Construction method based on petroleum engineering safety risk dynamic evaluation model

Data is collected through sensor networks, geographic elevation conversion and multi-level impact assessment are carried out, and a dynamic assessment model for safety risks of petroleum engineering is constructed, which solves the problem of insufficient analysis of multi-level influencing factors and risk propagation paths in traditional models, and improves dynamic perception of petroleum engineering and responsiveness.

CN119005695AActive Publication Date: 2024-11-22BEIJING PEIYING CHEMICAL TECHNOLOGY CO LTD

Patent Information

Application Number
CN202411085027.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-22
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

Traditional petroleum engineering safety assessment models lack comprehensive consideration of multi-level geological factors and in-depth understanding of risk propagation paths, resulting in low dynamic perception and immediate response capabilities.

Method used

By acquiring and deploying sensor networks, collecting environmental data in real time, conducting geographic elevation transformation and multi-level impact assessment, combining multi-field coupled numerical simulations, a dynamic risk index matrix and risk feature vector are generated, and a dynamic assessment model for safety risks of petroleum engineering is constructed to carry out risks. Communication simulation and decision making.

Benefits of technology

It has improved the dynamic perception and immediate response capabilities of petroleum engineering safety risks, ensuring the scientificity and effectiveness of risk monitoring and management in the oil extraction process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005695A_ABST
    Figure CN119005695A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of model construction, in particular to a construction method based on a petroleum engineering safety risk dynamic evaluation model. The method comprises the following steps: acquiring geological data of a petroleum engineering area; performing multi-dimensional sensor deployment on the geological data of the petroleum engineering area to generate a petroleum exploitation sensor deployment network; environment sensing data collection is carried out based on an oil exploitation sensor deployment network, and standard oil exploitation environment collection data is obtained; performing oil exploitation geographical elevation conversion on the standard oil exploitation environment acquisition data to generate oil exploitation geographical elevation data; and performing multi-level oil exploitation influence evaluation based on the oil exploitation geographical elevation data to generate oil exploitation multi-level influence data. According to the invention, through data integration, dynamic monitoring and risk propagation path analysis of petroleum engineering stage data, and through petroleum engineering safety risk assessment, the dynamic perception and instant response capability of petroleum engineering safety risks is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of model construction, and in particular to a construction method based on a dynamic assessment model of petroleum engineering safety risks. Background Art

[0002] In the early days, the safety assessment of petroleum engineering mainly relied on experience and qualitative analysis. With the development of computing technology, methods based on probabilistic risk assessment (PRA) have emerged, which improve the scientific nature of the assessment through quantitative analysis. However, traditional PRA methods often lack consideration of dynamic factors and are difficult to adapt to the complex and changing petroleum engineering environment. As the safety assessment model of petroleum engineering gradually develops towards dynamic and intelligent directions. The dynamic risk assessment (DRA) model introduces time series analysis and dynamic simulation technology, which can monitor and evaluate risk changes in real time. These models combine multiple data sources, such as sensor data, historical accident data, and environmental monitoring data, and improve the accuracy and timeliness of risk prediction through machine learning and data mining technology. In recent years, with the application of big data technology and the Internet of Things (IoT), the safety assessment model of petroleum engineering has been further optimized. Big data technology can process massive amounts of complex data and improve data analysis and processing capabilities, while IoT technology realizes real-time data collection and transmission, enhancing the dynamic response capability of the model. However, the current traditional geological impact assessment is often limited to a single level of analysis and lacks comprehensive consideration of multi-level influencing factors. At the same time, the analysis of risk transmission paths is often limited to the surface level and lacks an in-depth understanding of the transmission of risks at different stages, which leads to low dynamic perception and immediate response capabilities for petroleum engineering safety risks. Summary of the invention

[0003] Based on this, it is necessary to provide a method for constructing a dynamic assessment model for petroleum engineering safety risks to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for constructing a dynamic assessment model for petroleum engineering safety risks is provided, the method comprising the following steps:

[0005] Step S1: Acquire geological data of the petroleum engineering area; perform multi-dimensional sensor deployment on the geological data of the petroleum engineering area to generate an oil production sensor deployment network; perform environmental sensor data collection based on the oil production sensor deployment network to obtain standard oil production environment collection data;

[0006] Step S2: converting the standard oil production environment collection data into oil production geographic elevation data to generate oil production geographic elevation data; conducting a multi-level oil production impact assessment based on the oil production geographic elevation data to generate oil production multi-level impact data; conducting a multi-field coupling numerical simulation of the multi-level geological impact factors of oil production to generate oil and gas production risk impact factors;

[0007] Step S3: Perform data security monitoring based on oil and gas production risk influencing factors to generate oil and gas production risk monitoring data; perform stream engine optimization on the oil and gas production risk monitoring data to generate a dynamic risk indicator matrix; perform cluster parallel processing on the dynamic risk indicator matrix to generate an oil production risk feature vector;

[0008] Step S4: construct a dynamic assessment model for oil engineering safety risks; import the dynamic risk indicator matrix into the dynamic assessment model for oil engineering safety risks to predict mining risks and generate oil engineering mining risk prediction data; perform risk propagation simulation on the oil engineering mining risk prediction data and generate a oil engineering risk propagation path map;

[0009] Step S5: Mark the high-risk stages of the petroleum engineering risk propagation path map and generate high-risk petroleum engineering stage data; make dynamic risk decisions on the high-risk petroleum engineering stage data and generate high-risk petroleum engineering stage decision strategies to execute petroleum engineering safety risk adjustment operations.

[0010] The present invention can collect environmental data such as temperature, pressure, humidity, etc. in real time by acquiring and deploying sensor networks, thereby optimizing oil production environmental monitoring and management. Standardized data collection helps to accurately evaluate the environmental conditions of the project area and provide reliable data support for subsequent steps. Through geographic elevation conversion and multi-level impact assessment, the impact of oil production on geology and environment can be fully understood. Multi-field coupled numerical simulation helps to simulate the complex interaction of different geological influencing factors, thereby accurately assessing the risk of production. The generation of dynamic risk indicator matrix and risk characteristic vector makes it possible to monitor and evaluate the safety risks of oil production in real time. Stream engine optimization and cluster parallel processing improve data processing efficiency and response speed, which helps to quickly identify and respond to potential risks. Through dynamic evaluation models and risk prediction data, various risks that occur in the oil production process can be identified and predicted in advance. Risk propagation simulation and path map generation help to understand the risk diffusion mechanism and guide the formulation of more effective risk management strategies. Identifying and dynamically deciding high-risk stages helps to adjust and optimize production strategies in a timely manner at critical moments, reduce the probability of risk occurrence, and ensure the safety and stability of oil projects. Therefore, the present invention improves the dynamic perception and immediate response capabilities of petroleum engineering safety risks by integrating data, dynamically monitoring and analyzing risk propagation paths of petroleum engineering stage data, and conducting petroleum engineering safety risk assessment.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: using GIS to obtain regional geological data for petroleum engineering;

[0013] Step S12: Analyze the mining range of the petroleum engineering regional geological data to generate petroleum mining range data;

[0014] Step S13: Perform multi-dimensional sensor deployment based on the oil production range data to generate an oil production sensor deployment network;

[0015] Step S14: Collect environmental sensor data based on the oil production sensor deployment network to obtain oil production environment collection data; perform data preprocessing on the oil production environment collection data to generate standard oil production environment collection data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization.

[0016] The present invention can quickly and accurately obtain geological data of the oil engineering area through the GIS system. These data include key information such as topography, landform, geological structure, etc., which are helpful to fully understand the geological conditions of the oil production area and provide basic data support for subsequent production planning. By analyzing the geological data, the most suitable production range can be determined, the resource utilization efficiency can be maximized, and unnecessary production range and resource waste can be reduced. At the same time, areas with poor geological conditions or potential risks can be avoided to ensure the safety and economy of production. Multi-dimensional sensor deployment based on production range data can achieve comprehensive monitoring of the production process. The sensor deployment network can monitor geological changes, equipment operating status and environmental conditions in real time, detect and handle abnormal conditions in time, and ensure the stability and efficiency of the production process. By collecting environmental data through the sensor network, the environmental conditions of the production area can be fully understood. The data preprocessing steps (data cleaning, missing value filling and data standardization) ensure the accuracy and consistency of the data and provide a reliable data basis for subsequent analysis and decision-making.

[0017] Preferably, step S2 comprises the following steps:

[0018] Step S21: extracting geological data from the standard oil production environment collection data to obtain oil production geological data, wherein the oil production geological data includes geological exploration data and drilling data;

[0019] Step S22: converting the geological exploration data and the drilling data into oil production geographic elevation data to generate oil production geographic elevation data;

[0020] Step S23: Perform multi-level oil production impact assessment based on oil production geographic elevation data to generate multi-level oil production impact data;

[0021] Step S24: Perform multi-field coupling numerical simulation on the multi-level geological influencing factors of oil production to generate oil and gas production risk influencing factors.

