Method, device and equipment for predicting global risk situation of oil and gas pipe network and medium

Abstract

The invention discloses an oil and gas pipe network global risk situation prediction method and device, equipment and a medium. The method is characterized by comprising the steps of performing data acquisition on a target oil and gas pipe network based on a preset acquisition period, and determining at least one piece of operation data of the target oil and gas pipe network; obtaining a standard operation data range corresponding to the operation data, identifying the operation data based on the standard operation data range, and determining an initial detection identifier of the operation data; if the initial detection identifier of the operation data is a problem identifier, determining the operation data as risk operation data; and performing risk identification on the target oil and gas pipe network according to the risk operation data, and determining a final risk prediction value of the target oil and gas pipe network. According to the method, the accuracy of risk prediction is improved, so that the occurrence of pipe network faults is effectively prevented, false alarm and missing alarm are reduced, and the risk prediction capability of complex working conditions and emergencies is improved.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas pipeline network operations, and in particular to a method, device, equipment and medium for predicting the global risk situation of an oil and gas pipeline network. Background Art

[0002] With the continuous expansion of oil and gas pipeline networks and the increasing complexity of their operating environments, ensuring their safe and efficient operation has become a pressing issue. Over the long term, oil and gas pipeline networks are susceptible to various factors, including equipment aging, environmental fluctuations, and human intervention. These factors can lead to pipeline leaks, pressure anomalies, temperature fluctuations, and cyberattacks. Failure to promptly detect and effectively warn of these issues can result in significant economic losses and environmental damage. Therefore, risk prediction and situational awareness technologies for oil and gas pipeline networks are crucial.

[0003] Existing oil and gas pipeline network risk prediction methods mostly rely on traditional physical models or simple statistical analysis, typically considering only localized operational data and neglecting the overall risk profile of the pipeline network. Relying on a single type of sensor data and failing to fully utilize multiple sources of data (such as network operation data and sensor data) results in a weak understanding of the overall operational status of the pipeline network. Furthermore, traditional risk prediction methods rely primarily on empirical rules and simple threshold judgments, making them prone to false positives and false negatives, especially under complex operating conditions. This inability to identify potential risk patterns from massive amounts of data results in low accuracy and reliability of prediction results. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for predicting the global risk situation of an oil and gas pipeline network, so as to solve the technical problem in the prior art that the risk situation prediction of an oil and gas pipeline network is one-sided and has low accuracy.

[0005] According to one aspect of the present invention, a method for predicting the global risk situation of an oil and gas pipeline network is provided, comprising:

[0006] Collecting data from a target oil and gas pipeline network based on a preset collection period to determine at least one operating data of the target oil and gas pipeline network;

[0007] Obtaining a standard operating data range corresponding to the operating data, identifying the operating data based on the standard operating data range, and determining an initial detection identifier for the operating data;

[0008] If the initial detection identifier of the operation data is the problem identifier, determining the operation data as risky operation data;

[0009] The target oil and gas pipeline network is subjected to risk identification based on the risk operation data to determine a final risk prediction value of the target oil and gas pipeline network.

[0010] According to another aspect of the present invention, a device for predicting the global risk situation of an oil and gas pipeline network is provided, comprising:

[0011] an acquisition module, configured to acquire data from a target oil and gas pipeline network based on a preset acquisition cycle, and determine at least one operating data of the target oil and gas pipeline network;

[0012] an identification module, configured to obtain a standard operating data range corresponding to the operating data, identify the operating data based on the standard operating data range, and determine an initial detection identifier for the operating data;

[0013] a judgment module, configured to determine the operation data as risky operation data if the initial detection identifier of the operation data is the problem identifier;

[0014] The prediction module is used to identify the risk of the target oil and gas pipeline network according to the risk operation data and determine the final risk prediction value of the target oil and gas pipeline network.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the global risk situation of the oil and gas pipeline network described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the global risk situation of an oil and gas pipeline network described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiments of the present invention collects data from a target oil and gas pipeline network based on a preset collection cycle to determine at least one operating data point of the target oil and gas pipeline network. A standard operating data range corresponding to the operating data is obtained, and the operating data is identified based on the standard operating data range to determine an initial detection flag for the operating data. This multi-dimensional operating data comprehensively reflects the operating status of the pipeline network, improving the accuracy of analysis and identification. The initial detection flag enhances the accuracy of risk identification. If the initial detection flag of the operating data is a problem flag, the operating data is determined to be risky operating data. Risk identification is performed on the target oil and gas pipeline network based on the risky operating data to determine a final risk prediction value for the target oil and gas pipeline network. This solves the technical problem of one-sided and low-accuracy risk status prediction for oil and gas pipeline networks in the prior art. It improves the accuracy of risk prediction. Through dynamic adjustment of an intelligent model, the real-time and adaptability of the prediction results are enhanced, effectively preventing pipeline network failures and reducing false positives and missed positives. This enhances the risk prediction capabilities for complex operating conditions and emergencies.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flowchart of a method for predicting the global risk situation of an oil and gas pipeline network is provided for an embodiment of the present invention;

[0024] Figure 2 A flowchart of another method for predicting the global risk situation of an oil and gas pipeline network provided by an embodiment of the present invention;

