Edge computing intelligent gateway system for oil and gas industry

Abstract

The invention relates to the technical field of oil and gas management, in particular to an edge computing intelligent gateway system for the oil and gas industry. The data acquisition unit is used for acquiring real-time operation data from oil and gas production equipment and preprocessing the real-time operation data; the edge processing unit comprises a processor and at least one memory module; the communication module supports two-way communication with a central data center; the self-diagnosis and recovery module is used for automatically identifying faults or performance reduction of the system and implementing corrective measures by restarting affected sub-modules or reconfiguring system resources; the correlation analysis module identifies potential production efficiency improvement points or safety risks through an algorithm in the edge processing unit, through integration of advanced data processing and real-time analysis functions, the system significantly improves the intelligent level of oil and gas production, provides powerful support for decision making in the production process, and improves the production efficiency of the oil and gas production. The manual intervention requirement is reduced, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas management, and particularly to an edge computing intelligent gateway system for the oil and gas industry. Background Art

[0002] In the modern oil and gas industry, with the rapid development of technology, a large amount of data has been generated, which is of great value for operation optimization, safety monitoring, resource management, and future decision-making. For example, CN110048894A discloses a multi-well data acquisition and intelligent monitoring method and system for oil and gas production. Data acquisition terminals are arranged in each oil and gas wellhead area for acquiring production data, where the production data includes dynamometer cards, current, voltage, pressure, and temperature. An edge computing platform is arranged at the oil and gas production site. The edge computing platform is an intelligent monitoring gateway with computing capabilities and acceleration hardware. The intelligent monitoring gateway communicates with a number of data acquisition terminals through a LoRa network to form a star network, receives the data acquired by the data acquisition terminals, and analyzes and processes the data. A machine learning training platform communicates with the edge computing platform through a network, is used to receive the data analyzed and processed by the edge computing platform, trains to obtain a learning model, and pushes and loads the learning model to the edge computing platform. The edge computing platform uses the learning model to perform learning and inference on the received data to achieve online monitoring and response. While solving the problems of oilfield Internet of Things construction, the present invention simplifies the network structure and reduces the construction and maintenance costs. Another example is CN112859795A, which discloses a method and system for safety data acquisition and management of oil and gas equipment. The method includes acquiring on-site safety data of target oil and gas equipment; based on edge computing, transmitting the on-site safety data to a cloud server in real time, where the cloud server uses a private cloud; and receiving diagnosis and debugging of a remote terminal when there are safety risks in the on-site safety data. This application solves the technical problems of being unable to remotely and real-time monitor the operation parameters of oil and gas equipment, and the statistical analysis and management of equipment data. Through this application, remote real-time monitoring of the operation parameters of oil and gas equipment, statistical analysis of equipment data, remote management, and safety warning are achieved.

[0003] However, most of the traditional data processing systems deployed in the current industry rely on a central server for data collection and analysis, which not only causes huge data transmission delays but also increases the risks during the operation process, because immediate response to critical data is the key to ensuring safety and efficiency.

[0004] The limitations of the prior art are also manifested in the limitations of data processing. Although a large amount of data has been collected, traditional methods often fail to make full use of this data because they lack the ability to analyze real-time data and the function of timely identifying potential risks. For example, the data generated by on-site devices in remote oil fields needs to be transmitted to a central system for processing and analysis. This centralized architecture limits the speed and efficiency of real-time data processing and is also not conducive to rapid response in case of emergencies.

[0005] In addition, although some predictive maintenance and anomaly detection methods have been adopted, the response of these systems is still not fast enough, and conventional methods may not be able to effectively identify hidden patterns or potential risks in complex environments. These systems usually lack self-diagnosis and self-recovery capabilities. Once a failure or anomaly occurs, manual intervention may be required, which increases the operating cost and potential safety risks. Summary of the Invention

[0006] Based on the above purposes, the present invention provides an edge computing intelligent gateway system for the oil and gas industry.

