A natural gas transmission pipeline pressure safety intelligent control method and system

Abstract

The present application relates to the technical field of pipeline control, in particular to a natural gas external transmission pipeline pressure safety intelligent control method and system, first, according to the characteristics that pressure abnormality usually appears as abnormal timing fluctuation, the abnormality degree of pressure is preliminarily determined and the abnormal time of the pressure of each monitoring node is screened out, after the similar nodes of each monitoring node are screened out according to the similar situation of flow velocity characteristics, according to the characteristics that similar nodes will show similar pressure performance under normal conditions, the abnormality degree deviation analysis between each monitoring node and each similar node is carried out, so that the abnormal node is more accurately screened out, finally, according to the distribution of the abnormality degree of natural gas shown by the node on the whole pipeline, the overall abnormality of natural gas is more accurately determined, so that the effect of natural gas pipeline control according to the overall abnormality of natural gas is better.

Description

Technical Field

[0001] This invention relates to the field of pipeline control technology, specifically to an intelligent control method and system for pressure safety of natural gas export pipelines. Background Technology

[0002] In the operation and management of natural gas transmission pipelines, pressure safety control is a core element in ensuring the safe and stable operation of the pipeline. Current technologies primarily analyze pressure data based on the magnitude of changes over time, identifying pressure anomalies and implementing pipeline control measures when pressure changes exceed a threshold. However, these methods only reflect localized pressure anomalies and cannot account for anomalies across the entire natural gas transmission pipeline. Furthermore, analyzing solely based on the magnitude of pressure changes has significant limitations, failing to accurately quantify anomalies within the pipeline, resulting in poor effectiveness of current technologies for natural gas pipeline control. Summary of the Invention

[0003] To address the technical problem of poor control performance of existing technologies for natural gas pipelines, the purpose of this application is to provide an intelligent pressure safety control method and system for natural gas export pipelines. The specific technical solution adopted is as follows:

[0004] The first aspect of this application provides a method for intelligent pressure safety control of natural gas transmission pipelines, including:

[0005] Pressure and flow rate data are collected for each monitoring node in the natural gas transmission pipeline at each sampling time. Based on the pressure fluctuations within the temporal neighborhood of each monitoring node at each sampling time, the corresponding degree of pressure anomaly is determined. Based on the degree of pressure anomaly, the time of pressure anomaly for each monitoring node is selected.

[0006] Based on the similarity of the temporal distribution of flow velocity data between each monitoring node and every other monitoring node, the corresponding flow velocity similarity is determined; similar nodes for each monitoring node are then selected based on the flow velocity similarity.

[0007] Based on the deviations in the distribution of pressure anomalies and the number of pressure anomaly moments between each monitoring node and its corresponding similar nodes, the abnormal monitoring differences of each monitoring node are determined; and abnormal nodes are selected based on these abnormal monitoring differences.

[0008] Based on the differences in abnormal monitoring of each abnormal node and the upward trend of the corresponding pressure abnormality at the time of pressure abnormality, the corresponding natural gas abnormality degree is determined; based on the continuous distribution of abnormal nodes on the natural gas export pipeline and the overall magnitude of the corresponding natural gas abnormality degree, the overall natural gas abnormality is determined; and fuzzy control is performed on the natural gas pipeline based on the overall natural gas abnormality.

[0009] Furthermore, the process of obtaining the degree of pressure anomaly includes:

[0010] Use all sampling times within a preset time neighborhood for each sampling time as the corresponding reference time;

[0011] The local pressure fluctuation level is determined based on the variance of the pressure data at all reference times corresponding to each sampling time for each monitoring node; the comparative pressure fluctuation level is determined based on the mean of the local pressure fluctuation levels at all reference times corresponding to each sampling time.

[0012] The difference between the local pressure fluctuation level of each monitoring node at each sampling time and the comparative pressure fluctuation level is normalized to determine the corresponding time-series fluctuation anomaly level; the pressure anomaly level at each sampling time is determined based on the mean between the normalized value of the local pressure fluctuation level of each monitoring node at each sampling time and the time-series fluctuation anomaly level.

[0013] Furthermore, the process of obtaining the moment of pressure anomaly includes:

[0014] At each monitoring node, the sampling time corresponding to the pressure anomaly level exceeding the preset pressure anomaly threshold is taken as the pressure anomaly time for each monitoring node.

[0015] Furthermore, the process of obtaining the flow velocity similarity includes:

[0016] After arranging the flow velocity data of each monitoring node at all sampling times in chronological order, the corresponding time-series flow velocity data sequence is determined.

[0017] Each monitoring node is taken as the target node in turn; other monitoring nodes outside the target nodes are taken as the corresponding reference nodes; the Pearson correlation coefficient between the time series flow velocity data sequence of the target node and the time series flow velocity data sequence of each reference node is positively correlated to determine the corresponding flow velocity similarity trend factor.

[0018] At each sampling time, the instantaneous flow velocity difference of each reference node is determined based on the difference between the flow velocity data of the target node and the flow velocity data of each reference node; the mean of the instantaneous flow velocity difference of each reference node at all sampling times is negatively correlated to determine the consistency of the corresponding flow velocity data.

[0019] The product between the velocity similarity trend factor and the velocity data consistency is normalized to determine the velocity similarity between the target node and each reference node.

[0020] Furthermore, the process of filtering out similar nodes for each monitoring node based on the flow velocity similarity includes:

[0021] Reference nodes with flow velocity similarity greater than a preset similarity threshold are used as similar nodes to the target node.

[0022] Furthermore, the process of obtaining the anomaly monitoring differences includes:

[0023] All pressure anomaly time periods for each monitoring node are obtained; all sampling times within the pressure anomaly time periods are pressure anomaly times, all pressure anomaly times are distributed continuously in time sequence, and neither the preceding nor following sampling time of the pressure anomaly time period is a pressure anomaly time; based on the cumulative value of the pressure anomaly degree of all pressure anomaly times for each monitoring node, the corresponding pressure anomaly characteristic value is determined.