[0025] Figure 3 A flowchart of another method for predicting the global risk situation of an oil and gas pipeline network provided by an embodiment of the present invention;

[0026] Figure 4 A schematic structural diagram of a device for predicting global risk situations in an oil and gas pipeline network provided by an embodiment of the present invention;

[0027] Figure 5 FIG. 1 is a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Figure 1 The present invention provides a flowchart of a method for predicting the global risk situation of an oil and gas pipeline network. This embodiment is applicable to situations where risk prediction of an oil and gas pipeline network is performed based on the operating data of the oil and gas pipeline network. The method can be executed by a device for predicting the global risk situation of an oil and gas pipeline network. The device can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110 : Collect data from a target oil and gas pipeline network based on a preset collection cycle to determine at least one operating data of the target oil and gas pipeline network.

[0032] The preset collection period may be a time period preset for collecting running data at a fixed time.

[0033] Operational data can be data generated during the operation of the oil and gas pipeline network. It should be noted that the types of operational data primarily include sensor transmission data and network data generated during the operation of the oil and gas pipeline network. For example, sensor transmission data can include the values ​​of pressure sensors, temperature sensors, and oil and gas flow sensors; network data can include data such as equipment status and operation logs in the oil and gas pipeline network.

[0034] Specifically, during the operation process of the target oil and gas pipeline network, sensor transmission data and network data are collected from the target oil and gas pipeline network at every preset collection period to obtain various operation data of different data types.

[0035] S120: Acquire a standard operating data range corresponding to the operating data, identify the operating data based on the standard operating data range, and determine an initial detection identifier for the operating data.

[0036] The standard operating data range may be a reference range set for operating data of each data type based on normal operating conditions; the standard operating data range may be used to determine whether the operating data is abnormal.

[0037] Among them, the initial detection identifier can be used to indicate the difference between the operating data and the standard operating data range; the initial detection identifier includes a problem identifier, a non-problem identifier and a suspected problem identifier; it should be noted that if the initial detection identifier is a problem identifier, it means that the operating data is completely outside the standard operating data range, the operating data is abnormal, and there is a fault; the non-problem identifier indicates that the operating data is completely within the standard operating data range and the operating data is normal; the suspected problem identifier indicates that part of the operating data is within the standard operating data range, part of the operating data is outside the standard operating data range, there is a possibility of abnormality in the operating data, and further judgment of the operating data is required.

[0038] Optionally, in the present invention, the standard operating data range can be obtained in the following manner: collecting standard operating data corresponding to the operating data.

[0039] Collect the last non-problem record of the oil and gas pipeline network, and extract the corresponding non-problem historical operation data from the last non-problem record.

[0040] The non-problem historical operation data is compared with the standard operation data, and a standard operation data range is generated according to the relationship between the numerical values, wherein the standard operation data range includes a left boundary and a right boundary.

[0041] Among them, the standard operating data can be the operating data of each data type generated under normal operating conditions; it should be noted that when the target oil and gas pipeline network is in normal operating state, the operating data of the target oil and gas pipeline network is collected as standard operating data.

[0042] The non-problem records may be records of the normal operation of the target oil and gas pipeline in other time periods.

[0043] The non-problem historical operation data may be operation data corresponding to non-problem records.

[0044] The left boundary and the right boundary may be data boundaries that are different from the standard operating data range; the standard operating data range is constructed by the left boundary and the right boundary.

[0045] Specifically, by collecting the standard operating data and the previous non-problem record corresponding to the operating data of the target oil and gas pipeline network, and extracting the corresponding non-problem historical operating data from the previous non-problem record, the non-problem historical operating data is compared with the standard operating data, and the standard operating data range is generated according to the numerical size relationship, where the standard operating data range includes a left boundary and a right boundary.

[0046] Specifically, corresponding to each piece of operating data, a standard operating data range corresponding to the operating data is obtained, the operating data is identified based on the standard operating data range, and an initial detection identifier of the operating data is determined.

[0047] Optionally, in another optional embodiment of the present invention, identifying the operating data based on the standard operating data range and determining the initial detection identifier of the operating data includes:

[0048] If the operating data are not within the standard operating data range, generating a problem indicator for the operating data;

[0049] If the operating data are all within the standard operating data range, generating a non-problem mark for the operating data;

[0050] If at least one of the operating data is within the standard operating data range and at least one of the operating data is not within the standard operating data range, a suspected problem identifier is generated for the operating data.

[0051] Specifically, based on the standard operating data range corresponding to the operating data, if all the operating data are not within the standard operating data range, a problem identification is generated for the operating data; if all the operating data are within the standard operating data range, a non-problem identification is generated for the operating data; if there is at least one operating data within the standard operating data range and there is at least one operating data not within the standard operating data range, a suspected problem identification is generated for the operating data.

[0052] S130: If the initial detection identifier of the operation data is the problem identifier, determine the operation data as risky operation data.

[0053] Risky operation data may be operation data that presents a risk of impacting the normal operation of the oil and gas pipeline network. It should be noted that the initial detection of the operation data is marked as a problem flag, indicating that the operation data is abnormal and presents a risk of impacting the oil and gas pipeline network, and the operation data is marked as risky operation data.

