Oil and gas storage and transportation safety analysis method and system based on big data

Abstract

The invention discloses an oil and gas storage and transportation safety analysis method and system based on big data, and belongs to the technical field of oil and gas storage and transportation supervision, and the method comprises the steps: obtaining data collection information, and storing the data collection information in a data lake; performing unified management and integration on the original data from different sources; obtaining a preset data processing rule, wherein the data processing rule comprises a standard data format corresponding to the original data; processing the original data into a plurality of data copies according to a standard data format; respectively storing the plurality of data copies in different areas of a database; a data analysis request sent by a user through the intelligent terminal is received, the data analysis request carries data analysis information, and the data analysis information comprises an analysis index, an analysis time period and an analysis area; and analyzing and processing the data copy in the database according to the data analysis request. The method has the effect of improving the oil and gas storage and transportation safety management level.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas storage and transportation supervision, and in particular to a method and system for oil and gas storage and transportation safety analysis based on big data. Background Art

[0002] With the rapid development of information technology, technologies such as big data, the Internet of Things, and cloud computing have been widely used in the field of oil and gas storage and transportation. The application of these technologies has made the oil and gas storage and transportation process more intelligent and efficient, and also provided new methods and means for oil and gas storage and transportation safety analysis.

[0003] However, the process of oil and gas storage and transportation involves a large amount of data and information, such as pipeline operation data, oil and gas reserves data, environmental monitoring data, etc.; these data are massive, multi-dimensional, and real-time. The intelligence level of traditional data analysis systems is relatively low, and they are unable to achieve comprehensive, real-time monitoring and early warning of the oil and gas storage and transportation process. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present application provides an oil and gas storage and transportation safety analysis method and system based on big data to solve the problems raised in the above-mentioned background technology.

[0005] The present application provides a method and system for analyzing oil and gas storage and transportation safety based on big data, which adopts the following technical solutions: In a first aspect, the present application provides a method for oil and gas storage and transportation safety analysis based on big data, comprising the following steps: Acquire data collection information, wherein the data collection information includes sensor data and monitoring video data; Storing the data collection information in a data lake; Clean and transform the raw data; Unified management and integration of raw data from different sources; Acquire a preset data processing rule, wherein the data processing rule includes a standard data format corresponding to the original data; Processing the original data into several data copies according to the standard data format; Store several copies of data in different areas of the database; Receiving a data analysis request sent by a user through a smart terminal, the data analysis request carrying data analysis information, the data analysis information including analysis indicators, analysis time period, and analysis area; The data copy in the database is analyzed and processed according to the data analysis request.

[0006] Furthermore, after the step of analyzing and processing the data copy in the database according to the data analysis request, the method further includes: Extracting historical data information within a past period of time from a database, wherein the historical data information includes pipeline flow data, transportation planning records, and maintenance record data; Merging the data copy in the database with the historical data information to form a complete data set; Get the transportation planning form; Based on the complete data set and transportation planning form, output the forecast results of the flow rate of each oil and gas pipeline in the future period; Obtain the corresponding transport carrying capacity of each pipeline from the preset database; If it is predicted that the flow rate of a certain section of oil and gas pipeline will increase significantly and exceed its transportation carrying capacity, an early warning information is generated, which includes the impact range and blockage time of each risk pipeline that may be blocked.

[0007] Furthermore, after the step of generating the warning information, the following step is further included: Calculate the flow growth trend corresponding to each risk pipeline according to the prediction work results and the transmission carrying capacity, wherein the flow growth trend is used to represent the flow change exceeding the transmission carrying capacity; Obtain the historical blockage records corresponding to each risk pipeline; Considering the flow growth trend, transmission carrying capacity and historical blockage records of the risk pipeline, the risk level of blockage of the risk pipeline is evaluated. The higher the risk level, the greater the possibility of blockage of the risk pipeline. Analyze the importance of the affected area based on the impact scope; Querying important areas from a preset database, wherein the important areas include areas involving key oil transportation nodes and / or areas close to residential areas; If the impact range of the risk pipeline is a critical area, a risk enhancement instruction is generated and executed; Find the key parts within the risk pipeline impact range, including welds, elbows, tees, valves and joints; If the critical parts are found, risk enhancement instructions are generated and executed.

[0008] Furthermore, after the step of evaluating the risk level of risk pipeline blockage, the method further includes: Based on the blockage time, assess the time urgency with which the pipeline blockage may occur; Determine the execution priority corresponding to each risk pipeline according to the risk level and time urgency, and the execution priority is divided into low, medium and high; If the execution priority is high, an emergency processing instruction is generated and executed; If the execution priority is low or medium, a flow distribution plan is adjusted, wherein the flow distribution plan is used to transfer part of the flow from the pipeline section with higher risk to other pipeline sections with stronger carrying capacity; The traffic distribution plan is pushed to the user's smart terminal.

