Gas pipe network safety monitoring method and system based on Internet of Things

Abstract

The invention relates to the technical field of the Internet of Things, and particularly discloses a gas pipe network safety monitoring method and system based on the Internet of Things, and the method comprises the steps: transmitting collected pressure and temperature data to an SCADA cloud platform through an MQTT protocol, and carrying out the encryption processing of the data through a national secret SM2 algorithm, so as to guarantee the safety of the data; comparing and analyzing the data before and after transmission through a data accuracy analysis module, and judging the accuracy of the data; according to the method, the monitoring period is divided into a plurality of time subunits on the basis of accurate data, pressure and temperature data in each subunit are comprehensively analyzed, whether the operation state of the pipe network is stable or not is evaluated, and the unstable time subunits and the historical normal monitoring period are compared and analyzed through a K-means clustering algorithm. And whether periodic normal fluctuation exists or not is judged, so that timely early warning and troubleshooting of abnormal conditions are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a gas pipeline network safety monitoring method and system based on the Internet of Things. Background Art

[0002] The SCADA cloud platform is an integrated management and control full-configuration platform. It mainly collects IoT sensing device data in real time through the ISO standard (ISO / IEC PRF 0922) MQTT (Message Queuing Telemetry Transport) message queue in the form of national secret SM2 encrypted messages, creates a model application mode, realizes rapid access to equipment, and preliminarily completes data governance. Through threshold setting, it can determine in real time whether each indicator data received is abnormal, achieve efficient supervision, and summarize and store the received data, and display the data in the form of graphs and tables to achieve big data application analysis.

[0003] With the development of Internet of Things technology, by deploying sensors at key locations of gas pipelines, various parameters of pipeline operation (such as pressure, temperature, etc.) can be collected in real time, and the data can be transmitted to the central control system through wireless networks for analysis and processing; this monitoring method based on the Internet of Things has greatly improved the intelligent management level of gas pipelines, but there are still problems such as data transmission security and data accuracy verification;

[0004] In addition, traditional data analysis methods can often only monitor a single indicator and lack the ability to comprehensively analyze multiple parameters, making it difficult to comprehensively evaluate the operating status of the pipeline network. Especially when faced with a complex and changeable operating environment, how to accurately judge the stability of the pipeline network's operating status and take effective response measures in a timely manner has become an urgent problem to be solved. Summary of the invention

[0005] The purpose of the present invention is to provide a gas pipeline network safety monitoring method and system based on the Internet of Things to solve the problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A gas pipeline network safety monitoring method based on the Internet of Things comprises the following steps:

[0008] S1: Obtain the operation data of the gas pipeline network within the monitoring period, compare and analyze the operation data before and after transmission, and determine the accuracy of the operation data during the transmission process;

[0009] Wherein, the operation data includes: pressure data and temperature data;

[0010] S2: marking the transmitted operation data according to the analysis result, and dividing the operation data into accurate operation data and inaccurate operation data;

[0011] S3: Based on accurate data, the monitoring period is divided into several equal time sub-units, and the pressure data and temperature data of each time sub-unit are comprehensively analyzed to evaluate whether the operation status of the gas pipeline network in each time sub-unit is stable;

[0012] S4: According to the analysis results, the real-time operation status of the gas pipeline network in all time sub-units is marked, and the time sub-units are divided into stable time sub-units and unstable time sub-units;

[0013] S5: Compare and analyze the unstable time sub-unit with the historical normal monitoring cycle to determine whether there are normal periodic fluctuations. If so, increase the monitoring frequency. If not, issue a timely warning, stop the gas pipeline network operation, and conduct abnormal investigation.

