Oil and gas pipe network risk information early warning system and method

Abstract

The invention relates to the technical field of oil and gas pipe network monitoring, in particular to an oil and gas pipe network risk intelligence early warning system and method.The method comprises the steps that real-time oil and gas data in a pipeline are obtained through a sensor in the oil and gas pipe network, and real-time video data of the surrounding environment of the pipeline are obtained through video monitoring equipment outside the oil and gas pipe network; the edge computing device receives the monitoring task instruction sent by the central server, and sets critical parameters for each section of pipeline in the pipeline according to the monitoring task instruction; an abnormal pipeline section is judged by analyzing critical parameters and real-time oil and gas data; real-time oil and gas data and real-time video data are received through an edge computing device, and the real-time oil and gas data and the real-time video data are dynamically aggregated in a dynamic aggregation period, so that the speed and accuracy of identifying the development trend of the pipeline oil and gas data are improved; and monitoring and predicting the oil and gas data and the video data through a monitoring model, identifying abnormal indexes of the pipe network, and sending an alarm signal.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas pipeline network monitoring, and in particular to an oil and gas pipeline network risk intelligence early warning system and method. Background Art

[0002] The oil and gas pipeline network is an important infrastructure that connects oil and gas fields, refineries, gas storage facilities and end users. With the continuous growth of energy demand, oil and gas theft incidents in the oil and gas pipeline network occur from time to time, which not only causes economic losses, but also may cause safety accidents. The offline management mode of oilfield operations makes it impossible for on-site operators to monitor the safety production of each workstation in real time, accurately and comprehensively. Safety supervision lacks a comprehensive understanding of the safety dynamics of the station area. The backwardness of safety monitoring and safety early warning technologies has seriously affected the safety assurance and management capabilities of oilfield production, as well as the improvement of the overall level of emergency response and rescue.

[0003] Common risk monitoring methods include deploying sensors to monitor key parameters such as pipe network pressure and flow in real time based on the Internet of Things technology to detect anomalies, and obtaining video data through video surveillance equipment to achieve online monitoring. However, due to the large amount of data, the computing pressure of the central server is increased, and even the computing capacity of some central servers cannot meet the needs of monitoring.

[0004] Therefore, how to monitor the pipeline network operation indicators in real time without increasing the computing pressure of the central server, predict the occurrence of risk events through abnormal indicators, and deal with risk events in time has become an urgent problem to be solved. To this end, we provide an oil and gas pipeline network risk intelligence early warning system and method. Summary of the invention

[0005] The present invention pre-processes and screens sensor data locally according to different monitoring tasks, reducing the burden on the central server. By monitoring and predicting sensor data through a monitoring model, abnormal indicators of the pipeline network can be identified and alarm signals can be sent, thereby achieving early warning and intervention of potential risks.

[0006] The technical solution proposed by the present invention is: a risk intelligence early warning method for oil and gas pipeline networks, the method comprising: The sensors in the oil and gas pipeline network are used to obtain real-time oil and gas data inside the pipeline, and the video monitoring equipment outside the oil and gas pipeline network is used to obtain real-time video data of the pipeline surrounding environment, so as to monitor the operation status of the pipeline network and the surrounding environment; According to the monitoring task instructions, set critical parameters for each section of the pipeline; By analyzing critical parameters and real-time oil and gas data, abnormal pipeline sections can be identified; specifically: obtaining real-time oil and gas data and the outlet pressure in the critical parameters , respectively Compare and calculate to determine whether the pipeline section is abnormal, where: Indicates the conversion ratio; Receive real-time oil and gas data and real-time video data through edge computing devices, dynamically aggregate the real-time oil and gas data and real-time video data with a dynamic aggregation cycle, shorten or increase the aggregation cycle to improve the speed and accuracy of identifying the development trend of pipeline oil and gas data; Monitor and predict the oil and gas data and the video data through a monitoring model, identify abnormal indicators of the pipeline network and send an alarm signal; The pipeline data includes the pipeline geographic location, pipeline size, historical maintenance records and historical operation data; the real-time oil and gas data includes pressure data, flow rate data, temperature data, gas concentration data and voiceprint data; the real-time video data includes pipeline infrared thermal images.