[0009] Furthermore, the steps of generating and executing emergency processing instructions specifically include: Query the standard pipeline flow corresponding to the risk pipeline from the preset database; Calculate the flow difference according to the historical data information, where the flow difference is the difference between the pipeline flow data and the standard pipeline flow; Query pipeline flow difference threshold value from a preset database; If the flow difference reaches the pipeline flow difference threshold, real-time image data inside the pipeline is acquired through an image sensing sensor; Retrieving pipeline inner wall problem data according to the real-time image data, wherein the pipeline inner wall problem data includes pipeline rough wear and / or pipeline deposits; If the pipeline is found to be rough and worn, the user is reminded to replace or repair the risky pipeline; If pipeline deposits are found, the user is reminded to clean the risky pipeline.

[0010] Furthermore, the steps of uniformly managing and integrating raw data from different sources specifically include: During the training period T train In the process, data from different data sources i at different times t are collected for training data S train ; ; ; During the test period T test In the data from different data sources i at different times t, the test data S test ; ; ; The test period T test A set of test point categories in the label (i) The reliability of the calculation is the confidence level Cl label ; ; Where: D label(i) The category is label (i) The distance from the test point to the decision classification surface, D jis the distance from all test points to the decision classification surface; Calculate the similarity between the data point x′ and each point in the array X = {x1, x2, . . . , xn} to obtain the matching degree µ; ; in, , the symbol (·) represents the inner product of two vectors; The data analysis result result(label, Cl, µ) is obtained, where label is the output category label; the data analysis result is used to reflect the category of the original data, the degree of confidence, and the similarity with other data points.

[0011] In a second aspect, the present application provides an oil and gas storage and transportation safety analysis system based on big data, comprising: A data acquisition information acquisition module is used to acquire data acquisition information, wherein the data acquisition information includes sensor data and monitoring video data; A data storage module, used to store the data collection information in a data lake; Data cleaning module, used to clean and convert raw data; Data management module, used to uniformly manage and integrate raw data from different sources; A data processing rule acquisition module, used to acquire preset data processing rules, wherein the data processing rules include a standard data format corresponding to the original data; A data processing module, used for processing the original data into a plurality of data copies according to the standard data format; A partition storage module is used to store several data copies in different areas of the database; A data analysis request receiving module, used to receive a data analysis request sent by a user through an intelligent terminal, wherein the data analysis request carries data analysis information, and the data analysis information includes analysis indicators, analysis time period, and analysis area; The analysis and processing module is used to analyze and process the data copies in the database according to the data analysis request.

[0012] In a third aspect, the present application provides an intelligent terminal, comprising a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned big data-based oil and gas storage and transportation safety analysis method.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute the above-mentioned oil and gas storage and transportation safety analysis method based on big data.

[0014] In summary, compared with the prior art, the above technical solution has the following beneficial effects: (1) Through the storage method of the data lake, centralized management and efficient access to massive data are achieved. At the same time, the cleaning, conversion, and unified management and integration of the original data ensure the accuracy and consistency of the data, providing a reliable data source for subsequent data analysis. According to the preset data processing rules, the original data is processed into several copies of data in standard data formats and stored in different areas of the database. This processing method not only improves the efficiency of data processing, but also enhances the readability and analyzability of the data; (2) This method can receive data analysis requests sent by users through smart terminals, and intelligently screen, aggregate and calculate the data copies in the database according to the analysis indicators, analysis period and analysis area in the request. This intelligent data analysis method can perform customized analysis according to different needs, improving the pertinence and accuracy of the analysis. It realizes all-round monitoring and analysis of oil and gas storage and transportation safety, and improves the management level of oil and gas storage and transportation safety; (3) This method can realize real-time monitoring and data analysis of various parameters in the oil and gas storage and transportation process, timely discover and warn potential safety hazards, and improve the management level of oil and gas storage and transportation safety. Through intelligent data analysis, the operating status and safety status of oil and gas storage and transportation facilities can be accurately judged, abnormal situations can be discovered and handled in a timely manner, thereby reducing the probability of oil and gas storage and transportation accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a method for analyzing oil and gas storage and transportation safety based on big data according to an embodiment of the present application; Figure 2 is a schematic diagram of a process for extracting historical data information within a past period of time from a database in an embodiment of the present application; Figure 3 It is a flowchart of obtaining the historical blockage record corresponding to each risk pipeline in an embodiment of the present application; Figure 4 It is a schematic diagram of the process of pushing the traffic allocation solution to the user's smart terminal in an embodiment of the present application; Figure 5 It is a flowchart of querying the standard pipeline flow corresponding to the risk pipeline from a preset database in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The present application is further described in detail below in conjunction with all the accompanying drawings.

