Safe and intelligent control method and system for pressure of natural gas output pipeline

Abstract

The invention relates to the technical field of pipeline control, in particular to a natural gas output pipeline pressure safety intelligent control method and system.The method comprises the steps that firstly, according to the characteristic that when pressure is abnormal, abnormal time sequence fluctuation usually appears, the pressure abnormal degree is preliminarily determined, and the pressure abnormal moment of each monitoring node is screened out; after the similar nodes of each monitoring node are screened out according to the similar condition of the flow velocity characteristics, pressure abnormal degree deviation analysis is carried out between each monitoring node and each similar node according to the characteristic that the similar nodes can show similar pressure expression under the normal condition, so that abnormal nodes are screened out more accurately; and finally, according to the distribution of the natural gas anomaly degree represented by the nodes on the whole pipeline, more accurate natural gas overall anomaly is determined, and the effect of controlling the natural gas pipeline according to the natural gas overall anomaly is better.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipeline control, and in particular to a natural gas external pipeline pressure safety intelligent control method and system. BACKGROUND

[0002] In the operation and management of a natural gas external pipeline, pressure safety control is a core link for ensuring the safe and stable operation of the pipeline. In the prior art, pressure data is analyzed according to the size of the change in time sequence, and when pressure data with a pressure change greater than a change threshold is monitored, it is determined that the pressure is abnormal and the natural gas pipeline is controlled. However, the corresponding method of the prior art can only reflect local pressure abnormality and cannot take into account the overall abnormality of the natural gas external pipeline. Moreover, the method of analyzing only the size of the pressure change has high limitations and cannot accurately quantify the abnormality in the pipeline, resulting in poor effects of the prior art on natural gas pipeline control. SUMMARY

[0003] In order to solve the technical problem of poor effects of the prior art on natural gas pipeline control, the purpose of the present application is to provide a natural gas external pipeline pressure safety intelligent control method and system, and the technical solution adopted is as follows: The first aspect of the present application provides a natural gas external pipeline pressure safety intelligent control method, comprising: acquiring pressure data and flow rate data of each monitoring node in the natural gas external pipeline at each sampling time; determining the corresponding pressure abnormality degree according to the pressure fluctuation in the time sequence neighborhood of each sampling time of each monitoring node; and screening the pressure abnormal time of each monitoring node according to the pressure abnormality degree; determining the corresponding flow rate similarity according to the flow rate data time sequence distribution similarity between each monitoring node and each other monitoring node; and screening the similar node of each monitoring node according to the flow rate similarity; determining the abnormal monitoring difference of each monitoring node according to the pressure abnormality degree distribution deviation and the pressure abnormal time number deviation between each monitoring node and the corresponding each similar node; and screening the abnormal node according to the abnormal monitoring difference; determining the corresponding natural gas abnormality degree according to the abnormal monitoring difference of each abnormal node and the pressure abnormality degree rising trend of the pressure abnormal time; determining the natural gas overall abnormality according to the continuous distribution of the abnormal node on the natural gas external pipeline and the overall size of the corresponding natural gas abnormality degree; and performing fuzzy control on the natural gas pipeline according to the natural gas overall abnormality.

[0004] Further, the pressure abnormality degree acquisition process comprises: all sampling time points in a preset time neighborhood range of each sampling time point are taken as corresponding reference time points; a corresponding local pressure fluctuation degree is determined according to a variance of pressure data of all reference time points corresponding to each monitoring node at each sampling time point, and a corresponding comparative pressure fluctuation degree is determined according to a mean value of local pressure fluctuation degrees of all reference time points corresponding to each sampling time point; a difference between the local pressure fluctuation degree of each monitoring node at each sampling time point and the comparative pressure fluctuation degree is normalized to determine a corresponding time sequence fluctuation abnormality degree, and a pressure abnormality degree of each sampling time point is determined according to a mean value between the normalized value of the local pressure fluctuation degree of each monitoring node at each sampling time point and the time sequence fluctuation abnormality degree.

[0005] Further, the pressure abnormality time point acquisition process comprises: At each monitoring node, a sampling time point corresponding to a pressure abnormality degree greater than a preset pressure abnormality threshold value is taken as a pressure abnormality time point of each monitoring node.

[0006] Further, the flow rate similarity acquisition process comprises: After time-sequentially arranging flow rate data of each monitoring node at all sampling time points, a corresponding time sequence flow rate data sequence is determined. Each monitoring node is sequentially taken as a target node, other monitoring nodes outside the target node are taken as corresponding reference nodes, and a positive correlation mapping is performed on a Pearson correlation coefficient between the time sequence flow rate data sequence of the target node and a time sequence flow rate data sequence of each reference node to determine a corresponding flow rate similarity trend factor. At each sampling time point, an instantaneous flow rate difference of each reference node is determined according to a difference between flow rate data of the target node and flow rate data of each reference node, and a negative correlation mapping is performed on a mean value of the instantaneous flow rate difference of each reference node at all sampling time points to determine a corresponding flow rate data consistency. A product between the flow rate similarity trend factor and the flow rate data consistency is normalized to determine a flow rate similarity between the target node and each reference node.

[0007] Further, the process of screening out a similar node of each monitoring node according to the flow rate similarity comprises: A reference node corresponding to a flow rate similarity greater than a preset similarity threshold value is taken as a similar node of the target node.