[0024] The difference between the number of abnormal pressure time periods at each monitoring node and the number of abnormal pressure time periods at each corresponding similar node is normalized to determine the corresponding abnormality; the difference between the abnormal pressure feature value at each monitoring node and the abnormal pressure feature value at each corresponding similar node is normalized to determine the corresponding abnormality.

[0025] The reference difference between each monitoring node and each similar node is determined by multiplying the difference in the number of anomalies and the difference in the pressure anomalies; the anomaly monitoring difference of each monitoring node is determined by the mean of the reference differences between each monitoring node and all similar nodes.

[0026] Furthermore, the process of filtering out abnormal nodes based on the anomaly monitoring differences includes:

[0027] Monitoring nodes that exhibit abnormal monitoring differences exceeding a preset monitoring threshold are designated as abnormal nodes.

[0028] Furthermore, the process of obtaining the degree of natural gas anomaly includes:

[0029] Based on the average pressure anomaly severity at all pressure anomaly times within each pressure anomaly time period of each anomaly node, a corresponding reference anomaly severity is determined. The reference anomaly severity at each pressure anomaly time period is then arranged chronologically and subjected to curve fitting to determine the time-series curve of the reference anomaly severity for each anomaly node. The normalized value of the slope of the tangent line corresponding to the time-series curve of the reference anomaly severity for each pressure anomaly time period is used as the corresponding anomaly rise characteristic value. Based on the average of the anomaly rise characteristic values ​​for all pressure anomaly time periods of each anomaly node, the corresponding trend anomaly characteristic value is determined.

[0030] The degree of natural gas anomaly at each anomaly node is determined by multiplying the anomaly monitoring difference of each anomaly node with the trend anomaly characteristic value.

[0031] Furthermore, the process of obtaining the overall anomaly of the natural gas includes:

[0032] All abnormal monitoring sections in the natural gas export pipeline are acquired; wherein, all monitoring nodes in each abnormal monitoring section are abnormal nodes, the abnormal nodes are continuously distributed in the natural gas export pipeline, and the preceding and following monitoring nodes of the abnormal monitoring section are not abnormal nodes.

[0033] The corresponding local anomaly level is determined based on the average of the natural gas anomaly levels of all anomaly nodes in each anomaly monitoring segment.

[0034] The corresponding local anomaly of natural gas is determined by multiplying the number of all abnormal nodes in each anomaly monitoring segment with the degree of local anomaly.

[0035] The cumulative values ​​of local anomalies of natural gas in all abnormal monitoring sections of the natural gas transmission pipeline are normalized to determine the overall anomaly of natural gas.

[0036] Secondly, this application provides an intelligent control system for the pressure safety of natural gas export pipelines, the system comprising:

[0037] The data acquisition and preprocessing module is used to acquire pressure and flow rate data of each monitoring node in the natural gas transmission pipeline at each sampling time; determine the corresponding pressure anomaly degree based on the pressure fluctuation within the time-series neighborhood of each monitoring node at each sampling time; and filter out the pressure anomaly times of each monitoring node based on the pressure anomaly degree.

[0038] The similar node filtering module is used to determine the corresponding flow velocity similarity based on the similarity of the time-series distribution of flow velocity data between each monitoring node and each other monitoring node; and to filter out similar nodes for each monitoring node based on the flow velocity similarity.

[0039] The abnormal node screening module is used to determine the abnormal monitoring differences of each monitoring node based on the deviation of the distribution of the degree of pressure anomaly between each monitoring node and its corresponding similar nodes, as well as the deviation of the number of pressure anomaly times; and to screen out abnormal nodes based on the abnormal monitoring differences.

[0040] The natural gas pipeline control module is used to determine the corresponding natural gas anomaly degree based on the anomaly monitoring differences of each abnormal node and the upward trend of the corresponding pressure anomaly degree at the time of pressure anomaly; to determine the overall natural gas anomaly based on the continuous distribution of abnormal nodes on the natural gas export pipeline and the overall magnitude of the corresponding natural gas anomaly degree; and to perform fuzzy control on the natural gas pipeline based on the overall natural gas anomaly.

[0041] Thirdly, this application provides a computer device including a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to perform the method as described in the first aspect of this application or any embodiment of the first aspect.

[0042] Fourthly, this application provides a computer program product comprising computer program code, which, when executed, performs the method as described in the first aspect of this application or any embodiment thereof.

[0043] Fifthly, this application provides a computer-readable storage medium that stores computer program code, which, when executed, performs the method as described in the first aspect of this application or any embodiment thereof.

[0044] This application has the following beneficial effects:

[0045] This application first determines the degree of pressure anomaly and identifies the pressure anomaly moments at each monitoring node based on the characteristic that abnormal pressure usually manifests as abnormal temporal fluctuations. After identifying similar nodes for each monitoring node based on similar flow velocity characteristics, it performs a pressure anomaly degree deviation analysis between each monitoring node and each similar node, based on the characteristic that similar nodes exhibit similar pressure performance under normal conditions, thereby more accurately identifying abnormal nodes. Finally, based on the distribution of natural gas anomaly degree exhibited by the nodes across the entire pipeline, a more accurate overall natural gas anomaly is determined, resulting in better control of the natural gas pipeline based on the overall natural gas anomaly. Attached Figure Description

[0046] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1This is a flowchart of a method for intelligent pressure safety control of natural gas export pipelines according to an embodiment of the present invention;

[0048] Figure 2 This is a structural diagram of a natural gas export pipeline pressure safety intelligent control system provided in one embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of a computer device structure provided in one embodiment of the present invention. Detailed Implementation

[0050] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a natural gas export pipeline pressure safety intelligent control method and system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0052] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent pressure safety control method and system for natural gas export pipelines provided by this invention.