[0007] Preferably, the sensor includes one or more of a pressure sensor, a flow sensor, a temperature sensor, a gas concentration sensor and an acoustic wave sensor, and the historical operation data includes pressure, flow, temperature and gas concentration data during pipeline operation.

[0008] Preferably, the step of setting critical parameters for each section of the pipeline in accordance with the monitoring task instruction includes: Determine the scope of the pipe network and key components; Critical parameters are set for each pipeline, including pipeline inlet pressure, inlet temperature, outlet pressure and outlet temperature.

[0009] Preferably, receiving the real-time oil and gas data and the real-time video data through the edge computing device comprises the following steps: Install edge computing devices at oil and gas pipeline nodes; Establishing a wireless network connection between edge computing devices and sensors; Remove noise, correct outliers and supplement incomplete data records from received sensor data to improve data quality; Add timestamps to processed sensor data and perform time series aggregation on sensor data to reduce the amount of data transmitted; Perform data pre-analysis through edge computing devices for trend prediction and threshold alarms; Important events, including oil and / or gas leaks, are transmitted to a central server after processing the sensor data.

[0010] Preferably, adding a timestamp to the processed sensor data comprises the following steps: Divide a plurality of buffers in the internal memory of the edge computing device, wherein the buffer is an array, a queue, or a lightweight database in memory; Add a timestamp to each pre-processed sensor data entry into the buffer.

[0011] Preferably, the time series aggregation of the sensor data to reduce the amount of data transmitted includes: Set a sliding window to group and summarize the acquired sensor data according to the preset frequency. Specifically, the sensor data is collected through the sliding window, and the data in each time window constitutes a grouped data set. ; Calculate each grouped data set The average value, maximum value and minimum value of the data in the dataset are used to form a characteristic index data set. ,in, Indicates In the time window A subset of data from a sensor; ,in Respectively represent In the grouped data set The average, maximum and minimum values ​​of the data of each sensor; Aggregate dynamic data in an event-driven manner to form dynamic data sets ,in, Indicates The first time an event occurs A subset of sensor data.

[0012] Preferably, the method further includes performing data pre-analysis by an edge computing device for trend prediction and threshold alarm, specifically comprising the following steps: Monitoring pressure changes, including: setting a pressure safety threshold P, generating an alarm signal if the pressure in the pipeline is lower than P, and recording the abnormal time point t1, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; Monitoring temperature changes, including: setting a temperature safety threshold T, generating an alarm signal if the temperature in the pipeline is higher than T, and recording the abnormal time point t2, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; Monitoring chemical concentration changes, including: setting a concentration safety threshold Q, generating an alarm signal if the concentration in the pipeline is lower than Q, and recording the abnormal time point t3, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; Monitor the changes in the soundprint on the outside of the pipeline, read the preset environmental soundprint signal, compare the acquired soundprint signal with the preset environmental soundprint signal in the frequency domain, obtain the difference value of the energy at each frequency, and calculate the average difference value , set the voiceprint security threshold S, if the average difference value is greater than S, generate an alarm signal, and record the abnormal time point t4, and send the grouped data set and data subset including the abnormal time point to the central server, where, Indicates The energy difference at each frequency.

[0013] Preferably, the monitoring and predicting of the oil and gas data and the video data by using a monitoring model, identifying abnormal indicators of the pipeline network and sending an alarm signal includes: The monitoring model is loaded into the digital twin model of the pipeline network. The monitoring model is: ,in, is the intercept, is the regression coefficient, is the error term, ; Acquire the grouped data set and data subset including the abnormal time point of the corresponding sensor from the buffer storage area; Extract key indicator data from grouped data sets and data subsets, normalize them, and input them into the monitoring model. The monitoring model outputs the probability value of the event occurring. ,if, Then the event will occur, is the preset event occurrence threshold; The numerical twin model of the pipeline network highlights the sensors that generate abnormal data and generates alarm icons to remind staff and handle them in time; Associate alarm icons with corresponding grouped data sets and data subsets to facilitate staff to obtain data from corresponding sensors.