[0017] The present application embodiment discloses a method and system for analyzing oil and gas storage and transportation safety based on big data, referring to Figure 1, a safety analysis method for oil and gas storage and transportation based on big data includes: S101. Obtain data collection information.

[0018] Specifically, the system acquires data collection information, including sensor data and monitoring video data; through various sensors (such as temperature sensors, pressure sensors, flow sensors, etc.) and monitoring cameras installed on oil and gas storage and transportation facilities, key parameters and on-site videos of the oil and gas storage and transportation process are collected in real time. This helps to ensure the comprehensiveness and real-time nature of the data and provides a basis for subsequent analysis.

[0019] S102: Storing the data collection information in a data lake.

[0020] Specifically, the system stores the data collection information in the data lake; using big data storage technology, such as Hadoop or Spark, the collected sensor data and surveillance video data are stored in the data lake. The data lake is a centralized repository that can store all structured, semi-structured, and unstructured data of any scale. It facilitates subsequent data processing and analysis, while supporting flexible expansion and efficient access to data.

[0021] S103, cleaning and converting the original data.

[0022] Specifically, the system cleans and converts the raw data; uses data cleaning tools (such as Apache Pig, Hive, etc.) to pre-process the raw data, including removing duplicate data, filling missing values, correcting erroneous data, etc.; data conversion involves converting the data into a format suitable for analysis. This is conducive to improving data quality and ensuring the accuracy of analysis results.

[0023] S104. Unify the management and integration of raw data from different sources.

[0024] Specifically, the system uniformly manages and integrates raw data from different sources; it integrates data from different sensors and monitoring systems through data integration technology, which helps eliminate data silos and facilitates cross-system and cross-platform data analysis and application.

[0025] S105: Obtain preset data processing rules.

[0026] Specifically, the system obtains preset data processing rules, which include standard data formats corresponding to original data; users formulate data processing rules based on business needs and data characteristics, including data formats, data conversion rules, data verification rules, etc., and store them in the rule base in advance. This is conducive to ensuring the consistency and standardization of data processing and improving data processing efficiency.

[0027] S106. Process the original data into several data copies according to the standard data format.

[0028] Specifically, the system processes the original data into several data copies according to the standard data format; and generates multiple data copies (such as time series data, aggregated data, related data, etc.) according to different analysis needs and processing requirements based on the preset data processing rules. This is conducive to meeting diverse analysis needs and improving the flexibility and efficiency of data analysis.

[0029] S107. Store the multiple data copies in different areas of the database respectively.

[0030] Specifically, the system stores several types of data copies in different areas of the database; according to the type and purpose of the data copy, it is stored in different areas or tables of the database for fast access and efficient management. This is conducive to optimizing the data storage structure and improving data access speed and storage efficiency.

[0031] S108: Receive a data analysis request sent by the user via the smart terminal.

[0032] Specifically, the system receives data analysis requests sent by users through smart terminals, and the data analysis requests carry data analysis information, including analysis indicators, analysis time periods, and analysis areas; through mobile applications, web pages and other smart terminals, the system receives data analysis requests submitted by users, including analysis indicators (such as temperature, pressure, flow, etc.), analysis time periods (such as the past week, the past month, etc.) and analysis areas (such as a certain oil tank, a certain section of pipeline, etc.). This is conducive to the interaction between users and the system and meets the personalized analysis needs of users.

[0033] S109: Analyze and process the data copy in the database according to the data analysis request.

[0034] Specifically, the system analyzes and processes the data copies in the database according to the data analysis request. According to the analysis request submitted by the user, the corresponding data copies are extracted from the database, and data analysis tools (such as SQL, Python, R, etc.) are used to perform data analysis, such as trend analysis, anomaly detection, correlation analysis, etc. This is conducive to providing users with intuitive and accurate analysis results, helping users to promptly discover and resolve safety hazards in the process of oil and gas storage and transportation.

[0035] In another embodiment, S104 specifically includes the following sub-steps: During the training period T train In the process, data from different data sources i at different times t are collected for training data S train ; ; ; During the test period T test In the data from different data sources i at different times t, the test data S test ; ; ; The test period T test A set of test point categories in the label (i) The reliability of the calculation is the confidence level Cl label ; ; Where: D label(i) The category is label (i) The distance from the test point to the decision classification surface, D j is the distance from all test points to the decision classification surface; Calculate the similarity between the data point x′ and each point in the array X = {x1, x2, . . . , xn} to obtain the matching degree µ; ; in, , the symbol (·) represents the inner product of two vectors; The data analysis result result(label, Cl, µ) is obtained, where label is the output category label; the data analysis result is used to reflect the category of the original data, the degree of confidence, and the similarity with other data points.