[0053] This application provides an intelligent pressure safety control method for natural gas export pipelines. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of an intelligent pressure safety control method for natural gas export pipelines according to an embodiment of the present invention. The method includes:

[0054] Step S101: Collect pressure and flow rate data of each monitoring node in the natural gas transmission pipeline at each sampling time; determine the corresponding pressure anomaly degree based on the pressure fluctuation in the time-series neighborhood of each monitoring node at each sampling time; and filter out the pressure anomaly time of each monitoring node based on the pressure anomaly degree.

[0055] In one specific implementation of this invention, each pump station and valve area of ​​the natural gas export pipeline is used as a monitoring node, and a pressure sensor and a flow velocity sensor are installed at each monitoring node. The pressure sensor collects pressure data of each monitoring node in the natural gas export pipeline at each sampling time; the flow velocity sensor collects flow velocity data of each monitoring node in the natural gas export pipeline at each sampling time; the sampling frequency is set to once per second; the sampling time period is set to the day prior to the current time, which can be adjusted according to the specific implementation environment, and will not be further elaborated here.

[0056] First, when pressure is abnormal, the pressure data will exhibit abnormal and disordered fluctuations in time series. For each sampling time, the more drastic the pressure data fluctuations in its neighborhood, the greater the degree of fluctuation compared to other sampling times, and the more abnormal the corresponding pressure fluctuations. Therefore, this application determines the corresponding degree of pressure anomaly based on the pressure fluctuations in the time series neighborhood of each sampling time of each monitoring node.

[0057] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the degree of pressure anomaly includes:

[0058] All sampling times within a preset time neighborhood for each sampling time are used as corresponding reference times. The local pressure fluctuation level is determined based on the variance of the pressure data at all reference times corresponding to each monitoring node at each sampling time. Variance characterizes the discreteness of a set of data. For each sampling time of each monitoring node, the larger the variance of the pressure data within its preset time neighborhood, the more discrete the pressure data is within the time neighborhood of the corresponding sampling time, the more significant the fluctuation characteristics, and the greater the degree of pressure anomaly. In a specific implementation of this invention, the preset time neighborhood is set to the time range corresponding to the 20 closest sampling times for each sampling time. This can be adjusted according to the specific implementation environment and will not be further elaborated here.

[0059] The corresponding comparative pressure fluctuation level is determined by the average of the local pressure fluctuation levels at all reference times corresponding to each sampling time. The difference between the local pressure fluctuation level and the comparative pressure fluctuation level at each monitoring node at each sampling time is normalized to determine the corresponding time-series fluctuation anomaly level. For each sampling time, the larger the corresponding local pressure fluctuation level is compared to the overall local pressure fluctuation levels at all reference times within the time-series neighborhood, the more significant the pressure fluctuation at that sampling time is, and the less it conforms to the overall pressure fluctuation characteristics within its time-series neighborhood. Therefore, the probability of a pressure anomaly at that sampling time is higher. Therefore, based on the correlation, the pressure anomaly level at each sampling time is further determined by the average of the normalized value of the local pressure fluctuation level at each monitoring node at each sampling time and the time-series fluctuation anomaly level. In another specific implementation of this invention, the product of the normalized value of the local pressure fluctuation level at each monitoring node at each sampling time and the time-series fluctuation anomaly level is normalized to determine the pressure anomaly level at each sampling time. Implementers can adjust this according to the specific implementation environment, and further details are omitted here. It should be noted that, unless otherwise specified, the normalization method in the embodiments of the present invention is linear normalization, which will not be elaborated further here.

[0060] In one specific implementation of this invention, the process of obtaining the degree of pressure anomaly is expressed by a formula: ;in, For monitoring nodes In the The degree of pressure anomaly at each sampling time; For monitoring nodes In the The variance of the pressure data at all reference times corresponding to a sampling time, that is, the degree of local pressure fluctuation. For monitoring nodes In the The average of the local pressure fluctuations at all reference times corresponding to each sampling time, that is, the comparison of pressure fluctuations. It is a linear normalization function; For monitoring nodes In the The degree of temporal fluctuation anomaly corresponding to each sampling time.

[0061] Further, the pressure anomaly time is initially screened based on the degree of pressure anomaly. Preferably, in some possible implementations of this invention, the process of obtaining the pressure anomaly time includes: at each monitoring node, the sampling time corresponding to the pressure anomaly degree greater than a preset pressure anomaly threshold is taken as the pressure anomaly time of each monitoring node. In a specific implementation of this invention, the preset pressure anomaly threshold is set to 0.4, which can be adjusted according to the specific implementation environment, and will not be further elaborated here.

[0062] Step S102: Determine the corresponding flow velocity similarity based on the similarity of the flow velocity data time series distribution between each monitoring node and each other monitoring node; filter out similar nodes for each monitoring node based on the flow velocity similarity.

[0063] Hydrogen sulfide (H2S) and carbon dioxide (CO2) in natural gas are highly corrosive. They react with pipeline metal to form sulfides, leading to metal corrosion. The oxides or other corrosion products produced by corrosion may accumulate inside the pipeline, forming a sticky layer. All of these can cause abnormal pipeline pressure. If the sensor is in an abnormal area, the pressure measured does not reflect the true pressure of the entire pipeline. Therefore, after determining the time of pressure abnormality, further analysis of natural gas pipeline anomalies is required.