[0014] The present invention also provides an oil and gas pipeline network risk intelligence early warning system, which is used to execute the oil and gas pipeline network risk intelligence early warning method.

[0015] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the oil and gas pipeline network risk intelligence early warning method.

[0016] Beneficial effects of the present invention: 1. The present invention can monitor the working status and surrounding environment of the pipeline in real time and detect potential risks and abnormal situations in time by installing multiple sensors and video surveillance cameras in the oil and gas pipeline network. This real-time monitoring capability enables the system to respond quickly and take necessary measures to prevent accidents.

[0017] 2. By installing an edge computing device, the present invention can pre-process and filter sensor data locally, reducing the burden on the central server. At the same time, the data connection between the edge computing device and the central server can ensure that the processed and filtered data is transmitted to the central server in a timely manner, improving the efficiency of data processing. By monitoring and predicting sensor data through a monitoring model, abnormal indicators of the pipeline network can be identified and alarm signals can be sent, thereby achieving early warning and intervention of potential risks.

[0018] 3. In the present invention, the edge computing device and the central server have different tasks. The edge computing device is responsible for preprocessing sensor data and determining abnormal pipeline segments. Different data packets are sent to the central server according to different tasks. For example, when performing an anti-theft oil monitoring task, the central server sends the corresponding monitoring task instructions, the edge computing device monitors the sensor data, determines the abnormal pipeline segment and generates an abnormal alarm signal, and then sends the abnormal sensor data and alarm signal to the central server; if a conventional monitoring task is performed, the data collected by the corresponding sensor is sent to the central server, and the central server is responsible for issuing monitoring task instructions, receiving data sent by the edge computing device, and predicting the pipeline status.

[0019] 4. The present invention combines sliding windows and event-driven data aggregation strategies, and can flexibly adjust the data processing mode and granularity according to specific needs. Through real-time monitoring and dynamic aggregation, potential risks and abnormal situations can be discovered and responded to in a timely manner. By calculating multiple characteristic indicators (such as average, maximum, minimum) and building dynamic data sets, the working status and surrounding environment of the pipeline can be more comprehensively understood. This method can adapt to oil and gas pipeline network systems of different types and sizes, and has strong versatility and scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The present invention is a flow chart of an oil and gas pipeline network risk intelligence early warning method. DETAILED DESCRIPTION

[0021] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0022] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0023] refer to Figure 1 The technical solution provided by the present invention is: an oil and gas pipeline network risk intelligence early warning method, comprising the following steps: 1. Install multiple sensors and video surveillance cameras in the oil and gas pipeline network to monitor the working status of the pipeline and the surrounding environment in real time. The sensors include one or more of pressure sensors, flow sensors, temperature sensors, gas concentration sensors, acoustic wave sensors and video surveillance equipment, and the video surveillance cameras include one or more of high-definition cameras and infrared imaging cameras.

[0024] 2. According to the monitoring task instructions, set critical parameters for each section of the pipeline, specifically: Determine the scope of the pipeline network and key components, including the length of the pipeline, distribution range, number of valves and connection methods.

[0025] Critical parameters are set for each pipeline, including pipeline inlet pressure, inlet temperature, outlet pressure and outlet temperature. The critical parameters here include but are not limited to the inlet and outlet of the actual pipeline (the inlet and outlet of two actually connected pipelines or the inlet and outlet of a pipeline), which need to be determined according to different monitoring task instructions.

[0026] In this embodiment, in the anti-oil theft monitoring, the inlet and outlet are selected in the pipelines that are prone to oil theft (remote areas or areas where video surveillance is difficult), and the pipelines in this part are divided into multiple virtual pipeline segments, and each pipeline segment is assigned an inlet and outlet.