[0007] An edge computing intelligent gateway system for the oil and gas industry, the system includes: Central data center; Data acquisition unit, configured with a variety of sensor interfaces, for obtaining real-time operation data from oil and gas production equipment and preprocessing the data; Edge processing unit, including a processor and at least one memory module, the processor is used to perform tasks such as data filtering, temporary storage, and critical data identification, and the memory module is used to temporarily store the preprocessed data received from the data acquisition unit; Communication module, supporting two-way communication with the central data center, receiving critical data from the edge processing unit and sending it to the central data center, and at the same time receiving instructions from the central data center and transmitting them to the edge processing unit; Self-diagnosis and recovery module, having a system status monitoring function based on predefined rules, automatically identifying system failures or performance degradation, and implementing corrective measures by restarting affected sub-modules or reconfiguring system resources. This self-diagnosis and recovery module determines potential system problems by analyzing data processing logs and performance metrics from the edge processing unit; Correlation analysis module, configured to analyze the correlation between the operation data collected from the data acquisition unit and the historical data from the central data center, and identify potential production efficiency improvement points or safety risks through algorithms in the edge processing unit.

[0008] Furthermore, the real-time operation data obtained by the data acquisition unit includes: Pressure data, temperature data, flow data, equipment status information, composition analysis data, safety data, and environmental monitoring data.

[0009] Further, the processor of the edge processing unit specifically includes: Data filtering: The processor performs an initial screening on the raw operation data received from the data acquisition unit, identifying and eliminating abnormal, redundant, or invalid data through set parameter thresholds, data integrity verification, and timestamp verification, and only retaining information valuable for subsequent analysis and decision-making. Temporary storage: The processor temporarily stores the filtered valid data in the memory module for immediate data processing and quick access, ensuring the system's response speed and real-time data processing ability by alleviating network latency and reducing the continuous data transmission requirements for the central data center. Critical data identification: The processor analyzes the data in the memory to identify data elements or patterns that are critical for production operations, safety monitoring, or future decision-making. This critical data will be marked and given priority processing to ensure that urgent or important information can be quickly responded to and transmitted.

[0010] Further, the critical data identification specifically includes: Defining threshold values for critical operation parameters by the processor, including pressure, temperature, and flow. When the monitored data exceeds these thresholds, it is identified as critical data. Using machine learning algorithms for pattern recognition, analyzing historical and real-time data to identify data patterns and trends indicating equipment failures, upcoming maintenance requirements, or potential safety issues. After identifying the critical data, classifying its priority based on the urgency, importance, and impact scope of the data. Dynamic context analysis: The processor considers relevant information from other systems and external sources, including weather conditions, the status of nearby operations, or geographical location information, to understand the critical data in context. Real-time notification and response mechanism: After the critical data is identified and classified, the processor activates a preset notification and response mechanism, including automatically adjusting production parameters, sending alerts to the central control center, or directly taking corrective measures on-site.

[0011] Further, the communication module specifically includes: Receiving critical data: The communication module is configured with an interface for receiving critical data from the edge processing unit. This data has been priority marked and classified by the edge processing unit, ensuring that the transmitted information is targeted and urgent. Data Encryption and Transmission: Before transmitting to the central data center, the communication module encrypts the critical data received, and then, through communication protocols and network connections, sends this data to the central data center; Receiving Center Instructions: The communication module has the function of continuous monitoring and can receive instructions and feedback from the central data center in real time; Instruction Parsing and Forwarding: After receiving an instruction, the communication module parses and validates it to confirm its effectiveness and security. After confirmation, the module forwards this instruction to the edge processing unit.

[0012] Furthermore, the self-diagnosis and recovery module specifically includes: Integrated real-time monitoring agents based on the microservices architecture. The real-time monitoring agents are distributed at key nodes of the intelligent gateway system, collecting system operation parameters in real time and transmitting the data to a preset fault detection engine. This fault detection engine uses pre-set benchmark thresholds and anomaly detection methods to identify readings outside the normal operation indicators; When potential faults are found, start an automated diagnostic sequence. This sequence uses a set of standardized test scripts and diagnostic tools, including the ping tool or traceroute; Based on the output of the automatic diagnosis, the system triggers pre-set recovery strategies. These recovery strategies include automatically repairing damaged data files using error correction codes, implementing a quick rollback to return to the nearest stable configuration state, or starting a backup channel to bypass damaged components.

