Drilling and completion technology data multidimensional analysis and dynamic optimization method and system

Abstract

The present application relates to the technical field of remote monitoring, and discloses a method and system for multi-dimensional analysis and dynamic optimization of drilling and completion technology data, comprising: establishing a multi-dimensional data model of multi-source heterogeneous data; establishing a drilling and completion knowledge graph of a drilling and completion scene, analyzing potential correlation of the drilling and completion scene, and establishing a triple relationship network of the drilling and completion scene; outputting a risk factor and a factor correlation strength matrix of the drilling and completion scene, and calculating a risk probability matrix of the drilling and completion scene according to the risk factor, the factor correlation strength matrix and the multi-dimensional data model; generating a risk traceability report of the risk probability matrix to generate a drilling frontier solution set of the drilling and completion scene; simulating a borehole trajectory and equipment load of the drilling frontier solution set to analyze an optimization coefficient of the drilling frontier solution set, and determining a drilling target solution of the drilling and completion scene according to the optimization coefficient to perform dynamic optimization of the drilling and completion scene. The present application can improve drilling efficiency of the drilling and completion scene.

Description

Technical Field

[0001] This invention relates to a method and system for multidimensional analysis and dynamic optimization of drilling and completion technology data, belonging to the field of remote monitoring technology. Background Technology

[0002] Multidimensional analysis and dynamic optimization of drilling and completion technology data refers to a technical system that uses data science, artificial intelligence, petroleum engineering and other methods to deeply mine, correlate and optimize multi-source, multi-dimensional and dynamic data generated throughout the entire life cycle of drilling and completion, so as to improve operational efficiency, reduce engineering risks and optimize cost control.

[0003] Traditional methods of multidimensional analysis and dynamic optimization of drilling and completion data mainly rely on engineers' experience and static analysis of isolated data sources. For example, potential risks are identified by reviewing historical reports, two-dimensional charts, and single-well logging curves, and operations are carried out based on preset and fixed drilling parameter schemes. This approach cannot establish deep correlations and quantitative impacts between data, and lacks the ability to make global predictions and proactive responses to complex downhole conditions, resulting in low drilling efficiency. Summary of the Invention

[0004] This invention provides a method and system for multidimensional analysis and dynamic optimization of drilling and completion technology data, the main purpose of which is to improve drilling efficiency in drilling and completion scenarios.

[0005] To achieve the above objectives, the present invention provides a method for multidimensional analysis and dynamic optimization of drilling and completion technology data, comprising:

[0006] Acquire multi-source heterogeneous data from drilling and completion scenarios, determine a unified spatiotemporal reference for the multi-source heterogeneous data, and establish a multi-dimensional data model for the multi-source heterogeneous data.

[0007] Establish a drilling and completion knowledge graph for the drilling and completion scenarios, and based on the drilling and completion knowledge graph, analyze the potential relationships between the drilling and completion scenarios to establish a triplet relationship network for the drilling and completion scenarios.

[0008] The risk factors and factor correlation strength matrix of the drilling and completion scenario are output through the triplet relationship network, and the risk probability matrix of the drilling and completion scenario is calculated based on the risk factors, the factor correlation strength matrix and the multidimensional data model.

[0009] A risk tracing report is generated to produce the risk probability matrix, thereby generating the drilling front solution set for the drilling and completion scenario;

[0010] The wellbore trajectory and equipment load of the drilling front solution set are simulated to analyze the optimization coefficients of the drilling front solution set. Based on the optimization coefficients, the drilling target solution of the drilling and completion scenario is determined to perform dynamic optimization of the drilling and completion scenario.

[0011] Optionally, establishing a multidimensional data model for the multi-source heterogeneous data includes:

[0012] Based on the unified spatiotemporal reference of the multi-source heterogeneous data, the multi-source heterogeneous data is time-aligned to obtain aligned multi-source heterogeneous data.

[0013] The spatial coordinates of the aligned multi-source heterogeneous data are then unified to obtain unified multi-source heterogeneous data.

[0014] Frequency synchronization is performed on the unified multi-source heterogeneous data to obtain synchronized multi-source heterogeneous data.

[0015] Establish the dimension axis of the synchronized multi-source heterogeneous data, wherein the dimension axis includes a required dimension and an extended dimension;

[0016] Based on the dimension axis, a multidimensional data model of the synchronous multi-source heterogeneous data is established.

[0017] Optionally, the step of analyzing the potential relationships between drilling and completion scenarios based on the drilling and completion knowledge graph includes:

[0018] Extract the entity association paths and multi-hop relationships from the drilling and completion knowledge graph;

[0019] Map the entity association paths and multi-hop relationships to entity embedding vectors;

[0020] Calculate the entity similarity of the entity embedding vectors;

[0021] Based on the entity similarity, determine the similar entities of the entity embedding vector;

[0022] Based on the similar entities, the entity association paths, and the multi-hop relationships, the potential associations of the drilling and completion scenarios are determined.

[0023] Optionally, establishing the triplet relationship network for the drilling and completion scenario includes:

[0024] Define the triplet structure for the drilling and completion scenario;

[0025] Determine the entity type and core entity relationship of the triple structure;

[0026] Based on the entity type and core entity relationship, the potential association relationship of the drilling and completion scenario is used to generate triples for the drilling and completion scenario, wherein the triples include explicit relation triples, potential relation triples and attribute triples.