[0014] As a further solution of the present invention: the operation data before transmission and the operation data after transmission are compared and analyzed, and the data accuracy index is calculated to determine the accuracy of the operation data during the transmission process;

[0015] The data accuracy index acquisition process is as follows:

[0016] Get the running data before transmission, denoted as D b ;

[0017] Get the running data after transmission, denoted as D a ;

[0018] The operation data before the transmission is recorded as one set of data, and the operation data after the transmission is recorded as another set of data;

[0019] Get the mean and standard deviation of each group of data respectively;

[0020] Set the running data to normal distribution and set the prior distribution to

[0021] In the formula, P(D b ) is the prior probability distribution, μ b is the mean value of the data before transmission, σ b is the standard deviation of the data before transmission;

[0022] For each transmitted data point D a , calculate its likelihood under the prior distribution;

[0023] The likelihood calculation expression under the prior distribution is:

[0024]

[0025] In the formula, P(D a |D b ) represents the probability of the data after transmission given the data before transmission, i represents the number of running data during transmission, represents the actual value of the i-th data, μ b represents the mean value of the data before transmission, σ a It represents the standard deviation of the data after transmission, and exp represents the exponential function with e as the low value;

[0026] Compute the posterior distribution according to Bayes’ theorem;

[0027] The Bayesian theorem calculates the posterior distribution expression as:

[0028] P(D b |D a )∝P(D a |D b )*P(D b );

[0029] In the formula, P(D b |D a ) represents the probability of the data before transmission given the data before transmission, P(D b ) represents the prior probability distribution;

[0030] The probability of the data after transmission is calculated by the ratio of the probability of the data before transmission to obtain the data accuracy index.

[0031] As a further solution of the present invention: the operation data after transmission is marked according to the analysis result, and the operation data is divided into accurate operation data and inaccurate operation data, specifically including:

[0032] Determine whether the data accuracy index is greater than or equal to the preset data accuracy index threshold. If so, record it as accurate data; if not, record it as inaccurate data.

[0033] As a further solution of the present invention: the monitoring period is divided into a number of equal time sub-units, the pressure data and temperature data of each time sub-unit are comprehensively analyzed, and the abnormal fluctuation coefficient of each time sub-unit is calculated, which specifically includes:

[0034] For the pressure data and temperature data in each time subunit, an ARIMA model is constructed respectively, and the pressure fluctuation coefficient and the temperature fluctuation coefficient are calculated according to the ARIMA model;

[0035] The pressure fluctuation coefficient and the temperature fluctuation coefficient are normalized, and the abnormal fluctuation coefficient of each time subunit is calculated.

[0036] As a further solution of the present invention: the process of obtaining the pressure fluctuation coefficient is:

[0037] According to the ARIMA forecasting model, obtain the predicted value of the pressure at time t by the ARIMA model;

[0038] For each time subunit, the predicted value of the pressure at time t by the ARIMA model is processed with the time pressure value to calculate the pressure fluctuation coefficient within the subunit;

[0039] The pressure fluctuation coefficient calculation expression is:

[0040]

[0041] In the formula, γ j represents the pressure fluctuation coefficient of the jth time subunit, j represents the number of time subunits, j is a positive integer greater than 0, Δt is the length of each time subunit, P(t) is the pressure value at time t, and Pz(t) is the pressure prediction value of the ARIMA model at time t.

[0042] As a further solution of the present invention: it is characterized in that the temperature fluctuation coefficient acquisition process is:

[0043] According to the ARIMA prediction model, obtain the predicted value of the temperature at time t by the ARIMA model;

[0044] The predicted value of the temperature at time t by the ARIMA model and the actual temperature value are processed to calculate the temperature fluctuation coefficient;

[0045] The temperature fluctuation coefficient calculation expression is:

[0046]

[0047] In the formula, δ j represents the temperature fluctuation coefficient of the jth time subunit, j represents the number of time subunits, j is a positive integer greater than 0, Δt is the length of each time subunit, T(t) is the temperature value at time t, and Tz(t) is the temperature prediction value of the ARIMA model at time t.