[0054] Specifically, if the initial detection identification of the operation data is a problem identification, the operation data is determined to be risky operation data.

[0055] S140: Perform risk identification on the target oil and gas pipeline network according to the risk operation data, and determine a final risk prediction value of the target oil and gas pipeline network.

[0056] The final risk prediction value can be a data value that predicts the risk of the target oil and gas pipeline network. It should be noted that the final risk prediction value can provide feedback on the risk situation of the target oil and gas pipeline network. If the final risk prediction value is too high, it means that there is a high probability that the target oil and gas pipeline network will experience an abnormality, resulting in losses, and the operation of the target oil and gas pipeline network needs to be stopped immediately to investigate the existing problems. If the final risk prediction value is low, it means that there is a small probability that the target oil and gas pipeline network will experience an abnormality, and the abnormal operating data should be inspected and repaired. For example, the target oil and gas pipeline network may have risks such as pipeline leakage, pressure anomalies, temperature fluctuations, and cyber attacks.

[0057] Specifically, the risk of the target oil and gas pipeline network is identified based on the risk operation data, and the final risk prediction value of the target oil and gas pipeline network is determined.

[0058] The technical solution of the embodiments of the present invention collects data from a target oil and gas pipeline network based on a preset collection cycle to determine at least one operating data point of the target oil and gas pipeline network. A standard operating data range corresponding to the operating data is obtained, and the operating data is identified based on the standard operating data range to determine an initial detection flag for the operating data. This multi-dimensional operating data comprehensively reflects the operating status of the pipeline network, improving the accuracy of analysis and identification. The initial detection flag enhances the accuracy of risk identification. If the initial detection flag of the operating data is a problem flag, the operating data is determined to be risky operating data. Risk identification is performed on the target oil and gas pipeline network based on the risky operating data to determine a final risk prediction value for the target oil and gas pipeline network. This solves the technical problem of one-sided and low-accuracy risk status prediction for oil and gas pipeline networks in the prior art. It improves the accuracy of risk prediction. Through dynamic adjustment of an intelligent model, the real-time and adaptability of the prediction results are enhanced, effectively preventing pipeline network failures and reducing false positives and missed positives. This enhances the risk prediction capabilities for complex operating conditions and emergencies.

[0059] Figure 2 This is a flowchart of another method for predicting the global risk situation of an oil and gas pipeline network provided by an embodiment of the present invention. The relationship between this embodiment and the above embodiment specifically introduces a specific method for further identifying the operating data of non-problem marks, such as Figure 2 As shown, the method includes:

[0060] S210: Collect data from a target oil and gas pipeline network based on a preset collection period to determine at least one operating data of the target oil and gas pipeline network.

[0061] S220: Acquire a standard operating data range corresponding to the operating data, identify the operating data based on the standard operating data range, and determine an initial detection identifier for the operating data.

[0062] S230. If the initial detection identifier of the operating data is the suspected problem identifier, the operating data that is not greater than the left boundary value of the standard operating data range is divided into a first data group, and the operating data that is not less than the right boundary value of the standard operating data range is divided into a second data group.

[0063] The left boundary value of the standard operating data range may be a numerical value corresponding to the left boundary of the standard operating data range.

[0064] The first data group may be a data group that records operating data that falls outside the left boundary of the standard operating data range. It should be noted that each piece of operating data is sequentially compared with the left boundary of the standard operating data, and only operating data that falls within the left boundary of the standard operating data range is stored in the first data group.

[0065] The second data group may be a data group that records operating data that falls outside the right boundary of the standard operating data range. It should be noted that each piece of operating data is sequentially compared with the right boundary of the standard operating data, and only operating data with a value not less than the right boundary of the standard operating data range is stored in the second data group.

[0066] Specifically, when the initial detection identifier of the operating data is identified as a suspected problem identifier, each operating data is compared with the left boundary value of the standard operating data in turn, and the operating data with a left boundary value not greater than the standard operating data range is stored in the first data group, and each operating data is compared with the right boundary value of the standard operating data, and the operating data with a right boundary value not less than the standard operating data range is stored in the second data group.

[0067] S240: Determine a first suspected problem factor based on the first data group and the second data group.

[0068] The first suspected problem factor may be a data value for identifying whether the operating data has risks.

[0069] Specifically, a first suspected problem factor is constructed based on the first data group and the second data group. For example, F1 represents the first suspected problem factor, N represents the total number of running data, N1 represents the number of data in the first data group, N2 represents the number of data in the second data group, L represents the left boundary value of the standard running data range, U represents the right boundary value of the standard running data range, R represents the width of the standard running data range, Ai represents the value of the i-th data in the first data group, and Aj represents the value of the j-th data in the second data group. The construction process of the first suspected problem factor is as follows:

[0070]

[0071] S250: Normalize the operation data and perform curve fitting to obtain an oil and gas pipeline network operation curve, and determine a second suspected problem factor based on the variance of the oil and gas pipeline network operation curve and the oil and gas pipeline network operation curve.

[0072] The oil and gas pipeline network operation curve can be used to display the patterns and trends of the operation data of the oil and gas pipeline network. It should be noted that all the operation data are normalized and the normalized operation data is used to generate a fitting curve, namely the oil and gas pipeline network operation curve.