[0027] If pipeline operation is being monitored, the inlet and outlet should be selected from pipelines with more connection points (for example, with multiple bends or many branches) or the connection ends of two adjacent pipelines.

[0028] The edge computing device multiplies the real-time oil and gas data collected by the sensor by a preset conversion ratio Then, update the critical parameters at the outlet of the pipeline. For example, if the inlet pressure of the pipeline is , the updated inlet pressure is ; Among them, the conversion ratio is determined according to the allowable fluctuation range of pipeline pressure.

[0029] Get real-time oil and gas data and the outlet pressure in the critical parameters Respectively Perform comparative calculations to determine whether this section of the pipeline is abnormal.

[0030] For example, if , then the pipeline is judged to be normal. If , it is determined that there is an abnormality in the section between the outlet and the sensor position of the pipeline. , it is determined that an abnormality occurs in the section between the inlet and the sensor position of the pipeline. Indicates the total length of the pipeline. Indicates the distance from the sensor to the pipeline outlet on this section of pipeline. represents the error term.

[0031] 3. Receive real-time oil and gas data and real-time video data through edge computing devices, specifically: First, edge computing devices are installed at oil and gas pipeline nodes.

[0032] Secondly, establish a wireless or wired network connection between the edge computing device and the sensor.

[0033] Then, the received sensor data is subjected to noise removal, outlier correction, and incomplete data record supplementation to improve data quality. Timestamps are added to the processed sensor data, and time series aggregation is performed on the sensor data to reduce the amount of data transmitted.

[0034] Finally, data pre-analysis is performed by edge computing devices for trend prediction and threshold alarms. Important events, processed sensor data, are transmitted to the central server, and the important events include oil and / or gas leaks.

[0035] Among them, adding a timestamp to the processed sensor data can be achieved through the following steps: Divide a plurality of buffers in the internal memory of the edge computing device, wherein the buffer is an array, a queue, or a lightweight database in memory; Add a timestamp to each pre-processed sensor data entry into the buffer.

[0036] The time series aggregation of sensor data is used to reduce the amount of transmitted data, including the following steps: Set a sliding window to group and summarize the acquired sensor data according to the preset frequency. Specifically, the sensor data is collected through the sliding window, and the data in each time window constitutes a grouped data set. ; Calculate each grouped data set The average value, maximum value and minimum value of the data in the dataset are used to form a characteristic index data set. ,in, Indicates In the time window A subset of data from a sensor; ,in Respectively represent In the grouped data set The average, maximum, and minimum values ​​of the data from each sensor.

[0037] In this embodiment, the size of the sliding window and the sliding step is determined, such as one window every 5 minutes, sliding once every minute. The local range of the time series data is defined by the sliding window so that statistical analysis can be performed within the range. The sensor data is grouped according to the sliding window, and the data in each time window constitutes a grouped data set. This helps to divide the continuous data stream into manageable small blocks for further processing and analysis. The average, maximum and minimum values ​​of the data in each grouped data set are calculated to form a characteristic indicator data set. These statistics can provide basic information about the distribution and changes of the data, which helps to identify anomalies or trends.

[0038] Dynamic data aggregation is performed in an event-driven manner to form a dynamic data set: ,in, Indicates The first time an event occurs A subset of sensor data.

[0039] When performing dynamic data aggregation in an event-driven manner, it is important to note that: First, determine which sensor data is critical to detecting a specific event, such as an oil spill. For example, an unusual increase in temperature, a sudden drop in pressure, or a change in the concentration of a specific chemical could be a sign of an oil spill.

[0040] At the same time, the infrared thermal imaging device is installed to obtain infrared thermal images of the pipeline and monitor the temperature of the fluid in the pipeline. After identifying the oil theft incident, the infrared thermal image of the abnormal pipeline section is obtained to monitor the oil and gas leakage.