[0022] The present invention can obtain detailed geological exploration and drilling information by extracting geological data. These data can help to fully understand the underground structure and the distribution of oil and gas reservoirs, provide necessary data support for accurate exploitation, and ensure the scientificity and rationality of the exploitation process. By converting the geological exploration data and the drilling data into geographic elevation, more accurate geographic elevation information can be obtained. This helps to accurately locate the location and depth of the oil and gas reservoir, provide accurate guidance for drilling operations, reduce blind drilling and unnecessary costs, and improve drilling efficiency and success rate. Through multi-level impact assessment using geographic elevation data, the geological and environmental impacts of oil production at different levels can be comprehensively assessed. This helps to identify potential risks and problems, formulate corresponding countermeasures, and ensure the safety and sustainability of oil production activities. Through multi-field coupled numerical simulation, the interaction and combined impact of different geological influencing factors in the exploitation process can be analyzed in detail. This helps to accurately assess the risks of oil and gas exploitation, provide a scientific basis for decision-making, and thus reduce risks.

[0023] Preferably, step S23 includes the following steps:

[0024] Step S231: performing mining strata division based on the oil mining geographic elevation data to generate mining strata division data; performing stratum lithology analysis on the standard oil mining environment acquisition data based on the mining stratum division data to generate stratum lithology analysis data; performing fault structure analysis on the stratum lithology analysis data to generate oil mining geological impact data;

[0025] Step S232: Perform oil and gas mining rock mechanical property analysis on the oil mining geographic elevation data to generate rock mechanical property data; perform formation pressure analysis on the standard oil mining environment collection data through the rock mechanical property data to generate oil mining mechanical influence data;

[0026] Step S233: Calculate the oil and gas reservoir distribution based on the oil production geographic elevation data to obtain the oil and gas reservoir distribution data; evaluate the oil and gas fluid properties based on the oil and gas reservoir distribution data to generate the oil and gas fluid property evaluation data; integrate the oil production geological influence data, the oil production mechanical influence data and the oil and gas fluid property evaluation data to generate the multi-level influence data of oil production.

[0027] The present invention can effectively determine the geological characteristics and resource distribution of each layer by accurately dividing the mining strata, optimize the mining plan, maximize resource utilization, and reduce interference with irrelevant strata. Through lithology analysis, the rock types and physical properties of different strata can be understood, and detailed geological information can be provided for drilling and mining to ensure the accuracy and safety of construction. Fault structure analysis can identify and evaluate potential geological risks, avoid mining accidents caused by fault activities, and ensure the safety and stability of the mining process. Understanding the mechanical properties of rocks is helpful to evaluate the stability and bearing capacity of the strata, optimize drilling parameters and mining strategies, and reduce mining risks. Through formation pressure analysis, changes in formation pressure can be predicted and monitored to prevent accidents such as blowouts and well collapses, and ensure the safety of the mining process. Accurately calculating the distribution of oil and gas reservoirs can optimize well location design and mining plans, maximize oil and gas recovery rates, and improve economic benefits. Evaluating the properties of oil and gas fluids can understand the physical and chemical properties of oil and gas, provide an important basis for processing and market sales, and improve the quality and market competitiveness of oil and gas products. Through the integrated analysis of multi-dimensional data, we can comprehensively and systematically evaluate the multi-level impacts of oil extraction, optimize extraction decisions, and ensure the sustainability and efficiency of extraction activities.

[0028] Preferably, calculating the distribution of oil and gas reservoirs based on the oil production geographic elevation data includes:

[0029] Carry out terrain modeling on the oil extraction geographic elevation data to generate oil extraction terrain data; generate contour lines on the oil extraction terrain data to obtain oil extraction contour line data; calculate the curvature of the oil extraction contour line data to obtain oil extraction terrain change data;

[0030] Use geological exploration data to judge the reservoir level of oil production terrain change data and generate initial oil production reservoir level thickness data; collect well logging data through initial oil production reservoir level thickness data to generate well logging data; calculate the porosity of well logging data based on formation lithology analysis data to obtain reservoir porosity data;

[0031] Based on the reservoir porosity data, the reservoir characteristics of the initial oil production reservoir layer thickness data are analyzed to obtain the initial reservoir permeability evaluation data and the initial reservoir saturation data; the initial reservoir permeability evaluation data and the initial reservoir saturation data are used to optimize the reservoir distribution of the oil production topographic change data to generate the oil production reservoir thickness map;

[0032] The oil and gas reservoir distribution is calculated on the oil production reservoir thickness map to obtain the oil and gas reservoir distribution data.

[0033] The present invention can depict the topographic features of the mining area in detail through terrain modeling, provide basic data for subsequent contour generation and curvature calculation, and help accurately locate and plan mining activities. Contour data can intuitively display the ups and downs of the terrain, help identify potential reservoir distribution areas, and provide reference for further geological analysis and mining plans. Curvature calculation can reveal the changing trend and complexity of the terrain, help identify the location and characteristics of the reservoir, and improve mining accuracy and efficiency. Through the comprehensive analysis of geological exploration data, the level and thickness of the reservoir can be accurately divided, the distribution range and characteristics of the reservoir can be determined, and guidance can be provided for logging data collection. Through the comprehensive analysis of geological exploration data, the level and thickness of the reservoir can be accurately divided, the distribution range and characteristics of the reservoir can be determined, and guidance can be provided for logging data collection. Porosity data can reflect the oil storage capacity of the reservoir, help evaluate the distribution and reserves of oil and gas, and provide a scientific basis for the formulation of mining strategies. By analyzing the permeability and saturation of the reservoir, the fluidity and content of oil and gas in the reservoir can be evaluated, providing an important reference for optimizing mining strategies. Reservoir distribution optimization can more accurately reflect the actual situation of the reservoir, optimize the mining plan, and ensure the efficiency and safety of the mining process. Through comprehensive calculations, the spatial distribution of oil and gas reservoirs can be accurately determined, and the well location design and mining plan can be optimized.

[0034] Preferably, step S3 comprises the following steps:

[0035] Step S31: Perform data security monitoring based on oil and gas production risk influencing factors to generate oil and gas production risk monitoring data;

[0036] Step S32: Optimizing the oil and gas production risk monitoring data using a stream engine to generate a dynamic risk indicator matrix;

[0037] Step S33: splitting the dynamic risk indicator matrix into data blocks to obtain dynamic risk data blocks; distributing the dynamic risk data blocks into cluster nodes to generate distributed dynamic risk data blocks;

[0038] Step S34: parallel processing of distributed dynamic risk data blocks to obtain local risk feature data; risk factor aggregation of the local risk feature data to generate an initial risk feature set; data dimension reduction of the initial risk feature set to generate an oil production risk feature vector.

[0039] By monitoring the risk influencing factors of oil and gas production, the present invention can obtain risk information in the production process in real time, timely discover and warn of potential risks, and ensure the safety and continuity of production activities. Stream engine optimization can improve the efficiency of data processing and analysis, and the generated dynamic risk indicator matrix can reflect the real-time dynamics of risk changes, providing accurate and timely information for risk management and decision-making. Data block splitting and cluster node distribution can effectively manage and process large-scale risk data, improve the speed and efficiency of data processing through distributed processing, and realize efficient management and analysis of risk data. Parallel processing improves the efficiency of data processing, and risk factor aggregation and data dimensionality reduction help to extract and simplify key risk features. The generated risk feature vector can accurately reflect the risk features in the oil and gas production process, and help formulate more accurate and effective risk management strategies.

[0040] Preferably, step S32 includes the following steps:

[0041] Step S321: accessing the oil and gas production risk monitoring data through stream data to obtain the oil and gas production risk monitoring data stream;

[0042] Step S322: define event patterns for the oil and gas production risk monitoring data stream through complex time processing rules to generate an oil and gas production event monitoring stream; perform key event detection on the oil and gas production event detection stream to generate oil and gas production risk key events;

[0043] Step S323: Allocate risk weights to key oil and gas production risk events and generate a dynamic risk indicator matrix.

[0044] The present invention can acquire and process risk monitoring data in the oil and gas production process in real time through stream data access, ensure the real-time and continuity of data, and provide a basis for subsequent event detection and analysis. Complex time processing rules and event pattern definitions can help identify and extract important events in risk monitoring data. Through key event detection, potential risk points can be discovered in time, early warning and response can be carried out, and major accidents can be avoided. Through the risk weight allocation of key events, the severity of various risks can be quantified and evaluated. The generated dynamic risk indicator matrix can fully reflect the current risk status, provide an accurate basis for risk management and decision-making, and optimize risk control strategies. Through stream data access and real-time processing, the real-time and continuity of risk monitoring data are ensured, and potential risk events can be quickly responded to and processed. Through complex time processing rules and key event detection, important risk events can be accurately identified and extracted, and the accuracy of risk assessment can be improved. The dynamic risk indicator matrix integrates the weight allocation of multiple risk events, can fully reflect the risk status in the production process, and provides a reliable basis for scientific decision-making. Early detection and identification of key risk events, risk warning and timely response, reduce the possibility of accidents, and ensure the safety and stability of the production process.