[0013] Furthermore, the self-diagnosis and recovery module also includes: Remote Intervention Interface: For complex problems that require manual intervention, this self-diagnosis and recovery module provides an encrypted remote terminal interface, allowing technical support personnel to connect to the system and perform troubleshooting; Adaptive Tuning: By continuously collecting system performance data and using predictive analysis based on historical data, the self-diagnosis and recovery module identifies potential performance bottlenecks or future fault points and automatically adjusts the system configuration accordingly.

[0014] Furthermore, in the correlation analysis module, potential production efficiency improvement points or security risks are identified through algorithms in the edge processing unit, specifically as follows: Multi-dimensional Data Fusion: Utilize the edge processing unit to receive data from various sensors and devices in real time. Through data fusion technology, construct a comprehensive multi-dimensional view of the production site. This view combines data from different sources and displays it in a single interface; Association Rule Mining: Apply association rule mining algorithms to identify hidden patterns, correlations, or causal relationships existing between different data sources; Trend Prediction and Anomaly Detection: Using machine learning-based anomaly detection algorithms, continuously monitor changes in operating parameters, identify trends or immediate readings that deviate from the normal operating range, and give early warnings of potential equipment failures or unsafe conditions; Optimization Suggestion Generation: Based on association analysis, generate improvement suggestions, which include adjusting equipment parameters, changing maintenance plans, and implementing safety measures to improve production efficiency or reduce accident risks.

[0015] Furthermore, the anomaly detection algorithm is based on the Isolation Forest algorithm, and the Isolation Forest is used to effectively detect anomaly points, specifically including: Isolation Trees: The Isolation Forest consists of multiple isolation trees. When constructing each isolation tree, a random feature is selected and a random splitting value of this feature is chosen, which is between the maximum value and the minimum value, until the maximum height is reached or there are no more points to split.

[0016] Anomaly Score: The constructed Isolation Forest is used to predict anomalies, which is completed by calculating the path length; The calculation of the anomaly score is expressed by the following formula: ; where, is an instance, is the sample size, is in all isolation trees the average path length of; is a normalization factor, which is the average value of the path lengths given by the following formula: ; is the harmonic number, approximately .

[0017] Advantages of the present invention: In the present invention, by integrating advanced data processing and real-time analysis functions, the system significantly improves the intelligent level of oil and gas production. In particular, advanced algorithms such as FP-Growth and Isolation Forest adopted by the edge processing unit enable the system to quickly identify key data and abnormal patterns where the data is generated, so as to achieve an immediate response to potential production risks and efficiency bottlenecks. In addition, the association analysis module further explores the internal relationships between equipment parameters, reveals potential optimization points, and provides strong support for decision-making in the production process.

[0018] In the present invention, the communication module optimizes the data transmission process, ensuring the real-time, reliable and secure data transmission. The two-way communication mechanism with the central data center strengthens the cooperation between the edge and the center, enabling critical data and instructions to be transmitted in a timely and accurate manner, greatly improving the response speed and processing ability for emergency events. In addition, the addition of the self-diagnosis and recovery module enhances the stability and autonomy of the system, reduces the need for manual intervention, and lowers the maintenance cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a schematic diagram of the system module of an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the objectives, technical solutions and advantages of the present invention more clearly understood, the following further elaborates on the present invention in conjunction with specific embodiments.