[0008] Further, the abnormal monitoring difference acquisition process comprises: acquiring all pressure abnormal time periods of each monitoring node; all sampling time points in the pressure abnormal time periods are pressure abnormal time points, all pressure abnormal time points are continuously distributed in time sequence, and the previous sampling time point and the next sampling time point of the pressure abnormal time period are not pressure abnormal time points; determining a corresponding pressure abnormal characteristic value according to an accumulated value of pressure abnormal degrees of all pressure abnormal time points of each monitoring node; normalizing a difference between a number of pressure abnormal time periods of each monitoring node and a number of pressure abnormal time periods of each corresponding similar node to determine a corresponding abnormal number difference; normalizing a difference between the pressure abnormal characteristic value of each monitoring node and the pressure abnormal characteristic value of each corresponding similar node to determine a corresponding pressure abnormal difference; determining a reference difference between each monitoring node and each similar node according to a product between the abnormal number difference and the pressure abnormal difference; determining an abnormal monitoring difference of each monitoring node according to a mean value of the reference differences between each monitoring node and all similar nodes.

[0009] Further, the process of screening out abnormal nodes according to the abnormal monitoring difference comprises: regarding a monitoring node corresponding to an abnormal monitoring difference greater than a preset monitoring threshold as an abnormal node.

[0010] Further, the process of acquiring the natural gas abnormal degree comprises: determining a corresponding reference abnormal degree according to a mean value of pressure abnormal degrees of all pressure abnormal time points in each pressure abnormal time period of each abnormal node; arranging reference abnormal degrees of all pressure abnormal time periods of each abnormal node in time sequence and performing curve fitting to determine a reference abnormal degree time sequence curve of each abnormal node; regarding a normalized value of a tangent slope of each pressure abnormal time period on the reference abnormal degree time sequence curve as a corresponding abnormal rising characteristic value; determining a trend abnormal characteristic value of each abnormal node according to a mean value of abnormal rising characteristic values of all pressure abnormal time periods of each abnormal node; determining a natural gas abnormal degree of each abnormal node according to a product between the abnormal monitoring difference of each abnormal node and the trend abnormal characteristic value.

[0011] Further, the process of acquiring the natural gas overall abnormality comprises: acquiring all abnormal monitoring sections in the natural gas transmission pipeline; wherein all monitoring nodes in each abnormal monitoring section are abnormal nodes, the abnormal nodes are continuously distributed in the natural gas transmission pipeline, and the previous monitoring node and the next monitoring node of the abnormal monitoring section are not abnormal nodes; determine a corresponding local abnormality degree according to a mean value of the gas abnormality degree of all abnormal nodes in each abnormal monitoring section; determine a corresponding gas local abnormality according to a product between the number of all abnormal nodes in each abnormal monitoring section and the local abnormality degree; normalize the cumulative value of the gas local abnormality of all abnormal monitoring sections in the gas transmission pipeline to determine a gas overall abnormality.

[0012] In a second aspect, the present application provides a pressure safety intelligent control system for a gas transmission pipeline, which comprises: a data acquisition and preprocessing module, configured to acquire pressure data and flow rate data of each monitoring node in the gas transmission pipeline at each sampling time, determine a corresponding pressure abnormality degree according to pressure fluctuation in a time sequence neighborhood of each sampling time of each monitoring node, and screen pressure abnormal time of each monitoring node according to the pressure abnormality degree; a similar node screening module, configured to determine a corresponding flow rate similarity according to flow rate data time sequence distribution similarity between each monitoring node and each other monitoring node, and screen similar nodes of each monitoring node according to the flow rate similarity; an abnormal node screening module, configured to determine abnormal monitoring difference of each monitoring node according to pressure abnormality degree distribution deviation and pressure abnormal time number deviation between each monitoring node and corresponding similar nodes, and screen abnormal nodes according to the abnormal monitoring difference; a gas pipeline control module, configured to determine a corresponding gas abnormality degree according to abnormal monitoring difference of each abnormal node and pressure abnormality degree rising trend of pressure abnormal time, determine a gas overall abnormality according to continuous distribution of abnormal nodes on the gas transmission pipeline and overall size of the corresponding gas abnormality degree, and perform fuzzy control on the gas pipeline according to the gas overall abnormality.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor. The memory is configured to store computer program code, and the processor is configured to call and run the computer program code from the memory to execute the method of the first aspect or any embodiment of the first aspect of the present application.

[0014] In a fourth aspect, the present application provides a computer program product, which comprises computer program code, and when the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is executed.

[0015] In a fifth aspect, the present application provides a computer readable storage medium storing computer program codes, when the computer program codes are executed, to perform the method of the first aspect or any of the embodiments of the first aspect.

[0016] The present application has the following beneficial effects: The present application firstly determines the pressure abnormality degree and screens out the pressure abnormal time of each monitoring node according to the characteristics that the pressure usually shows abnormal time sequence fluctuation when the pressure is abnormal; after screening out the similar nodes of each monitoring node according to the similar characteristics of flow rate, the pressure abnormality degree deviation analysis is performed between each monitoring node and each similar node according to the characteristics that the similar nodes show similar pressure performance under normal conditions, so that the abnormal nodes are more accurately screened out; finally, the natural gas overall abnormality is more accurately determined according to the distribution of the natural gas abnormality degree of the nodes on the whole pipeline, and the effect of controlling the natural gas pipeline according to the natural gas overall abnormality is better. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art and the advantages thereof, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these drawings without creative labor.

[0018] Figure 1 A flow chart of a natural gas external pipeline pressure safety intelligent control method provided by an embodiment of the present application; Figure 2 A structural diagram of a natural gas external pipeline pressure safety intelligent control system provided by an embodiment of the present application; Figure 3 A computer device structural schematic diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined object, the specific implementation, structure, features and effects of the natural gas external pipeline pressure safety intelligent control method and system according to the present application are described in detail as follows in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form. In addition, the terms "first", "second" are only for descriptive purposes, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features with "first", "second" can be explicitly or implicitly included one or more features.

[0020] 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 the present application belongs.

[0021] The specific scheme of the natural gas external pipeline pressure safety intelligent control method and system provided by the present application is described in detail below in combination with the drawings.