[0041] Second, set thresholds or triggers that meet specific conditions for each key indicator. These thresholds should be determined based on historical data analysis, expert knowledge, or industry standards. Edge computing devices continuously receive and process data streams from sensors, analyze each data record in real time, and check whether the preset event trigger conditions are met.

[0042] Once a data point or a series of data points meets the event trigger condition, the event is immediately marked and the timestamp of its occurrence is recorded.

[0043] Finally, dynamically adjust the time window for data aggregation based on the importance and urgency of the event. For example, for emergencies such as oil spills, the aggregation cycle may need to be shortened to identify trends and patterns more quickly. Aggregate and analyze relevant data within a certain time range before and after the event to obtain more comprehensive situational information. This helps to understand the cause, scope of impact and subsequent development trends of the event. When an important event is detected, an alarm message is immediately generated, including the type of event, time of occurrence, location, and preliminary judgment of the impact. Alarm information is sent to relevant personnel in a timely manner through SMS, email, mobile application push and other methods to ensure a quick response. Record the detection, response process and results of each event in detail for post-analysis and improvement.

[0044] In this embodiment, if the central server issues an anti-oil theft monitoring task instruction, since the anti-oil theft monitoring task requires a quick response, data collection and abnormality judgment are mainly performed by the edge computing device. The edge computing device selects different sensors for collecting data according to different tasks. For example, the temperature, pressure, concentration of specific chemical substances, and voiceprint data mentioned above are collected to obtain corresponding data from the corresponding sensors; at the same time, the monitoring model shortens the aggregation cycle, increases the speed of data stream processing, and increases the speed of predicting the operating status of other pipelines.

[0045] If the central server issues a routine monitoring task, the sensors selected by the edge computing device include pressure sensors and flow sensors, and the collected relevant data are pre-processed and sent to the central server. The monitoring model expands the aggregation cycle and ensures the accuracy of the prediction by expanding the data volume of each grouped data set.

[0046] In this embodiment, the monitoring and alarm function of the edge computing device is implemented through the following steps: Monitoring pressure changes through a pressure monitoring model includes: setting a pressure safety threshold P; generating an alarm signal if the pressure in the pipeline is lower than P, and recording the abnormal time point t1; sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; Monitoring temperature changes through a temperature monitoring model, including: setting a temperature safety threshold T, generating an alarm signal if the temperature in the pipeline is higher than T, and recording the abnormal time point t2, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; Monitoring the concentration change of chemical substances through the concentration monitoring model, including: setting a concentration safety threshold Q, generating an alarm signal if the concentration in the pipeline is lower than Q, and recording the abnormal time point t3, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; The soundprint monitoring model is used to monitor the soundprint changes on the outside of the pipeline, including: reading the preset environmental soundprint signal, comparing the acquired soundprint signal with the preset environmental soundprint signal in the frequency domain, obtaining the energy difference value at each frequency, and calculating the average difference value. , set the voiceprint security threshold S, if the average difference value is greater than S, generate an alarm signal, and record the abnormal time point t4, and send the grouped data set and data subset including the abnormal time point to the central server, where, Indicates The energy difference at each frequency.

[0047] In summary, through preprocessing by the edge computing device, only the sensor data when an alarm occurs is sent to the central server and processed by the pipeline network digital twin model, which can reduce the computing pressure of the central server.

[0048] 4. Establish a data connection between the edge computing device and the central server, and set up a buffer storage area in the central server to temporarily store the processed and filtered sensor data; 5. Establish data synchronization between the digital twin model of the pipeline network and the central server, so that the digital twin model of the pipeline network can obtain sensor data in real time.