[0022] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those of ordinary skill in the technical field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly. Embodiment 1

[0023] As Figure 1As shown in the figure, an edge computing intelligent gateway system for the oil and gas industry, the system includes: a central data center; a data acquisition unit, configured with a variety of sensor interfaces, for obtaining real-time operation data from oil and gas production equipment and preprocessing the data; an edge processing unit, including a processor and at least one memory module, the processor is used to perform tasks such as data filtering, temporary storage, and critical data identification, and the memory module is used to temporarily store the preprocessed data received from the data acquisition unit; a communication module, supporting two-way communication with the central data center, receiving critical data from the edge processing unit and sending it to the central data center, and at the same time receiving instructions from the central data center and transmitting them to the edge processing unit; a self-diagnosis and recovery module, having a system status monitoring function based on predefined rules, automatically identifying system failures or performance degradation, and implementing corrective measures by restarting affected sub-modules or reconfiguring system resources, the self-diagnosis and recovery module determines potential system problems by analyzing data processing logs and performance metrics from the edge processing unit; a correlation analysis module, configured to analyze the correlation between the operation data collected from the data acquisition unit and the historical data from the central data center, and identify potential production efficiency improvement points or safety risks through algorithms in the edge processing unit; Through the collaborative work of the above modules, the system realizes efficient data processing, real-time monitoring, and rapid response at the edge level, reduces the dependence on the central server, and at the same time optimizes the data flow and resource allocation in the oil and gas production process.

[0024] The real-time operation data obtained by the data acquisition unit includes: Pressure data: including pressure readings real-time monitored from key equipment such as wellheads, pipelines, and valves. Abnormal pressure changes may indicate potential equipment failures or safety risks; Temperature data: The system real-time monitors the temperature of equipment and the environment through temperature sensors. Temperature is an important parameter affecting the fluidity of oil and gas and the performance of equipment, so it needs to be closely monitored; Flow data: including the flow rate and total volume of fluids such as crude oil, natural gas, or water, which are key indicators for evaluating production performance; Equipment status information: such as on / off status, operating mode, vibration level, etc. These data help operators to understand the equipment operation status and performance in real-time; Composition analysis data: used to analyze the collected crude oil or natural gas samples in real-time to determine the proportion of chemical substances in them, such as sulfur content, hydrocarbon content, and the content of other impurities; Safety data: such as combustible gas concentration, radiation level, regional oxygen content, etc. These data are crucial for preventing potential safety accidents; Environmental monitoring data: including meteorological conditions (such as temperature, humidity, wind speed, wind direction) and other environmental data in the nearby area, which are very important for ensuring safe operation and environmental protection.

[0025] The processor of the edge processing unit specifically includes: Data filtering: The processor performs an initial screening on the raw operation data received from the data acquisition unit, identifying and eliminating abnormal, redundant or invalid data through set parameter thresholds, data integrity verification and timestamp verification, only retaining information valuable for subsequent analysis and decision-making, reducing unnecessary data load, optimizing data transmission and storage, and ensuring the effective utilization of system resources; Temporary storage: The processor temporarily stores the filtered valid data in the memory module for immediate data processing and quick access, ensuring the system's response speed and real-time data processing ability by alleviating network latency and reducing the continuous data transmission requirements for the central data center; Critical data identification: The processor analyzes the data in the memory, identifying data elements or patterns that are critical to production operations, safety monitoring or future decision-making. This critical data will be marked and given priority processing to ensure that urgent or important information can be quickly responded to and transmitted; Through the above steps, the edge processing unit can effectively manage a large amount of real-time data collected from oil and gas production equipment, achieve intelligent processing and optimization of data, provide support for quick decision-making and fault response, and at the same time reduce the overall cost of data transmission and storage. Embodiment 2