[0022] The present application provides a natural gas external pipeline pressure safety intelligent control method, please refer to Figure 1 , which shows a natural gas external pipeline pressure safety intelligent control method flow chart provided by an embodiment of the present application, the method comprises: Step S101: collecting the pressure data and flow rate data of each monitoring node in the natural gas external pipeline at each sampling time; determining the corresponding pressure abnormality degree according to the pressure fluctuation in the time sequence neighborhood of each sampling time of each monitoring node; screening out the pressure abnormal time of each monitoring node according to the pressure abnormality degree.

[0023] In one specific implementation of the embodiment of the present application, each pump station and valve area of the natural gas external pipeline is taken as a monitoring node, and a pressure sensor and a flow rate sensor are installed at each monitoring node position; the pressure data of each monitoring node in the natural gas external pipeline at each sampling time is collected by the pressure sensor; the flow rate data of each monitoring node in the natural gas external pipeline at each sampling time is collected by the flow rate sensor; the sampling frequency is set to collect once per second; the sampling time period is set to one day before the current time, which can be adjusted according to the specific implementation environment, and will not be described further here.

[0024] Firstly, when the pressure is abnormal, the pressure data will show abnormal and disordered fluctuation in time sequence; for each sampling time, the more intense the fluctuation of the pressure data in the neighborhood of the sampling time is, the greater the fluctuation degree corresponding to other sampling times is, and the more abnormal the corresponding pressure fluctuation is; therefore, according to the fluctuation of the pressure data in the time sequence neighborhood of each sampling time of each monitoring node, the application determines the corresponding pressure abnormality degree.

[0025] Preferably, in some possible implementation manners of the embodiments of the application, the acquisition process of the pressure abnormality degree comprises: all sampling times in the preset time neighborhood range of each sampling time are taken as corresponding reference times; according to the variance of the pressure data of each monitoring node at each sampling time corresponding to all reference times, the corresponding local pressure fluctuation degree is determined; the variance represents the discreteness of a group of data, for each sampling time of each monitoring node, the greater the variance of the pressure data in the preset time neighborhood range is, the more discrete the pressure data in the time neighborhood of the corresponding sampling time is, the more significant the fluctuation characteristics shown are, and the greater the pressure abnormality degree is. In a specific implementation manner of the embodiments of the application, the preset time neighborhood range is set to the time range corresponding to the closest 20 sampling times of each sampling time, which can be adjusted according to the specific implementation environment, and will not be further described here.

[0026] According to the mean value of the local pressure fluctuation degrees of all reference times corresponding to each sampling time, the corresponding comparative pressure fluctuation degree is determined; the difference between the local pressure fluctuation degree and the comparative pressure fluctuation degree of each monitoring node at each sampling time is normalized to determine the corresponding time sequence fluctuation abnormality degree. For each sampling time, the greater the local pressure fluctuation degree corresponding to the sampling time is compared with the local pressure fluctuation degrees of the reference times in the time sequence neighborhood, the more significant the pressure fluctuation of the corresponding sampling time is, the more inconsistent with the overall characteristics of the pressure fluctuation in the time sequence neighborhood, and the higher the possibility of pressure abnormality of the sampling time is; therefore, according to the mean value between the normalized value of the local pressure fluctuation degree and the time sequence fluctuation abnormality degree of each monitoring node at each sampling time, the pressure abnormality degree of each sampling time is further determined according to the correlation. In another specific implementation manner of the embodiments of the application, the product of the normalized value of the local pressure fluctuation degree and the time sequence fluctuation abnormality degree of each monitoring node at each sampling time is normalized to determine the pressure abnormality degree of each sampling time, and the implementer can adjust it according to the specific implementation environment, and will not be further described here. It should be noted that, except for special instructions, the normalization method in the embodiments of the application adopts linear normalization, and will not be further described here.

[0027] In a specific implementation of the embodiment of the present invention, the process of obtaining the degree of pressure anomaly is expressed by the formula: ;in, For monitoring nodes In the The degree of pressure anomaly at each sampling moment; For monitoring nodes In the The variance of the pressure data at all reference moments corresponding to a sampling moment, that is, the corresponding degree of local pressure fluctuation; For monitoring nodes In the The average value of the local pressure fluctuation degree of all reference moments corresponding to the sampling moment, that is, the comparison pressure fluctuation degree; is a linear normalization function; For monitoring nodes In the The abnormal degree of time series fluctuation corresponding to each sampling moment.

[0028] The pressure anomaly moment at which the pressure anomaly occurs is further preliminarily screened out based on the degree of pressure anomaly reflecting the pressure anomaly. Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the pressure anomaly moment includes: at each monitoring node, taking the sampling moment corresponding to the pressure anomaly degree greater than the preset pressure anomaly threshold as the pressure anomaly moment of each monitoring node. In a specific implementation of the embodiments of the present 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.

[0029] Step S102: determining 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 filtering out similar nodes of each monitoring node based on the flow velocity similarity.

[0030] Hydrogen sulfide (H2S) and carbon dioxide (CO2) in natural gas are highly corrosive. They react with pipeline metal to generate sulfides, leading to metal corrosion. Oxides or other corrosion products produced by corrosion may accumulate inside the pipeline, forming a viscous layer, which will cause abnormal pipeline pressure. If the sensor is in the abnormal area, the measured pressure does not reflect the true pressure of the entire pipeline. Therefore, further analysis of the natural gas pipeline abnormality is required after determining the moment of pressure abnormality.