[0036] Specifically, the system is in the training period T train In the training data set S, data is collected from various data sources i (such as different sensors, monitoring systems, etc.) and at different times t to form a training data set S train This data is used to train a machine learning model or classifier, enabling it to recognize features and patterns in the data. test In the same way, data is collected from each data source i and at different times t to form a test data set S test These data are used to evaluate the performance of the trained model or classifier. Through training and testing, the model or classifier's ability to classify the original data can be verified to ensure its accuracy and reliability in practical applications. The separation of training and testing data sets helps avoid overfitting and improve the generalization ability of the model.

[0037] For the test period T test A set of test points in the class are labeled (i), and calculate its confidence level Cl label Confidence level Cl label You can calculate the category as label (i) The distance D from the test point to the decision classification surface label(i) The distance D from all test points to the decision classification surface j The larger the ratio, the more confident the test point is that it belongs to that category. The confidence level provides additional information for the data analysis results, that is, the degree of confidence of the model or classifier in classifying a data point. Data points with high confidence levels are more likely to be correctly classified, while data points with low confidence levels require further verification or analysis.

[0038] For a data point x′, calculate its similarity with each point in the array X = {x1, x2, ..., xn} to obtain the matching degree µ. The matching degree µ can be obtained by calculating the inner product of the vectors of the data point x′ and each point in the array X, and dividing it by the product of the modulus length of the vector of each point. The larger this value is, the more similar x′ is to the data point in the array X. Similarity matching provides an additional dimension to the data analysis results, namely the correlation and similarity between data points. Through similarity matching, the potential relationships and patterns between data points can be discovered, which is helpful for further data analysis and mining.

[0039] The data analysis results obtained in the above steps are output in the form of result(label, Cl, µ), where label is the output category label, Cl is the confidence level, and µ is the matching degree. The data analysis results provide comprehensive information, including the category of the data point, the degree of confidence, and the similarity with other data points. This information helps the system better understand the characteristics and patterns of the data and make more accurate decisions and judgments.

[0040] Reference Figure 2 Further, after S109, as another implementation mode, the embodiment of the present application may further include the following steps: S201, extracting historical data information within a past period of time from a database.

[0041] Specifically, the system extracts historical data information from the database over a period of time, including but not limited to pipeline flow data, transportation planning records, maintenance record data, etc. Historical data information provides an important reference for subsequent flow prediction and carrying capacity verification. By analyzing historical data, we can understand the flow change trend of oil and gas pipelines, the implementation of transportation planning, and maintenance records, which helps to more accurately predict future flow and evaluate pipeline status.

[0042] S202: Merge the data copy in the database with the historical data information to form a complete data set.

[0043] Specifically, the system merges the data copy in the database with the historical data information to form a complete data set; the data copy in the database (i.e., the real-time data after cleaning, conversion, and integration) is merged with the extracted historical data information to form a complete data set. Data fusion makes the data set more comprehensive and rich, including real-time data and historical data, providing more sufficient information support for subsequent traffic prediction.

[0044] S203: Obtain a transportation planning form.

[0045] Specifically, the system obtains the transportation planning form; obtains the latest transportation planning form from the relevant system. The transportation planning form is generated by the user based on actual work needs. The form records in detail the transportation plan and arrangement of each oil and gas pipeline in the future. The transportation planning form is one of the important inputs for flow forecasting. It provides the expected value and change trend of future flow, which helps to more accurately predict the actual flow.

[0046] S204. Based on the complete data set and transportation planning form, output the prediction results of the flow of each oil and gas pipeline in the future period of time.

[0047] Specifically, the system outputs the forecast results of the flow rate of each oil and gas pipeline in the future based on the complete data set and transportation planning form; based on the complete data set and transportation planning form, the system uses machine learning algorithms or statistical models to predict the flow rate of each oil and gas pipeline in the future and outputs the forecast results. The flow forecast results help to understand the flow status of oil and gas pipelines in advance and provide decision support for transportation scheduling and pipeline maintenance.

[0048] S205: Obtain the corresponding transport carrying capacity of each pipeline from a preset database.

[0049] Specifically, the system obtains the corresponding transport capacity of each pipeline from the preset database; the transport capacity of each pipeline is obtained from the preset database, which is one of the important parameters for pipeline design and operation. The transport capacity provides a benchmark value for subsequent capacity verification, which helps to evaluate whether the pipeline can meet future flow requirements.

[0050] S206. If it is predicted that the flow rate of a certain section of the oil and gas pipeline will increase significantly and exceed its transportation carrying capacity, a warning message is generated.

[0051] Specifically, if the system predicts that the flow rate of a certain section of oil and gas pipeline will increase significantly and exceed its transportation capacity, it will generate early warning information based on the prediction results and the carrying capacity verification results. The early warning information includes key information such as the impact range and blockage time of each risk pipeline. Early warning information can timely discover potential pipeline blockage risks and provide decision makers with a reference for emergency response measures. By taking preventive measures in advance, pipeline blockage accidents can be effectively avoided and the safe and stable operation of the oil and gas storage and transportation system can be guaranteed.

