking risk analysis device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to the smart card blocking risk analysis method, the implementation of this device can refer to the implementation of the smart card blocking risk analysis method; repeated details will not be elaborated further.

[0206] This invention also provides an intelligent analysis device for card blocking risks, which improves the efficiency and accuracy of intelligent analysis of card blocking risks and reduces the false alarm rate of card blocking risks. Figure 7 This is a schematic diagram of the structure of a smart card risk analysis device according to an embodiment of the present invention, as shown below. Figure 7 As shown, the device includes:

[0207] The drilling parameter acquisition module 701 is used to acquire drilling parameters in real time; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke and drilling pressure;

[0208] The cycle state determination module 702 is used to determine whether the working condition is in a cycle state within a predetermined time period before the current moment based on the drilling parameters; the cycle state is defined as the pump stroke parameter being continuously greater than a first stroke speed threshold and the vertical pressure being continuously greater than a first pressure threshold.

[0209] The feature extraction module 703 is used to extract features of the current time window and features of the reference time window; calculate the arithmetic mean of each drilling parameter in the current time window as the current feature; and calculate the arithmetic mean of each drilling parameter in the reference time window as the reference feature.

[0210] The continuous monitoring and analysis module 704 is used to continuously monitor and analyze the torque trend anomalies of multiple drilling parameters and corresponding preset thresholds based on the calculated current features and baseline features, and to determine whether each drilling parameter meets the corresponding parameter conditions.

[0211] The alarm information generation module 705 is used to generate a blockage risk alarm information when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles.

[0212] In one embodiment, the loop state determination module is specifically used for:

[0213] Using the current moment as the reference point, trace back the first preset time interval as the verification period;

[0214] The verification period is divided into multiple sub-windows of equal length. For each sub-window, it is determined whether the corresponding pumping parameters are continuously greater than the first pumping speed threshold and whether the vertical pressure is continuously greater than the first pressure threshold.

[0215] If the pump parameters corresponding to more than a preset number of sub-windows are continuously greater than the first pump speed threshold and the vertical pressure is continuously greater than the first pressure threshold, determine whether the working condition is in a cyclic state within the predetermined time period before the current moment.

[0216] In one embodiment, the feature extraction module is specifically used for:

[0217] Using the current moment as the time reference point, extract the drilling parameter time series data within the first predetermined time interval;

[0218] The arithmetic mean values ​​of the measured values ​​of rotational speed, torque, stand pressure, pump stroke, and drilling pressure in the time series data of drilling parameters collected within the interval are calculated to obtain the current average values ​​of rotational speed, torque, stand pressure, pump stroke, and drilling pressure, forming the characteristics of the current time window that reflects the real-time changes in operating conditions.

[0219] In one embodiment, the current time window is a time interval from the current moment back to a first predetermined duration; the reference time window is a time interval from the current moment back to a second predetermined duration to a third predetermined duration; and the well depth difference between the reference time window and the current time window is less than a predetermined depth tolerance.

[0220] In one embodiment, the feature extraction module is specifically used for:

[0221] Extract drilling parameter time series data within a continuous interval from the second to the third predetermined time period before the current moment;

[0222] While ensuring that the difference between the measured well depth at the start and end points of the interval is less than the preset depth tolerance, the average reference rotational speed, average reference torque, average reference stand pressure, average reference pump stroke, and average reference drilling pressure of different drilling parameter time series data are calculated to form the characteristics of the reference time window that characterizes the historical stable state.

[0223] In one embodiment, the parameter conditions include one or any combination of the following: the arithmetic mean of torque increases by more than a torque threshold, the arithmetic mean of stand pressure increases by more than a stand pressure threshold, the arithmetic mean of rotational speed changes by less than a rotational speed tolerance threshold, the arithmetic mean of pump stroke changes by less than a pump stroke tolerance threshold, and the arithmetic mean of drilling pressure changes by less than a drilling pressure tolerance threshold.

[0224] In one embodiment, the continuous monitoring and analysis module is specifically used for:

[0225] Continuous monitoring and analysis of torque trend anomalies were performed on multiple drilling parameters and corresponding preset thresholds to determine whether the following conditions were met:

[0226] The difference between the current arithmetic mean of torque and the baseline arithmetic mean of torque exceeds the torque change threshold;

[0227] The difference between the current arithmetic mean of vertical pressure and the benchmark arithmetic mean of vertical pressure exceeds the vertical pressure change threshold, or when the vertical pressure data is invalid, the difference between the current arithmetic mean of total pump stroke and the benchmark arithmetic mean of total pump stroke is less than the pump stroke tolerance threshold.