[0073] The second suspected problem factor may represent the abnormal degree of fluctuation in the operating data, and the user can assist in determining whether there is a potential problem.

[0074] Optionally, after obtaining the oil and gas pipeline network operation curve, the variance of the oil and gas pipeline network operation curve is calculated to evaluate the degree of fluctuation of the operation data, and then the second suspected problem factor is obtained based on the oil and gas pipeline network operation curve.

[0075] Specifically, the operation data is normalized and curve fitting is performed to obtain the oil and gas pipeline network operation curve, and the second suspected problem factor is determined based on the variance of the oil and gas pipeline network operation curve and the oil and gas pipeline network operation curve. For example, F2 represents the second suspected problem factor, σ 2 Represents the variance of the fitted curve. The calculation process of the second suspected problem factor is as follows:

[0076]

[0077] S260: Determine a comprehensive problem factor of the operation data based on the first suspected problem factor and the second suspected problem factor.

[0078] Among them, the comprehensive problem factor is used to determine whether there is a problem with the operating data. It should be noted that the comprehensive problem factor combines the risk level of the operating data with suspected problem markers and the abnormality of data fluctuations, and can determine whether there is a problem with the operating data with suspected problem markers.

[0079] Specifically, the first suspected problem factor and the second suspected problem factor are combined to generate a comprehensive problem factor.

[0080] Optionally, when combining the first suspected problem factor and the second suspected problem factor, different weight coefficients are set for the first suspected problem factor and the second suspected problem factor, respectively, and then the first suspected problem factor and the second suspected problem factor are combined based on the weight coefficients. For example, the first suspected problem factor is set to a1, the second suspected problem factor is set to a2, and a1+a2=1, and the calculation process of the comprehensive problem factor is as follows:

[0081] F=F1·a1+F2·a2

[0082] S270: If the comprehensive problem factor is greater than the factor threshold, generate a problem identifier for the operation data.

[0083] The factor threshold may be a pre-set value used to determine whether the comprehensive problem factor of the operating data meets the data value of a problem. It should be noted that the comprehensive problem factor of the operating data is compared with the factor threshold. If the comprehensive problem factor is greater than the factor threshold, it indicates that the risk value of the operating data is high, and the suspected problem flag of the operating data is changed to a problem flag. If the comprehensive problem factor is not greater than the factor threshold, it indicates that the operating data is normal, and the suspected problem flag of the operating data is changed to a non-problem flag.

[0084] Specifically, if the comprehensive problem factor is greater than a factor threshold, a problem identifier is generated for the operation data.

[0085] S280: If the initial detection identifier of the operation data is the problem identifier, determine the operation data as risky operation data.

[0086] S290: Perform risk identification on the target oil and gas pipeline network according to the risk operation data, and determine a final risk prediction value of the target oil and gas pipeline network.

[0087] The embodiment of the present invention further identifies and confirms the operating data with suspected problem markers. Through a refined data group division method, it can more accurately identify deviations in the operating data, and whether it is an abnormality that is too low or too high, it can be captured and processed in a timely manner. By combining the deviation degree and the fitting curve variance of the suspected problem factor, the stability and abnormality of the pipeline network operation can be comprehensively evaluated, and the accuracy and comprehensiveness of the risk prediction can be enhanced; when generating the comprehensive problem factor, by setting different weight coefficients, the relative importance of the first suspected problem factor and the second suspected problem factor can be flexibly adjusted to adapt to different pipeline network operating conditions and risk assessment requirements. It supports automated real-time monitoring of pipeline network operation data, can detect potential problems at an early stage, generate early warnings in a timely manner, and help managers respond quickly to prevent fault expansion.

[0088] Figure 3 This is a flowchart of another method for predicting the global risk situation of an oil and gas pipeline network provided by an embodiment of the present invention. The relationship between this embodiment and the above embodiment is that it specifically introduces a specific method for realizing risk operation identification, such as Figure 3 As shown, the method includes:

[0089] S310: Collect data from a target oil and gas pipeline network based on a preset collection cycle to determine at least one operating data of the target oil and gas pipeline network.

[0090] S320: Obtain a standard operating data range corresponding to the operating data, identify the operating data based on the standard operating data range, and determine an initial detection identifier for the operating data.

[0091] S330: If the initial detection identifier of the operation data is the problem identifier, determine the operation data as risky operation data.

[0092] S340: Obtain historical operation data from a preset historical fault database.

[0093] The historical fault database may be a database pre-established to store operational data leading to failures in the target oil and gas pipeline network. It should be noted that when a failure occurs in the target oil and gas pipeline network, the time of each failure is recorded, and the operational data collected during the time period corresponding to the failure time is used as historical operational data, which is then stored in the pre-established historical fault database.

[0094] Specifically, a historical fault database corresponding to the target oil and gas pipeline network is accessed, data query is performed in the historical fault database, and historical operation data in the historical fault database is obtained.

[0095] S350: Perform risk identification on the target oil and gas pipeline network based on the historical operation data and the risk operation data, and determine the final risk prediction value.

[0096] Specifically, after querying and obtaining historical operation data, the historical operation data and risk operation data are compared to identify the risks of the target oil and gas pipeline network and determine the final risk prediction value.