[0045] Preferably, step S4 comprises the following steps:

[0046] Step S41: constructing a dynamic assessment model for oil engineering safety risks; importing a dynamic risk indicator matrix into the dynamic assessment model for oil engineering safety risks to perform mining risk prediction and generate oil engineering mining risk prediction data;

[0047] Step S42: defining the network nodes of the petroleum engineering project through the oil and gas production risk influencing factors to obtain the network node data of the petroleum engineering project; constructing the risk propagation network structure based on the network node data of the petroleum engineering project to obtain the initial risk propagation network structure;

[0048] Step S43: assigning node weights to the initial risk propagation network structure according to the oil production risk prediction data to generate a risk propagation network structure; simulating the propagation process of the risk propagation network structure to generate risk propagation process simulation data;

[0049] Step S44: Based on the risk propagation process simulation data, the node propagation path of the risk propagation network structure is traced to generate a petroleum engineering risk propagation path diagram.

[0050] The present invention can systematically and dynamically evaluate various risks in petroleum engineering by constructing a dynamic evaluation model. By importing the dynamic risk indicator matrix into the model for mining risk prediction, accurate and real-time risk prediction data can be generated, which helps to timely identify and evaluate potential risks and improve the foresight and effectiveness of risk management. By defining and constructing a risk propagation network structure, the various nodes in the petroleum engineering project and their mutual relationships can be fully understood, which helps to systematically identify and analyze the risk propagation path and improve the overall control ability of risks. Through node weight allocation and propagation process simulation, the importance and influence of each node in risk propagation can be quantitatively evaluated, and the generated propagation process simulation data can truly reflect the dynamic process of risk propagation, help identify key nodes and potential risk propagation paths, and formulate effective risk control strategies. Through node propagation path tracking, the specific path and process of risk propagation can be intuitively displayed, and the generated risk propagation path map can help to fully understand and monitor the dynamic changes of risk propagation, take measures to prevent or slow down the spread of risks in a timely manner, and ensure the safety and stability of petroleum engineering projects. By constructing a risk dynamic evaluation model and a propagation network structure, various risks in petroleum engineering can be comprehensively and systematically evaluated and managed. Real-time prediction and simulation of the risk propagation process can identify and assess potential risks in advance, and improve the foresight and initiative of risk management. Quantitative node weight allocation and propagation process simulation can accurately assess the importance and influence of each node and improve the accuracy of risk assessment. The generated risk propagation path map can intuitively display the specific path and process of risk propagation, help take timely measures to control and mitigate risk propagation, and ensure the safety and stability of the project.

[0051] Preferably, step S41 includes the following steps:

[0052] Step S411: splitting the dynamic risk indicator matrix into data to obtain a model training set, a model verification set and a model test set;

[0053] Step S412: Perform model training on the model training set using a deep neural network algorithm to generate a risk assessment training model; perform model generalization capability evaluation on the risk assessment training model using a model validation set to generate model generalization performance data;

[0054] Step S413: adjusting the model architecture and hyperparameters of the risk assessment training model through the model generalization performance data, thereby generating a risk assessment adjustment model; performing forward propagation calculation on the risk assessment adjustment model according to the model test set, thereby generating risk assessment test data;

[0055] Step S414: perform predictive performance evaluation on the risk assessment test data to generate model predictive performance evaluation data; perform iterative optimization on the risk assessment adjustment model based on the model predictive performance evaluation data to generate a dynamic assessment model for petroleum engineering safety risks; import the dynamic risk indicator matrix into the dynamic assessment model for petroleum engineering safety risks to perform mining risk prediction to generate petroleum engineering mining risk prediction data.

[0056] The present invention can effectively avoid the overfitting problem of the model in the training process through data splitting, and at the same time ensure the data independence and representativeness of the model in the training, verification and testing stages, and improve the credibility and stability of the model evaluation. Through the training of deep neural networks, complex patterns and laws can be learned from a large amount of data, and the generated risk assessment training model can accurately predict various risks in petroleum engineering exploitation. Model generalization ability evaluation can evaluate the performance of the model on new data, ensure that the model has good generalization ability, and can adapt to the risk prediction needs under different conditions. Model architecture and hyperparameter adjustment can further optimize the performance and accuracy of the model, and ensure that the model can perform well on different data sets. The risk assessment test data generated by forward propagation calculation can evaluate the prediction ability of the model in practical applications, and provide empirical support for further optimization and improvement of the model. Through predictive performance evaluation and model iterative optimization, the prediction accuracy and stability of the model can be continuously improved and enhanced, and the generated dynamic assessment model of petroleum engineering safety risks can effectively predict and manage various risks in the exploitation process. Importing the dynamic risk indicator matrix into the model for exploitation risk prediction can achieve real-time and accurate risk monitoring and early warning, and help decision makers formulate effective risk management strategies in a timely manner.

[0057] Preferably, step S5 comprises the following steps:

[0058] Step S51: marking the petroleum engineering safety risks on the petroleum engineering risk propagation path map to obtain petroleum engineering stage risk marking data;

[0059] Step S52: Compare the petroleum engineering stage risk identification data with a preset stage risk identification data threshold value, and when the petroleum engineering stage risk identification data is greater than or equal to the preset stage risk identification threshold value, high-risk petroleum engineering stage data is generated;

[0060] Step S53: Perform dynamic risk decision-making on high-risk petroleum engineering stage data, generate high-risk petroleum engineering stage decision-making strategies, and execute petroleum engineering safety risk adjustment operations.

[0061] The present invention can clearly identify and display the distribution and impact paths of safety risks in different stages of petroleum engineering by marking the risk propagation path map, and help decision makers to fully understand and analyze the risk situation in each stage. By setting the stage risk identification threshold, the petroleum engineering stage with high risk can be quickly identified, and high-risk events can be warned and responded to in time to avoid potential safety accidents and production interruptions. Through dynamic risk decision-making, safety risk management strategies and emergency measures can be formulated and adjusted according to real-time high-risk data to ensure the safe production and operation of petroleum engineering. This strategic decision can effectively reduce the possibility of accidents and ensure the safety of personnel and equipment. Through dynamic monitoring and risk identification, safety risks in petroleum engineering can be responded to in real time to avoid accidents. By setting thresholds and comparative analysis, early warning and identification of high-risk stages can be carried out, providing important decision-making basis for decision makers. Through dynamic risk decision-making and adjustment operations, various risks in petroleum engineering can be effectively controlled and managed to ensure the smooth progress and safety of production.

[0062] The beneficial effect of the present invention is that by acquiring geological data of the petroleum engineering area, key geological information can be obtained, providing accurate basic data for subsequent sensor deployment and decision-making. By deploying multi-dimensional sensors on geological data, a sensor network covering the entire oil production area can be established to collect environmental sensor data. Through environmental sensor data collection, standard oil production environment data can be obtained to provide a basis for subsequent evaluation and decision-making. By converting the standard oil production environment collection data into geographic elevation, oil production geographic elevation data can be generated, further providing a basis for oil production impact assessment. Based on oil production geographic elevation data, multi-level oil production impact assessment can be performed to obtain multi-level impact data of oil production, which helps understand the impact of production on the environment. Multi-field coupled numerical simulation of multi-level geological impact factors of oil production can generate oil and gas production risk impact factors for subsequent risk monitoring and evaluation. Data security monitoring based on oil and gas production risk impact factors can generate oil and gas production risk monitoring data for real-time monitoring and control of production risks. Stream engine optimization of oil and gas production risk monitoring data can generate a dynamic risk indicator matrix to provide more accurate data for subsequent risk assessment and prediction. By constructing a dynamic assessment model for oil engineering safety risks and importing a dynamic risk indicator matrix into the model for mining risk prediction, oil engineering mining risk prediction data can be generated, and risk propagation simulation can be performed to generate a oil engineering risk propagation path map. The oil engineering risk propagation path map is marked with high risks at different stages to generate high-risk oil engineering stage data, and dynamic risk decisions are made on the high-risk oil engineering stage data to generate high-risk oil engineering stage decision strategies to perform oil engineering safety risk adjustment operations, which can achieve the assessment, prediction and decision-making of oil engineering safety risks, thereby improving the safety and sustainability of oil engineering. Therefore, the present invention improves the dynamic perception and immediate response capabilities of oil engineering safety risks by integrating data, dynamically monitoring and analyzing risk propagation paths for oil engineering stage data, and evaluating oil engineering safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of the steps of a construction method based on a dynamic assessment model for safety risks in petroleum engineering;

[0064] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0065] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0066] Figure 4 for Figure 1Detailed implementation steps of step S4 in FIG.