[0049] 6. Monitor and predict the oil and gas data and the video data through the monitoring model, identify abnormal indicators of the pipeline network and send an alarm signal. The specific steps are as follows: The monitoring model is loaded into the digital twin model of the pipeline network. The monitoring model is: ,in, is the intercept, is the regression coefficient, is the error term, ;

[0050] Acquire the grouped data set and data subset including the abnormal time point of the corresponding sensor from the buffer storage area;

[0051] Extract key indicator data from the grouped data set and data subset, such as temperature, pressure, flow value, etc., normalize them, and input them into the monitoring model. The monitoring model outputs the probability value of the event occurring. ,if, It indicates the possibility of a specific event (such as oil spill, oil theft) occurring within a certain time window. It is the preset event occurrence threshold.

[0052] Add alarm icons to sensors that generate abnormal data to remind staff and handle them in a timely manner.

[0053] Establish an association between the alarm icon and the corresponding grouped data set and data subset. This is achieved through data ID, timestamp or other unique identifiers. The staff can quickly obtain the data of the corresponding sensor by clicking the alarm icon or querying the association. These data include raw data, key indicator data, and historical records, which help the staff to fully understand the background and causes of abnormal situations. Associating alarm icons with data sets not only facilitates the data acquisition and analysis process of the staff, but also provides them with more information support and decision-making basis. By comprehensively analyzing the relevant data, the staff can more accurately judge the nature and severity of the abnormal situation and formulate corresponding response strategies.

[0054] The video images around the pipeline are collected by surveillance cameras to assist staff in understanding the situation around the pipeline and obtain some image information for later use as evidence.

[0055] The present invention also provides an oil and gas pipeline network risk intelligence early warning system, which is used to execute the oil and gas pipeline network risk intelligence early warning method.

[0056] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the oil and gas pipeline network risk intelligence early warning method.

[0057] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0058] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0059] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A risk intelligence early warning method for oil and gas pipeline network, characterized in that: The method comprises: The sensors in the oil and gas pipeline network are used to obtain real-time oil and gas data inside the pipeline, and the video monitoring equipment outside the oil and gas pipeline network is used to obtain real-time video data of the pipeline surrounding environment, so as to monitor the operation status of the pipeline network and the surrounding environment; The edge computing device receives the monitoring task instructions sent by the central server, and sets critical parameters for each section of the pipeline according to the monitoring task instructions; By analyzing critical parameters and real-time oil and gas data, abnormal pipeline sections can be identified; specifically: obtaining real-time oil and gas data and the outlet pressure in the critical parameters , respectively Compare and calculate to determine whether the pipeline section is abnormal, where: Indicates the conversion ratio; Receive real-time oil and gas data and real-time video data through edge computing devices, dynamically aggregate the real-time oil and gas data and real-time video data with a dynamic aggregation cycle, shorten or increase the aggregation cycle to improve the speed and accuracy of identifying the development trend of pipeline oil and gas data; Monitor and predict the oil and gas data and the video data through a monitoring model, identify abnormal indicators of the pipeline network and send an alarm signal; The pipeline data includes the pipeline geographic location, pipeline size, historical maintenance records and historical operation data; the real-time oil and gas data includes pressure data, flow rate data, temperature data, gas concentration data and voiceprint data; the real-time video data includes pipeline infrared thermal images.

2. The oil and gas pipeline network risk intelligence early warning method according to claim 1 is characterized in that: The sensor includes one or more of a pressure sensor, a flow sensor, a temperature sensor, a gas concentration sensor and an acoustic wave sensor, and the historical operation data includes pressure, flow, temperature and gas concentration data during pipeline operation.

3. The oil and gas pipeline network risk intelligence early warning method according to claim 1 is characterized in that: The step of setting critical parameters for each section of the pipeline according to the monitoring task instruction includes: Determine the scope of the pipe network and key components; Critical parameters are set for each pipeline, including pipeline inlet pressure, inlet temperature, outlet pressure and outlet temperature.