[0097] Optionally, in another optional embodiment of the present invention, the performing risk identification on the target oil and gas pipeline network based on the historical operation data and the risk operation data to determine the final risk prediction value includes:

[0098] If there is no historical operation data whose similarity to the risk operation data is greater than the similarity threshold, performing risk prediction on the risk operation data using a pre-trained deep neural network model to determine a first risk prediction value;

[0099] identifying risk additional data in the risky operation data based on the historical operation data;

[0100] Performing risk prediction based on the risk operation data, the risk additional data, and the historical operation data through a Bayesian network to obtain a second risk prediction value;

[0101] The final risk prediction value is determined based on the first risk prediction value and the second risk prediction value.

[0102] Optionally, a similarity calculation is performed between the historical operating data and the risk operating data. If no data in the historical operating data has a similarity greater than a similarity threshold with the risk operating data, it indicates that the risk operating data and the faults corresponding to the historical operating data are not correlated, and further risk identification of the risk operating data is required. The similarity threshold may be a pre-set value used to determine the correlation between the risk operating data and the historical operating data.

[0103] Optionally, the similarity calculation between the historical operation data and the risk operation data is performed by quantifying the similarity between the historical operation data and the risk operation data through a metric, wherein the metric may be a calculation method such as Euclidean distance or cosine similarity.

[0104] Optionally, in the target oil and gas pipeline network, the behavioral characteristics of the historical operation data in a previous time period have certain similarities with the performance of the risk operation data. By calculating the similarity between the operation data, it can help evaluate whether the risk operation data has potential risks of similar anomalies.

[0105] Optionally, in another optional embodiment of the present invention, the performing risk identification on the target oil and gas pipeline network based on the historical operation data and the risk operation data to determine the final risk prediction value further includes:

[0106] If there is a historical operation data whose similarity to the risk operation data is greater than a similarity threshold, the historical final risk prediction value corresponding to the historical operation data with the highest similarity is determined as the final risk prediction value.

[0107] The historical final risk prediction value may be a final risk prediction value predicted during a time period corresponding to the historical operating data. It should be noted that when the historical fault database stores historical operating data, the final risk prediction value corresponding to the historical operating data may be stored simultaneously as the historical final risk prediction value.

[0108] Optionally, in the process of comparing historical operation data with risk operation data, if there is at least one historical operation data whose similarity with the risk operation data is greater than a similarity threshold, the historical operation data with the highest similarity is identified, and the historical final risk prediction value corresponding to the historical fault database is obtained in the historical fault database, and the historical final risk prediction value is determined as the final risk prediction value. The embodiment of the present invention can quickly determine the risk prediction value by the similarity between the historical operation data and the risk operation data. When the similarity between the risk operation data and the historical operation data is high, the historical final risk prediction value is directly used to avoid calculating the risk prediction from scratch. It can quickly obtain a more accurate risk assessment when encountering similar scenarios, improve prediction efficiency and accuracy, and reduce complex calculation processes.

[0109] Optionally, a pre-trained deep neural network model can be used to identify the risk level of the target oil and gas pipeline network based on risk operation data. The first risk prediction value output by the pre-trained deep neural network model can reflect the risk level of the target oil and gas pipeline network under the operating state. The pre-trained deep neural network model is trained based on historical operation data and fault records corresponding to the historical operation data. The deep neural network model is trained by recording historical operation data and risk events of various operating states, and the model parameters are optimized through the backpropagation algorithm and gradient descent method. The training process adjusts the model parameters of the deep neural network model so that the model can minimize the error between the prediction results and the actual risk events. The deep neural network model can learn to extract useful features and potential patterns from the input multi-dimensional data, and can identify different risk types and the relationships between them.

[0110] Optionally, the risk operation data is input into a pre-trained deep neural network model, and after forward propagation of the pre-trained deep neural network model, a first risk prediction value can be output.

[0111] Optionally, after comparing the risk operation data with the historical operation data for similarity, the historical operation data with the highest similarity is selected as the basic data, and irrelevant data in the basic data is filtered out in the risk operation data, and the irrelevant data is used as risk additional data; wherein, the risk additional data can be newly added or characteristic risk data in the risk operation data of the target oil and gas pipeline network.

[0112] Optionally, the input of the Bayesian network is risk operation data, risk additional data in the risk operation data, and basic data. In the Bayesian network, each node represents a risk operation data or basic data. Each node represents the probability of the node value according to the conditional probability distribution, which is estimated through the basic data. These probability distributions describe that a risk operation data depends on other risk operation data. The dependency relationship between different operation data is established through the Bayesian network, and the conditional probability of each node can be calculated. By comparing the risk additional data with the basic data, it can be determined whether the risk additional data has changed the result of the risk prediction, and then based on the conditional probability, the risk value corresponding to the risk operation data, that is, the second risk prediction value, can be inferred.

[0113] Specifically, if there is no historical operation data whose similarity with the risk operation data is greater than the similarity threshold, the risk operation data is risk predicted by a pre-trained deep neural network model to determine a first risk prediction value; the risk additional data in the risk operation data is identified based on the historical operation data; the risk prediction is performed based on the risk operation data, the risk additional data and the historical operation data through a Bayesian network to obtain a second risk prediction value; and the final risk prediction value is determined based on the first risk prediction value and the second risk prediction value.