[0052] Reference Figure 3 Further, after S206, as another implementation, the embodiment of the present application may further include the following steps: S301. Calculate the flow growth trend corresponding to each risk pipeline according to the prediction work results and the transportation carrying capacity.

[0053] Specifically, the system calculates the flow growth trend corresponding to each risk pipeline based on the prediction results and the transport carrying capacity. The flow growth trend is used to indicate the flow change that exceeds the transport carrying capacity, which can be obtained by comparing the difference between the predicted flow and the transport carrying capacity and their rate of change. The flow growth trend provides an important basis for assessing the risk level of risk pipeline blockage. By understanding the speed and magnitude of flow growth, the possibility of pipeline blockage can be judged more accurately.

[0054] S302: Obtain the historical blockage records corresponding to each risk pipeline.

[0055] Specifically, the system obtains the historical blockage records corresponding to each risk pipeline; obtains the historical blockage records corresponding to each risk pipeline from the database, including the time, location, cause, duration, and solution of the blockage. The historical blockage records provide a historical reference for assessing the risk level of risk pipeline blockage. By analyzing the historical blockage records, we can understand the blockage rules and characteristics of the pipeline, which helps to more accurately assess the current risk status.

[0056] S303. Assess the risk level of risk pipeline blockage.

[0057] Specifically, the system considers factors such as the flow growth trend, transportation carrying capacity, and historical blockage records of risk pipelines, and uses risk assessment models or algorithms to assess the risk level of risk pipeline blockage. The higher the risk level, the greater the possibility of blockage of the risk pipeline. Risk level assessment provides decision makers with intuitive risk prompts. By understanding the risk level, decision makers can more accurately determine which pipelines need to take preventive measures first, thereby effectively avoiding the occurrence of pipeline blockage accidents.

[0058] S304. Analyze the importance of the affected area.

[0059] Specifically, the system analyzes the importance of the affected areas based on the impact range in the forecast work results. This can be achieved by considering factors such as the geographical location, economic value, and population density of the affected areas. Analyzing the importance of the affected areas helps decision makers determine the risk channels to be prioritized. For areas with higher importance, more attention needs to be paid to their risk status and corresponding preventive measures need to be taken to ensure safety.

[0060] S305: Query important areas from a preset database.

[0061] Specifically, the system queries important areas from a preset database, including areas involving key oil transfer nodes and / or areas close to residential areas. Once a pipeline blockage accident occurs in these areas, it may cause serious consequences. Querying important areas helps decision makers to more accurately identify potential high-risk areas. For these areas, more stringent monitoring and preventive measures are needed to ensure safety.

[0062] S306: If the impact range of the risk pipeline is an important area, a risk enhancement instruction is generated and executed.

[0063] Specifically, if the impact range of the risk pipeline is an important area, the system generates and executes a risk enhancement instruction; the risk enhancement instruction is used to increase the original risk level of the risk pipeline by one level. For example, the original risk level of the risk pipeline is medium risk, and the risk enhancement instruction can increase the risk level of the current risk pipeline to high risk.

[0064] S307. Find the key parts within the impact range of the risk pipeline.

[0065] Specifically, the system searches for key parts within the risk pipeline’s influence range, including welds, elbows, tees, valves, and joints; searches for key parts within the risk pipeline’s influence range, which are usually where pipelines are prone to failure or blockage. By checking the conditions of these parts, potential risks can be discovered in a timely manner and appropriate measures can be taken. Finding key parts helps locate potential risk points more accurately. By strengthening monitoring and maintenance of these parts, the safety and reliability of the pipeline can be further improved.

[0066] S308: If the critical part is found, a risk enhancement instruction is generated and executed.

[0067] Specifically, if the system finds a critical part, it will generate and execute a risk enhancement instruction. If the risk pipeline is affected by an important area, or if a critical part (such as welds, elbows, tees, valves, and joints) is found, a risk enhancement instruction will be generated and executed. Risk enhancement instructions may include strengthening monitoring, increasing inspection frequency, taking temporary measures, etc. Generating and executing risk enhancement instructions helps to respond to potential risks in a timely manner. By taking preventive measures, the possibility of pipeline blockage accidents can be reduced, thereby ensuring the safe and stable operation of the oil and gas storage and transportation system.

[0068] Reference Figure 4 Further, after S303, as another implementation mode, the embodiment of the present application may further include the following steps: S401. Evaluate the time urgency of possible pipeline blockage according to the blockage time.

[0069] Specifically, the system evaluates the time urgency of the possible pipeline blockage based on the blockage time; this step requires the use of the blockage time data obtained in the previous evaluation. The blockage time is usually based on historical data, real-time monitoring data, and possible future trend forecasts. By comparing the current time with the predicted blockage time, the time urgency of the possible blockage can be evaluated. For example, if the predicted blockage time is very close to the current time, the time urgency is high; conversely, if the predicted blockage time is far away, the time urgency is low. Assessing time urgency will help to formulate more reasonable processing strategies in the future, ensuring that the most effective measures are taken within a limited time.