[0228] The absolute value of the difference between the current arithmetic mean of rotational speed and the reference arithmetic mean of rotational speed is less than the rotational speed tolerance threshold, or when the rotational speed is zero, the absolute value of the difference between the current arithmetic mean of drilling pressure and the reference arithmetic mean of drilling pressure is less than the drilling pressure tolerance threshold.

[0229] In one embodiment, a preprocessing module is further included for:

[0230] The collected drilling parameters are preprocessed; the preprocessing includes data cleaning, unit standardization, and missing value imputation.

[0231] Based on the drilling parameters, determine whether the operating conditions are in a cyclical state within a predetermined time period prior to the current moment, including:

[0232] Based on the pre-processed drilling parameters, determine whether the working conditions are in a cyclic state within the predetermined time period before the current moment.

[0233] In one embodiment, the drilling parameter acquisition module is specifically used for:

[0234] The system continuously acquires engineering parameter measurements of rotational speed, torque, stand pressure, pump pressure, and drilling pressure at a frequency of up to one second, and simultaneously records timestamps and well depth data.

[0235] A dynamic data stream is formed; this data stream is transmitted to the database for storage in real time in the form of a time series.

[0236] This invention provides an embodiment of a computer device for implementing all or part of the above-described intelligent analysis method for card blocking risks. The computer device specifically includes the following components:

[0237] The computer device comprises a processor, memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between related devices; the computer device can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the computer device can be implemented with reference to the embodiments for implementing the intelligent analysis method for card blocking risks and the embodiments for implementing the intelligent analysis device for card blocking risks, the contents of which are incorporated herein by reference, and repeated details will not be described again.

[0238] Figure 8This is a schematic diagram of a computer device provided in an embodiment of the present invention, which discloses a schematic block diagram of the system configuration of a computer device 1000 according to an embodiment of this application. Figure 8 As shown, the computer device 1000 may include a central processing unit 1001 and a memory 1002; the memory 1002 is coupled to the central processing unit 1001. It is worth noting that... Figure 8 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0239] In one embodiment, the card blocking risk intelligent analysis function can be integrated into the central processing unit 1001. The central processing unit 1001 can be configured to perform the following control:

[0240] Real-time acquisition of drilling parameters; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure;

[0241] Based on the drilling parameters, determine whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter being continuously greater than the first stroke speed threshold and the stand pressure being continuously greater than the first pressure threshold.

[0242] Extract features from the current time window and the baseline time window; calculate the arithmetic mean of each drilling parameter within the current time window as the current feature; calculate the arithmetic mean of each drilling parameter within the baseline time window as the baseline feature;

[0243] Based on the calculated current and baseline characteristics, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and their corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions.

[0244] When it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, a blockage risk alarm message is generated.

[0245] In another embodiment, the card blocking risk intelligent analysis device can be configured separately from the central processing unit 1001. For example, the card blocking risk intelligent analysis device can be configured as a chip connected to the central processing unit 1001, and the card blocking risk intelligent analysis function can be realized through the control of the central processing unit.

[0246] like Figure 8 As shown, the computer device 1000 may further include: a communication module 1003, an input unit 1004, an audio processor 1005, a display 1006, and a power supply 1007. It is worth noting that the computer device 1000 does not necessarily need to include... Figure 8 All components shown; in addition, the computer device 1000 may also include Figure 8For components not shown, please refer to existing technologies.

[0247] like Figure 8 As shown, the central processing unit 1001, sometimes also referred to as a controller or operation control, may include a microprocessor or other processor device and / or logic device. The central processing unit 1001 receives input and controls the operation of various components of the computer device 1000.

[0248] The memory 1002 may be, for example, one or more of a cache, flash memory, hard drive, removable medium, volatile memory, non-volatile memory, or other suitable device. It can store the aforementioned device-related information, and may also store programs for executing that information. The central processing unit 1001 can execute the program stored in the memory 1002 to perform information storage or processing, etc.

[0249] Input unit 1004 provides input to central processing unit 1001. This input unit 1004 may be, for example, a keypad or touch input device. Power supply 1007 provides power to computer device 1000. Display 1006 displays images, text, and other display objects. This display may be, for example, an LCD display, but is not limited to this.

[0250] The memory 1002 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs, etc. The memory 1002 can also be some other type of device. The memory 1002 includes a buffer memory 1021 (sometimes referred to as a buffer). The memory 1002 may include an application / function storage unit 1022 for storing application programs and function programs or processes for executing operations of the computer device 1000 via the central processing unit 1001.

[0251] The memory 1002 may also include a data storage unit 1023 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the computer device. The driver storage unit 1024 of the memory 1002 may include various drivers for the computer device for communication functions and / or for performing other functions of the computer device (such as messaging applications, address book applications, etc.).