[0114] Optionally, in another optional embodiment of the present invention, determining the final risk prediction value based on the first risk prediction value and the second risk prediction value includes:

[0115] Obtaining a risk prediction value difference based on the first risk prediction value and the second risk prediction value;

[0116] When the risk prediction value difference is less than a first percentage of the first risk prediction value and less than a first percentage of the second risk prediction value, determining a risk prediction mean according to the first risk prediction value and the second risk prediction value, and determining the risk prediction mean as the final risk prediction value;

[0117] In the case where the risk prediction value difference is not less than the first percentage of the first risk prediction value, or is not less than the first percentage of the second risk prediction value, if the first risk prediction value is greater than the second risk prediction value, determining a reduction coefficient based on the risk prediction value difference; adjusting the first risk prediction value based on the reduction coefficient to determine the final risk prediction value;

[0118] When the risk prediction value difference is not less than the first percentage of the first risk prediction value, or not less than the first percentage of the second risk prediction value, if the first risk prediction value is less than the second risk prediction value, an increase coefficient is determined based on the risk prediction value difference; the first risk prediction value is adjusted based on the increase coefficient to determine the final risk prediction value.

[0119] The risk prediction value difference may be the absolute value of the difference between the first risk prediction value and the second risk prediction value.

[0120] Among them, the first percentage of the first risk prediction value can be the data value corresponding to the first percentage of the first risk prediction value; the first percentage of the second risk prediction value can be the data value corresponding to the first percentage of the second risk prediction value.

[0121] Optionally, the risk prediction value difference is compared with a first percentage of the first risk prediction value and a first percentage of the second risk prediction value. If the risk prediction value difference is less than the first percentage of the first risk prediction value and less than the first percentage of the second risk prediction value, a risk prediction mean is determined based on the first risk prediction value and the second risk prediction value, and the risk prediction mean is determined as the final risk prediction value. The risk prediction mean may be the average of the first risk prediction value and the second risk prediction value.

[0122] Optionally, when the risk prediction value difference is not less than the first percentage of the first risk prediction value, or not less than the first percentage of the second risk prediction value, if the first risk prediction value is greater than the second risk prediction value, the downgrade coefficient is determined based on the risk prediction value difference; the first risk prediction value is adjusted based on the downgrade coefficient to determine the final risk prediction value; wherein, the downgrade coefficient is inversely proportional to the risk prediction value difference.

[0123] Optionally, when the risk prediction value difference is not less than the first percentage of the first risk prediction value, or not less than the first percentage of the second risk prediction value, if the first risk prediction value is less than the second risk prediction value, an increase coefficient is determined based on the risk prediction value difference; the first risk prediction value is adjusted based on the increase coefficient to determine the final risk prediction value; wherein, the increase coefficient is directly proportional to the risk prediction value difference.

[0124] For example, specifically, assume that at a certain moment, the first risk prediction value output by the deep neural network model is 0.85, the second risk prediction value output by the Bayesian network is 0.75, the risk prediction value difference is 0.1, a is 10, 10% of the first risk prediction value is 0.085, and 10% of the second risk prediction value is 0.075. The risk prediction value difference exceeds the respective 10% thresholds and needs to be adjusted. Since the first risk prediction value is greater than the second risk prediction value, the first risk prediction value is adjusted by determining a reduction coefficient based on the risk prediction value difference. The reduction coefficient range is [0.8, 1), and the increase coefficient range is (1, 1.3). Assuming that the reduction coefficient is selected as 0.9, the final risk prediction value is 0.85*0.9=0.765.

[0125] By comparing the difference between the first and second risk prediction values, the embodiment of the present invention effectively avoids the error caused by a single model, making the final prediction result more robust and reducing the interference of extreme prediction results. The prediction value is dynamically adjusted according to the size of the difference, and different adjustment strategies can be obtained for different operating conditions. This makes the prediction method more flexible and able to cope with the complex operating environment of the oil and gas pipeline network and changeable operating conditions. Through the dynamic adjustment of the adjustment coefficient, the final prediction value can be fine-tuned according to the actual situation, thereby improving the accuracy and reliability of the risk prediction. Especially when the prediction differences between models are large, the adjustment mechanism ensures that the final prediction value is more in line with the actual risk. When the prediction values ​​are close, using the mean can reduce the uncertainty of a single model, and when the differences are large, the prediction value is made more conservative by adjusting the coefficient, which enhances the perception of potential risks and ensures efficiency and reliability in decision-making.

[0126] Figure 4 This is a schematic diagram of the structure of a device for predicting the global risk situation of an oil and gas pipeline network provided by an embodiment of the present invention. Figure 4 As shown, the device includes: a collection module 410, a recognition module 420, a judgment module 430 and a prediction module 440; wherein,

[0127] The acquisition module 410 is configured to acquire data from a target oil and gas pipeline network based on a preset acquisition cycle, and determine at least one operating data of the target oil and gas pipeline network;

[0128] an identification module 420 configured to obtain a standard operating data range corresponding to the operating data, identify the operating data based on the standard operating data range, and determine an initial detection identifier for the operating data;

[0129] A judgment module 430 is configured to determine that the operating data is risky operating data if the initial detection identifier of the operating data is the problem identifier;

[0130] The prediction module 440 is configured to identify the risk of the target oil and gas pipeline network based on the risk operation data and determine a final risk prediction value of the target oil and gas pipeline network.