[0067] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0068] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0069] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0070] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0071] To achieve this, please refer to Figures 1 to 4 A method for constructing a dynamic assessment model for petroleum engineering safety risks is provided, the method comprising the following steps:

[0072] Step S1: Acquire geological data of the petroleum engineering area; perform multi-dimensional sensor deployment on the geological data of the petroleum engineering area to generate an oil production sensor deployment network; perform environmental sensor data collection based on the oil production sensor deployment network to obtain standard oil production environment collection data;

[0073] Step S2: converting the standard oil production environment collection data into oil production geographic elevation data to generate oil production geographic elevation data; conducting a multi-level oil production impact assessment based on the oil production geographic elevation data to generate oil production multi-level impact data; conducting a multi-field coupling numerical simulation of the multi-level geological impact factors of oil production to generate oil and gas production risk impact factors;

[0074] Step S3: Perform data security monitoring based on oil and gas production risk influencing factors to generate oil and gas production risk monitoring data; perform stream engine optimization on the oil and gas production risk monitoring data to generate a dynamic risk indicator matrix; perform cluster parallel processing on the dynamic risk indicator matrix to generate an oil production risk feature vector;

[0075] Step S4: construct a dynamic assessment model for oil engineering safety risks; import the dynamic risk indicator matrix into the dynamic assessment model for oil engineering safety risks to predict mining risks and generate oil engineering mining risk prediction data; perform risk propagation simulation on the oil engineering mining risk prediction data and generate a oil engineering risk propagation path map;

[0076] Step S5: Mark the high-risk stages of the petroleum engineering risk propagation path map and generate high-risk petroleum engineering stage data; make dynamic risk decisions on the high-risk petroleum engineering stage data and generate high-risk petroleum engineering stage decision strategies to execute petroleum engineering safety risk adjustment operations.

[0077] The present invention can collect environmental data such as temperature, pressure, humidity, etc. in real time by acquiring and deploying sensor networks, thereby optimizing oil production environmental monitoring and management. Standardized data collection helps to accurately evaluate the environmental conditions of the project area and provide reliable data support for subsequent steps. Through geographic elevation conversion and multi-level impact assessment, the impact of oil production on geology and environment can be fully understood. Multi-field coupled numerical simulation helps to simulate the complex interaction of different geological influencing factors, thereby accurately assessing the risk of production. The generation of dynamic risk indicator matrix and risk characteristic vector makes it possible to monitor and evaluate the safety risks of oil production in real time. Stream engine optimization and cluster parallel processing improve data processing efficiency and response speed, which helps to quickly identify and respond to potential risks. Through dynamic evaluation models and risk prediction data, various risks that occur in the oil production process can be identified and predicted in advance. Risk propagation simulation and path map generation help to understand the risk diffusion mechanism and guide the formulation of more effective risk management strategies. Identifying and dynamically deciding high-risk stages helps to adjust and optimize production strategies in a timely manner at critical moments, reduce the probability of risk occurrence, and ensure the safety and stability of oil projects. Therefore, the present invention improves the dynamic perception and immediate response capabilities of petroleum engineering safety risks by integrating data, dynamically monitoring and analyzing risk propagation paths of petroleum engineering stage data, and conducting petroleum engineering safety risk assessment.

[0078] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for constructing a dynamic assessment model for safety risks in petroleum engineering according to the present invention. In this example, the method for constructing a dynamic assessment model for safety risks in petroleum engineering according to the present invention includes the following steps:

[0079] Step S1: Acquire geological data of the petroleum engineering area; perform multi-dimensional sensor deployment on the geological data of the petroleum engineering area to generate an oil production sensor deployment network; perform environmental sensor data collection based on the oil production sensor deployment network to obtain standard oil production environment collection data;

[0080] In the embodiment of the present invention, relevant data including stratigraphic information, geological structure, lithology distribution, etc. are obtained from geological exploration, geological survey or existing geological database. Geological data can be obtained by using technical means such as geological survey, geophysical exploration, drilling, etc. Advanced geological detection equipment and technology, such as seismic exploration, electromagnetic detection, etc., are used to obtain high-precision geological data. Sensors suitable for oil production environment monitoring, such as temperature sensors, pressure sensors, humidity sensors, etc., are selected to ensure coverage of multiple environmental parameters. The sensor deployment location is determined according to geological data and environmental characteristics to ensure coverage of the entire oil production area, and geological heterogeneity and uneven resource distribution are taken into account. The layout and topology of the sensor network are designed to ensure communication and data transmission efficiency between sensors. Data acquisition protocols and communication protocols are formulated to ensure that sensors can transmit environmental data to the data center in real time and stably. Environmental data, including temperature, pressure, humidity, etc., are collected in real time through the sensor network, and the data is stored in the data center or cloud platform. The collected data is standardized to ensure the accuracy and comparability of the data, which is convenient for subsequent data analysis and decision support.

[0081] Step S2: converting the standard oil production environment collection data into oil production geographic elevation data to generate oil production geographic elevation data; conducting a multi-level oil production impact assessment based on the oil production geographic elevation data to generate oil production multi-level impact data; conducting a multi-field coupling numerical simulation of the multi-level geological impact factors of oil production to generate oil and gas production risk impact factors;

[0082] In the embodiment of the present invention, the collected environmental data is converted into geographic elevation and spatially analyzed by using geographic information system (GIS) software. The collected environmental data is integrated with geological data, including stratigraphic information, terrain features, etc., to generate geographic elevation data of the oil production area. According to the geological characteristics and resource distribution of the oil production area, the assessment is divided into different levels, such as surface layer, underground layer, etc. Quantitative analysis methods, such as impact matrix analysis, terrain change simulation, etc., are used to evaluate the multi-level impact of oil production on geological environment, hydrogeology, surface morphology, etc. Numerical simulation software, such as finite element analysis (FEM), finite difference method (FDM), etc., are used to simulate the complex interaction of different geological influencing factors in space and time. The geological parameters, surface characteristics, hydrogeological conditions, etc. of the model are set according to actual conditions to ensure the accuracy and credibility of the simulation results. The multi-field coupling results obtained by simulation are analyzed for data to extract risk influencing factors generated during oil and gas production, such as geological deformation, groundwater level changes, surface subsidence, etc. According to the analysis results, the potential impact of different influencing factors on oil engineering safety and environmental protection is quantified to provide a scientific basis for risk assessment.

[0083] Step S3: Perform data security monitoring based on oil and gas production risk influencing factors to generate oil and gas production risk monitoring data; perform stream engine optimization on the oil and gas production risk monitoring data to generate a dynamic risk indicator matrix; perform cluster parallel processing on the dynamic risk indicator matrix to generate an oil production risk feature vector;

[0084] In an embodiment of the present invention, environmental data and monitoring indicator data, such as geological deformation monitoring, hydrogeological monitoring, surface subsidence monitoring, etc., are collected in real time by using a deployed sensor network. The collected monitoring data is stored in a data center or cloud platform, and real-time data quality checks and corrections are performed to ensure the reliability and integrity of the data. A specific data stream engine or real-time data processing platform, such as Apache Kafka, Spark Streaming, etc., is selected to process real-time streaming data. The data processing process is designed and optimized, including steps such as data cleaning, real-time computing, and anomaly detection to generate a dynamic risk indicator matrix. A high-performance computing cluster or cloud computing platform is configured to support large-scale data processing and parallel computing requirements. Suitable parallel processing algorithms, such as MapReduce, Spark, etc., are selected and implemented to efficiently process dynamic risk indicator matrix data. Key features, such as risk trends, abnormal event predictions, etc., are extracted from the processed data to form a characteristic vector of oil production risk.

[0085] Step S4: construct a dynamic assessment model for oil engineering safety risks; import the dynamic risk indicator matrix into the dynamic assessment model for oil engineering safety risks to predict mining risks and generate oil engineering mining risk prediction data; perform risk propagation simulation on the oil engineering mining risk prediction data and generate a oil engineering risk propagation path map;

[0086] In the embodiment of the present invention, by selecting a model suitable for the safety risk assessment of petroleum engineering, it can be a model based on statistical analysis, machine learning or deep learning, such as logistic regression, decision tree, neural network, etc. The dynamic risk indicator matrix generated in step S3 and other relevant data are integrated into the assessment model to establish a complete risk assessment framework. The imported risk indicator matrix is ​​subjected to preprocessing steps such as data cleaning, feature selection and standardization to improve the accuracy and stability of the model. The model is trained using historical data, and the performance of the model is evaluated using methods such as cross-validation. The prediction results are generated, i.e., various risks occurring during the exploitation process of petroleum engineering. A specific risk propagation model, such as a Bayesian network, a propagation dynamics model, etc., is selected to simulate the propagation path and influence mechanism of different risk factors in the petroleum engineering system. Risk propagation simulation and analysis are performed based on the predicted data, key risk nodes and propagation paths are identified, and a risk propagation path map is generated. The generated risk propagation path map is used to provide decision makers with scientific basis and strategic suggestions to help them formulate effective risk management and response measures.