[0026] Based on Embodiment 1, the critical data identification in the edge computing intelligent gateway system for the oil and gas industry specifically includes: Defining thresholds for critical operation parameters by the processor, including pressure, temperature and flow rate, and identifying the data as critical when the monitored data exceeds these thresholds; Using machine learning algorithms for pattern recognition, analyzing historical and real-time data to identify data patterns and trends indicating equipment failures, upcoming maintenance requirements or potential safety issues; After identifying the critical data, classifying its priority based on the urgency, importance and scope of influence of the data. High-priority data, such as data indicating an immediate safety risk, will be marked as urgent so that the system can take immediate action; Dynamic context analysis: The processor considers relevant information from other systems and external sources, including weather conditions, the status of nearby operations or geographical location information, to understand the critical data in context; Real-time Notification and Response Mechanism: After critical data is identified and classified, the processor activates the preset notification and response mechanisms, including automatically adjusting production parameters, sending alerts to the central control center, or directly taking corrective measures on-site. Embodiment 3

[0027] Based on Embodiment 1, the communication module in the edge computing intelligent gateway system for the oil and gas industry specifically includes: Receiving Critical Data: The communication module is configured with interfaces for receiving critical data from the edge processing unit. This data is marked and classified by the edge processing unit according to priority, ensuring that the transmitted information is targeted and urgent. Data Encryption and Transmission: Before transmitting to the central data center, the communication module encrypts the received critical data. Subsequently, through communication protocols and network connections, the data is sent to the central data center, reducing latency and improving the reliability of data transmission. Receiving Central Instructions: The communication module has the function of continuous monitoring and can receive instructions and feedback from the central data center in real time. Instruction Parsing and Forwarding: After receiving an instruction, the communication module parses and validates it to confirm its effectiveness and security. After confirmation, the module forwards the instruction to the edge processing unit. Embodiment 4

[0028] Based on Embodiment 1, the self-diagnosis and recovery module in the edge computing intelligent gateway system for the oil and gas industry specifically includes: Integrating a real-time monitoring agent based on a microservices architecture. The real-time monitoring agents are distributed at key nodes of the intelligent gateway system, collecting system operation parameters in real time and transmitting the data to a preset fault detection engine. The fault detection engine uses pre-set benchmark thresholds and anomaly detection methods to identify readings outside the normal operation indicators. When potential faults are detected, start an automated diagnostic sequence. This sequence uses a set of standardized test scripts and diagnostic tools, including the ping tool or traceroute. Based on the output of the automatic diagnosis, the system triggers a pre-set recovery strategy. This recovery strategy includes automatically repairing damaged data files using error correction codes, implementing a quick rollback to return to the nearest stable configuration state, or starting a backup channel to bypass damaged components.

[0029] The self-diagnosis and recovery module also includes: Remote Intervention Interface: For complex problems that require manual intervention, the self-diagnosis and recovery module provides an encrypted remote terminal interface, allowing technical support personnel to connect to the system and perform troubleshooting. Adaptive Tuning: By continuously collecting system performance data and using predictive analytics based on historical data, the self-diagnosis and recovery module identifies potential performance bottlenecks or future failure points and automatically adjusts system configurations accordingly (such as memory allocation, network bandwidth limits, etc.). Example 5

[0030] Based on Example 1, in the edge computing intelligent gateway system for the oil and gas industry, in the correlation analysis module, potential production efficiency improvement points or safety risks are identified through algorithms in the edge processing unit, as follows: Multi-dimensional Data Fusion: The edge processing unit is used to receive data from various sensors and devices in real time. Through data fusion technology, a comprehensive multi-dimensional view of the production site is constructed, which combines data from different sources and is presented in a single interface; Association Rule Mining: Association rule mining algorithms are applied to identify hidden patterns, correlations, or causal relationships between different data sources. For example, the system may find that certain specific combinations of pressure and temperature may lead to equipment performance degradation or safety hazards; Trend Prediction and Anomaly Detection: Machine learning-based anomaly detection algorithms are used to continuously monitor changes in operating parameters, identify trends or immediate readings that deviate from the normal operating range, and give early warnings of potential equipment failures or unsafe conditions; Optimization Suggestion Generation: Based on correlation analysis, improvement suggestions are generated, which include adjusting equipment parameters, changing maintenance schedules, and implementing safety measures to improve production efficiency or reduce accident risks.