[0131] The technical solution of the embodiments of the present invention collects data from a target oil and gas pipeline network based on a preset collection cycle to determine at least one operating data point of the target oil and gas pipeline network. A standard operating data range corresponding to the operating data is obtained, and the operating data is identified based on the standard operating data range to determine an initial detection flag for the operating data. This multi-dimensional operating data comprehensively reflects the operating status of the pipeline network, improving the accuracy of analysis and identification. The initial detection flag enhances the accuracy of risk identification. If the initial detection flag of the operating data is a problem flag, the operating data is determined to be risky operating data. Risk identification is performed on the target oil and gas pipeline network based on the risky operating data to determine a final risk prediction value for the target oil and gas pipeline network. This solves the technical problem of one-sided and low-accuracy risk status prediction for oil and gas pipeline networks in the prior art. It improves the accuracy of risk prediction. Through dynamic adjustment of an intelligent model, the real-time and adaptability of the prediction results are enhanced, effectively preventing pipeline network failures and reducing false positives and missed positives. This enhances the risk prediction capabilities for complex operating conditions and emergencies.

[0132] Optionally, the identification module 420 is specifically configured to:

[0133] If the operating data are not within the standard operating data range, generating a problem indicator for the operating data;

[0134] If the operating data are all within the standard operating data range, generating a non-problem mark for the operating data;

[0135] If at least one of the operating data is within the standard operating data range and at least one of the operating data is not within the standard operating data range, a suspected problem identifier is generated for the operating data.

[0136] Optionally, the identification module 420 is further configured to:

[0137] If the initial detection identifier of the operating data is the suspected problem identifier, the operating data not greater than the left boundary value of the standard operating data range is divided into a first data group, and the operating data not less than the right boundary value of the standard operating data range is divided into a second data group;

[0138] determining a first suspected problem factor based on the first data group and the second data group;

[0139] Normalizing the operation data and performing curve fitting to obtain an oil and gas pipeline network operation curve, and determining a second suspected problem factor based on a variance of the oil and gas pipeline network operation curve and the oil and gas pipeline network operation curve;

[0140] determining a comprehensive problem factor of the operation data based on the first suspected problem factor and the second suspected problem factor;

[0141] If the comprehensive problem factor is greater than the factor threshold, a problem indicator is generated for the operation data.

[0142] Optionally, the prediction module 440 is specifically configured to:

[0143] Obtain historical operation data from the preset historical fault database;

[0144] The target oil and gas pipeline network is subjected to risk identification based on the historical operation data and the risk operation data to determine the final risk prediction value.

[0145] Optionally, the prediction module 440 is further configured to:

[0146] If there is no historical operation data whose similarity to the risk operation data is greater than the similarity threshold, performing risk prediction on the risk operation data using a pre-trained deep neural network model to determine a first risk prediction value;

[0147] identifying risk additional data in the risky operation data based on the historical operation data;

[0148] Performing risk prediction based on the risk operation data, the risk additional data, and the historical operation data through a Bayesian network to obtain a second risk prediction value;

[0149] The final risk prediction value is determined based on the first risk prediction value and the second risk prediction value.

[0150] Optionally, the prediction module 440 is further configured to:

[0151] Obtaining a risk prediction value difference based on the first risk prediction value and the second risk prediction value;

[0152] When the risk prediction value difference is less than a first percentage of the first risk prediction value and less than a first percentage of the second risk prediction value, determining a risk prediction mean according to the first risk prediction value and the second risk prediction value, and determining the risk prediction mean as the final risk prediction value;

[0153] In the case where the risk prediction value difference is not less than the first percentage of the first risk prediction value, or is not less than the first percentage of the second risk prediction value, if the first risk prediction value is greater than the second risk prediction value, determining a reduction coefficient based on the risk prediction value difference; adjusting the first risk prediction value based on the reduction coefficient to determine the final risk prediction value;

[0154] When the risk prediction value difference is not less than the first percentage of the first risk prediction value, or not less than the first percentage of the second risk prediction value, if the first risk prediction value is less than the second risk prediction value, an increase coefficient is determined based on the risk prediction value difference; the first risk prediction value is adjusted based on the increase coefficient to determine the final risk prediction value.

[0155] Optionally, the prediction module 440 is further configured to:

[0156] If there is a historical operation data whose similarity to the risk operation data is greater than a similarity threshold, the historical final risk prediction value corresponding to the historical operation data with the highest similarity is determined as the final risk prediction value.

[0157] The global risk situation prediction device for the oil and gas pipeline network provided in the embodiment of the present invention can execute the global risk situation prediction method for the oil and gas pipeline network provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0158] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0159] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0160] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0161] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any other suitable processors, controllers, microcontrollers, etc. Processor 11 executes the various methods and processes described above, such as the method for predicting the global risk situation of an oil and gas pipeline network.

[0162] In some embodiments, the method for predicting the global risk situation of an oil and gas pipeline network may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting the global risk situation of an oil and gas pipeline network described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for predicting the global risk situation of an oil and gas pipeline network in any other appropriate manner (for example, by means of firmware).