[0087] Step S5: Mark the high-risk stages of the petroleum engineering risk propagation path map and generate high-risk petroleum engineering stage data; make dynamic risk decisions on the high-risk petroleum engineering stage data and generate high-risk petroleum engineering stage decision strategies to execute petroleum engineering safety risk adjustment operations.

[0088] In an embodiment of the present invention, the risk level and impact degree of each stage or node are identified by the risk propagation path map generated based on step S4. According to the risk assessment results, the entire exploitation process of the petroleum project is divided into different stages, and the high-risk stages or key nodes are identified. In combination with the risk assessment results and the propagation path map, decision-making strategies and countermeasures are formulated for high-risk stages. Taking into account real-time data updates and risk changes, the decision-making strategy is dynamically adjusted to ensure that it adapts to the changes and complexity in the exploitation process of the petroleum project. According to the formulated decision-making strategy, the corresponding safety risk adjustment operations are performed, including adjusting the project progress, improving safety facilities, optimizing operating procedures, etc. During the implementation process, the risk status and effects are continuously monitored, and timely feedback and adjustment measures are given to ensure the safe operation and environmental protection of the petroleum project.

[0089] Preferably, step S1 comprises the following steps:

[0090] Step S11: using GIS to obtain regional geological data for petroleum engineering;

[0091] Step S12: Analyze the mining range of the petroleum engineering regional geological data to generate petroleum mining range data;

[0092] Step S13: Perform multi-dimensional sensor deployment based on the oil production range data to generate an oil production sensor deployment network;

[0093] Step S14: Collect environmental sensor data based on the oil production sensor deployment network to obtain oil production environment collection data; perform data preprocessing on the oil production environment collection data to generate standard oil production environment collection data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization.

[0094] In an embodiment of the present invention, by determining the way and source of data acquisition, such as geological survey reports, satellite remote sensing data, ground exploration data, etc., geological maps and exploration reports can be obtained from local mineral resources bureaus, or high-resolution surface coverage information can be obtained using public satellite data platforms. Geological data from different sources are imported into GIS software (such as ArcGIS, QGIS) for integration and processing. Clean the data to remove duplicate or inaccurate data points to ensure the quality and accuracy of geological data. Use GIS tools to analyze geological characteristics, such as stratum distribution, lithology, structural characteristics, etc. Perform geological terrain analysis, generate terrain models and terrain maps, so as to facilitate subsequent mining range analysis and sensor layout optimization. Perform spatial analysis based on geological data on the GIS platform to determine the geological area suitable for mining. Use terrain models and terrain maps, combined with geological characteristics, to analyze the potential distribution area of ​​oil resources and the feasible mining range. Use GIS tools to create a spatial data model of the mining range, including polygonal or raster layers, for describing and visualizing the mining range. Determine the boundaries and restrictions of the mining area, such as environmental protection areas, geological safety areas, etc., as well as the relationship with surrounding land use and resources. Evaluate the economic feasibility, technical feasibility and environmental impact of different mining ranges. Use spatial analysis tools and models to optimize mining strategies and select the optimal mining area and development plan. Select suitable multi-dimensional sensors based on the determined mining range and geological characteristics. Including environmental monitoring sensors (such as weather stations, water quality sensors), security monitoring equipment (such as surveillance cameras, vibration sensors), geological exploration equipment (such as drilling machines, seismographs), etc. Design the sensor layout plan and determine the location, installation height and coverage of the sensors. Consider the communication network between sensors, select specific data transmission technology and communication protocols to ensure real-time data transmission and effective management. Optimize the sensor deployment network to ensure that sensors can fully cover the mining area and monitor the integrity and accuracy of data. Implement remote monitoring and data management systems to respond to sensor data anomalies in a timely manner to ensure the stable operation and security of the system. The deployed sensor network collects environmental data in real time, such as temperature, humidity, air pressure, groundwater level and other multi-dimensional data. During the data collection process, ensure the timeliness and continuity of the data to avoid data loss and delay. Perform preliminary cleaning on the collected environmental data to remove outliers and erroneous data to ensure data quality and accuracy. Fill in missing data values ​​and use specific interpolation methods or statistical methods to fill in missing data to ensure data integrity and continuity. Standardize the data collected by different sensors to unify the dimensions and range of the data for subsequent data analysis and comparison. Generate a standard oil production environment collection data set based on the standardized data for subsequent risk assessment and decision analysis.

[0095] As an example of the present invention, refer to Figure 2As shown, in this example, step S2 includes:

[0096] Step S21: extracting geological data from the standard oil production environment collection data to obtain oil production geological data, wherein the oil production geological data includes geological exploration data and drilling data;

[0097] Step S22: converting the geological exploration data and the drilling data into oil production geographic elevation data to generate oil production geographic elevation data;

[0098] Step S23: Perform multi-level oil production impact assessment based on oil production geographic elevation data to generate multi-level oil production impact data;

[0099] Step S24: Perform multi-field coupling numerical simulation on the multi-level geological influencing factors of oil production to generate oil and gas production risk influencing factors.

[0100] In an embodiment of the present invention, geological data including geological exploration data and drilling data are extracted from data collected from a standard oil production environment. The integrity and accuracy of the data are ensured, and the existing outliers or erroneous data are processed. Geological exploration data are extracted, including geological characteristics, stratigraphic information, lithology distribution, etc. A geological analysis tool (such as a geological information system) is used to parse and analyze the exploration data to extract key geological parameters. Geological information is extracted from the drilling data, including stratigraphic structure, rock type, porosity and other data at different depths. The drilling data is interpreted and analyzed to generate a geological profile and a stratigraphic distribution map. The geological information in the geological exploration data and the drilling data is converted to geographic elevation. The original data is converted to geographic elevation data using a geographic information system (GIS) tool or professional geological modeling software. The converted geographic elevation data is integrated into a unified data model to ensure the consistency and comparability of the data. A geographic elevation model for oil production is established, including the spatial distribution and change trend of various geological parameters. A multi-level impact assessment model is established based on the geographic elevation data for oil production. Combine geological data and geographic elevation data to analyze the multi-level impact of oil extraction on the surrounding environment, including geology, hydrology, ecology and other aspects. Use numerical simulation methods or professional geological engineering software to calculate and analyze the impact assessment model. Generate multi-level impact data of oil extraction, including the spatial distribution, change trend and quantitative assessment results of influencing factors. Based on the multi-level impact data of oil extraction, conduct multi-field coupling numerical simulation. Couple multiple factors such as geological influencing factors, terrain characteristics, and hydrological environment to simulate the comprehensive impact of oil extraction on groundwater, surface water, geological structure, etc. Use numerical simulation results to analyze the risk influencing factors of oil extraction, including geological stability, hydrological safety, ecological protection, etc. Generate spatial distribution maps and quantitative analysis results of oil and gas extraction risk influencing factors to provide a scientific basis for risk assessment and decision-making.

[0101] Preferably, step S23 includes the following steps:

[0102] Step S231: performing mining strata division based on the oil mining geographic elevation data to generate mining strata division data; performing stratum lithology analysis on the standard oil mining environment acquisition data based on the mining stratum division data to generate stratum lithology analysis data; performing fault structure analysis on the stratum lithology analysis data to generate oil mining geological impact data;

[0103] Step S232: Perform oil and gas mining rock mechanical property analysis on the oil mining geographic elevation data to generate rock mechanical property data; perform formation pressure analysis on the standard oil mining environment collection data through the rock mechanical property data to generate oil mining mechanical influence data;

[0104] Step S233: Calculate the oil and gas reservoir distribution based on the oil production geographic elevation data to obtain the oil and gas reservoir distribution data; evaluate the oil and gas fluid properties based on the oil and gas reservoir distribution data to generate the oil and gas fluid property evaluation data; integrate the oil production geological influence data, the oil production mechanical influence data and the oil and gas fluid property evaluation data to generate the multi-level influence data of oil production.

[0105] In an embodiment of the present invention, the geographic elevation data of oil production is imported and processed by using a geographic information system (GIS) tool. The depth range and resolution of the production stratum division are determined, and the analysis parameters are set according to the actual production requirements. The geographic elevation data is divided using a stratum division algorithm, such as an algorithm based on depth, stratum characteristics or geological conditions. The production stratum division data is generated according to the division results, including the name of the stratum, the depth range and its characteristic description. Based on the production stratum division data, the standard oil production environment acquisition data is subjected to stratum lithology analysis. The key parameters such as the lithology composition, rock type, and porosity of each stratum are analyzed to generate stratum lithology analysis data. The stratum lithology analysis data is subjected to fault structure analysis. The fault characteristics that affect the stratum structure and stability are identified and described, and the geological impact data of oil production is generated for subsequent risk assessment and engineering design. The rock mechanics analysis method is used to analyze the rock mechanical properties of the oil production geographic elevation data. The mechanical properties such as elastic modulus, compressive strength, and tensile strength of the rock are measured and analyzed. Based on the rock mechanics property data, the standard oil production environment acquisition data is subjected to formation pressure analysis. Calculate and evaluate the mechanical effects on the formation during the mining process, including formation deformation, stress distribution, etc. Combine the results of rock mechanical property analysis and formation pressure analysis data to generate oil mining mechanical impact data. These data will be used to evaluate the geological and mechanical risks that occur during the mining process and provide a basis for engineering safety management. Use oil mining geographic elevation data to calculate the distribution of oil and gas reservoirs. Use geological information systems or professional geological modeling software to analyze and depict the distribution of reservoirs in space. Based on oil and gas reservoir distribution data, evaluate the properties of oil and gas fluids. Including the evaluation and analysis of parameters such as oil and gas production potential, fluid properties (such as viscosity, density, etc.) and formation permeability. Integrate oil mining geological impact data, oil mining mechanical impact data, and oil and gas fluid property evaluation data. Generate multi-level impact data for oil mining, reflecting the comprehensive impact of different factors in the mining process, and providing a basis for decision-making and risk management.