[0064] Under normal circumstances, monitoring nodes in similar flow regions should typically exhibit similar pressure characteristics. If a monitoring node shows a significant pressure deviation compared to other monitoring nodes in a similar flow region, it indicates a potential anomaly in the pipeline area where that monitoring node is located, and this anomaly reflects the overall true pressure anomaly in the pipeline. Therefore, based on this characteristic, similar nodes in similar flow regions corresponding to each monitoring node can be selected. By comparing the pressure deviations between each monitoring node and its similar nodes, a more accurate selection of monitoring nodes exhibiting pressure anomalies can be made. Before this, similar nodes for each monitoring node need to be selected based on the characteristics of similar flow regions. Similar flow regions exhibit similar gas velocities; therefore, in this embodiment of the invention, the velocity similarity is determined based on the similarity of the temporal distribution of velocity data between each monitoring node and every other monitoring node.

[0065] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining flow velocity similarity includes:

[0066] After arranging the flow velocity data of each monitoring node in chronological order at all sampling times, the corresponding time-series flow velocity data sequence is determined. Each monitoring node is then designated as the target node. Other monitoring nodes besides the target nodes are designated as the corresponding reference nodes. The Pearson correlation coefficients between the time-series flow velocity data sequences of the target nodes and the time-series flow velocity data sequences of each reference node are positively correlated to determine the corresponding flow velocity similarity trend factor.

[0067] In one specific implementation of this invention, the mean of the Pearson correlation coefficient between the time-series velocity data sequence of the target node and the time-series velocity data sequence of each reference node, and the real number 1, is used as the corresponding velocity similarity trend factor. This method performs positive correlation mapping, limiting the value range of the velocity similarity trend factor to between 0 and 1, thus avoiding the impact of negative values ​​on subsequent analysis. According to the definition of the Pearson correlation coefficient, the larger the obtained velocity similarity trend factor, the closer the temporal values ​​of the velocity data between the target node and the corresponding reference node are to each other; that is, the more similar the flow regime, the greater the corresponding velocity similarity should be.

[0068] The velocity similarity trend factor only analyzes velocity similarity from the overall trend of velocity data over time. Therefore, further analysis is needed at the level of detail, comparing the specific magnitudes of velocity data at each sampling time to more accurately quantify velocity similarity. In this embodiment of the invention, at each sampling time, the instantaneous velocity difference of each reference node is determined based on the difference between the velocity data of the target node and the velocity data of each reference node. The mean of the instantaneous velocity differences of each reference node at all sampling times is negatively correlated to determine the corresponding velocity data consistency. For both the target node and the reference node, the smaller the overall difference in velocity data at each sampling time, the higher the temporal consistency in the numerical magnitude of the velocity data between the two nodes, the higher the corresponding velocity similarity, and the more likely they are to be in the same flow regime region.

[0069] Furthermore, based on the correlation, the product between the velocity similarity trend factor and the velocity data consistency is normalized to determine the velocity similarity between the target node and each reference node. This ensures that the greater the velocity similarity, the more likely the corresponding reference node and the target node are to be in the same flow regime region, meaning the reference node is more likely to be a similar node to the target node.

[0070] In some possible implementations of this invention, the process of obtaining flow velocity similarity is expressed by the following formula: ;in, For the target node With the corresponding first Flow velocity similarity between reference nodes; For the target node With the corresponding first Flow velocity similarity trend factor between reference nodes; This represents the number of sampling times. For the target node In the Flow velocity data at each sampling time; For the target node The corresponding number The reference node at the _th ... Flow velocity data at each sampling time; It is the absolute value symbol; For the target node The corresponding number The reference node at the _th ... The instantaneous flow velocity difference at each sampling time; For the target node With the corresponding first Consistency of flow rate data among reference nodes.

[0071] Furthermore, similar nodes for each monitoring node can be selected based on flow velocity similarity. Specifically, reference nodes with flow velocity similarity greater than a preset similarity threshold are used as similar nodes to the target node. In one specific implementation of this invention, the preset similarity threshold is set to 0.8, which can be adjusted according to the specific implementation environment.

[0072] Step S103: Determine the abnormal monitoring difference of each monitoring node based on the deviation of the pressure anomaly degree distribution and the deviation of the number of pressure anomaly times between each monitoring node and its corresponding similar nodes; screen out abnormal nodes based on the abnormal monitoring difference.

[0073] After identifying similar nodes in similar flow regions corresponding to each monitoring node, further analysis can be conducted based on the characteristic that monitoring nodes in similar flow regions should typically exhibit similar pressure performance under normal circumstances. By analyzing the deviations in pressure performance between each monitoring node and its similar nodes, abnormal nodes exhibiting significant pressure performance deviations from their similar nodes can be screened out. The degree of pressure anomaly characterizes the pressure anomaly performance of each monitoring node at various sampling times. Therefore, for a monitoring node, the greater the relative deviation in the distribution of pressure anomaly degree between it and its similar nodes, the more likely that the monitoring node has experienced a genuine anomaly. Thus, this embodiment of the invention further determines the anomaly monitoring difference of each monitoring node based on the deviation in the distribution of pressure anomaly degree between each monitoring node and its corresponding similar nodes, as well as the deviation in the number of pressure anomaly times. The greater the anomaly monitoring difference, the more significant the pressure anomaly performance of the corresponding monitoring node is compared to other similar nodes, and the higher the probability that it is a genuine anomaly node.

[0074] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the anomaly monitoring difference includes:

[0075] All pressure anomaly time periods are acquired for each monitoring node. All sampling moments within a pressure anomaly time period are considered pressure anomalies, and these anomalies are distributed continuously in time. Neither the preceding nor following sampling moment of a pressure anomaly time period is considered a pressure anomaly. The corresponding pressure anomaly characteristic value is determined by summing the pressure anomaly severity of all pressure anomalies at each monitoring node. Pressure anomaly time periods are the time periods formed by merging adjacent pressure anomalies. For each pressure anomaly time period, a larger pressure anomaly characteristic value indicates a more abnormal pressure performance within that time period.