[0048] As a further solution of the present invention: according to the analysis results, the real-time operation status of the gas pipeline network in all time sub-units is marked, and the time sub-units are divided into stable time sub-units and unstable time sub-units, specifically including:

[0049] Get the abnormal fluctuation coefficient ε of each time subunit j , determine the abnormal fluctuation coefficient ε jWhether it is greater than or equal to the preset abnormal fluctuation coefficient threshold, if so, it is recorded as an unstable time sub-unit, if not, it is recorded as a stable time sub-unit.

[0050] As a further solution of the present invention: the unstable time sub-unit is compared and analyzed with the historical normal monitoring period to determine whether there is a periodic normal fluctuation, specifically including:

[0051] The K-means clustering algorithm is used to analyze the fluctuation of the operating data in the current unstable time subunit and the fluctuation of the corresponding historical operating data, calculate the Euclidean distance between the real-time operating data and the historical operating data, and judge whether there is periodic normal fluctuation based on the comparison between the Euclidean distance and the preset threshold.

[0052] As a further solution of the present invention: the process of obtaining the Euclidean distance between the real-time operation data and the historical operation data is as follows:

[0053] Obtaining the operation data of the unstable time subunit and the historical operation data in the corresponding historical time subunit;

[0054] Construct a feature vector for the running data in each time sub-unit in real time, denoted as X m ;

[0055] Construct a feature vector for the running data in each time sub-unit of history as the initial centroid, denoted as C m ;

[0056] For each abnormal time subunit, the Euclidean distance between the feature vector of the running data set and the initial centroid of the historical running data is calculated;

[0057] The Euclidean distance calculation formula is:

[0058]

[0059] In the formula, E(X m ,C m ) indicates X m With C m The Euclidean distance between them, m represents the number of time subunits, n represents the number of selected data points in the time subunit, X mn is the nth data point in the mth time subunit of the real-time pressure value, C mn It is the nth data point in the mth time subunit of the historical pressure value.

[0060] A gas pipeline network safety monitoring system based on the Internet of Things, comprising:

[0061] A data acquisition module, the data acquisition module is used to obtain the operation data of the gas pipeline network within the monitoring period, wherein the operation data includes: pressure data and temperature data;

[0062] A data accuracy analysis module, wherein the data accuracy analysis module compares and analyzes the operation data before transmission and the operation data after transmission to determine the accuracy of the operation data during the transmission process;

[0063] A data comprehensive analysis module, which is used to divide the monitoring period into a number of equal time sub-units, comprehensively analyze the pressure data and temperature data of each time sub-unit, and evaluate whether the gas pipeline network operation status in each time sub-unit is stable;

[0064] Comparative analysis and early warning module, which is used to compare and analyze the unstable time sub-unit with the historical normal monitoring cycle to determine whether there is a periodic normal fluctuation. If so, the monitoring frequency is strengthened. If not, a timely warning is issued and the gas pipeline network operation is stopped to conduct abnormality investigation.

[0065] Beneficial effects of the present invention:

[0066] (1) The present invention realizes the real-time collection and intelligent analysis of gas pipeline network operation data by introducing Internet of Things technology and advanced data processing algorithms, significantly improving the safety monitoring level of the gas pipeline network. Through the Internet of Things technology, the present invention can deploy sensors at key locations of the pipeline network to collect various key parameters of the pipeline network operation (such as pressure and temperature) in real time; these data are transmitted to the SCADA cloud platform through the MQTT protocol and encrypted using the national secret SM2 algorithm to ensure the security and reliability of data transmission. The present invention uses a data accuracy analysis module to compare and analyze the data before and after transmission to determine the accuracy of the data during the transmission process, thereby ensuring the basic data quality for subsequent analysis; this process not only improves the data reliability, but also The invention not only improves reliability, but also avoids misjudgment caused by data errors. The invention also uses the ARIMA model to model and predict the pressure data and temperature data in each time subunit, and comprehensively evaluates whether the operation status of the gas pipeline network in each time subunit is stable by calculating the pressure fluctuation coefficient and the temperature fluctuation coefficient. This method can not only accurately identify abnormal conditions in the operation of the pipeline network, but also send out early warning signals in time by comparing preset thresholds to ensure the safety of the pipeline network operation. In general, the invention realizes comprehensive monitoring of the operation status of the gas pipeline network through multi-level data processing and analysis, greatly improves the intelligent level of pipeline network safety management, effectively prevents potential safety hazards, and ensures the stability and reliability of urban gas supply.