[0027] Calculate the triplet weights of the triplet;

[0028] Based on the triple weights, establish the triple relation network of the triples.

[0029] Optionally, the step of outputting the risk factors and factor correlation strength matrix of the drilling and completion scenario through the triplet relationship network includes:

[0030] Define the risk events in the drilling and completion scenario;

[0031] Based on the aforementioned risk events, the risk factor chain of the drilling and completion scenario is output using the triplet relationship network;

[0032] Based on the aforementioned risk factor chain, the risk factors for the drilling and completion scenario are determined.

[0033] Define the risk matrix dimensions for the drilling and completion scenario;

[0034] Calculate the correlation strength between the risk factor and the risk event;

[0035] Based on the correlation strength and risk matrix dimensions, a factor correlation strength matrix for the drilling and completion scenario is established.

[0036] Optionally, calculating the correlation strength between the risk factor and the risk event includes:

[0037] Analyze the base probability that the risk factors will lead to the risk event;

[0038] Define the accident loss of the aforementioned risk event;

[0039] The correlation strength between the risk factor and the risk event is calculated using the following formula, based on the base probability and the event loss:

[0040]

[0041] in, Indicates risk factors and risk incidents The strength of the association, Indicates risk factors Leading to risk incidents The base probability, The weighting coefficients represent the base probability. Indicates risk incident The accident losses, Indicates the loss normalization benchmark, This represents the weighting coefficient of the severity component. Indicates risk factors Leading to risk incidents Detectability score, The weighting coefficients representing the detectability score. Indicates risk factors Leading to risk incidents Real-time operating condition correction coefficient, This represents the weighting coefficient of the real-time operating condition correction coefficient.

[0042] Optionally, calculating the risk probability matrix of the drilling and completion scenario based on the risk factors, the factor correlation strength matrix, and the multidimensional data model includes:

[0043] Based on the multidimensional data model, calculate the degree of deviation of the risk factors;

[0044] The deviation degree is dynamically corrected using the factor correlation strength matrix to obtain a first corrected deviation degree.

[0045] The first correction deviation is corrected by multidimensional coupling to obtain the second correction deviation.

[0046] Based on the second correction deviation, the single accident probability of the drilling and completion scenario is calculated to calculate the risk probability matrix of the drilling and completion scenario.

[0047] Optionally, the step of performing multidimensional coupling correction on the first correction deviation to obtain the second correction deviation includes:

[0048] Analyze the geological risk coefficients of the drilling and completion scenarios corresponding to the degree of the first correction deviation;

[0049] Identify the equipment health status of the risk factor corresponding to the first degree of correction deviation;

[0050] Based on the geological risk coefficient and the equipment health status, the first correction deviation is adjusted by multidimensional coupling to obtain the second correction deviation.

[0051] Optionally, the simulation of the wellbore trajectory and equipment load of the drilling front solution set includes:

[0052] Establish a mechanical-geological coupling model for the drilling and completion scenario corresponding to the drilling front solution set;

[0053] Based on the drilling front solution set, calculate the lateral force of the drill bit corresponding to the drilling and completion scenario;

[0054] Based on the drill bit lateral force and the mechanical-geological coupling model, the drill bit trajectory coordinates of the drilling and completion scenario are output to determine the wellbore trajectory of the drilling front solution set;

[0055] Analyze the equipment load indicators in the drilling and completion scenario;

[0056] Based on the drilling front solution set and the equipment load index, the equipment load curve of the drilling and completion scenario is fitted to analyze the equipment load of the drilling and completion scenario.

[0057] To address the aforementioned problems, the present invention also provides a multi-dimensional analysis and dynamic optimization system for drilling and completion technology data, the system comprising:

[0058] The data model building module is used to acquire multi-source heterogeneous data from drilling and completion scenarios, determine a unified spatiotemporal benchmark for the multi-source heterogeneous data, and establish a multi-dimensional data model for the multi-source heterogeneous data.

[0059] The relational network construction module is used to establish a drilling and completion knowledge graph of the drilling and completion scenario, and based on the drilling and completion knowledge graph, analyze the potential relationships of the drilling and completion scenario to establish a triplet relational network of the drilling and completion scenario.

[0060] The risk probability analysis module is used to output the risk factors and factor correlation strength matrix of the drilling and completion scenario through the triplet relationship network, and to calculate the risk probability matrix of the drilling and completion scenario based on the risk factors, the factor correlation strength matrix and the multidimensional data model.

[0061] The frontier solution set determination module is used to generate a risk tracing report of the risk probability matrix, so as to generate the drilling frontier solution set of the drilling and completion scenario;

[0062] The drilling and completion dynamic optimization module is used to simulate the wellbore trajectory and equipment load of the drilling front solution set, analyze the optimization coefficients of the drilling front solution set, and determine the drilling target solution of the drilling and completion scenario based on the optimization coefficients, so as to perform dynamic optimization of the drilling and completion scenario.