[0070] S402: Determine the execution priority corresponding to each risk pipeline according to the risk level and time urgency.

[0071] Specifically, the system determines the execution priority corresponding to each risk pipeline according to the risk level and time urgency, and the execution priority is divided into low, medium and high levels; considering the risk level (such as high risk, medium risk, low risk) and time urgency (such as urgent, relatively urgent, non-urgent), an execution priority is set for each risk pipeline. Priorities can be divided into low, medium and high levels, where high priority means that the risk is high and time is urgent, and immediate action is required; medium priority means that the risk is high or time is relatively urgent and needs to be handled as soon as possible; low priority means that the risk is relatively low or time is relatively ample and can be handled later. By setting execution priorities, it can ensure that limited resources (such as personnel, equipment, etc.) are used most effectively and give priority to the issues that need the most attention.

[0072] S403: If the execution priority is high, generate and execute an emergency processing instruction.

[0073] Specifically, if the execution priority of the system is high, an emergency handling instruction is generated and executed; when the execution priority of a pipeline is determined to be high, the system should immediately generate the corresponding emergency handling instruction. Emergency handling instructions include measures such as immediately dispatching maintenance personnel, starting backup pipelines, closing or reducing the flow of risk pipelines. The system also needs to monitor the execution of instructions to ensure that emergency handling measures are effectively implemented. The timely generation and execution of emergency handling instructions can minimize the losses and impacts caused by pipeline blockage.

[0074] S404: If the execution priority is low or medium, adjust the traffic distribution plan.

[0075] Specifically, if the execution priority of the system is low or medium, the system adjusts the flow distribution plan, which is used to transfer part of the flow from the higher-risk sections to other sections with stronger carrying capacity; for pipelines with low or medium execution priority, the system can reduce the risk by adjusting the flow distribution plan. The flow distribution plan aims to transfer part of the flow from higher-risk sections to other sections with stronger carrying capacity to reduce the load on risky pipelines. The adjustment plan needs to consider factors such as the pipeline's carrying capacity, flow demand, and possible flow transfer paths. By adjusting the flow distribution plan, the risk of pipeline blockage can be effectively reduced without increasing additional resource investment.

[0076] S405: Push the traffic allocation plan to the user's smart terminal.

[0077] Specifically, the system pushes the traffic allocation plan to the user's smart terminal. The system pushes the adjusted traffic allocation plan to the user's smart terminal in an appropriate form (such as text messages, emails, APP notifications, etc.). The pushed content should include the specific content of the traffic allocation plan, implementation time, precautions and other information. Users can view and confirm the plan through the smart terminal, and interact with the system when necessary to propose modifications or feedback on the implementation status. Pushing the traffic allocation plan to the user's smart terminal can improve the transparency and traceability of information, help users better understand and implement the plan, and thus jointly reduce the risk of pipeline blockage.

[0078] In another embodiment, referring to Figure 5 , S403 specifically includes the following sub-steps: S501. Query the standard pipeline flow corresponding to the risk pipeline from a preset database.

[0079] Specifically, the system queries the standard pipeline flow corresponding to the risk pipeline from the preset database; the system first accesses the preset database, which stores the standard flow data of various pipelines under normal conditions. According to the type, size, material and other parameters of the risk pipeline, the system can retrieve the corresponding standard pipeline flow. Obtaining the standard pipeline flow is the basis for evaluating whether the current pipeline flow is abnormal, which helps to calculate the flow difference in subsequent steps.

[0080] S502: Calculate the flow difference according to the historical data information.

[0081] Specifically, the system calculates the flow difference based on the historical data information, and the flow difference is the difference between the pipeline flow data and the standard pipeline flow; the system collects and processes the historical flow data of the risk pipeline, and calculates the flow difference, that is, the deviation between the actual flow and the standard flow, by comparing the historical flow data with the standard pipeline flow. The calculation of the flow difference can intuitively reflect the abnormal situation of the pipeline flow and provide a basis for subsequent decision-making.

[0082] S503: Query the pipeline flow difference threshold from a preset database.

[0083] Specifically, the system queries the pipeline flow difference threshold from the preset database; the system accesses the preset database again, this time to obtain the pipeline flow difference threshold. The threshold is pre-set by the user based on factors such as pipeline type, usage conditions, safety standards, etc., and is used to determine whether the flow difference has reached a level that requires emergency measures. Setting the flow difference threshold helps the system make more accurate judgments and avoid overreaction or delayed processing.

[0084] S504: If the flow difference reaches the pipeline flow difference threshold, real-time image data inside the pipeline is acquired through an image perception sensor.