[0031] Under normal circumstances, the monitoring nodes in the similar flow state area should generally exhibit similar pressure performance, if a certain monitoring node has a large pressure performance deviation from other monitoring nodes in the similar flow state area, it indicates that the pipeline area where the monitoring node is located may have an abnormality, and the abnormality reflects the real pressure abnormality of the whole pipeline; therefore, according to the characteristics, after similar nodes corresponding to each monitoring node in the similar flow state area are screened out, by comparing the pressure performance deviation of each monitoring node and each similar node, a more accurate monitoring node with pressure abnormality can be screened out. Before that, similar nodes of each monitoring node need to be screened out according to the characteristics of the similar flow state area; the similar flow state area exhibits similar gas flow velocity, therefore, according to the similar situation of the time sequence distribution of the flow velocity data between each monitoring node and each other monitoring node, the flow velocity similarity is determined.

[0032] Preferably, in some possible implementation manners of the embodiment of the present application, the flow velocity similarity acquisition process comprises: After arranging the flow velocity data of each monitoring node at all sampling time points in time sequence, the corresponding time sequence flow velocity data sequence is determined; each monitoring node is sequentially taken as a target node; other monitoring nodes outside the target node are taken as corresponding reference nodes; the Pearson correlation coefficient between the time sequence flow velocity data sequence of the target node and the time sequence flow velocity data sequence of each reference node is positively correlated, and the corresponding flow velocity similarity trend factor is determined.

[0033] In one specific implementation manner of the embodiment of the present application, the mean value between the Pearson correlation coefficient between the time sequence flow velocity data sequence of the target node and the time sequence flow velocity data sequence of each reference node and the real number 1 is taken as the corresponding flow velocity similarity trend factor, by positively correlating through this method, the value range of the flow velocity similarity trend factor can be limited within 0 to 1, and the influence of the appearance of negative value on subsequent analysis is avoided. According to the definition of the Pearson correlation coefficient, the greater the obtained flow velocity similarity trend factor is, the more consistent the value of the flow velocity data in time sequence between the target node and the corresponding reference node is, that is, the more similar the flow state is, and the corresponding flow velocity similarity should be greater.

[0034] The flow rate similarity trend factor only analyzes the flow rate similarity from the overall change trend of the flow rate data in time sequence, and further analyzes the comparison of the specific size of the flow rate data at each sampling time in the dimension of detailed analysis, so as to more accurately quantify the flow rate similarity. In each sampling time, according to the difference between the flow rate data of the target node and the flow rate data of each reference node, the instantaneous flow rate difference of each reference node is determined; the mean value of the instantaneous flow rate difference of each reference node at all sampling times is negatively correlated and mapped to determine the corresponding flow rate data consistency. For the target node and the reference node, the smaller the difference between the flow rate data at each sampling time, the higher the time sequence consistency of the numerical value of the flow rate data in time sequence, and the higher the corresponding flow rate similarity, and it is more likely to be in the same flow state region.

[0035] Further, according to the correlation, the product between the flow rate similarity trend factor and the flow rate data consistency is normalized to determine the flow rate similarity between the target node and each reference node; the greater the flow rate similarity, the more likely the corresponding reference node and the target node are in the same flow state region, that is, the reference node is more likely to belong to the similar node of the target node.

[0036] In some possible implementation manners of the embodiment of the present application, the flow rate similarity acquisition process is represented by a formula as follows: ; wherein, is the flow rate similarity between the target node and the corresponding reference node; is the flow rate similarity trend factor between the target node and the corresponding reference node; is the number of sampling times; is the flow rate data of the target node at the i th sampling time; is the flow rate data of the corresponding reference node at the i th sampling time; is the absolute value symbol; is the instantaneous flow rate difference of the corresponding reference node at the i th sampling time; is the flow rate data consistency between the target node and the corresponding reference node.

[0037] ​​​​​​​​Further, the similar nodes of each monitoring node can be screened according to the flow rate similarity, specifically, the reference nodes corresponding to the flow rate similarity greater than a preset similarity threshold are taken as the similar nodes of the target node. In one specific implementation manner of the embodiment of the application, the preset similarity threshold is set to 0.8, which can be adjusted according to the specific implementation environment.

[0038] Step S103: determining the abnormal monitoring difference of each monitoring node according to the pressure abnormality degree distribution deviation and the pressure abnormal time number deviation between each monitoring node and the corresponding similar nodes; and screening the abnormal nodes according to the abnormal monitoring difference.

[0039] After the similar nodes of each monitoring node in the similar flow state region are determined, further, according to the feature that the monitoring nodes in the similar flow state region should generally show similar pressure performance under normal circumstances, the abnormal nodes showing greater pressure performance deviation from the similar nodes can be screened by analyzing the pressure performance deviation between each monitoring node and the similar nodes. The pressure abnormality degree can represent the pressure abnormal performance of each monitoring node at each sampling moment, therefore, the greater the pressure abnormality degree distribution deviation between the monitoring node and the similar nodes, the more likely the monitoring node is abnormal. Therefore, the embodiment of the application further determines the abnormal monitoring difference of each monitoring node according to the pressure abnormality degree distribution deviation and the pressure abnormal time number deviation between each monitoring node and the corresponding similar nodes, so that the greater the abnormal monitoring difference, the more significant the pressure abnormal performance of the corresponding monitoring node compared with other similar nodes, and the higher the possibility that the corresponding monitoring node is a real abnormal node.

[0040] Preferably, in some possible implementation manners of the embodiment of the application, the process of obtaining the abnormal monitoring difference includes: obtaining all pressure abnormal time periods of each monitoring node; all sampling moments in the pressure abnormal time period are pressure abnormal moments, all pressure abnormal moments are continuously distributed in time sequence, and the previous sampling moment and the next sampling moment of the pressure abnormal time period are not pressure abnormal moments; determining the corresponding pressure abnormal feature value according to the cumulative value of the pressure abnormality degree of all pressure abnormal moments of each monitoring node. The pressure abnormal time period is each time period formed by combining adjacent pressure abnormal moments; the greater the corresponding pressure abnormal feature value of each pressure abnormal time period, the more abnormal the pressure performance in the corresponding time period.