[0031] The anomaly detection algorithm is based on the Isolation Forest algorithm, and the Isolation Forest is used to effectively detect outliers, specifically including: Isolation Trees: The Isolation Forest consists of multiple isolation trees. When constructing each isolation tree, a random feature is selected and a random split value for that feature is chosen, which is between the maximum and minimum values, until the maximum height is reached or there are no more points to split.

[0032] Anomaly Score: The constructed Isolation Forest is used to predict anomalies, which is completed by calculating the path length; The calculation of the anomaly score is expressed using the following formula: ; Where, is an instance, is the sample size, is in all isolation trees is the average path length; is a normalization factor, which is the average of the path lengths given by the following formula; ; is a harmonic number, approximately (Euler's constant).

[0033] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the present invention is limited to these examples; under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the present invention as described above, which are not provided in detail for the sake of brevity.

[0034] The present invention is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An edge computing intelligent gateway system for the oil and gas industry, characterized in that, The system includes: A central data center; A data acquisition unit, configured with a variety of sensor interfaces, for obtaining real-time operation data from oil and gas production equipment and preprocessing the data; An edge processing unit, including a processor and at least one memory module, the processor is used to perform tasks such as data filtering, temporary storage, and critical data identification, and the memory module is used to temporarily store the preprocessed data received from the data acquisition unit; A communication module, supporting two-way communication with the central data center, receiving critical data from the edge processing unit and sending it to the central data center, while receiving instructions from the central data center and transmitting them to the edge processing unit; A self-diagnosis and recovery module, with a system status monitoring function based on predefined rules, automatically identifying system failures or performance degradation, and implementing corrective measures by restarting affected sub-modules or reconfiguring system resources. This self-diagnosis and recovery module determines potential system problems by analyzing data processing logs and performance metrics from the edge processing unit; An association analysis module, configured to analyze the association between the operation data collected from the data acquisition unit and the historical data from the central data center, and identify potential production efficiency improvement points or safety risks through algorithms in the edge processing unit.

2. The edge computing intelligent gateway system for the oil and gas industry according to claim 1, characterized in that, The real-time operation data obtained by the data acquisition unit includes: pressure data, temperature data, flow data, equipment status information, composition analysis data, safety data, and environmental monitoring data.

3. The edge computing intelligent gateway system for the oil and gas industry according to claim 1, characterized in that, The processor of the edge processing unit specifically includes: Data filtering: The processor performs an initial screening on the raw operation data received from the data acquisition unit, identifying and eliminating abnormal, redundant, or invalid data through set parameter thresholds, data integrity verification, and timestamp verification, and only retaining information valuable for subsequent analysis and decision-making; Temporary storage: The processor temporarily stores the filtered valid data in the memory module for immediate data processing and quick access, ensuring the system's response speed and real-time data processing ability by alleviating network latency and reducing the continuous data transmission requirements for the central data center; Critical data identification: The processor analyzes the data in the memory, identifying data elements or patterns that are critical for production operations, safety monitoring, or future decision-making. This critical data will be marked and given priority processing to ensure that urgent or important information can be quickly responded to and transmitted.

4. An edge computing intelligent gateway system for the oil and gas industry according to claim 1, characterized in that, Critical data identification specifically includes: Defining thresholds for critical operation parameters by the processor, including pressure, temperature, and flow, and identifying the data as critical when the monitored data exceeds these thresholds; Using machine learning algorithms for pattern recognition, analyzing historical and real-time data to identify data patterns and trends indicating equipment failures, upcoming maintenance requirements, or potential safety issues; After identifying the critical data, classifying its priority based on the urgency, importance, and impact scope of the data; Dynamic context analysis: The processor considers relevant information from other systems and external sources, including weather conditions, the status of nearby operations, or geographical location information, to understand the critical data in context; Real-time Notification and Response Mechanism: After the critical data is identified and classified, the processor activates the preset notification and response mechanisms, including automatically adjusting production parameters, sending alarms to the central control center, or directly taking corrective measures on-site.