[0063] First, by constructing a unified spatiotemporal benchmark and multidimensional data model for multi-source heterogeneous data in drilling and completion scenarios, deep integration and efficient organization of geological, engineering, and equipment data were achieved, laying a solid data foundation for subsequent analysis. Based on this, a drilling and completion knowledge graph was established and potential relationships were mined, constructing a triplet relationship network. This network effectively reveals the deep logic and causal mechanisms between data, significantly improving the accuracy and comprehensiveness of risk identification. Through this network, risk factors and factor correlation strength matrices are output. Combined with the multidimensional data model, a risk probability matrix is ​​calculated, enabling a quantitative assessment of potential risks during the drilling and completion process. Compared to dynamic prediction, this method significantly outperforms traditional experience-driven static analysis methods. The risk source tracing report generated based on the risk probability matrix can accurately pinpoint the source of risk, providing a scientific basis for decision-making. Simultaneously, it generates a drilling front solution set, and by combining wellbore trajectory and equipment load simulation analysis to optimize coefficients, it further selects the optimal drilling target solution, achieving dynamic optimization and intelligent adjustment of drilling parameters. Overall, this solution not only significantly improves the safety, efficiency, and economy of drilling and completion operations but also promotes the transformation of the drilling and completion process towards intelligence, data-driven approaches, and precise decision-making, providing strong technical support for the efficient development of oil and gas fields. Therefore, this invention can improve drilling efficiency in drilling and completion scenarios. Attached Figure Description

[0064] Figure 1 This is a flowchart illustrating a method for multidimensional analysis and dynamic optimization of drilling and completion technical data according to an embodiment of the present invention.

[0065] Figure 2 This is a schematic diagram of a module for implementing the multidimensional analysis and dynamic optimization method for drilling and completion technical data according to an embodiment of the present invention.

[0066] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0067] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0068] This application provides a method for multi-dimensional analysis and dynamic optimization of drilling and completion technical data. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0069] Reference Figure 1The diagram shown is a flowchart illustrating a method for multidimensional analysis and dynamic optimization of drilling and completion technology data according to an embodiment of the present invention. In this embodiment, the method includes:

[0070] S1. Acquire multi-source heterogeneous data of drilling and completion scenarios, determine a unified spatiotemporal reference for the multi-source heterogeneous data, and establish a multi-dimensional data model of the multi-source heterogeneous data.

[0071] It should be explained that the drilling and completion scenario refers to the overall operational stages, working conditions, and technical challenges involved in the entire process of oil and gas exploration and development, from drilling to completion. The multi-source heterogeneous data refers to the diverse data generated from different sources, in different formats and structures within the drilling and completion scenario. This includes geological data, engineering data, equipment data, and other data.

[0072] This invention establishes a unified spatiotemporal benchmark for the multi-source heterogeneous data, thereby building a multidimensional data model of the multi-source heterogeneous data. This enables the deep fusion and efficient organization of geological, engineering, and equipment data, laying a solid data foundation for subsequent analysis.

[0073] In detail, establishing the multidimensional data model of the multi-source heterogeneous data includes:

[0074] Based on the unified spatiotemporal reference of the multi-source heterogeneous data, the multi-source heterogeneous data is time-aligned to obtain aligned multi-source heterogeneous data.

[0075] The spatial coordinates of the aligned multi-source heterogeneous data are then unified to obtain unified multi-source heterogeneous data.

[0076] Frequency synchronization is performed on the unified multi-source heterogeneous data to obtain synchronized multi-source heterogeneous data.

[0077] Establish the dimension axes of the synchronized multi-source heterogeneous data, wherein the dimension axes include mandatory dimensions and extended dimensions;

[0078] Based on the dimension axis, a multidimensional data model of the synchronous multi-source heterogeneous data is established.

[0079] The unified spatiotemporal reference refers to a set of standardized rules used to integrate the time reference system and spatial coordinate system of multi-source data. The aligned multi-source heterogeneous data refers to intermediate data that has completed time reference unification but has not yet processed spatial differences. The unified multi-source heterogeneous data refers to data that has completed spatial coordinate transformation based on time alignment. The synchronized multi-source heterogeneous data refers to data that further resolves sampling frequency differences after spatiotemporal unification. The required dimensions refer to the basic dimensions that must be included in the multidimensional data model, including time and space. The extended dimensions refer to auxiliary dimensions that are dynamically added according to analysis needs, including geological strata, equipment status, and environmental parameters. The multidimensional data model refers to a structured data organization method with dimension axes and fact tables as the core.

[0080] Optionally, performing time alignment on the multi-source heterogeneous data to obtain aligned multi-source heterogeneous data can convert the timestamps of the multi-source heterogeneous data sources into the ISO 8601 standard format.

[0081] Optionally, the spatial coordinates of the aligned multi-source heterogeneous data are unified to obtain the geological data (such as the XYZ coordinates of seismic interpretation) in the unified multi-source heterogeneous data → the data is unified by transforming it to the wellbore coordinate system through a rotation and translation matrix. The equipment data can be unified by calculating the relative position based on the wellbore trajectory model.

[0082] S2. Establish a drilling and completion knowledge graph for the drilling and completion scenarios, and based on the drilling and completion knowledge graph, analyze the potential relationships of the drilling and completion scenarios to establish a triplet relationship network for the drilling and completion scenarios.

[0083] This invention establishes a drilling and completion knowledge graph for the drilling and completion scenario, providing a foundation for subsequent risk analysis. The drilling and completion knowledge graph is a domain knowledge base organized in a structured triplet format (entity-relationship-entity / attribute), used to describe parameters, events, rules, and causal relationships throughout the drilling and completion process. Specifically, the drilling and completion knowledge graph can be constructed and stored using Neo4j for the drilling and completion knowledge domain data.