[0041] Since the pressure of the monitoring nodes in the similar flow state region is similar under normal circumstances, if the number of pressure abnormal time periods and the numerical value of pressure abnormal degree corresponding to each monitoring node and other similar nodes are more similar, it means that the pressure abnormality of the corresponding monitoring node is the pressure performance specific to the corresponding flow state region, and does not reflect the real pressure abnormality of the entire pipeline; on the contrary, if the number of pressure abnormal time periods and the numerical value of pressure abnormal degree corresponding to each monitoring node and other similar nodes are less similar, it means that the corresponding monitoring node does not conform to the pressure performance of the corresponding flow state region, and the pressure abnormality it reflects is more likely to be a real overall pipeline pressure abnormality, and the corresponding abnormal node is more likely to be real.

[0042] Therefore, the difference between the number of pressure abnormal time periods of each monitoring node and the number of pressure abnormal time periods of each corresponding similar node is further normalized to determine the corresponding abnormal number difference; the difference between the pressure abnormal characteristic value of each monitoring node and the pressure abnormal characteristic value of each corresponding similar node is normalized to determine the corresponding pressure abnormal difference.

[0043] Considering that the pressure performance in the similar flow state region is similar under normal circumstances, if the distribution of pressure abnormal time periods between the monitoring node and each similar node is more similar, and the overall size of the pressure abnormal characteristic value of each pressure abnormal time period is more similar, it means that it is more consistent with the pressure performance consistency of the corresponding similar flow state region under normal circumstances, and the pressure abnormality of the monitoring node cannot reflect the real pressure of the entire pipeline, but belongs to the pressure characteristics of the corresponding similar flow state region; therefore, for each monitoring node, the smaller the abnormal number difference between it and each similar node, the more similar the distribution of pressure abnormal time periods between the corresponding monitoring node and the corresponding similar node in the number dimension, and the more likely the corresponding pressure abnormality belongs to the pressure abnormality performance of the corresponding similar flow state region; similarly, the smaller the pressure abnormality difference, the more similar the overall size of the pressure abnormal characteristic value of each abnormal time period between the corresponding monitoring node and the corresponding similar node, and the more consistent with the pressure abnormality performance of the similar flow state region; that is, under the reference of the corresponding similar node, the corresponding monitoring node is more likely to not be an abnormal node that reflects the overall pipeline pressure abnormality.

[0044] The abnormal quantity difference and the pressure abnormality difference are further combined, and the reference difference between each monitoring node and each similar node is determined based on the product of the abnormal quantity difference and the pressure abnormality difference; then, a comparative analysis is performed in combination with all similar nodes, and the abnormal monitoring difference of each monitoring node is determined based on the mean of the reference difference between each monitoring node and all similar nodes, so that the smaller the abnormal monitoring difference, the more the corresponding monitoring node conforms to the abnormal pressure characteristics of the similar flow pattern area between each similar node, and the lower the possibility of the corresponding monitoring node belonging to the abnormal node; conversely, the greater the abnormal monitoring difference, the more likely the corresponding monitoring node does not belong to the pressure abnormality characteristics exhibited by the similar flow pattern area, and the higher the possibility of the corresponding monitoring node belonging to the abnormal node; and the greater the abnormal monitoring difference, the more abnormal the real pressure of the pipeline reflected.

[0045] In a specific implementation of the embodiment of the present invention, the process of obtaining the abnormal monitoring difference is expressed by the formula: ;in, For monitoring nodes The abnormal monitoring differences; For monitoring nodes The number of similar nodes; For monitoring nodes The accumulated value of the pressure anomaly degree at all pressure anomaly moments, that is, the corresponding pressure anomaly characteristic value; For monitoring nodes The corresponding Abnormal pressure characteristic values ​​of similar nodes; For monitoring nodes The number of periods of abnormal pressure; For monitoring nodes The corresponding The number of abnormal pressure periods of similar nodes; For monitoring nodes The corresponding The pressure anomaly differences between similar nodes; For monitoring nodes The corresponding The difference in the number of anomalies between similar nodes; For monitoring nodes The corresponding The reference difference between similar nodes.

[0046] For each monitoring node, the greater the corresponding abnormal monitoring difference, the higher the possibility that the monitoring node is an abnormal node, and the more abnormal the real pressure of the pipeline it reflects. Therefore, the abnormal node with abnormal pressure performance can be screened by setting a threshold. Preferably, in some possible implementation manners of the embodiment of the present application, the process of screening the abnormal node according to the abnormal monitoring difference comprises: taking the monitoring node corresponding to the abnormal monitoring difference greater than a preset monitoring threshold as an abnormal node. In a specific implementation manner of the embodiment of the present application, the preset monitoring threshold is set to 0.7, which can be adjusted according to the specific implementation environment, and will not be described further here. It should be noted that for the monitoring node with the number of similar nodes being 0, since the abnormal monitoring difference cannot be calculated, the monitoring node with the number of similar nodes being 0 and the pressure abnormal moment is taken as an abnormal node for analysis to ensure the completeness of the embodiment, and will not be described further here.

[0047] Step S104: determining the corresponding natural gas abnormality according to the abnormal monitoring difference of each abnormal node and the corresponding pressure abnormality degree rising trend of the pressure abnormal moment, determining the natural gas overall abnormality according to the continuous distribution of the abnormal nodes on the natural gas delivery pipeline and the overall size of the corresponding natural gas abnormality, and performing fuzzy control on the natural gas pipeline according to the natural gas overall abnormality.