4. The oil and gas pipeline network risk intelligence early warning method according to claim 3 is characterized in that: The receiving of real-time oil and gas data and real-time video data by an edge computing device comprises the following steps: Install edge computing devices at oil and gas pipeline nodes; Establishing a wireless network connection between edge computing devices and sensors; Remove noise, correct outliers and supplement incomplete data records from received sensor data to improve data quality; Add timestamps to processed sensor data and perform time series aggregation on sensor data to reduce the amount of data transmitted; Perform data pre-analysis through edge computing devices for trend prediction and threshold alarms; Important events, including oil and / or gas leaks, are transmitted to a central server after processing the sensor data.

5. The oil and gas pipeline network risk intelligence early warning method according to claim 4 is characterized in that: The adding of a timestamp to the processed sensor data comprises the following steps: Divide a plurality of buffers in the internal memory of the edge computing device, wherein the buffer is an array, a queue, or a lightweight database in memory; Add a timestamp to each pre-processed sensor data entry into the buffer.

6. The oil and gas pipeline network risk intelligence early warning method according to claim 5 is characterized in that: The time series aggregation of the sensor data is used to reduce the amount of transmitted data, including: Set a sliding window to group and summarize the acquired sensor data according to the preset frequency. Specifically, the sensor data is collected through the sliding window, and the data in each time window constitutes a grouped data set. ; Calculate each grouped data set The average value, maximum value and minimum value of the data in the dataset are used to form a characteristic index data set. ,in, Indicates In the time window A subset of data from a sensor; ,in Respectively represent In the grouped data set The average, maximum and minimum values ​​of the data of each sensor; Aggregate dynamic data in an event-driven manner to form dynamic data sets ,in, Indicates The first time an event occurs A subset of sensor data.

7. The oil and gas pipeline network risk intelligence early warning method according to claim 6 is characterized in that: It also includes performing data pre-analysis through an edge computing device for trend prediction and threshold alarm, specifically including the following steps: Monitoring pressure changes, including: setting a pressure safety threshold P, generating an alarm signal if the pressure in the pipeline is lower than P, and recording the abnormal time point t1, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; Monitoring temperature changes, including: setting a temperature safety threshold T, generating an alarm signal if the temperature in the pipeline is higher than T, and recording the abnormal time point t2, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area; Monitor changes in chemical concentrations, including: setting a concentration safety threshold Q, generating an alarm signal if the concentration in the pipeline is lower than Q, and recording the abnormal time point t3, sending the grouped data set and data subset including the abnormal time point to the central server, and storing them in the buffer storage area Monitor the changes in the soundprint on the outside of the pipeline, read the preset environmental soundprint signal, compare the acquired soundprint signal with the preset environmental soundprint signal in the frequency domain, obtain the difference value of the energy at each frequency, and calculate the average difference value , set the voiceprint security threshold S, if the average difference value is greater than S, generate an alarm signal, and record the abnormal time point t4, and send the grouped data set and data subset including the abnormal time point to the central server, where, Indicates The energy difference at each frequency.

8. The oil and gas pipeline network risk intelligence early warning method according to claim 7 is characterized in that: The monitoring and prediction of the oil and gas data and the video data by using the monitoring model, identifying abnormal indicators of the pipeline network and sending an alarm signal, includes: The monitoring model is loaded into the digital twin model of the pipeline network. The monitoring model is: ,in, is the intercept, is the regression coefficient, is the error term, ; Acquire the grouped data set and data subset including the abnormal time point of the corresponding sensor from the buffer storage area; Extract key indicator data from grouped data sets and data subsets, normalize them, and input them into the monitoring model. The monitoring model outputs the probability value of the event occurring. ,if, Then the event will occur, is the preset event occurrence threshold; The numerical twin model of the pipeline network highlights the sensors that generate abnormal data and generates alarm icons to remind staff and handle them in time; Associate alarm icons with corresponding grouped data sets and data subsets to facilitate staff to obtain data from corresponding sensors.

9. An oil and gas pipeline network risk intelligence early warning system, characterized in that: The system is used to execute an oil and gas pipeline network risk intelligence early warning method as described in any one of claims 1-8 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement an oil and gas pipeline network risk intelligence early warning method as described in any one of claims 1 to 8.

Images