[0106] Preferably, calculating the distribution of oil and gas reservoirs based on the oil production geographic elevation data includes:

[0107] Carry out terrain modeling on the oil extraction geographic elevation data to generate oil extraction terrain data; generate contour lines on the oil extraction terrain data to obtain oil extraction contour line data; calculate the curvature of the oil extraction contour line data to obtain oil extraction terrain change data;

[0108] Use geological exploration data to judge the reservoir level of oil production terrain change data and generate initial oil production reservoir level thickness data; collect well logging data through initial oil production reservoir level thickness data to generate well logging data; calculate the porosity of well logging data based on formation lithology analysis data to obtain reservoir porosity data;

[0109] Based on the reservoir porosity data, the reservoir characteristics of the initial oil production reservoir layer thickness data are analyzed to obtain the initial reservoir permeability evaluation data and the initial reservoir saturation data; the initial reservoir permeability evaluation data and the initial reservoir saturation data are used to optimize the reservoir distribution of the oil production topographic change data to generate the oil production reservoir thickness map;

[0110] The oil and gas reservoir distribution is calculated on the oil production reservoir thickness map to obtain the oil and gas reservoir distribution data.

[0111] In an embodiment of the present invention, terrain modeling is performed on the oil production geographic elevation data by using a geographic information system (GIS) tool or professional geological modeling software. The geomorphic features of the terrain, such as mountains, plains, rivers, etc., are determined, and detailed oil production terrain data are generated. Based on the terrain data, oil production contour data is generated. The spacing and density of the contour lines are determined to reflect the elevation changes of the terrain and provide basic data for subsequent analysis. The curvature of the oil production contour data is calculated. The curvature calculation can evaluate the curvature and change rate of the terrain and reveal the complexity and stability of the terrain. The reservoir level judgment is performed on the oil production terrain change data using geological exploration data. The boundaries and distribution of different strata are determined to generate initial oil production reservoir level thickness data. The initial oil production reservoir level thickness data is used to collect well logging data. Based on the well logging data and the formation lithology analysis data, the porosity of each reservoir is calculated to obtain reservoir porosity data. Reservoir characteristics analysis is performed based on the reservoir porosity data. Calculate and evaluate the permeability and saturation of the initial reservoir, and generate initial reservoir permeability evaluation data and initial reservoir saturation data. Use the initial reservoir permeability evaluation data and initial reservoir saturation data to optimize the reservoir distribution of the oil production terrain change data. The optimization process takes into account the spatial distribution characteristics of permeability and saturation to improve the effective recovery rate and output of the reservoir. Generate an oil production reservoir thickness map based on the optimized reservoir distribution data. The thickness map reflects the distribution of reservoir thickness in different regions and depths, and provides basic data for the calculation of oil and gas reservoir distribution. Calculate the distribution of oil and gas reservoirs based on the oil production reservoir thickness map and terrain data. Use geological information systems or professional geological modeling software to analyze and simulate the distribution of oil and gas in different strata and generate oil and gas reservoir distribution data.

[0112] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0113] Step S31: Perform data security monitoring based on oil and gas production risk influencing factors to generate oil and gas production risk monitoring data;

[0114] Step S32: Optimizing the oil and gas production risk monitoring data using a stream engine to generate a dynamic risk indicator matrix;

[0115] Step S33: splitting the dynamic risk indicator matrix into data blocks to obtain dynamic risk data blocks; distributing the dynamic risk data blocks into cluster nodes to generate distributed dynamic risk data blocks;

[0116] Step S34: parallel processing of distributed dynamic risk data blocks to obtain local risk feature data; risk factor aggregation of the local risk feature data to generate an initial risk feature set; data dimension reduction of the initial risk feature set to generate an oil production risk feature vector.

[0117] In an embodiment of the present invention, oil and gas production related data from various sensors, monitoring equipment and geological exploration data are collected. Data from different sources, including geological data, environmental data, equipment operation data, etc., are integrated to form a complete oil and gas production monitoring data set. Key factors affecting oil and gas production safety, such as geological structure, groundwater conditions, seismic activity, etc., are determined. According to the actual situation, a specific model or algorithm is selected to analyze and quantify these influencing factors. Data analysis technology is used to monitor the safety risks in the oil and gas production process. Monitoring data is analyzed in real time or regularly to identify abnormal conditions and generate oil and gas production risk monitoring data. Design and implement a stream processing engine for processing large-scale data, such as Apache Kafka, Apache Flink, etc. Optimize the configuration of the stream engine to ensure that it can process high-speed and large-capacity data streams. The oil and gas production risk monitoring data is input into the stream engine to generate a dynamic risk indicator matrix. Determine and calculate various risk indicators, such as geological risk, operational risk, environmental risk, etc., and construct a dynamic indicator matrix. Divide the dynamic risk indicator matrix into data blocks of the same size. Ensure that each data block contains enough information for subsequent parallel processing. Distribute data blocks to multiple nodes in the cluster to form distributed dynamic risk data blocks. Rationally allocate and manage according to the computing power and storage resources of the cluster. Process distributed dynamic risk data blocks in parallel in the cluster. Use a distributed computing framework (such as ApacheSpark) or a custom parallel processing algorithm to efficiently process each data block. Aggregate local risk features in the processed data blocks. Calculate comprehensive indicators of various risk factors to reflect the overall oil and gas production safety risk status. Perform data dimensionality reduction on the aggregated initial risk feature set. Use principal component analysis (PCA) or other dimensionality reduction techniques to convert complex risk feature data into a more concise oil production risk feature vector.

[0118] Preferably, step S32 includes the following steps:

[0119] Step S321: accessing the oil and gas production risk monitoring data through stream data to obtain the oil and gas production risk monitoring data stream;

[0120] Step S322: define event patterns for the oil and gas production risk monitoring data stream through complex time processing rules to generate an oil and gas production event monitoring stream; perform key event detection on the oil and gas production event detection stream to generate oil and gas production risk key events;

[0121] Step S323: Allocate risk weights to key oil and gas production risk events and generate a dynamic risk indicator matrix.

[0122] In an embodiment of the present invention, the oil and gas production risk monitoring data streams from various monitoring devices, sensors and other data sources are connected to the system. Ensure the stability and real-time performance of the data source to support subsequent event processing and analysis. Use a stream processing framework (such as Apache Kafka, Apache Flink, etc.) to manage and process data streams. Configure the data stream pipeline to ensure that the data can arrive and be processed on time. Design and implement complex time processing rules to identify and define different types of oil and gas production event patterns. According to actual needs and domain knowledge, formulate rules and algorithms that can capture important events. According to the defined event pattern rules, extract and generate oil and gas production event monitoring streams from the oil and gas production risk monitoring data stream. Ensure that the identification and extraction of events can accurately reflect the actual engineering safety and operation conditions. Perform key event detection on the generated oil and gas production event monitoring stream. Use machine learning algorithms or rule engines to identify and filter out events with important impacts to form a set of key events for oil and gas production risks. Assign risk weights to the detected key events of oil and gas production risks. Assign risk weights to each event based on the type, severity and potential impact of the event. Combine the assigned risk weights to build a dynamic risk indicator matrix. Ensure that the matrix can reflect the combined impact of different events and risk factors, and provide a basis for subsequent risk assessment and management.

[0123] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0124] Step S41: constructing a dynamic assessment model for oil engineering safety risks; importing a dynamic risk indicator matrix into the dynamic assessment model for oil engineering safety risks to perform mining risk prediction and generate oil engineering mining risk prediction data;

[0125] Step S42: defining the network nodes of the petroleum engineering project through the oil and gas production risk influencing factors to obtain the network node data of the petroleum engineering project; constructing the risk propagation network structure based on the network node data of the petroleum engineering project to obtain the initial risk propagation network structure;

[0126] Step S43: assigning node weights to the initial risk propagation network structure according to the oil production risk prediction data to generate a risk propagation network structure; simulating the propagation process of the risk propagation network structure to generate risk propagation process simulation data;

[0127] Step S44: Based on the risk propagation process simulation data, the node propagation path of the risk propagation network structure is traced to generate a petroleum engineering risk propagation path diagram.