[0084] Based on the drilling and completion knowledge graph, this invention analyzes the potential relationships between drilling and completion scenarios to provide a basis for the subsequent construction of a triplet relationship network, thereby improving the accuracy of drilling and completion site analysis.

[0085] In detail, the analysis of potential correlations among drilling and completion scenarios based on the drilling and completion knowledge graph includes:

[0086] Extract the entity association paths and multi-hop relationships from the drilling and completion knowledge graph;

[0087] Map the entity association paths and multi-hop relationships to entity embedding vectors;

[0088] Calculate the entity similarity of the entity embedding vectors;

[0089] Based on the entity similarity, determine the similar entities of the entity embedding vector;

[0090] Based on the similar entities, the entity association paths, and the multi-hop relationships, the potential associations of the drilling and completion scenarios are determined.

[0091] In this context, the entity association path refers to a sequential chain in a knowledge graph consisting of a series of entities directly or indirectly connected by relationships, representing the logical or physical association between entities. The multi-hop relationship refers to the indirect association between entities connected by two or more consecutive relationships, revealing the potential interaction between non-directly connected entities. The entity embedding vector refers to the numerical representation of entities in the knowledge graph mapped to a low-dimensional continuous vector space, preserving the semantic and structural relationships between entities. The entity similarity refers to the degree of semantic or functional similarity between entities calculated through the embedding vector. The similar entities refer to entities that are close in distance (similarity higher than a threshold) in the embedding space. The potential association relationship refers to the implicit relationship that is not explicitly defined in the knowledge graph but is inferred through path reasoning or similarity analysis.

[0092] Optionally, the mapping of the entity association path and multi-hop relationship into entity embedding vectors can be achieved using algorithms such as TransE and GraphSAGE.

[0093] Optionally, the entity similarity of the entity embedding vector can be calculated using cosine similarity.

[0094] This invention establishes a ternary relationship network for the drilling and completion scenario, which can effectively reveal the deep logic and causal mechanism between data, and significantly improve the accuracy and comprehensiveness of risk identification.

[0095] Specifically, establishing the triplet relationship network for the drilling and completion scenario includes:

[0096] Define the triplet structure for the drilling and completion scenario;

[0097] Determine the entity type and core entity relationship of the triple structure;

[0098] Based on the entity type and core entity relationship, the potential association relationship of the drilling and completion scenario is used to generate triples for the drilling and completion scenario, wherein the triples include explicit relation triples, potential relation triples and attribute triples.

[0099] Calculate the triplet weights of the triplet;

[0100] Based on the triplet weights, a triplet relationship network is established for the triplets.

[0101] The triplet structure refers to the smallest logical unit representing knowledge, an atomic assertion consisting of three components. The entity type refers to the classification system of objects in the drilling and completion domain, determining the semantic role of an entity in the knowledge network, such as geological entities, engineering entities, and equipment entities. The core entity relationship refers to the set of basic semantic relationships describing the interaction between entities, such as relationships like cause, need, location, and recommendation. The explicit relationship triplet refers to verified relationships extracted directly from structured data or expert rules. The potential relationship triplet refers to unrecorded relationships discovered through data analysis and similarity reasoning. The attribute triplet refers to feature assertions describing the instantaneous state of an entity. The triplet weight refers to a comprehensive score that quantifies the reliability of the relationship, used for conflict resolution and reasoning ranking. The triplet relationship network refers to a semantic network composed of a large number of interconnected triplets.

[0102] Optionally, the process of establishing the triplet relationship network based on the triplet weights can be achieved using a graph database schema.

[0103] S3. Output the risk factors and factor correlation strength matrix of the drilling and completion scenario through the triplet relationship network, and calculate the risk probability matrix of the drilling and completion scenario based on the risk factors, the factor correlation strength matrix and the multidimensional data model.

[0104] This invention uses the triplet relationship network to output the risk factors and factor correlation strength matrix of the drilling and completion scenario, and combines them with a multidimensional data model to calculate the risk probability matrix, thereby realizing the quantitative assessment and dynamic prediction of potential risks during the drilling and completion process.

[0105] Specifically, the step of outputting the risk factors and factor correlation strength matrix of the drilling and completion scenario through the triplet relationship network includes:

[0106] Define the risk events in the drilling and completion scenario;

[0107] Based on the aforementioned risk events, the risk factor chain of the drilling and completion scenario is output using the triplet relationship network;

[0108] Based on the aforementioned risk factor chain, the risk factors for the drilling and completion scenario are determined.

[0109] Define the risk matrix dimensions for the drilling and completion scenario;

[0110] Calculate the correlation strength between the risk factor and the risk event;

[0111] Based on the correlation strength and risk matrix dimensions, a factor correlation strength matrix for the drilling and completion scenario is established.

[0112] Wherein, the risk accident refers to an unexpected abnormal event that occurs during drilling or well completion operations, which may lead to personal injury, equipment damage or project delays; the risk factor chain refers to a path composed of multiple interrelated risk factors arranged in causal relationship or chronological order, ultimately leading to the risk accident; the risk factor refers to an engineering parameter that can be directly measured and has a significant impact on the accident; the risk matrix dimension refers to the three-dimensional structure of the matrix; the correlation strength refers to the degree of influence of the risk factor on the risk accident; and the factor correlation strength matrix refers to a weighted adjacency matrix that quantitatively describes the causal relationship between risk factors and risk accidents.