[0085] Specifically, if the flow difference reaches the pipeline flow difference threshold, the system acquires real-time image data inside the pipeline through the image perception sensor; when the flow difference exceeds the set threshold, the system triggers the image perception sensor, such as a camera or endoscope, to acquire real-time images of the inside of the pipeline. The acquisition of real-time image data can intuitively display the situation inside the pipeline and provide direct evidence for subsequent problem diagnosis.

[0086] S505: Retrieve pipeline inner wall problem data according to the real-time image data.

[0087] Specifically, the system retrieves the pipeline inner wall problem data based on the real-time image data, and the pipeline inner wall problem data includes pipeline rough wear and / or pipeline deposits; the system processes and analyzes the real-time image data, such as using image recognition technology to identify pipeline inner wall problems. Based on the analysis results, the system retrieves pipeline inner wall problem data corresponding to the identified problem, such as pipeline rough wear, pipeline deposits, etc. Through image analysis and problem data retrieval, the system can accurately identify problems inside the pipeline and provide a basis for subsequent treatment measures.

[0088] S506: If the pipeline is found to be rough and worn, the user is reminded to replace or repair the risky pipeline.

[0089] Specifically, if the rough wear of the pipeline is retrieved, the user will be reminded to replace or repair the risky pipeline; when the system identifies the rough wear of the inner wall of the pipeline, it will send a reminder message to the user through the smart terminal or other communication methods. The reminder message will include information such as the severity of the wear, recommended repair or replacement measures, etc. Timely reminders can enable users to take timely measures to avoid further deterioration of the pipeline due to wear, or even lead to more serious consequences.

[0090] S507: If pipeline deposits are found, the user is reminded to clean the risky pipeline.

[0091] Specifically, if pipeline deposits are retrieved, the user will be reminded to clean the risky pipeline. When the system identifies deposits inside the pipeline, it will also send a cleaning reminder to the user through a smart terminal or other communication methods. The reminder information will include information such as the type and location of the deposits, and recommended cleaning methods. Timely cleaning reminders enable users to take timely measures to avoid pipelines being blocked by deposits and affecting normal use.

[0092] Based on the above method, the embodiment of the present application also discloses a big data-based oil and gas storage and transportation safety analysis system. A big data-based oil and gas storage and transportation safety analysis system includes: A data acquisition information acquisition module, which is used to acquire data acquisition information, wherein the data acquisition information includes sensor data and monitoring video data; A data storage module, the data storage module is used to store the data collection information in a data lake; Data cleaning module, which is used to clean and convert raw data; Data management module: The data management module is used to uniformly manage and integrate raw data from different sources; A data processing rule acquisition module, the data processing rule acquisition module is used to acquire preset data processing rules, the data processing rules include a standard data format corresponding to the original data; A data processing module, the data processing module is used to process the original data into several data copies according to the standard data format; A partition storage module, which is used to store several data copies in different areas of the database; A data analysis request receiving module, which is used to receive a data analysis request sent by a user through an intelligent terminal, wherein the data analysis request carries data analysis information, and the data analysis information includes analysis indicators, analysis time period, and analysis area; The analysis and processing module is used to analyze and process the data copies in the database according to the data analysis request.

[0093] An embodiment of the present application also discloses an intelligent terminal, which includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes the above-mentioned big data-based oil and gas storage and transportation safety analysis method.

[0094] The embodiment of the present application also discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program that can be loaded by a processor and executes the above-mentioned oil and gas storage and transportation safety analysis method based on big data, and the computer-readable storage medium includes, for example, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0095] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A method for oil and gas storage and transportation safety analysis based on big data, characterized in that: The following steps are involved: Acquire data collection information, wherein the data collection information includes sensor data and monitoring video data; Storing the data collection information in a data lake; Clean and transform the raw data; Unified management and integration of raw data from different sources; Acquire a preset data processing rule, wherein the data processing rule includes a standard data format corresponding to the original data; Processing the original data into several data copies according to the standard data format; Store several copies of data in different areas of the database; Receiving a data analysis request sent by a user through a smart terminal, the data analysis request carrying data analysis information, the data analysis information including analysis indicators, analysis time period, and analysis area; The data copy in the database is analyzed and processed according to the data analysis request.

2. The method for oil and gas storage and transportation safety analysis based on big data according to claim 1 is characterized in that: After the step of analyzing and processing the data copy in the database according to the data analysis request, the method further includes: Extracting historical data information within a past period of time from a database, wherein the historical data information includes pipeline flow data, transportation planning records, and maintenance record data; Merging the data copy in the database with the historical data information to form a complete data set; Get the transportation planning form; Based on the complete data set and transportation planning form, output the forecast results of the flow rate of each oil and gas pipeline in the future period; Obtain the corresponding transport carrying capacity of each pipeline from the preset database; If it is predicted that the flow rate of a certain section of oil and gas pipeline will increase significantly and exceed its transportation carrying capacity, an early warning information is generated, which includes the impact range and blockage time of each risk pipeline that may be blocked.