[0067] (2) The present invention can effectively determine whether the current operating status conforms to normal periodic fluctuations by clustering the operating data in the current unstable time subunit and the data in the historical normal monitoring period. This process can not only avoid false alarms caused by data fluctuations, but also issue early warnings in time when abnormal situations actually occur, thereby ensuring the safe operation of the gas pipeline network. Secondly, by setting reasonable preset thresholds and comparing the Euclidean distance between real-time operating data and historical data, the present invention can accurately distinguish between normal fluctuations and abnormal fluctuations, thereby avoiding unnecessary shutdowns and troubleshooting. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The present invention will be further described below in conjunction with the accompanying drawings.

[0069] Figure 1 This is a flowchart of the specific steps of a gas pipeline network safety monitoring method based on the Internet of Things of the present invention;

[0070] Figure 2 It is a flowchart of the operation data accuracy judgment process in the present invention;

[0071] Figure 3 It is a flow chart of a gas pipeline network safety monitoring system based on the Internet of Things in the present invention. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] See also Figure 1 As shown, the present invention is a gas pipeline network safety monitoring method based on the Internet of Things, comprising the following steps:

[0074] S1: Obtain the operation data of the gas pipeline network within the monitoring period, compare and analyze the operation data before and after transmission, and determine the accuracy of the operation data during the transmission process;

[0075] Wherein, the operation data includes: pressure data and temperature data;

[0076] S2: marking the transmitted operation data according to the analysis result, and dividing the operation data into accurate operation data and inaccurate operation data;

[0077] S3: Based on accurate data, the monitoring period is divided into several equal time sub-units, and the pressure data and temperature data of each time sub-unit are comprehensively analyzed to evaluate whether the operation status of the gas pipeline network in each time sub-unit is stable;

[0078] S4: According to the analysis results, the real-time operation status of the gas pipeline network in all time sub-units is marked, and the time sub-units are divided into stable time sub-units and unstable time sub-units;

[0079] S5: Compare and analyze the unstable time sub-unit with the historical normal monitoring cycle to determine whether there are normal periodic fluctuations. If so, increase the monitoring frequency. If not, issue a timely warning, stop the gas pipeline network operation, and conduct abnormal investigation.

[0080] Example 2

[0081] See also Figure 2 As shown, based on Example 1, the operation data of the gas network is obtained, and the operation data before transmission and the operation data after transmission are compared and analyzed to determine the accuracy of the operation data during the transmission process. Specifically, the following steps are performed:

[0082] The data transmission process includes:

[0083] The operation data is transmitted to the SCADA cloud platform via the MQTT protocol, and the transmitted data is encrypted using the national encryption SM2 algorithm;

[0084] It should be noted that the SCADA cloud platform uses Docker technology to package applications into image files, enabling rapid deployment of application servers and data servers. It can also achieve cross-platform deployment of the platform in cloud environments, Linux systems, and Windows systems, and is suitable for use in various large, medium, and small enterprise environments.

[0085] The platform's PaaS layer provides an App development environment, where users can quickly complete customized development and publish in real time using low-code and drag-and-drop components without affecting the production environment, avoiding monitoring gaps caused by iterative restarts.

[0086] End users can use any browser to log in, view and use PC-side SaaS layer applications without installing any software or browser plug-ins. There is no configuration requirement for the terminal computer, which reduces the cost of use. The SCADA cloud platform PaaS layer can also implement mobile App development in a hybrid way of Android and H5 to meet the different usage environments of end users.