[0163] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0164] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0165] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0166] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0167] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0168] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0169] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0170] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for predicting the global risk situation of an oil and gas pipeline network, characterized in that: include: Collecting data from a target oil and gas pipeline network based on a preset collection period to determine at least one operating data of the target oil and gas pipeline network; Obtaining a standard operating data range corresponding to the operating data, identifying the operating data based on the standard operating data range, and determining an initial detection identifier for the operating data; If the initial detection identification of the operation data is a problem identification, determining the operation data as risky operation data; Risk identification is performed on the target oil and gas pipeline network based on the risk operation data to determine a final risk prediction value of the target oil and gas pipeline network.

2. The method according to claim 1, characterized in that The identifying the operating data based on the standard operating data range and determining the initial detection identifier of the operating data includes: If the operating data are not within the standard operating data range, generating a problem indicator for the operating data; If the operating data are all within the standard operating data range, generating a non-problem mark for the operating data; If at least one of the operating data is within the standard operating data range and at least one of the operating data is not within the standard operating data range, a suspected problem identifier is generated for the operating data.

3. The method according to claim 1, characterized in that If the initial detection identifier of the operation data is the problem identifier, before determining the operation data as risky operation data, the method further includes: If the initial detection mark of the operating data is a suspected problem mark, the operating data not greater than the left boundary value of the standard operating data range is divided into a first data group, and the operating data not less than the right boundary value of the standard operating data range is divided into a second data group; determining a first suspected problem factor based on the first data group and the second data group; Normalizing the operation data and performing curve fitting to obtain an oil and gas pipeline network operation curve, and determining a second suspected problem factor based on a variance of the oil and gas pipeline network operation curve and the oil and gas pipeline network operation curve; determining a comprehensive problem factor of the operation data based on the first suspected problem factor and the second suspected problem factor; If the comprehensive problem factor is greater than the factor threshold, a problem indicator is generated for the operation data.

4. The method according to claim 1, wherein The step of performing risk identification on the target oil and gas pipeline network according to the risk operation data and determining a final risk prediction value of the target oil and gas pipeline network includes: Obtain historical operation data from the preset historical fault database; The target oil and gas pipeline network is subjected to risk identification based on the historical operation data and the risk operation data to determine the final risk prediction value.

5. The method according to claim 4, characterized in that The step of performing risk identification on the target oil and gas pipeline network based on the historical operation data and the risk operation data to determine the final risk prediction value includes: If there is no historical operation data whose similarity to the risk operation data is greater than the similarity threshold, performing risk prediction on the risk operation data using a pre-trained deep neural network model to determine a first risk prediction value; identifying risk additional data in the risky operation data based on the historical operation data; Performing risk prediction based on the risk operation data, the risk additional data, and the historical operation data through a Bayesian network to obtain a second risk prediction value; The final risk prediction value is determined based on the first risk prediction value and the second risk prediction value.

6. The method according to claim 5, characterized in that The determining the final risk prediction value based on the first risk prediction value and the second risk prediction value includes: Obtaining a risk prediction value difference based on the first risk prediction value and the second risk prediction value; When the risk prediction value difference is less than a first percentage of the first risk prediction value and less than a first percentage of the second risk prediction value, determining a risk prediction mean according to the first risk prediction value and the second risk prediction value, and determining the risk prediction mean as the final risk prediction value; In the case where the risk prediction value difference is not less than the first percentage of the first risk prediction value, or is not less than the first percentage of the second risk prediction value, if the first risk prediction value is greater than the second risk prediction value, determining a reduction coefficient based on the risk prediction value difference; adjusting the first risk prediction value based on the reduction coefficient to determine the final risk prediction value; When the risk prediction value difference is not less than the first percentage of the first risk prediction value, or not less than the first percentage of the second risk prediction value, if the first risk prediction value is less than the second risk prediction value, an increase coefficient is determined based on the risk prediction value difference; the first risk prediction value is adjusted based on the increase coefficient to determine the final risk prediction value.

7. The method according to claim 4, characterized in that The performing risk identification on the target oil and gas pipeline network based on the historical operation data and the risk operation data to determine the final risk prediction value further includes: If there is a historical operation data whose similarity to the risk operation data is greater than a similarity threshold, the historical final risk prediction value corresponding to the historical operation data with the highest similarity is determined as the final risk prediction value.

8. A device for predicting the global risk situation of an oil and gas pipeline network, characterized in that: include: an acquisition module, configured to acquire data from a target oil and gas pipeline network based on a preset acquisition cycle, and determine at least one operating data of the target oil and gas pipeline network; an identification module, configured to obtain a standard operating data range corresponding to the operating data, identify the operating data based on the standard operating data range, and determine an initial detection identifier for the operating data; a judgment module, configured to determine the operation data as risky operation data if the initial detection identifier of the operation data is a problem identifier; The prediction module is used to identify the risk of the target oil and gas pipeline network according to the risk operation data and determine the final risk prediction value of the target oil and gas pipeline network.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the oil and gas pipeline network global risk situation prediction method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the oil and gas pipeline network global risk situation prediction method according to any one of claims 1 to 7 when executed.

Images