[0076] Since the pressure performance of monitoring nodes in similar flow regions is generally similar under normal circumstances, if the number of abnormal pressure time periods and the magnitude of the abnormal pressure are more similar between each monitoring node and other similar nodes, it indicates that the pressure abnormality of the corresponding monitoring node is specific to the flow region and does not reflect the true pressure abnormality of the entire pipeline. Conversely, if the number of abnormal pressure time periods and the magnitude of the abnormal pressure are less similar between each monitoring node and other similar nodes, it indicates that the corresponding monitoring node does not conform to the pressure performance of the flow region, and the magnitude of the abnormal pressure it reflects is more likely to be a true overall pipeline pressure abnormality, and the higher the probability that it is a real abnormal node.

[0077] Therefore, the difference between the number of abnormal pressure time periods at each monitoring node and the number of abnormal pressure time periods at each corresponding similar node is further normalized to determine the corresponding abnormality difference; the difference between the pressure abnormality feature value at each monitoring node and the pressure abnormality feature value at each corresponding similar node is normalized to determine the corresponding pressure abnormality difference.

[0078] Considering that pressure performance is generally similar across similar flow regions under normal conditions, the more similar the distribution of abnormal pressure time periods between a monitoring node and each similar node, and the more similar the overall magnitude of the abnormal pressure characteristic values ​​across these time periods, the more consistent the pressure performance is with the normal flow regions. In this case, the abnormal pressure performance of the monitoring node will not reflect the true pressure of the entire pipeline, but rather the pressure characteristics of the corresponding similar flow region. Therefore, for each monitoring node, the smaller the difference in the number of anomalies between it and each similar node, the more similar the distribution of abnormal pressure time periods is in terms of quantity, and the more likely the abnormal pressure is to belong to the pressure anomaly of the corresponding similar flow region. Similarly, the smaller the difference in pressure anomalies, the more similar the overall magnitude of the abnormal pressure characteristic values ​​across these time periods is, and the more consistent it is with the pressure anomaly of the similar flow region. In other words, with the reference of the corresponding similar nodes, the monitoring node is less likely to be an abnormal node that truly reflects the overall pressure anomaly in the pipeline.

[0079] Furthermore, the differences in the quantity and pressure of anomalies are combined. Based on the product of these differences, a reference difference is determined between each monitoring node and each similar node. Then, a comparative analysis is performed with all similar nodes. Based on the mean of the reference differences between each monitoring node and all similar nodes, the anomaly monitoring difference of each monitoring node is determined. The smaller the anomaly monitoring difference, the more the corresponding monitoring node matches the abnormal pressure characteristics of the similar flow region to other similar nodes, and the lower the probability that it is an anomaly node. Conversely, the larger the anomaly monitoring difference, the less likely the corresponding monitoring node is to exhibit pressure anomalies characteristic of the similar flow region, and the higher the probability that it is an anomaly node. Moreover, the larger the anomaly monitoring difference, the more abnormal the actual pressure of the pipeline it reflects.

[0080] In one specific implementation of this invention, the process of obtaining anomaly detection differences is expressed by the following formula: ;in, For monitoring nodes Differences in anomaly monitoring; For monitoring nodes The number of similar nodes; For monitoring nodes The cumulative value of the degree of pressure abnormality at all times of pressure abnormality, which is also the corresponding pressure abnormality characteristic value; For monitoring nodes The corresponding number Anomaly characteristics of pressure at similar nodes; For monitoring nodes The number of periods of abnormal stress; For monitoring nodes The corresponding number The number of time periods with abnormal pressure on similar nodes; For monitoring nodes With the corresponding first Anomaly in pressure differences between similar nodes; For monitoring nodes With the corresponding first The difference in the number of anomalies between similar nodes; For monitoring nodes With the corresponding first Reference differences between similar nodes.

[0081] For each monitoring node, the greater the abnormal monitoring difference, the higher the probability that it is an abnormal node, and the more abnormal the actual pressure of the pipeline it reflects. Therefore, abnormal nodes with abnormal pressure performance can be screened out by setting a threshold. Preferably, in some possible implementations of the embodiments of the present invention, the process of screening out abnormal nodes based on abnormal monitoring differences includes: taking the monitoring nodes with abnormal monitoring differences greater than a preset monitoring threshold as abnormal nodes. In a specific implementation of the embodiments of the present invention, the preset monitoring threshold is set to 0.7, which can be adjusted according to the specific implementation environment, and will not be elaborated further here. It should be noted that for monitoring nodes with zero similar nodes, since it is impossible to calculate the abnormal monitoring differences, monitoring nodes with zero similar nodes and abnormal pressure moments are analyzed as abnormal nodes to ensure the completeness of the embodiments, and will not be elaborated further here.

[0082] Step S104: Determine the corresponding natural gas anomaly degree based on the anomaly monitoring differences of each abnormal node and the upward trend of the corresponding pressure anomaly degree at the time of pressure anomaly; determine the overall natural gas anomaly based on the continuous distribution of abnormal nodes on the natural gas export pipeline and the overall magnitude of the corresponding natural gas anomaly degree; perform fuzzy control on the natural gas pipeline based on the overall natural gas anomaly.

[0083] As shown in step S103, the anomaly monitoring discrepancies not only reflect the probability that the corresponding monitoring node is an anomaly node, but also reflect the actual anomaly in the pipeline pressure. Therefore, for each anomaly node, the greater the anomaly monitoring discrepancy, the more abnormal the pipeline pressure it reflects, i.e., the greater the degree of natural gas anomaly. For each anomaly node, if the degree of pressure anomaly increases over time, it indicates that the anomaly at that node is becoming increasingly serious, thus requiring greater attention to the anomaly. Therefore, the anomaly monitoring discrepancy of that node should be given greater weight to make the determined degree of natural gas anomaly more accurate. Therefore, further, based on the anomaly monitoring discrepancies of each anomaly node and the upward trend of the corresponding pressure anomaly at the time of pressure anomaly, the corresponding degree of natural gas anomaly is determined, ensuring that the degree of natural gas anomaly reflects the pipeline natural gas anomaly at each anomaly node location.