3. The method for analyzing oil and gas storage and transportation safety based on big data according to claim 2 is characterized in that: After the step of generating the warning information, the method further includes: Calculate the flow growth trend corresponding to each risk pipeline according to the prediction work results and the transmission carrying capacity, wherein the flow growth trend is used to represent the flow change exceeding the transmission carrying capacity; Obtain the historical blockage records corresponding to each risk pipeline; Considering the flow growth trend, transmission carrying capacity and historical blockage records of the risk pipeline, the risk level of blockage of the risk pipeline is evaluated. The higher the risk level, the greater the possibility of blockage of the risk pipeline. Analyze the importance of the affected area based on the impact scope; Querying important areas from a preset database, wherein the important areas include areas involving key oil transportation nodes and / or areas close to residential areas; If the impact range of the risk pipeline is a critical area, a risk enhancement instruction is generated and executed; Find the key parts within the risk pipeline impact range, including welds, elbows, tees, valves and joints; If the critical parts are found, risk enhancement instructions are generated and executed.

4. The oil and gas storage and transportation safety analysis method based on big data according to claim 3 is characterized in that: After the step of evaluating the risk level of risk pipeline blockage, the method further includes: Based on the blockage time, assess the time urgency with which the pipeline blockage may occur; Determine the execution priority corresponding to each risk pipeline according to the risk level and time urgency, and the execution priority is divided into low, medium and high; If the execution priority is high, an emergency processing instruction is generated and executed; If the execution priority is low or medium, a flow distribution plan is adjusted, wherein the flow distribution plan is used to transfer part of the flow from the pipeline section with higher risk to other pipeline sections with stronger carrying capacity; The traffic distribution plan is pushed to the user's smart terminal.

5. The method for analyzing oil and gas storage and transportation safety based on big data according to claim 4 is characterized in that: The steps of generating and executing emergency processing instructions specifically include: Query the standard pipeline flow corresponding to the risk pipeline from the preset database; Calculate the flow difference according to the historical data information, where the flow difference is the difference between the pipeline flow data and the standard pipeline flow; Query pipeline flow difference threshold value from a preset database; If the flow difference reaches the pipeline flow difference threshold, real-time image data inside the pipeline is acquired through an image sensing sensor; Retrieving pipeline inner wall problem data according to the real-time image data, wherein the pipeline inner wall problem data includes pipeline rough wear and / or pipeline deposits; If the pipeline is found to be rough and worn, the user is reminded to replace or repair the risky pipeline; If pipeline deposits are found, the user is reminded to clean the risky pipeline.

6. The method for oil and gas storage and transportation safety analysis based on big data according to claim 1 is characterized in that: The steps of unified management and integration of raw data from different sources specifically include: During the training period T train In the process, data from different data sources i at different times t are collected for training data S train ; ； ； During the test period T test In the data from different data sources i at different times t, the test data S test ; ； ； The test period T test A set of test point categories in the label (i) The reliability of the calculation is the confidence level Cl label ; ； Where: D label(i) The category is label (i) The distance from the test point to the decision classification surface, D j is the distance from all test points to the decision classification surface; Calculate the similarity between the data point x′ and each point in the array X = {x1, x2, . . . , xn} to obtain the matching degree µ; ； in, , the symbol (·) represents the inner product of two vectors; The data analysis result result(label, Cl, µ) is obtained, where label is the output category label; the data analysis result is used to reflect the category of the original data, the degree of confidence, and the similarity with other data points.

7. A big data-based oil and gas storage and transportation safety analysis system, characterized in that: include: A data acquisition information acquisition module is used to acquire data acquisition information, wherein the data acquisition information includes sensor data and monitoring video data; A data storage module, used to store the data collection information in a data lake; Data cleaning module, used to clean and convert raw data; Data management module, used to uniformly manage and integrate raw data from different sources; A data processing rule acquisition module, used to acquire preset data processing rules, wherein the data processing rules include a standard data format corresponding to the original data; A data processing module, used for processing the original data into a plurality of data copies according to the standard data format; A partition storage module is used to store several data copies in different areas of the database; A data analysis request receiving module, used to receive a data analysis request sent by a user through an intelligent terminal, wherein the data analysis request carries data analysis information, and the data analysis information includes analysis indicators, analysis time period, and analysis area; The analysis and processing module is used to analyze and process the data copies in the database according to the data analysis request.

8. An intelligent terminal, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a method for analyzing oil and gas storage and transportation safety based on big data as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes a method for analyzing the safety of oil and gas storage and transportation based on big data as described in any one of claims 1 to 6.

Images