[0113] Further, calculating the correlation strength between the risk factor and the risk event includes:

[0114] Analyze the base probability that the risk factors will lead to the risk event;

[0115] Define the accident loss of the aforementioned risk event;

[0116] The correlation strength between the risk factor and the risk event is calculated using the base probability and the event loss.

[0117] Furthermore, as another embodiment of the present invention, the correlation strength is calculated using the following formula:

[0118]

[0119] in, Indicates risk factors and risk incidents The strength of the association, Indicates risk factors Leading to risk incidents The base probability, The weighting coefficients represent the base probability. Indicates risk incident The accident losses, Indicates the loss normalization benchmark. This represents the weighting coefficient of the severity component. Indicates risk factors Leading to risk incidents Detectability score The weighting coefficients representing the detectability score. Indicates risk factors Leading to risk incidents Real-time operating condition correction coefficient, This represents the weighting coefficient of the real-time operating condition correction coefficient.

[0120] Wherein, the basic probability refers to the historical statistical probability that risk factor i leads to accident j, the accident loss refers to the maximum economic loss that a single accident j may cause, the weighting coefficient of the basic probability refers to the importance of historical probability in the comprehensive assessment, and in this invention it can be 0.5, the loss normalization benchmark refers to the reference value that unifies losses of different magnitudes to a comparable range, the severity component weighting coefficient refers to the proportion of accident loss in the total score, and in this invention it can be 0.3, the detectability score refers to the ability to quantify the timely monitoring of risk factors, the weighting coefficient of the detectability score refers to the degree of influence of monitoring capability on overall risk, and in this invention it can be 0.15, the real-time operating condition correction coefficient refers to the instantaneous risk correction for the current over-limit operating condition, and the weighting coefficient of the real-time operating condition correction coefficient refers to the adjustment of real-time data on the overall intensity, and in this invention it can be 0.05.

[0121] The present invention calculates the risk probability matrix of the drilling and completion scenario based on the risk factors, the factor correlation strength matrix, and the multidimensional data model, which can improve the accuracy of risk analysis of the drilling and completion scenario.

[0122] Specifically, calculating the risk probability matrix of the drilling and completion scenario based on the risk factors, the factor correlation strength matrix, and the multidimensional data model includes:

[0123] Based on the multidimensional data model, calculate the degree of deviation of the risk factors;

[0124] The deviation degree is dynamically corrected using the factor correlation strength matrix to obtain a first corrected deviation degree.

[0125] The first correction deviation is corrected by multidimensional coupling to obtain the second correction deviation.

[0126] Based on the second correction deviation, the single accident probability of the drilling and completion scenario is calculated to calculate the risk probability matrix of the drilling and completion scenario.

[0127] Wherein, the degree of deviation refers to the relative deviation between the current value of the risk factor and the safety threshold; the first corrected degree of deviation refers to the result after preliminary weighted correction of the original degree of deviation through the correlation strength matrix; the second corrected degree of deviation refers to the result after multi-dimensional coupling of geological environment and equipment status; the single accident probability refers to the comprehensive probability estimate of the occurrence of a specific accident type; and the risk probability matrix refers to the decision matrix that quantifies the probability of all risk factor-accident combinations.

[0128] Optionally, the deviation of the risk factor based on the multidimensional data model can be calculated by the relative deviation between the current value of the risk factor and the safety threshold.

[0129] Further, the step of performing multi-dimensional coupling correction on the first correction deviation to obtain the second correction deviation includes:

[0130] Analyze the geological risk coefficients of the drilling and completion scenarios corresponding to the degree of the first correction deviation;

[0131] Identify the equipment health status of the risk factor corresponding to the first degree of correction deviation;

[0132] Based on the geological risk coefficient and the equipment health status, the first correction deviation is adjusted by multidimensional coupling to obtain the second correction deviation.

[0133] Furthermore, as another embodiment of the present invention, the second degree of correction deviation is calculated using the following formula:

[0134]

[0135] in, Indicates the degree of deviation of the second correction. Indicates the degree of deviation of the first correction. Indicates the geological risk coefficient. Indicates the health status of the device. This represents the health coupling coefficient.

[0136] The geological risk coefficient refers to a dimensionless parameter that quantifies the inherent influence of geological characteristics on accident risk; the equipment health refers to the degree of deviation between the current working state of the equipment and the ideal state; and the health coupling coefficient refers to the adjustment parameter that controls the impact of equipment health on the total risk.

[0137] S4. Generate a risk source report of the risk probability matrix to generate the drilling front solution set of the drilling and completion scenario.

[0138] This invention generates a risk tracing report based on the risk probability matrix, which, by generating a drilling front solution set for the drilling and completion scenario, can accurately locate the source of risk and provide a scientific basis for decision-making. The risk tracing report refers to an attribution analysis document based on the risk probability matrix, including documents such as root cause identification, path reconstruction, responsibility tracing, and remediation recommendations. The drilling front solution set refers to a Pareto optimal parameter combination generated through multi-objective optimization, including parameters such as weight on bit (WOB), rotational speed (RPM), flow rate, and mud weight.

[0139] S5. Simulate the wellbore trajectory and equipment load of the drilling front solution set to analyze the optimization coefficients of the drilling front solution set, and determine the drilling target solution of the drilling and completion scenario based on the optimization coefficients, so as to perform dynamic optimization of the drilling and completion scenario.