[0084] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the degree of natural gas anomaly includes:

[0085] Based on the average pressure anomaly severity at all pressure anomaly times within each pressure anomaly time period of each anomaly node, a corresponding reference anomaly severity is determined. The reference anomaly severity at each anomaly node is then arranged chronologically and subjected to curve fitting to determine a time-series curve for the reference anomaly severity at each anomaly node. The normalized value of the tangent slope corresponding to the time-series curve of the reference anomaly severity at each pressure anomaly time period is used as the corresponding anomaly rise characteristic value. Finally, based on the average of the anomaly rise characteristic values ​​at all pressure anomaly time periods of each anomaly node, a corresponding trend anomaly characteristic value is determined.

[0086] The larger the normalized value of the tangent slope, that is, the larger the abnormal upward characteristic value, the more obvious the upward trend of the pressure anomaly at the time sequence position of the corresponding abnormal pressure period, and the more serious the abnormality of pipeline natural gas. Therefore, for each abnormal node, if the difference in its abnormal monitoring is greater and the trend abnormal characteristic value representing the abnormal upward trend is more obvious, it indicates that the pipeline natural gas transmission anomaly at that abnormal node is more serious. So, the degree of natural gas anomaly at each abnormal node is determined by the product of the difference in abnormal monitoring and the trend abnormal characteristic value.

[0087] Anomalies only represent the location of abnormal pipeline pressure at a local point in the pipeline. For natural gas export pipelines, if anomalies are concentrated in a specific area, it indicates that the pipeline problem is not an isolated accidental event, but a developing and systematic structural or functional failure problem. Its severity and risk are far greater than sporadic and scattered anomalies. Therefore, the overall anomaly of natural gas can be determined by further analyzing the continuous distribution of anomalies on natural gas export pipelines and the overall magnitude of the corresponding natural gas anomalies.

[0088] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the overall anomaly of natural gas includes:

[0089] All abnormal monitoring sections in the natural gas export pipeline are acquired; in each abnormal monitoring section, all monitoring nodes are abnormal nodes, which are continuously distributed in the natural gas export pipeline, and the preceding and following monitoring nodes of the abnormal monitoring section are not abnormal nodes; the corresponding local abnormality is determined based on the average natural gas abnormality of all abnormal nodes in each abnormal monitoring section.

[0090] First, a higher degree of local anomaly indicates a higher overall pipeline risk for each anomaly node in the corresponding monitoring segment. Furthermore, for each monitoring segment, the more anomaly nodes it contains, the more concentrated the distribution of these nodes, and the higher the pipeline risk it reflects. Therefore, for natural gas export pipelines, the greater the overall number of anomaly nodes in each monitoring segment and the higher the overall degree of natural gas anomaly, the higher the overall natural gas anomaly reflecting the overall pipeline anomaly. Therefore, the corresponding local natural gas anomaly is determined by multiplying the number of all anomaly nodes in each monitoring segment by the degree of local anomaly. Then, combining the local natural gas anomalies of each monitoring segment, the cumulative value of the local natural gas anomalies of all monitoring segments in the natural gas export pipeline is normalized to determine the overall natural gas anomaly. A higher overall natural gas anomaly indicates a more abnormal overall pressure performance in the natural gas export pipeline, thus requiring more adjustment and control operations.

[0091] In one specific implementation of this invention, the process of obtaining the overall anomaly of natural gas is expressed by the following formula: ;in, The overall anomaly of natural gas at the current moment; This refers to the number of abnormal monitoring segments; For the first The number of abnormal nodes in each abnormal monitoring segment; For the first In the first abnormal monitoring segment Differences in anomaly monitoring among individual abnormal nodes; For the first In the first abnormal monitoring segment The mean of the abnormal rise characteristic values ​​of all time periods of abnormal pressure at each abnormal node; For the first In the first abnormal monitoring segment The degree of natural gas anomaly at each abnormal node; For the first In the first abnormal monitoring segment The degree of local anomaly of each abnormal node; For the first Local anomalies of natural gas in each monitoring segment. Since the sampling period in this embodiment of the invention is within one day prior to the current moment, the overall anomaly of natural gas calculated here pertains to the current moment.

[0092] After determining the overall anomaly of natural gas at the current moment, the final step is to control the natural gas pipeline based on this anomaly. In one specific implementation of this invention, the overall anomaly of natural gas at the current moment is used as a weighting factor for fuzzy control at that moment. The weighting factor for fuzzy control at the current moment, along with the average gas pressure data from all monitoring points on the pipeline at the current moment, is input into the fuzzy control algorithm to obtain control commands (such as reducing pressure, increasing pressure, etc.). That is, based on the fuzzy rule base and combined with the overall anomaly of natural gas in the pipeline, the pipeline control command is determined. Finally, the pressure of the natural gas export pipeline is controlled according to the pipeline control command. For example, when the control command is to reduce pressure, the pressure reducing valve is activated to adjust the pipeline pressure, thereby performing intelligent safety control of the natural gas export pipeline pressure.

[0093] In summary, a method for intelligent pressure safety control of natural gas export pipelines first determines the degree of pressure anomaly and identifies the timing of pressure anomalies at each monitoring node based on the characteristic that pressure anomalies typically manifest as abnormal temporal fluctuations. After identifying similar nodes for each monitoring node based on similar flow velocity characteristics, and considering that similar nodes exhibit similar pressure characteristics under normal conditions, a deviation analysis of the degree of pressure anomaly between each monitoring node and its similar nodes is performed to more accurately identify anomalous nodes. Finally, based on the distribution of the degree of natural gas anomaly exhibited by the nodes across the entire pipeline, a more accurate overall natural gas anomaly is determined, resulting in better control of the natural gas pipeline based on the overall natural gas anomaly.