[0128] In an embodiment of the present invention, a dynamic risk indicator matrix and other relevant data, such as geological data, environmental monitoring data, etc., are collected and prepared. Data cleaning, missing value filling and data standardization are performed to ensure data quality and consistency. A suitable evaluation model is selected, such as a regression model based on machine learning, a neural network model or a statistical model. The structure and algorithm of the evaluation model are constructed according to data characteristics and objectives. The prepared data set is divided into a training set, a validation set and a test set. The evaluation model is trained with the training set, and the generalization ability and performance of the model are evaluated with the validation set. The hyperparameters and structure of the model are adjusted, and the model is optimized to improve the prediction accuracy and robustness. The trained and optimized evaluation model is used to predict the future safety risks of petroleum engineering. The prediction data of petroleum engineering exploitation risks are generated, including the possibility and impact of risk events. According to the actual situation and influencing factors of petroleum engineering, the key nodes of the project are defined. The nodes may include important elements such as facilities, operating activities, environmental conditions, and the relationships and mutual influences between them. Based on the defined nodes and the associations between them, the risk propagation network structure of the petroleum engineering project is constructed. The network structure should reflect the risk propagation path and the impact diffusion mode between different nodes. Assign weights to each node based on the oil production risk prediction data and the importance of the node. The weights can be determined based on the probability of risk occurrence, the scope of impact, or other quantitative indicators. Use mathematical modeling or simulation technology to simulate the process of risk propagation in the constructed risk propagation network structure. The simulation process includes information such as the diffusion path of the risk from the starting node to other nodes and the change in risk level. Based on the results of the propagation simulation, track and record the propagation path and impact of the risk in the network structure. Determine the main propagation path and risk expansion direction, as well as the interaction between the nodes. Visualize the traced propagation path and related data to generate a petroleum engineering risk propagation path map. Graphically display the risk propagation process to help decision makers understand and respond to risk events.

[0129] Preferably, step S41 includes the following steps:

[0130] Step S411: splitting the dynamic risk indicator matrix into data to obtain a model training set, a model verification set and a model test set;

[0131] Step S412: Perform model training on the model training set using a deep neural network algorithm to generate a risk assessment training model; perform model generalization capability evaluation on the risk assessment training model using a model validation set to generate model generalization performance data;

[0132] Step S413: adjusting the model architecture and hyperparameters of the risk assessment training model through the model generalization performance data, thereby generating a risk assessment adjustment model; performing forward propagation calculation on the risk assessment adjustment model according to the model test set, thereby generating risk assessment test data;

[0133] Step S414: perform predictive performance evaluation on the risk assessment test data to generate model predictive performance evaluation data; perform iterative optimization on the risk assessment adjustment model based on the model predictive performance evaluation data to generate a dynamic assessment model for petroleum engineering safety risks; import the dynamic risk indicator matrix into the dynamic assessment model for petroleum engineering safety risks to perform mining risk prediction to generate petroleum engineering mining risk prediction data.

[0134] In an embodiment of the present invention, the dynamic risk indicator matrix is ​​split according to a certain ratio (for example, the ratio of training set, validation set, and test set) to ensure that the data of the training model is sufficient and effective. A model training set, a model validation set, and a model test set are formed respectively. A suitable deep neural network algorithm, such as a multilayer perceptron (MLP), a convolutional neural network (CNN), or a recurrent neural network (RNN), is selected for the construction of a risk assessment model. The deep neural network model is trained using the model training set, and the model parameters are optimized by the back propagation algorithm so that the model can better fit the training data. The model validation set is used to evaluate the generalization ability of the trained model, that is, the performance of the model on unseen validation data. The performance of the model on the validation set is analyzed, including indicators such as accuracy, precision, and recall, to evaluate the generalization ability of the model and whether there is an overfitting or underfitting problem. According to the model generalization performance data, the model architecture (such as the number of layers, the number of nodes, etc.) and hyperparameters (such as learning rate, batch size, etc.) are adjusted and optimized to further improve the performance and generalization ability of the model. Combined with the adjusted and optimized model architecture and hyperparameters, the final risk assessment adjustment model is generated. The model can more accurately predict the safety risks in the process of petroleum engineering exploitation, and has good generalization ability and stability. The model test set is used for forward propagation calculation to generate risk assessment test data. The prediction performance of the test data is evaluated to evaluate the prediction accuracy and effect of the model. According to the prediction performance evaluation data, the model is iteratively optimized to further improve the prediction ability and practicality of the model. The dynamic risk indicator matrix is ​​imported into the constructed dynamic assessment model of petroleum engineering safety risks. The model is used to predict and evaluate the risks of petroleum engineering exploitation, and the prediction data of petroleum engineering exploitation risks are generated, including potential risk events, their impact and probability of occurrence.

[0135] Preferably, step S5 comprises the following steps:

[0136] Step S51: marking the petroleum engineering safety risks on the petroleum engineering risk propagation path map to obtain petroleum engineering stage risk marking data;

[0137] Step S52: Compare the petroleum engineering stage risk identification data with a preset stage risk identification data threshold value, and when the petroleum engineering stage risk identification data is greater than or equal to the preset stage risk identification threshold value, high-risk petroleum engineering stage data is generated;

[0138] Step S53: Perform dynamic risk decision-making on high-risk petroleum engineering stage data, generate high-risk petroleum engineering stage decision-making strategies, and execute petroleum engineering safety risk adjustment operations.

[0139] In the embodiment of the present invention, each risk propagation path is analyzed and identified in detail by using the petroleum engineering risk propagation path diagram generated based on step S44. The key nodes and key events on each path and their potential impact on the safety of the petroleum engineering are determined. According to the analysis results, the petroleum engineering stage risk identification data is generated, and the risk level of each stage is identified and classified. Including information such as the description of the risk, possible impact, cost and time risk. A preset stage risk identification data threshold is set as a basis for determining high risk. The threshold can be set according to project characteristics, regulatory requirements and actual experience. The generated petroleum engineering stage risk identification data is compared and analyzed with the set threshold. When the petroleum engineering stage risk identification data is greater than or equal to the preset stage risk identification threshold, the stage is identified as a high-risk petroleum engineering stage, and the corresponding high-risk petroleum engineering stage data is generated. Dynamic risk decision analysis is performed on the high-risk petroleum engineering stage data. A safety risk adjustment strategy is formulated for each high-risk stage, including risk response measures, emergency response plans and resource allocation plans. According to the formulated dynamic risk decision strategy, the petroleum engineering safety risk adjustment operation is performed. Ensure the implementation of security risk control measures, monitor the effectiveness during execution, and adjust and optimize strategies based on actual conditions.

[0140] The beneficial effect of the present invention is that by acquiring geological data of the petroleum engineering area, key geological information can be obtained, providing accurate basic data for subsequent sensor deployment and decision-making. By deploying multi-dimensional sensors on geological data, a sensor network covering the entire oil production area can be established to collect environmental sensor data. Through environmental sensor data collection, standard oil production environment data can be obtained to provide a basis for subsequent evaluation and decision-making. By converting the standard oil production environment collection data into geographic elevation, oil production geographic elevation data can be generated, further providing a basis for oil production impact assessment. Based on oil production geographic elevation data, multi-level oil production impact assessment can be performed to obtain multi-level impact data of oil production, which helps understand the impact of production on the environment. Multi-field coupled numerical simulation of multi-level geological impact factors of oil production can generate oil and gas production risk impact factors for subsequent risk monitoring and evaluation. Data security monitoring based on oil and gas production risk impact factors can generate oil and gas production risk monitoring data for real-time monitoring and control of production risks. Stream engine optimization of oil and gas production risk monitoring data can generate a dynamic risk indicator matrix to provide more accurate data for subsequent risk assessment and prediction. By constructing a dynamic assessment model for oil engineering safety risks and importing a dynamic risk indicator matrix into the model for mining risk prediction, oil engineering mining risk prediction data can be generated, and risk propagation simulation can be performed to generate a oil engineering risk propagation path map. The oil engineering risk propagation path map is marked with high risks at different stages to generate high-risk oil engineering stage data, and dynamic risk decisions are made on the high-risk oil engineering stage data to generate high-risk oil engineering stage decision strategies to perform oil engineering safety risk adjustment operations, which can achieve the assessment, prediction and decision-making of oil engineering safety risks, thereby improving the safety and sustainability of oil engineering. Therefore, the present invention improves the dynamic perception and immediate response capabilities of oil engineering safety risks by integrating data, dynamically monitoring and analyzing risk propagation paths for oil engineering stage data, and evaluating oil engineering safety risks.