[0140] This invention simulates the wellbore trajectory and equipment load of the drilling front solution set, which can accurately analyze the optimization effect of the drilling front solution set and provide a basis for the optimization of subsequent drilling and completion scenarios.

[0141] Specifically, the simulation of the wellbore trajectory and equipment load of the drilling front solution includes:

[0142] Establish a mechanical-geological coupling model for the drilling and completion scenario corresponding to the drilling front solution set;

[0143] Based on the drilling front solution set, calculate the lateral force of the drill bit corresponding to the drilling and completion scenario;

[0144] Based on the drill bit lateral force and the mechanical-geological coupling model, the drill bit trajectory coordinates of the drilling and completion scenario are output to determine the wellbore trajectory of the drilling front solution set;

[0145] Analyze the equipment load indicators in the drilling and completion scenario;

[0146] Based on the drilling front solution set and the equipment load index, the equipment load curve of the drilling and completion scenario is fitted to analyze the equipment load of the drilling and completion scenario.

[0147] The aforementioned mechanics-geology coupling model refers to a numerical simulation model that couples the mechanical systems of the drill bit, drill string, and drilling fluid with geological conditions such as formation lithology, geostress, and structural features. The drill bit lateral force refers to the component force perpendicular to the drilling direction generated by the drill bit during drilling due to factors such as formation heterogeneity, wellbore curvature, or uneven stress on the drill string. The drill bit trajectory coordinates refer to the sequence of positions of the drill bit in three-dimensional space, typically expressed as well depth (MD), inclination angle, azimuth angle, or rectangular coordinates (X, Y, ...). Z) indicates that the wellbore trajectory refers to the actual spatial path formed from the wellhead to the bottom of the well. The equipment load index refers to the set of parameters used to quantify the mechanical load borne by equipment (such as drilling rigs, drill strings, mud pumps, etc.) during drilling and completion. The equipment load curve refers to the graphical representation of the equipment load index changing with well depth or time. The equipment load refers to the total mechanical, thermal, or hydrodynamic load borne by various types of equipment (such as drilling rigs, mud pumps, top drives, etc.) during drilling and completion operations.

[0148] Optionally, the step of calculating the drill bit lateral force corresponding to the drill bit in the drilling and completion scenario based on the drilling front solution set is calculated using a drill string mechanics model (such as beam-column theory) combined with a drill bit-rock interaction model.

[0149] Optionally, the fitting of the equipment load curve for the drilling and completion scenario based on the drilling front solution set and the equipment load index uses regression analysis or a neural network model to fit the load curve.

[0150] Finally, this invention analyzes the optimization coefficients of the drilling front solution set and determines the target solution for the drilling and completion scenario based on these coefficients. This enables real-time monitoring and efficient dynamic optimization of the drilling and completion scenario. The optimization coefficients are quantitative indicators used to comprehensively evaluate the merits of each candidate solution in the drilling front solution set. These coefficients are mainly analyzed using technical, economic, safety, and risk indicators. The target solution is the final solution determined from the drilling front solution set after sorting and filtering based on the optimization coefficients.

[0151] First, by constructing a unified spatiotemporal benchmark and multidimensional data model for multi-source heterogeneous data in drilling and completion scenarios, deep integration and efficient organization of geological, engineering, and equipment data were achieved, laying a solid data foundation for subsequent analysis. Based on this, a drilling and completion knowledge graph was established and potential relationships were mined, constructing a triplet relationship network. This network effectively reveals the deep logic and causal mechanisms between data, significantly improving the accuracy and comprehensiveness of risk identification. Through this network, risk factors and factor correlation strength matrices are output. Combined with the multidimensional data model, a risk probability matrix is ​​calculated, enabling a quantitative assessment of potential risks during the drilling and completion process. Compared to dynamic prediction, this method significantly outperforms traditional experience-driven static analysis methods. The risk source tracing report generated based on the risk probability matrix can accurately pinpoint the source of risk, providing a scientific basis for decision-making. Simultaneously, it generates a drilling front solution set, and by combining wellbore trajectory and equipment load simulation analysis to optimize coefficients, it further selects the optimal drilling target solution, achieving dynamic optimization and intelligent adjustment of drilling parameters. Overall, this solution not only significantly improves the safety, efficiency, and economy of drilling and completion operations but also promotes the transformation of the drilling and completion process towards intelligence, data-driven approaches, and precise decision-making, providing strong technical support for the efficient development of oil and gas fields. Therefore, this invention can improve drilling efficiency in drilling and completion scenarios.

[0152] like Figure 2 The diagram shown is a functional module diagram of a drilling and completion technology data multidimensional analysis and dynamic optimization system according to the present invention.

[0153] The drilling and completion technology data multidimensional analysis and dynamic optimization system 200 described in this invention can be installed in an electronic device. Depending on the functions implemented, the drilling and completion technology data multidimensional analysis and dynamic optimization system may include a data model construction module 201, a relationship network construction module 202, a risk probability analysis module 203, a frontier solution set determination module 204, and a drilling and completion dynamic optimization module 205. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0154] In this embodiment of the invention, the functions of each module / unit are as follows:

[0155] The data model construction module 201 is used to acquire multi-source heterogeneous data of drilling and completion scenarios, determine a unified spatiotemporal benchmark for the multi-source heterogeneous data, and establish a multi-dimensional data model of the multi-source heterogeneous data.