[0252] The communication module 1003 is a transmitter / receiver that transmits and receives signals via the antenna 1008. The communication module (transmitter / receiver) 1003 is coupled to the central processing unit 1001 to provide input signals and receive output signals, which is the same as in a conventional mobile communication terminal.

[0253] Based on different communication technologies, multiple communication modules 1003 can be configured in the same computer device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 1003 is also coupled to a speaker 1009 and a microphone 1010 via an audio processor 1005 to provide audio output via the speaker 1009 and receive audio input from the microphone 1010, thereby realizing typical telecommunications functions. The audio processor 1005 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 1005 is also coupled to a central processing unit 1001, enabling on-device recording via the microphone 1010 and on-device playback of stored sound via the speaker 1009.

[0254] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent analysis method for card blocking risks.

[0255] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described intelligent analysis method for card blocking risks.

[0256] In this embodiment of the invention, drilling parameters are acquired in real time; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure; based on the drilling parameters, it is determined whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter continuously exceeding a first stroke speed threshold and the standpipe pressure continuously exceeding a first pressure threshold; features of the current time window and features of the reference time window are extracted; the arithmetic mean of each drilling parameter within the current time window is calculated as the current feature; the arithmetic mean of each drilling parameter within the reference time window is calculated as the reference feature; based on the calculated current feature and reference feature, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions; when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, a jamming risk alarm is generated. This invention, through cyclic state operating condition analysis, eliminates interference from non-cyclic states, ensuring the stability of the monitoring environment and avoiding invalid analysis. It establishes a dual-time-window dynamic comparison mechanism, extracting data from the current window and the baseline window, calculating the arithmetic mean of parameters such as rotational speed and torque, and generating a feature set reflecting real-time changes and historical benchmarks. This enables early anomaly detection of jamming risks, solving the lag problem of traditional threshold monitoring. Furthermore, it establishes a multi-parameter collaborative verification system, jointly determining conditions such as torque mean exceeding the threshold, accompanying increase in vertical pressure, and rotational speed / drilling pressure fluctuation tolerance, automatically generating alarm information. This significantly improves the efficiency and accuracy of intelligent jamming risk analysis and reduces the false alarm rate of jamming risks.

[0257] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0258] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0259] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0260] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0261] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent analysis of card blocking risks, characterized in that, include: Real-time acquisition of drilling parameters; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure; Based on the drilling parameters, determine whether the operating conditions are in a cyclic state within a predetermined time period before the current moment; the cyclic state is defined as the pump stroke parameter being continuously greater than the first stroke speed threshold and the stand pressure being continuously greater than the first pressure threshold. Extract features from the current time window and the baseline time window; Calculate the arithmetic mean of all drilling parameters within the current time window as the current feature; The arithmetic mean of each drilling parameter within the baseline time window is used as the baseline feature; Based on the calculated current and baseline characteristics, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and their corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions. When it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles, a blockage risk alarm message is generated.

2. The method of claim 1, wherein, Based on the drilling parameters, determine whether the operating conditions are in a cyclical state within a predetermined time period prior to the current moment, including: Using the current moment as the reference point, trace back the first preset time interval as the verification period; The verification period is divided into multiple sub-windows of equal length. For each sub-window, it is determined whether the corresponding pumping parameters are continuously greater than the first pumping speed threshold and whether the vertical pressure is continuously greater than the first pressure threshold. If the pump parameters corresponding to more than a preset number of sub-windows are continuously greater than the first pump speed threshold and the vertical pressure is continuously greater than the first pressure threshold, determine whether the working condition is in a cyclic state within the predetermined time period before the current moment.

3. The method of claim 1, wherein, The current time window is the time interval from the current moment back to the first predetermined duration; the reference time window is the time interval from the current moment back to the second predetermined duration to the third predetermined duration. The difference in well depth between the reference time window and the current time window is less than the predetermined depth tolerance.

4. The method as described in claim 3, characterized in that, Extract features of the current time window, including: Using the current moment as the time reference point, extract the drilling parameter time series data within the first predetermined time interval; The arithmetic mean values ​​of the measured values ​​of rotational speed, torque, stand pressure, pump stroke, and drilling pressure in the time series data of drilling parameters collected within the interval are calculated to obtain the current average values ​​of rotational speed, torque, stand pressure, pump stroke, and drilling pressure, forming the characteristics of the current time window that reflects the real-time changes in operating conditions.

5. The method of claim 3, wherein, Extract features of the baseline time window, including: Extract drilling parameter time series data within a continuous interval from the second to the third predetermined time period before the current moment; While ensuring that the difference between the measured well depth at the start and end points of the interval is less than the preset depth tolerance, the average reference rotational speed, average reference torque, average reference stand pressure, average reference pump stroke, and average reference drilling pressure of different drilling parameter time series data are calculated to form the characteristics of the reference time window that characterizes the historical stable state.