[0048] As can be seen from step S103, the abnormal monitoring difference can not only reflect the possibility that the corresponding monitoring node is an abnormal node, but also reflect the abnormal situation of the real pressure of the pipeline. Therefore, for each abnormal node, the greater the corresponding abnormal monitoring difference, the more abnormal the pipeline pressure it reflects, that is, the greater the natural gas abnormality. For each abnormal node, if the pressure abnormality degree becomes greater and greater with time, it means that the abnormality of the abnormal node is becoming more and more serious, and therefore more attention should be paid to the abnormal problem of the abnormal node. Therefore, the abnormal monitoring difference of the abnormal node should be given greater weight to make the determined natural gas abnormality more accurate. Therefore, the corresponding natural gas abnormality is determined further according to the abnormal monitoring difference of each abnormal node and the corresponding pressure abnormality degree rising trend of the pressure abnormal moment, so that the natural gas abnormality can reflect the natural gas abnormality of the pipeline at the position of each abnormal node.

[0049] Preferably, in some possible implementation manners of the embodiment of the present application, the process of obtaining the natural gas abnormality comprises: According to the mean value of the pressure abnormality degree of all pressure abnormality time points in each pressure abnormality time period of each abnormal node, a corresponding reference abnormality degree is determined; the reference abnormality degrees of all pressure abnormality time periods of each abnormal node are arranged in time sequence and then curve fitting is performed to determine a reference abnormality degree time sequence curve of each abnormal node; a normalized value of a corresponding tangent slope of each pressure abnormality time period on the reference abnormality degree time sequence curve is taken as a corresponding abnormality rising feature value; and according to the mean value of the abnormality rising feature values of all pressure abnormality time periods of each abnormal node, a corresponding trend abnormality feature value is determined.

[0050] The greater the normalized value of the tangent slope, that is, the greater the abnormality rising feature value, the more obvious the rising trend of the pressure abnormality feature at the time sequence position of the corresponding abnormal pressure time period, and the more serious the abnormal situation of the pipeline natural gas; therefore, for each abnormal node, if the abnormality monitoring difference is greater and the trend abnormality feature value representing the abnormal rising trend is more obvious, the abnormality of the pipeline natural gas of the abnormal node is more serious, so finally the product of the abnormality monitoring difference and the trend abnormality feature value of each abnormal node is determined to determine the natural gas abnormality degree of each abnormal node.

[0051] The abnormal node only represents the abnormal position of the pipeline pressure at a local position of the pipeline, and for the natural gas export pipeline, if the abnormal nodes are concentrated in a certain specific area, it means that the problem of the pipeline is not an isolated accidental event, but a developing, systematic structural or functional failure problem, which is much more serious and risky than sporadic and scattered abnormalities, so the overall abnormality of the natural gas is further determined according to the continuous distribution of the abnormal nodes on the natural gas export pipeline and the overall size of the corresponding natural gas abnormality degree.

[0052] Preferably, in some possible implementation manners of the embodiments of the present application, the acquisition process of the overall abnormality of the natural gas comprises: 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 previous monitoring node and the next monitoring node of the abnormal monitoring section are not abnormal nodes; and according to the mean value of the natural gas abnormality degree of all abnormal nodes in each abnormal monitoring section, a corresponding local abnormality degree is determined.

[0053] First, the greater the degree of local abnormality, the higher the overall pipeline risk of each abnormal node in the corresponding abnormal monitoring section; and for each abnormal monitoring section, the more abnormal nodes it corresponds to, the more concentrated the distribution of abnormal nodes in the abnormal monitoring section, and the higher the pipeline risk it reflects; so for the natural gas export pipeline, the more abnormal nodes in each corresponding abnormal monitoring section as a whole, and the greater the overall degree of natural gas abnormality, the higher the overall abnormality of the natural gas reflecting the overall abnormality of the pipeline should be; therefore, the corresponding local abnormality of the natural gas is further determined based on the product of the number of all abnormal nodes in each abnormal monitoring section and the degree of local abnormality; then, combined with the local abnormality of the natural gas in each abnormal monitoring section, the cumulative value of the local abnormality of the natural gas in all abnormal monitoring sections in the natural gas export pipeline is normalized to determine the overall abnormality of the natural gas; so that the greater the overall abnormality of the natural gas, the more abnormal the overall pressure performance of the natural gas export pipeline, and the more necessary it is to adjust and control the natural gas pipeline.

[0054] In a specific implementation of the embodiment of the present invention, the process of obtaining the overall abnormality of natural gas is expressed by the formula: ;in, is the overall abnormality of natural gas at the current moment; is the number of abnormal monitoring segments; For the The number of abnormal nodes in an abnormal monitoring segment; For the In the abnormal monitoring section The difference of abnormal monitoring of abnormal nodes; For the In the abnormal monitoring section The mean of the abnormal rising characteristic values ​​of all pressure abnormal time periods of the abnormal node; For the In the abnormal monitoring section The degree of natural gas anomaly at each abnormal node; For the In the abnormal monitoring section The local abnormality degree of each abnormal node; For the Since the sampling period of the embodiment of the present invention is within one day before the current moment, the overall abnormality of the natural gas calculated here belongs to the current moment.

[0055] After determining the natural gas overall abnormality at the current moment, the natural gas pipeline needs to be controlled according to the natural gas overall abnormality; in a specific implementation manner of the embodiment of the present application, the natural gas overall abnormality at the current moment is taken as a weighting factor of fuzzy control at the current moment; the weighting factor of fuzzy control at the current moment and the average value of the gas pressure data of all monitoring points on the pipeline at the current moment are input into a fuzzy control algorithm, so that a control instruction (such as a pressure reduction, a pressure increase, etc.) is obtained; that is, according to the fuzzy rule base, the instruction of pipeline control is determined in combination with the natural gas overall abnormality of the pipeline; finally, the natural gas pipeline pressure control is performed according to the pipeline control instruction; for example, when the control instruction is pressure reduction, the pressure reduction valve is started to adjust the pipeline pressure, so that the natural gas pipeline pressure safety intelligent control is performed.