5. The edge computing intelligent gateway system for the oil and gas industry according to claim 1, wherein The communication module specifically includes: Receiving Critical Data: The communication module is configured with an interface for receiving critical data from the edge processing unit. This data has been marked with priority and classified by the edge processing unit to ensure the targeted and urgent nature of the transmitted information. Data Encryption and Transmission: Before transmitting to the central data center, the communication module encrypts the received critical data. Subsequently, through communication protocols and network connections, the data is sent to the central data center. Receiving Central Instructions: The communication module has the function of continuous monitoring and can receive instructions and feedback from the central data center in real time. Instruction Parsing and Forwarding: After receiving an instruction, the communication module parses and verifies it to confirm its validity and security. After confirmation, the module forwards the instruction to the edge processing unit.

6. The edge computing intelligent gateway system for the oil and gas industry according to claim 1, characterized in that The self-diagnosis and recovery module specifically includes: Integrating a real-time monitoring agent based on the microservices architecture. The real-time monitoring agents are distributed at key nodes of the intelligent gateway system, collecting system operation parameters in real time and transmitting the data to a preset fault detection engine. This fault detection engine uses pre-set benchmark thresholds and anomaly detection methods to identify readings outside the normal operation indicators. When potential faults are detected, start an automated diagnostic sequence that uses a set of standardized test scripts and diagnostic tools, including the ping tool or traceroute. Based on the output of the automatic diagnosis, the system triggers a pre-set recovery strategy, which includes automatically repairing damaged data files using error correction codes, implementing a quick rollback to return to the nearest stable configuration state, or starting a backup channel to bypass damaged components.

7. The edge computing intelligent gateway system for the oil and gas industry according to claim 1, characterized in that, The self-diagnosis and recovery module also includes: Remote Intervention Interface: For complex problems that require manual intervention, the self-diagnosis and recovery module provides an encrypted remote terminal interface that allows technical support personnel to connect to the system and perform troubleshooting. Adaptive Tuning: By continuously collecting system performance data and using predictive analysis based on historical data, the self-diagnosis and recovery module identifies potential performance bottlenecks or future fault points and automatically adjusts the system configuration accordingly.

8. An edge computing intelligent gateway system for the oil and gas industry according to claim 1, characterized in that, In the correlation analysis module, potential production efficiency improvement points or safety risks are identified through algorithms in the edge processing unit, specifically as follows: Multi-dimensional Data Fusion: Utilize the edge processing unit to receive data from various sensors and devices in real time. Through data fusion technology, construct a comprehensive multi-dimensional view of the production site, which combines data from different sources and displays it in a single interface. Association Rule Mining: Apply association rule mining algorithms to identify hidden patterns, correlations, or causal relationships between different data sources. Trend Prediction and Anomaly Detection: Use machine learning-based anomaly detection algorithms to continuously monitor changes in operation parameters, identify trends or immediate readings that deviate from the normal operation range, and give early warnings of potential equipment failures or unsafe conditions. Optimization suggestion generation: Based on correlation analysis, improvement suggestions are generated, which include adjusting equipment parameters, changing maintenance plans, and implementing safety measures to improve production efficiency or reduce accident risks.

9. The edge computing intelligent gateway system for the oil and gas industry according to claim 8, characterized in that, The anomaly detection algorithm is based on the Isolation Forest algorithm, and the Isolation Forest is used to effectively detect anomaly points, specifically including: Isolation tree: The Isolation Forest consists of multiple isolation trees. When constructing each isolation tree, a feature is randomly selected and a random split value of this feature is chosen, which is between the maximum value and the minimum value, until the maximum height is reached or there are no more points to split.

10. Anomaly score: The constructed Isolation Forest is used to predict anomalies, which is completed by calculating the path length; The calculation of the anomaly score is expressed using the following formula: ； Among them, is an instance, is the sample size, among all the isolated trees is the average path length; is a normalization factor and is the average of the path lengths given by the following formula: ; is a harmonic number, approximately .

Images