[0156] The relational network construction module 202 is used to establish a drilling and completion knowledge graph of the drilling and completion scenario, and based on the drilling and completion knowledge graph, analyze the potential relationships of the drilling and completion scenario to establish a triplet relational network of the drilling and completion scenario.

[0157] The risk probability analysis module 203 is used to output the risk factors and factor correlation strength matrix of the drilling and completion scenario through the triplet relationship network, and to calculate the risk probability matrix of the drilling and completion scenario based on the risk factors, the factor correlation strength matrix and the multidimensional data model.

[0158] The frontier solution set determination module 204 is used to generate a risk tracing report of the risk probability matrix to generate the drilling frontier solution set of the drilling and completion scenario;

[0159] The drilling and completion dynamic optimization module 205 is used to simulate the wellbore trajectory and equipment load of the drilling front solution set, analyze the optimization coefficients of the drilling front solution set, and determine the drilling target solution of the drilling and completion scenario based on the optimization coefficients, so as to perform dynamic optimization of the drilling and completion scenario.

[0160] In detail, the modules in the drilling and completion technology data multidimensional analysis and dynamic optimization system 200 described in this embodiment of the invention adopt the same methods as described above when in use. Figure 1 The method used is the same as the multidimensional analysis and dynamic optimization method for drilling and completion data described in the article, and can produce the same technical effect, so it will not be elaborated here.

[0161] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0162] Finally, it should be noted that in the above embodiments, each embodiment can be combined with each other or independent. Deleting any one of them will not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for multidimensional analysis and dynamic optimization of drilling and completion technology data, characterized in that, The method includes: Acquire multi-source heterogeneous data from drilling and completion scenarios, determine a unified spatiotemporal reference for the multi-source heterogeneous data, and establish a multi-dimensional data model for the multi-source heterogeneous data. Establish a drilling and completion knowledge graph for the drilling and completion scenarios, and based on the drilling and completion knowledge graph, analyze the potential relationships between the drilling and completion scenarios to establish a triplet relationship network for the drilling and completion scenarios. Through the triplet relationship network, the risk factors and factor correlation strength matrix of the drilling and completion scenario are output. Based on the risk factors, the factor correlation strength matrix, and the multidimensional data model, the risk probability matrix of the drilling and completion scenario is calculated. The calculation of the risk probability matrix based on the risk factors, the factor correlation strength matrix, and the multidimensional data model includes: calculating the deviation degree of the risk factors according to the multidimensional data model; dynamically correcting the deviation degree using the factor correlation strength matrix to obtain a first corrected deviation degree; performing multidimensional coupling correction on the first corrected deviation degree to obtain a second corrected deviation degree; and calculating the single-accident probability of the drilling and completion scenario based on the second corrected deviation degree to calculate the risk probability matrix of the drilling and completion scenario. The multidimensional coupling correction on the first corrected deviation degree to obtain the second corrected deviation degree includes: analyzing the geological risk coefficient of the drilling and completion scenario corresponding to the first corrected deviation degree; identifying the equipment health of the risk factors corresponding to the first corrected deviation degree; and performing multidimensional coupling correction on the first corrected deviation degree based on the geological risk coefficient and the equipment health degree to obtain the second corrected deviation degree. A risk tracing report is generated to produce the risk probability matrix, thereby generating the drilling front solution set for the drilling and completion scenario; The wellbore trajectory and equipment load of the drilling front solution set are simulated to analyze the optimization coefficients of the drilling front solution set. Based on the optimization coefficients, the target drilling solution for the drilling and completion scenario is determined to perform dynamic optimization of the drilling and completion scenario. The simulation of the wellbore trajectory and equipment load of the drilling front solution set includes: establishing a mechanical-geological coupling model of the drilling and completion scenario corresponding to the drilling front solution set; calculating the drill bit lateral force corresponding to the drill bit in the drilling and completion scenario based on the drilling front solution set; outputting the drill bit trajectory coordinates of the drilling and completion scenario based on the drill bit lateral force and the mechanical-geological coupling model to determine the wellbore trajectory of the drilling front solution set; analyzing the equipment load index of the drilling and completion scenario; and fitting the equipment load curve of the drilling and completion scenario based on the drilling front solution set and the equipment load index to analyze the equipment load of the drilling and completion scenario.

2. The method for multidimensional analysis and dynamic optimization of drilling and completion technical data as described in claim 1, characterized in that, The establishment of the multidimensional data model for the multi-source heterogeneous data includes: Based on the unified spatiotemporal reference of the multi-source heterogeneous data, the multi-source heterogeneous data is time-aligned to obtain aligned multi-source heterogeneous data. The spatial coordinates of the aligned multi-source heterogeneous data are then unified to obtain unified multi-source heterogeneous data. Frequency synchronization is performed on the unified multi-source heterogeneous data to obtain synchronized multi-source heterogeneous data. Establish the dimension axis of the synchronized multi-source heterogeneous data, wherein the dimension axis includes a required dimension and an extended dimension; Based on the dimension axis, a multidimensional data model of the synchronous multi-source heterogeneous data is established.

3. The method for multidimensional analysis and dynamic optimization of drilling and completion technical data as described in claim 2, characterized in that, The analysis of potential relationships among drilling and completion scenarios based on the drilling and completion knowledge graph includes: Extract the entity association paths and multi-hop relationships from the drilling and completion knowledge graph; Map the entity association paths and multi-hop relationships to entity embedding vectors; Calculate the entity similarity of the entity embedding vectors; Based on the entity similarity, determine the similar entities of the entity embedding vector; Based on the similar entities, the entity association paths, and the multi-hop relationships, the potential associations of the drilling and completion scenarios are determined.