6. The method of claim 1, wherein, The parameter conditions include one or any combination of the following: the arithmetic mean of torque increases by more than the torque threshold; the arithmetic mean of vertical pressure increases by more than the vertical pressure threshold; the change in the arithmetic mean of rotational speed is less than the rotational speed tolerance threshold; the change in the arithmetic mean of pump stroke is less than the pump stroke tolerance threshold; and the change in the arithmetic mean of drilling pressure is less than the drilling pressure tolerance threshold.

7. The method of claim 6, wherein, Based on calculated current and baseline characteristics, continuous monitoring and analysis of torque trend anomalies are performed on multiple drilling parameters and their corresponding preset thresholds to determine whether each drilling parameter meets the corresponding parameter conditions, including: Continuous monitoring and analysis of torque trend anomalies were performed on multiple drilling parameters and corresponding preset thresholds to determine whether the following conditions were met: The difference between the current arithmetic mean of torque and the baseline arithmetic mean of torque exceeds the torque change threshold; The difference between the current arithmetic mean of vertical pressure and the benchmark arithmetic mean of vertical pressure exceeds the vertical pressure change threshold, or when the vertical pressure data is invalid, the difference between the current arithmetic mean of total pump stroke and the benchmark arithmetic mean of total pump stroke is less than the pump stroke tolerance threshold. The absolute value of the difference between the current arithmetic mean of rotational speed and the reference arithmetic mean of rotational speed is less than the rotational speed tolerance threshold, or when the rotational speed is zero, the absolute value of the difference between the current arithmetic mean of drilling pressure and the reference arithmetic mean of drilling pressure is less than the drilling pressure tolerance threshold.

8. The method of claim 1, wherein, Also includes: The collected drilling parameters are preprocessed; the preprocessing includes data cleaning, unit standardization, and missing value imputation. Based on the drilling parameters, determine whether the operating conditions are in a cyclical state within a predetermined time period prior to the current moment, including: Based on the pre-processed drilling parameters, determine whether the working conditions are in a cyclic state within the predetermined time period before the current moment.

9. The method of claim 1, wherein, Real-time acquisition of drilling parameters, including: The system continuously acquires engineering parameter measurements of rotational speed, torque, stand pressure, pump pressure, and drilling pressure at a frequency of up to one second, and simultaneously records timestamps and well depth data. A dynamic data stream is formed; this data stream is transmitted to the database for storage in real time in the form of a time series.

10. A smart analysis device for card blocking risks, characterized in that, include: The drilling parameter acquisition module is used to acquire drilling parameters in real time; the drilling parameters include rotational speed, torque, standpipe pressure, pump stroke, and drilling pressure. The cycle state determination module is used to determine whether the working condition is in a cycle state within a predetermined time period before the current moment based on the drilling parameters; the cycle state is defined as the pump stroke parameter being continuously greater than a first stroke speed threshold and the vertical pressure being continuously greater than a first pressure threshold. The feature extraction module is used to extract features from the current time window and the baseline time window; Calculate the arithmetic mean of all drilling parameters within the current time window as the current feature; The arithmetic mean of each drilling parameter within the baseline time window is used as the baseline feature; The continuous monitoring and analysis module is used to continuously monitor and analyze torque trend anomalies for multiple drilling parameters and corresponding preset thresholds based on calculated current and baseline characteristics, and to determine whether each drilling parameter meets the corresponding parameter conditions. The alarm information generation module is used to generate a stuck risk alarm information when it is determined that each drilling parameter meets the corresponding parameter conditions in multiple consecutive detection cycles.

11. The apparatus as claimed in claim 10, characterized in that, The continuous monitoring and analysis module is specifically used for: Continuous monitoring and analysis of torque trend anomalies were performed on multiple drilling parameters and corresponding preset thresholds to determine whether the following conditions were met: The difference between the current arithmetic mean of torque and the baseline arithmetic mean of torque exceeds the torque change threshold; The difference between the current arithmetic mean of vertical pressure and the benchmark arithmetic mean of vertical pressure exceeds the vertical pressure change threshold, or when the vertical pressure data is invalid, the difference between the current arithmetic mean of total pump stroke and the benchmark arithmetic mean of total pump stroke is less than the pump stroke tolerance threshold. The absolute value of the difference between the current arithmetic mean of rotational speed and the reference arithmetic mean of rotational speed is less than the rotational speed tolerance threshold, or when the rotational speed is zero, the absolute value of the difference between the current arithmetic mean of drilling pressure and the reference arithmetic mean of drilling pressure is less than the drilling pressure tolerance threshold.

12. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 9.

13. 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 method of any one of claims 1 to 9.

14. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 9.

Images