[0087] Get the running data before transmission, denoted as D b ;

[0088] Get the running data after transmission, denoted as Da ;

[0089] The operation data before the transmission is recorded as one set of data, and the operation data after the transmission is recorded as another set of data;

[0090] Get the mean and standard deviation of each group of data respectively;

[0091] Set the running data to normal distribution and set the prior distribution to

[0092] In the formula, P(D b ) is the prior probability distribution, μ b is the mean value of the data before transmission, σ b is the standard deviation of the data before transmission;

[0093] For each transmitted data point D a , calculate its likelihood under the prior distribution;

[0094] The likelihood calculation expression under the prior distribution is:

[0095]

[0096] In the formula, P(D a |D b ) represents the probability of the data after transmission given the data before transmission, i represents the number of running data during transmission, represents the actual value of the i-th data, μ b represents the mean value of the data before transmission, σ a It represents the standard deviation of the data after transmission, and exp represents the exponential function with e as the low value;

[0097] Compute the posterior distribution according to Bayes’ theorem;

[0098] The Bayesian theorem calculates the posterior distribution expression as:

[0099] P(D b |D a )∝P(D a |D b )*P(D b );

[0100] In the formula, P(D b |D a ) represents the probability of the data before transmission given the data before transmission, P(D b ) represents the prior probability distribution;

[0101] The probability of the data after transmission is calculated by the ratio of the probability of the data before transmission to obtain the data accuracy index;

[0102] According to the analysis results, the transmitted operation data is marked and divided into accurate operation data and inaccurate operation data, including:

[0103] comparing the data accuracy index with a preset accuracy index threshold;

[0104] If the data accuracy index is greater than or equal to the preset data accuracy index threshold, it means that the data transmission is accurate and is recorded as accurate data;

[0105] If the data accuracy index is less than the preset data accuracy index threshold, it means that the data transmission is inaccurate and is recorded as inaccurate data.

[0106] Example 3

[0107] On the basis of Example 2, based on accurate data, the monitoring period is divided into several equal time sub-units, and the pressure data and temperature data of each time sub-unit are comprehensively analyzed to evaluate whether the operation status of the gas pipeline network in each time sub-unit is stable, specifically including:

[0108] For the pressure data and temperature data in each time subunit, an ARIMA model is constructed respectively;

[0109] The process of constructing the ARIMA model is:

[0110] Establish an ARIMA model. Assuming that the time series is a stationary time series, it can be modeled through the ARIMA model;

[0111] The ARIMA model is usually represented by ARIMA(p,d,q), where p is the order of the autoregressive term, d is the order of the difference, and q is the order of the moving average term;

[0112] The process of establishing an ARIMA model involves parameter selection and model fitting. The values ​​of p and q can usually be determined by analyzing the autocorrelation function (ACF) and partial autocorrelation function (PACF);

[0113] Apply the selected ARIMA model to the time series of temperature monitoring and pressure monitoring to perform model fitting; perform residual analysis on the model to evaluate the model fitting effect;

[0114] The residual sequence is [e1, e2, …, en], where the residual sequence represents the difference between the observed value and the model predicted value;

[0115] The ARIMA model expression is: mh = k1*y t-1 +k2*y t-2 +…+kd*y t-p +e t -g1et-1 -g2e t-2 -...-gqe t-q ;

[0116] Among them, y t ARIMA model for pressure or temperature value at time t, e t is the residual of the time series, k is the weight coefficient of the observation value of the time series, and is the weight coefficient of the residual of the time series;

[0117] According to the ARIMA forecasting model, obtain the predicted value of the pressure at time t by the ARIMA model;

[0118] Get the predicted value of temperature at time t from the ARIMA model;

[0119] For each time subunit, calculating the pressure fluctuation coefficient and the temperature fluctuation coefficient within the subunit;