[0141] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0142] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for constructing a dynamic assessment model for petroleum engineering safety risks, characterized in that: The following steps are involved: Step S1: Acquire geological data of the petroleum engineering region; perform multi-dimensional sensor deployment on the geological data of the petroleum engineering region to generate an oil production sensor deployment network; Based on the oil production sensor deployment network, environmental sensor data collection is carried out to obtain standard oil production environment collection data; Step S2: converting the standard oil production environment collection data into oil production geographic elevation data to generate oil production geographic elevation data; performing a multi-level oil production impact assessment based on the oil production geographic elevation data to generate oil production multi-level impact data; Conduct multi-field coupling numerical simulation on multi-level geological influencing factors of oil production to generate oil and gas production risk influencing factors; Step S3: Perform data security monitoring based on oil and gas production risk influencing factors to generate oil and gas production risk monitoring data; Optimize the flow engine of oil and gas production risk monitoring data to generate a dynamic risk indicator matrix; Perform cluster parallel processing on the dynamic risk indicator matrix to generate the oil production risk feature vector; Step S4: construct a dynamic assessment model for oil engineering safety risks; import the dynamic risk indicator matrix into the dynamic assessment model for oil engineering safety risks to predict mining risks and generate oil engineering mining risk prediction data; perform risk propagation simulation on the oil engineering mining risk prediction data and generate a oil engineering risk propagation path map; Step S5: Mark the high-risk stages of the petroleum engineering risk propagation path map and generate high-risk petroleum engineering stage data; make dynamic risk decisions on the high-risk petroleum engineering stage data and generate high-risk petroleum engineering stage decision strategies to execute petroleum engineering safety risk adjustment operations.

2. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: using GIS to obtain regional geological data for petroleum engineering; Step S12: Analyze the mining range of the petroleum engineering regional geological data to generate petroleum mining range data; Step S13: Perform multi-dimensional sensor deployment based on the oil production range data to generate an oil production sensor deployment network; Step S14: Collect environmental sensor data based on the oil production sensor deployment network to obtain oil production environment collection data; perform data preprocessing on the oil production environment collection data to generate standard oil production environment collection data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization.

3. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: extracting geological data from the standard oil production environment collection data to obtain oil production geological data, wherein the oil production geological data includes geological exploration data and drilling data; Step S22: converting the geological exploration data and the drilling data into oil production geographic elevation data to generate oil production geographic elevation data; Step S23: Perform multi-level oil production impact assessment based on oil production geographic elevation data to generate multi-level oil production impact data; Step S24: Perform multi-field coupling numerical simulation on the multi-level geological influencing factors of oil production to generate oil and gas production risk influencing factors.

4. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 3 is characterized in that: Step S23 includes the following steps: Step S231: performing mining strata division based on the oil mining geographic elevation data to generate mining strata division data; performing stratum lithology analysis on the standard oil mining environment acquisition data based on the mining stratum division data to generate stratum lithology analysis data; performing fault structure analysis on the stratum lithology analysis data to generate oil mining geological impact data; Step S232: Perform oil and gas mining rock mechanical property analysis on the oil mining geographic elevation data to generate rock mechanical property data; perform formation pressure analysis on the standard oil mining environment collection data through the rock mechanical property data to generate oil mining mechanical influence data; Step S233: Calculate the oil and gas reservoir distribution based on the oil production geographic elevation data to obtain the oil and gas reservoir distribution data; evaluate the oil and gas fluid properties based on the oil and gas reservoir distribution data to generate the oil and gas fluid property evaluation data; integrate the oil production geological influence data, the oil production mechanical influence data and the oil and gas fluid property evaluation data to generate the multi-level influence data of oil production.

5. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 4 is characterized in that: Calculation of oil and gas reservoir distribution based on oil production geographic elevation data includes: Carry out terrain modeling on the oil extraction geographic elevation data to generate oil extraction terrain data; generate contour lines on the oil extraction terrain data to obtain oil extraction contour line data; calculate the curvature of the oil extraction contour line data to obtain oil extraction terrain change data; Use geological exploration data to judge the reservoir level of oil production terrain change data and generate initial oil production reservoir level thickness data; collect well logging data through initial oil production reservoir level thickness data to generate well logging data; calculate the porosity of well logging data based on formation lithology analysis data to obtain reservoir porosity data; Based on the reservoir porosity data, the reservoir characteristics of the initial oil production reservoir layer thickness data are analyzed to obtain the initial reservoir permeability evaluation data and the initial reservoir saturation data; the initial reservoir permeability evaluation data and the initial reservoir saturation data are used to optimize the reservoir distribution of the oil production topographic change data to generate the oil production reservoir thickness map; The oil and gas reservoir distribution is calculated on the oil production reservoir thickness map to obtain the oil and gas reservoir distribution data.

6. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Perform data security monitoring based on oil and gas production risk influencing factors to generate oil and gas production risk monitoring data; Step S32: Optimizing the oil and gas production risk monitoring data using a stream engine to generate a dynamic risk indicator matrix; Step S33: splitting the dynamic risk indicator matrix into data blocks to obtain dynamic risk data blocks; distributing the dynamic risk data blocks into cluster nodes to generate distributed dynamic risk data blocks; Step S34: parallel processing of distributed dynamic risk data blocks to obtain local risk feature data; risk factor aggregation of the local risk feature data to generate an initial risk feature set; data dimension reduction of the initial risk feature set to generate an oil production risk feature vector.

7. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 6 is characterized in that: Step S32 includes the following steps: Step S321: accessing the oil and gas production risk monitoring data through stream data to obtain the oil and gas production risk monitoring data stream; Step S322: define event patterns for the oil and gas production risk monitoring data stream through complex time processing rules to generate an oil and gas production event monitoring stream; perform key event detection on the oil and gas production event detection stream to generate oil and gas production risk key events; Step S323: Allocate risk weights to key oil and gas production risk events and generate a dynamic risk indicator matrix.

8. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: constructing a dynamic assessment model for oil engineering safety risks; importing a dynamic risk indicator matrix into the dynamic assessment model for oil engineering safety risks to perform mining risk prediction and generate oil engineering mining risk prediction data; Step S42: defining the network nodes of the petroleum engineering project through the oil and gas production risk influencing factors to obtain the network node data of the petroleum engineering project; constructing the risk propagation network structure based on the network node data of the petroleum engineering project to obtain the initial risk propagation network structure; Step S43: assigning node weights to the initial risk propagation network structure according to the oil production risk prediction data to generate a risk propagation network structure; simulating the propagation process of the risk propagation network structure to generate risk propagation process simulation data; Step S44: Based on the risk propagation process simulation data, the node propagation path of the risk propagation network structure is traced to generate a petroleum engineering risk propagation path diagram.

9. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 8 is characterized in that: Step S41 includes the following steps: Step S411: splitting the dynamic risk indicator matrix into data to obtain a model training set, a model verification set and a model test set; Step S412: Perform model training on the model training set using a deep neural network algorithm to generate a risk assessment training model; perform model generalization capability evaluation on the risk assessment training model using a model validation set to generate model generalization performance data; Step S413: adjusting the model architecture and hyperparameters of the risk assessment training model through the model generalization performance data, thereby generating a risk assessment adjustment model; performing forward propagation calculation on the risk assessment adjustment model according to the model test set, and generating risk assessment test data; Step S414: perform predictive performance evaluation on the risk assessment test data to generate model predictive performance evaluation data; perform iterative optimization on the risk assessment adjustment model based on the model predictive performance evaluation data to generate a dynamic assessment model for petroleum engineering safety risks; import the dynamic risk indicator matrix into the dynamic assessment model for petroleum engineering safety risks to perform mining risk prediction to generate petroleum engineering mining risk prediction data.

10. The method for constructing a dynamic assessment model for petroleum engineering safety risks according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: marking the petroleum engineering safety risks on the petroleum engineering risk propagation path map to obtain petroleum engineering stage risk marking data; Step S52: Compare the petroleum engineering stage risk identification data with a preset stage risk identification data threshold value, and when the petroleum engineering stage risk identification data is greater than or equal to the preset stage risk identification threshold value, high-risk petroleum engineering stage data is generated; Step S53: Perform dynamic risk decision-making on high-risk petroleum engineering stage data, generate high-risk petroleum engineering stage decision-making strategies, and execute petroleum engineering safety risk adjustment operations.

Citation Information

Patent Citations

  • Method for quantitatively calculating integrated risks of shaft integrity

    CN107403266A

  • Well control risk dynamic quantitative evaluation method and system based on multi-factor fusion

    CN114819677A

  • System and method for monitoring underground environment of risk site in real time

    CN115237972A

  • Drilling engineering geological factor integrated quantitative analysis method and device

    CN116433057A

  • Offshore oil pollution monitoring system and method based on data analysis

    CN117787694A

Cited By

  • Land space monitoring system based on remote sensing data modeling

    CN120198820A

  • Coal seam gas extraction effective radius dynamic evaluation system based on porous linkage coupling

    CN121639040A

  • Porous linkage coupling-based coal seam gas extraction effective radius dynamic evaluation system

    CN121639040B