[0056] In summary, the natural gas pipeline pressure safety intelligent control method firstly determines the pressure abnormality degree and screens the pressure abnormal time of each monitoring node according to the characteristics that the pressure usually shows abnormal time sequence fluctuation when the pressure is abnormal; after screening the similar nodes of each monitoring node according to the similar situation of the flow rate characteristics, the pressure abnormality degree deviation analysis is performed between each monitoring node and each similar node according to the characteristics that the similar nodes show similar pressure performance under normal conditions, so that the abnormal node is more accurately screened; finally, the more accurate natural gas overall abnormality is determined according to the distribution of the natural gas abnormality degree of the nodes on the pipeline overall, so that the effect of the natural gas pipeline control according to the natural gas overall abnormality is better.

[0057] The present application also provides a natural gas pipeline pressure safety intelligent control system, please refer to Figure 2 which shows the structure diagram of the natural gas pipeline pressure safety intelligent control system provided by an embodiment of the present application, the system comprises: 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.

[0058] The data acquisition and preprocessing module 201 is used for acquiring the pressure data and flow rate data of each monitoring node in the natural gas pipeline at each sampling moment; determining the corresponding pressure abnormality degree according to the pressure fluctuation in the time sequence neighborhood of each sampling moment of each monitoring node; screening the pressure abnormal time of each monitoring node according to the pressure abnormality degree; The similar node screening module 202 is used for determining the corresponding flow rate similarity according to the flow rate data time sequence distribution similarity between each monitoring node and each other monitoring node; screening the similar nodes of each monitoring node according to the flow rate similarity; The abnormal node screening module 203 is configured to determine the abnormal monitoring difference of each monitoring node according to the pressure abnormal degree distribution deviation and the pressure abnormal time quantity deviation between each monitoring node and the corresponding similar node; and screen the abnormal node according to the abnormal monitoring difference. The natural gas pipeline control module 204 is configured to determine the corresponding natural gas abnormal degree according to the abnormal monitoring difference of each abnormal node and the corresponding pressure abnormal degree rising trend of the pressure abnormal time; determine the natural gas overall abnormality according to the continuous distribution of the abnormal node on the natural gas delivery pipeline and the overall size of the corresponding natural gas abnormal degree; and perform fuzzy control on the natural gas pipeline according to the natural gas overall abnormality.

[0059] It should be noted that the system provided in the above embodiments is only exemplified by the division of the above functional modules. In actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the above described functions. In addition, the natural gas delivery pipeline pressure safety intelligent control system and the natural gas delivery pipeline pressure safety intelligent control method provided in the above embodiments belong to the same concept, and the specific implementation process is described in the method embodiments, which will not be repeated here.

[0060] The embodiment of the present application also provides a computer device, please refer to Figure 3 which shows a computer device structure schematic diagram provided by an embodiment of the present application. 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 one of the natural gas delivery pipeline pressure safety intelligent control methods described above.

[0061] The embodiment of the present application also provides a computer program product, when the computer program product runs on the computer device, so that the computer device can execute any one of the natural gas delivery pipeline pressure safety intelligent control methods described above.

[0062] The embodiment of the present application also provides a computer readable storage medium, and the computer readable storage medium stores computer program code. When the computer program code runs on the computer device, the computer device can execute any one of the natural gas delivery pipeline pressure safety intelligent control methods described above.

[0063] In the embodiments provided in the present application, it should be understood that the computer device, computer program product and computer readable storage medium provided are all used to execute the corresponding method provided in the above, and thus the beneficial effects that can be achieved can refer to the beneficial effects of the method provided in the above, which will not be described here.

[0064] It should be noted that the above-mentioned sequence of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0065] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A method for intelligent pressure safety control of a natural gas transmission pipeline, characterized in that: The method comprises: Collect pressure data and flow rate data at each sampling moment for each monitoring node in the natural gas transmission pipeline; determine the corresponding pressure anomaly degree based on the pressure fluctuation within the time series neighborhood of each sampling moment of each monitoring node; and screen out the pressure anomaly moment of each monitoring node based on the pressure anomaly degree; 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 screen out similar nodes to each monitoring node based on the flow velocity similarity; Determine the abnormal monitoring difference of each monitoring node based on the deviation of the pressure anomaly distribution and the deviation of the number of pressure anomaly moments between each monitoring node and corresponding similar nodes; and screen out abnormal nodes based on the abnormal monitoring difference; The corresponding degree of natural gas anomaly is determined based on the abnormal monitoring differences of each abnormal node and the corresponding rising trend of the pressure anomaly degree at the time of pressure anomaly; the overall abnormality of natural gas is determined based on the continuous distribution of abnormal nodes on the natural gas transmission pipeline and the overall size of the corresponding natural gas anomaly degree; and fuzzy control of the natural gas pipeline is performed based on the overall abnormality of natural gas.

2. A natural gas transmission pipeline pressure safety intelligent control method according to claim 1, characterized in that: The process of obtaining the abnormal pressure degree includes: All sampling moments within the preset time neighborhood of each sampling moment are used as corresponding reference moments; Determine the corresponding local pressure fluctuation degree based on the variance of the pressure data of all reference moments corresponding to each monitoring node at each sampling moment; determine the corresponding comparative pressure fluctuation degree based on the mean of the local pressure fluctuation degrees of all reference moments corresponding to each sampling moment; The difference between the local pressure fluctuation degree of each monitoring node at each sampling moment and the comparison pressure fluctuation degree is normalized to determine the corresponding time series fluctuation abnormality degree; the pressure abnormality degree at each sampling moment is determined based on the average value between the normalized value of the local pressure fluctuation degree of each monitoring node at each sampling moment and the comparison pressure fluctuation degree.