[0094] This application also provides an intelligent control system for the pressure safety of natural gas export pipelines. Please refer to [link / reference]. Figure 2The diagram shows a structural diagram of a natural gas export pipeline pressure safety intelligent control system provided by an embodiment of the present invention. The system includes: a data acquisition and preprocessing module 201, a similar node screening module 202, an abnormal node screening module 203, and a natural gas pipeline control module 204.

[0095] The data acquisition and preprocessing module 201 is used to acquire pressure and flow rate data of each monitoring node in the natural gas transmission pipeline at each sampling time; determine the corresponding pressure anomaly degree based on the pressure fluctuation in the time-series neighborhood of each monitoring node at each sampling time; and filter out the pressure anomaly times of each monitoring node based on the pressure anomaly degree.

[0096] The similar node filtering module 202 is used to determine the corresponding flow velocity similarity based on the similarity of the flow velocity data time series distribution between each monitoring node and each other monitoring node; and to filter out similar nodes for each monitoring node based on the flow velocity similarity.

[0097] The abnormal node screening module 203 is used to determine the abnormal monitoring difference of each monitoring node based on the deviation of the pressure abnormality degree distribution and the deviation of the number of pressure abnormal times between each monitoring node and its corresponding similar nodes; and to screen out abnormal nodes based on the abnormal monitoring difference.

[0098] The natural gas pipeline control module 204 is used to determine the corresponding natural gas anomaly degree based on the anomaly monitoring differences of each abnormal node and the upward trend of the corresponding pressure anomaly degree at the time of pressure anomaly; to determine the overall natural gas anomaly based on the continuous distribution of abnormal nodes on the natural gas export pipeline and the overall magnitude of the corresponding natural gas anomaly degree; and to perform fuzzy control on the natural gas pipeline based on the overall natural gas anomaly.

[0099] It should be noted that the system provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the intelligent control system for pressure safety of natural gas export pipelines and the intelligent control method for pressure safety of natural gas export pipelines provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method embodiments and will not be repeated here.

[0100] This application also provides a computer device; please refer to [link / reference]. Figure 3The diagram illustrates a computer device structure according to an embodiment of the present invention. The computer device includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program 303, the computer device can execute any of the aforementioned intelligent control methods for pressure safety of natural gas export pipelines.

[0101] This application also provides a computer program product that, when run on a computer device, enables the computer device to execute any of the aforementioned intelligent control methods for pressure safety of natural gas export pipelines.

[0102] This application also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer device, the computer device can execute any of the aforementioned intelligent control methods for pressure safety of natural gas export pipelines.

[0103] In the embodiments provided in this application, it should be understood that the computer device, computer program product and computer-readable storage medium provided are all used to perform the corresponding methods provided above, and therefore the beneficial effects they can achieve can be referred to the beneficial effects of the methods provided above, which will not be repeated here.

[0104] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0105] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for intelligent pressure safety control of natural gas export pipelines, the method comprising: Pressure and flow rate data are collected for each monitoring node in the natural gas transmission pipeline at each sampling time; the degree of pressure anomaly is determined based on the pressure fluctuation within the time-series neighborhood of each monitoring node at each sampling time. The time of pressure anomaly for each monitoring node is selected based on the degree of pressure anomaly. The method is characterized by further comprising: determining the corresponding flow velocity similarity based on the similarity of the time-series distribution of flow velocity data between each monitoring node and each other monitoring node; and filtering out similar nodes for each monitoring node based on the flow velocity similarity. Based on the deviations in the distribution of pressure anomalies and the number of pressure anomaly moments between each monitoring node and its corresponding similar nodes, the abnormal monitoring differences of each monitoring node are determined; and abnormal nodes are selected based on these abnormal monitoring differences. Based on the differences in abnormal monitoring of each abnormal node and the upward trend of the corresponding pressure abnormality at the time of pressure abnormality, the corresponding natural gas abnormality degree is determined; based on the continuous distribution of abnormal nodes on the natural gas export pipeline and the overall magnitude of the corresponding natural gas abnormality degree, the overall natural gas abnormality is determined; and fuzzy control is performed on the natural gas pipeline based on the overall natural gas abnormality.

2. The intelligent control method for pressure safety of natural gas export pipelines according to claim 1, characterized in that, The process of obtaining the degree of pressure anomaly includes: Use all sampling times within a preset time neighborhood for each sampling time as the corresponding reference time; The local pressure fluctuation level is determined based on the variance of the pressure data at all reference times corresponding to each sampling time for each monitoring node; the comparative pressure fluctuation level is determined based on the mean of the local pressure fluctuation levels at all reference times corresponding to each sampling time. The difference between the local pressure fluctuation level of each monitoring node at each sampling time and the comparative pressure fluctuation level is normalized to determine the corresponding time-series fluctuation anomaly level; the pressure anomaly level at each sampling time is determined based on the mean between the normalized value of the local pressure fluctuation level of each monitoring node at each sampling time and the time-series fluctuation anomaly level.

3. The intelligent control method for pressure safety of natural gas export pipelines according to claim 1, characterized in that, The process of obtaining the moment of pressure anomaly includes: At each monitoring node, the sampling time corresponding to the pressure anomaly level exceeding the preset pressure anomaly threshold is taken as the pressure anomaly time for each monitoring node.