4. The method for multidimensional analysis and dynamic optimization of drilling and completion technical data as described in claim 3, characterized in that, The establishment of the triplet relationship network for the drilling and completion scenario includes: Define the triplet structure for the drilling and completion scenario; Determine the entity type and core entity relationship of the triple structure; Based on the entity type and core entity relationship, the potential association relationship of the drilling and completion scenario is used to generate triples for the drilling and completion scenario, wherein the triples include explicit relation triples, potential relation triples and attribute triples. Calculate the triplet weights of the triplet; Based on the triplet weights, a triplet relationship network is established for the triplets.

5. The method for multidimensional analysis and dynamic optimization of drilling and completion technical data as described in claim 4, characterized in that, The step of outputting the risk factors and factor correlation strength matrix of the drilling and completion scenario through the triplet relationship network includes: Define the risk events in the drilling and completion scenarios described above; Based on the aforementioned risk events, the risk factor chain of the drilling and completion scenario is output using the triplet relationship network; Based on the aforementioned risk factor chain, the risk factors for the drilling and completion scenario are determined. Define the risk matrix dimensions for the drilling and completion scenario; Calculate the correlation strength between the risk factor and the risk event; Based on the correlation strength and risk matrix dimensions, a factor correlation strength matrix for the drilling and completion scenario is established.

6. The method for multidimensional analysis and dynamic optimization of drilling and completion technical data as described in claim 5, characterized in that, The calculation of the correlation strength between the risk factor and the risk event includes: Analyze the base probability that the risk factors will lead to the risk event; Define the accident loss of the aforementioned risk event; The correlation strength between the risk factor and the risk event is calculated using the following formula, based on the base probability and the event loss: in, Indicates risk factors and risk incidents The strength of the association, Indicates risk factors Leading to risk incidents The base probability, The weighting coefficients represent the base probability. Indicates risk incident The accident losses, Indicates the loss normalization benchmark. This represents the weighting coefficient of the severity component. Indicates risk factors Leading to risk incidents Detectability score The weighting coefficients representing the detectability score. Indicates risk factors Leading to risk incidents Real-time operating condition correction coefficient, This represents the weighting coefficient of the real-time operating condition correction coefficient.

7. A multi-dimensional analysis and dynamic optimization system for drilling and completion technology data, characterized in that, The system includes: The data model building module is used to acquire multi-source heterogeneous data from drilling and completion scenarios, determine a unified spatiotemporal benchmark for the multi-source heterogeneous data, and establish a multi-dimensional data model for the multi-source heterogeneous data. The relational network construction module is used to establish a drilling and completion knowledge graph of the drilling and completion scenario, and based on the drilling and completion knowledge graph, analyze the potential relationships of the drilling and completion scenario to establish a triplet relational network of the drilling and completion scenario. The risk probability analysis module is used to output risk factors and factor correlation strength matrices for the drilling and completion scenario through the triplet relationship network, and to calculate the risk probability matrix of the drilling and completion scenario based on the risk factors, the factor correlation strength matrix, and the multidimensional data model. The calculation of the risk probability matrix based on the risk factors, the factor correlation strength matrix, and the multidimensional data model includes: calculating the deviation degree of the risk factors according to the multidimensional data model; dynamically correcting the deviation degree using the factor correlation strength matrix to obtain a first corrected deviation degree; and then... A first correction deviation degree is corrected by multidimensional coupling to obtain a second correction deviation degree. Based on the second correction deviation degree, the single accident probability of the drilling and completion scenario is calculated to calculate the risk probability matrix of the drilling and completion scenario. The first correction deviation degree is corrected by multidimensional coupling to obtain the second correction deviation degree, which includes: analyzing the geological risk coefficient of the drilling and completion scenario corresponding to the first correction deviation degree, identifying the equipment health of the risk factors corresponding to the first correction deviation degree, and correcting the first correction deviation degree by multidimensional coupling based on the geological risk coefficient and the equipment health to obtain the second correction deviation degree. The frontier solution set determination module is used to generate a risk tracing report of the risk probability matrix, so as to generate the drilling frontier solution set of the drilling and completion scenario; The drilling and completion dynamic optimization module is used to simulate the wellbore trajectory and equipment load of the drilling front solution set to analyze the optimization coefficients of the drilling front solution set and determine the drilling target solution of the drilling and completion scenario based on the optimization coefficients, so as to perform dynamic optimization of the drilling and completion scenario. The simulation of the wellbore trajectory and equipment load of the drilling front solution set includes: establishing a mechanical-geological coupling model of the drilling and completion scenario corresponding to the drilling front solution set; calculating the drill bit lateral force of the drill bit corresponding to the drilling and completion scenario based on the drilling front solution set; outputting the drill bit trajectory coordinates of the drilling and completion scenario based on the drill bit lateral force and the mechanical-geological coupling model to determine the wellbore trajectory of the drilling front solution set; analyzing the equipment load index of the drilling and completion scenario; and fitting the equipment load curve of the drilling and completion scenario based on the drilling front solution set and the equipment load index to analyze the equipment load of the drilling and completion scenario.

Images