3. A natural gas transmission pipeline pressure safety intelligent control method according to claim 1, characterized in that: The process of obtaining the abnormal pressure moment includes: At each monitoring node, the sampling moment corresponding to the pressure anomaly degree greater than the preset pressure anomaly threshold is used as the pressure anomaly moment of each monitoring node.

4. A natural gas transmission pipeline pressure safety intelligent control method 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 moments 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 other than the target node 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 moment, 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 moments is negatively correlated to determine the consistency of the corresponding flow velocity data; The product of the flow velocity similarity trend factor and the flow velocity data consistency is normalized to determine the flow velocity similarity between the target node and each reference node.

5. A natural gas transmission pipeline pressure safety intelligent control method according to claim 4, characterized in that: The process of screening out similar nodes of each monitoring node according to the flow rate similarity includes: The reference node corresponding to the flow rate similarity greater than the preset similarity threshold is regarded as the similar node of the target node.

6. A natural gas transmission pipeline pressure safety intelligent control method according to claim 1, characterized in that: The process of obtaining the abnormal monitoring difference includes: Obtain all pressure abnormality time periods for each monitoring node; all sampling moments in the pressure abnormality time period are pressure abnormality moments, all pressure abnormality moments are continuously distributed in time series, and the previous sampling moment and the next sampling moment of the pressure abnormality time period are not pressure abnormality moments; determine the corresponding pressure abnormality characteristic value based on the accumulated value of the pressure abnormality degree of all pressure abnormality moments of each monitoring node; Normalize the difference between the number of pressure anomaly time periods of each monitoring node and the number of pressure anomaly time periods of each corresponding similar node to determine the corresponding anomaly quantity difference; normalize the difference between the pressure anomaly characteristic value of each monitoring node and the pressure anomaly characteristic value of each corresponding similar node to determine the corresponding pressure anomaly difference; According to the product of the abnormal quantity difference and the pressure abnormality difference, the reference difference between each monitoring node and each similar node is determined; according to the mean of the reference differences between each monitoring node and all similar nodes, the abnormal monitoring difference of each monitoring node is determined.

7. A natural gas transmission pipeline pressure safety intelligent control method according to claim 1, characterized in that: The process of screening out abnormal nodes according to the abnormal monitoring differences includes: The monitoring nodes corresponding to the abnormal monitoring differences that are greater than the preset monitoring threshold are regarded as abnormal nodes.

8. A natural gas transmission pipeline pressure safety intelligent control method according to claim 6, characterized in that: The process of obtaining the degree of natural gas anomaly includes: Determine the corresponding reference abnormality degree based on the mean value of the pressure abnormality degree at all pressure abnormal moments in each pressure abnormality time period of each abnormal node; arrange the reference abnormality degrees of all pressure abnormality time periods of each abnormal node in chronological order and perform curve fitting to determine the reference abnormality degree time series curve of each abnormal node; use the normalized value of the tangent slope corresponding to each pressure abnormality time period on the reference abnormality degree time series curve as the corresponding abnormal rise characteristic value; determine the corresponding trend abnormality characteristic value based on the mean value of the abnormal rise characteristic values ​​of all pressure abnormality time periods of each abnormal node; The degree of natural gas anomaly at each abnormal node is determined according to the product of the abnormal monitoring difference of each abnormal node and the trend anomaly characteristic value.

9. A natural gas transmission pipeline pressure safety intelligent control method according to claim 6, characterized in that: The process of obtaining the overall abnormality of natural gas includes: Obtain all abnormal monitoring sections in the natural gas transmission pipeline; wherein all monitoring nodes in each abnormal monitoring section are abnormal nodes, the abnormal nodes are continuously distributed in the natural gas transmission pipeline, and the previous monitoring node and the next monitoring node in the abnormal monitoring section are not abnormal nodes; Determine the corresponding local abnormality level based on the average of the natural gas abnormality levels of all abnormal nodes in each abnormal monitoring segment; Determining the corresponding local abnormality of natural gas according to the product of the number of all abnormal nodes in each abnormal monitoring section and the degree of local abnormality; The accumulated values ​​of local abnormalities of natural gas in all abnormal monitoring sections in the natural gas transmission pipeline are normalized to determine the overall abnormality of natural gas.

10. A natural gas transmission pipeline pressure safety intelligent control system, characterized in that: The system comprises: The data acquisition and preprocessing module is used to collect pressure data and flow rate data of each monitoring node in the natural gas transmission pipeline at each sampling moment; determine the corresponding pressure anomaly degree based on the pressure fluctuation within the time series neighborhood of each monitoring node at each sampling moment; and filter out the pressure anomaly moment of each monitoring node based on the pressure anomaly degree; A similar node screening module 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 screen out similar nodes of each monitoring node based on the flow velocity similarity; An abnormal node screening module is used to determine the abnormal monitoring difference of each monitoring node based on the pressure abnormality distribution deviation and the pressure abnormality moment quantity deviation between each monitoring node and corresponding similar nodes; and screen out abnormal nodes based on the abnormal monitoring difference; The natural gas pipeline control module is used to determine the corresponding natural gas abnormality level based on the abnormal monitoring differences of each abnormal node and the corresponding pressure abnormality level rising trend at the time of pressure abnormality; determine the overall natural gas abnormality based on the continuous distribution of abnormal nodes on the natural gas transmission pipeline and the overall size of the corresponding natural gas abnormality level; and perform fuzzy control on the natural gas pipeline based on the said overall natural gas abnormality.

Images