4. The intelligent control method for pressure safety of natural gas export pipelines according to claim 1, characterized in that, The process of obtaining the flow velocity similarity includes: After arranging the flow velocity data of each monitoring node at all sampling times in chronological order, the corresponding time-series flow velocity data sequence is determined. Each monitoring node is taken as the target node in turn; other monitoring nodes outside the target nodes are taken as the corresponding reference nodes; the Pearson correlation coefficient between the time series flow velocity data sequence of the target node and the time series flow velocity data sequence of each reference node is positively correlated to determine the corresponding flow velocity similarity trend factor. At each sampling time, the instantaneous flow velocity difference of each reference node is determined based on the difference between the flow velocity data of the target node and the flow velocity data of each reference node; the mean of the instantaneous flow velocity difference of each reference node at all sampling times is negatively correlated to determine the consistency of the corresponding flow velocity data. The product between the velocity similarity trend factor and the velocity data consistency is normalized to determine the velocity similarity between the target node and each reference node.

5. The intelligent control method for pressure safety of natural gas export pipelines according to claim 4, characterized in that, The process of filtering out similar nodes for each monitoring node based on the flow velocity similarity includes: Reference nodes with flow velocity similarity greater than a preset similarity threshold are used as similar nodes to the target node.

6. The intelligent control method for pressure safety of natural gas export pipelines according to claim 1, characterized in that, The process for obtaining the anomaly monitoring differences includes: All pressure anomaly time periods for each monitoring node are obtained; all sampling times within the pressure anomaly time periods are pressure anomaly times, all pressure anomaly times are distributed continuously in time sequence, and neither the preceding nor following sampling time of the pressure anomaly time period is a pressure anomaly time; based on the cumulative value of the pressure anomaly degree of all pressure anomaly times for each monitoring node, the corresponding pressure anomaly characteristic value is determined. The difference between the number of abnormal pressure time periods at each monitoring node and the number of abnormal pressure time periods at each corresponding similar node is normalized to determine the corresponding abnormality; the difference between the abnormal pressure feature value at each monitoring node and the abnormal pressure feature value at each corresponding similar node is normalized to determine the corresponding abnormality. The reference difference between each monitoring node and each similar node is determined by multiplying the difference in the number of anomalies and the difference in the pressure anomalies; the anomaly monitoring difference of each monitoring node is determined by the mean of the reference differences between each monitoring node and all similar nodes.

7. The intelligent control method for pressure safety of natural gas export pipelines according to claim 1, characterized in that, The process of filtering out abnormal nodes based on the anomaly monitoring differences includes: Monitoring nodes that exhibit abnormal monitoring differences exceeding a preset monitoring threshold are designated as abnormal nodes.

8. The intelligent control method for pressure safety of natural gas export pipelines according to claim 6, characterized in that, The process of obtaining the degree of natural gas anomaly includes: Based on the average pressure anomaly severity at all pressure anomaly times within each pressure anomaly time period of each anomaly node, a corresponding reference anomaly severity is determined. The reference anomaly severity at each pressure anomaly time period is then arranged chronologically and subjected to curve fitting to determine the time-series curve of the reference anomaly severity for each anomaly node. The normalized value of the slope of the tangent line corresponding to the time-series curve of the reference anomaly severity for each pressure anomaly time period is used as the corresponding anomaly rise characteristic value. Based on the average of the anomaly rise characteristic values ​​for all pressure anomaly time periods of each anomaly node, the corresponding trend anomaly characteristic value is determined. The degree of natural gas anomaly at each anomaly node is determined by multiplying the anomaly monitoring difference of each anomaly node with the trend anomaly characteristic value.

9. The intelligent control method for pressure safety of natural gas export pipelines according to claim 6, characterized in that, The process for obtaining the overall anomaly of the natural gas includes: All abnormal monitoring sections in the natural gas export pipeline are acquired; wherein, all monitoring nodes in each abnormal monitoring section are abnormal nodes, the abnormal nodes are continuously distributed in the natural gas export pipeline, and the preceding and following monitoring nodes of the abnormal monitoring section are not abnormal nodes. The corresponding local anomaly level is determined based on the average of the natural gas anomaly levels of all anomaly nodes in each anomaly monitoring segment. The corresponding local anomaly of natural gas is determined by multiplying the number of all abnormal nodes in each anomaly monitoring segment with the degree of local anomaly. The cumulative values ​​of local anomalies of natural gas in all abnormal monitoring sections of the natural gas transmission pipeline are normalized to determine the overall anomaly of natural gas.

10. A pressure safety intelligent control system for natural gas export pipelines, the system comprising: The data acquisition and preprocessing module is used to collect pressure and flow rate data of each monitoring node in the natural gas transmission pipeline at each sampling time; and to determine the corresponding pressure anomaly degree based on the pressure fluctuation in the time-series neighborhood of each monitoring node at each sampling time. The time of pressure anomaly for each monitoring node is selected based on the degree of pressure anomaly. The system is characterized by further comprising: a similar node filtering module, used to determine the corresponding flow velocity similarity based on the similarity of the time-series distribution of flow velocity data between each monitoring node and each other monitoring node; and to filter out similar nodes for each monitoring node based on the flow velocity similarity; The abnormal node screening module is used to determine the abnormal monitoring differences of each monitoring node based on the deviation of the distribution of the degree of pressure anomaly between each monitoring node and its corresponding similar nodes, as well as the deviation of the number of pressure anomaly times; and to screen out abnormal nodes based on the abnormal monitoring differences. The natural gas pipeline control module is used to determine the corresponding natural gas anomaly degree based on the anomaly monitoring differences of each abnormal node and the upward trend of the corresponding pressure anomaly degree at the time of pressure anomaly; to determine the overall natural gas anomaly based on the continuous distribution of abnormal nodes on the natural gas export pipeline and the overall magnitude of the corresponding natural gas anomaly degree; and to perform fuzzy control on the natural gas pipeline based on the overall natural gas anomaly.

Images