[0120] The pressure fluctuation coefficient calculation expression is:

[0121]

[0122] In the formula, γ j represents the pressure fluctuation coefficient of the jth time subunit, j represents the number of time subunits, j is a positive integer greater than 0, Δt is the length of each time subunit, P(t) is the pressure value at time t, and Pz(t) is the pressure prediction value of the ARIMA model at time t;

[0123] The temperature fluctuation coefficient calculation expression is:

[0124]

[0125] In the formula, δ j represents the temperature fluctuation coefficient of the jth time subunit, j represents the number of time subunits, j is a positive integer greater than 0, Δt is the length of each time subunit, T(t) is the temperature value at time t, and Tz(t) is the temperature prediction value of the ARIMA model at time t;

[0126] Pressure fluctuation coefficient γ j and temperature fluctuation coefficient δ j Perform normalization processing and calculate the abnormal fluctuation coefficient of the corresponding time subunit;

[0127] The calculation expression of the abnormal fluctuation coefficient is:

[0128]

[0129] In the formula, ε jrepresents the abnormal fluctuation coefficient in the jth time subunit, a1 and a2 are preset proportional coefficients, and both a1 and a2 are greater than 0;

[0130] It should be noted that: From the calculation expression of abnormal fluctuation coefficient, it can be seen that the pressure fluctuation coefficient γ j and temperature fluctuation coefficient δ j and abnormal fluctuation coefficient ε j is in direct proportion to the abnormal fluctuation coefficient ε j The larger it is, the worse the gas pipeline network operation status in the corresponding time subunit is.

[0131] Example 4

[0132] On the basis of Example 3, according to the analysis results, the real-time operation status of the gas pipeline network in all time sub-units is marked, and the time sub-units are divided into stable time sub-units and unstable time sub-units, specifically including:

[0133] Get the abnormal fluctuation coefficient ε of each time subunit j , and the abnormal fluctuation coefficient ε j Compare with the preset abnormal fluctuation coefficient threshold;

[0134] If the abnormal fluctuation coefficient ε j If it is greater than or equal to the preset abnormal fluctuation coefficient threshold, it means that the operation state of the gas pipeline network in the corresponding time subunit is abnormal, and the corresponding time subunit is recorded as an unstable time subunit;

[0135] If the abnormal fluctuation coefficient ε j If the value is smaller than the preset abnormal fluctuation coefficient threshold, it indicates that the gas pipeline network operation status in the corresponding time subunit is normal, and the corresponding time subunit is recorded as a stable time subunit.

[0136] Example 5

[0137] On the basis of Example 4, the unstable time subunit is compared and analyzed with the historical normal monitoring cycle to determine whether there is a normal periodic fluctuation. If so, the monitoring frequency is strengthened. If not, a warning is issued in time and the gas network operation is stopped. The abnormality investigation specifically includes:

[0138] Use the K-means clustering algorithm to analyze the fluctuation of the operating data in the current unstable time subunit and the fluctuation of the corresponding historical operating data to determine whether the fluctuation of the operating data in the current period is a normal periodic fluctuation;

[0139] The process of constructing a K-means clustering algorithm for running data is as follows:

[0140] Obtaining the operation data of the unstable time subunit and the historical operation data in the corresponding historical time subunit;

[0141] Construct a feature vector for the running data in each time sub-unit in real time, denoted as X m ;

[0142] Construct a feature vector for the running data in each time sub-unit of history as the initial centroid, denoted as C m ;

[0143] For each abnormal time subunit, the Euclidean distance between the feature vector of the running data set and the initial centroid of the historical running data is calculated;

[0144] The Euclidean distance calculation formula is:

[0145]

[0146] In the formula, E(X m ,C m ) indicates X m With C m The Euclidean distance between them, m represents the number of time subunits, n represents the number of selected data points in the time subunit, X mn is the nth data point in the mth time subunit of the real-time pressure value, C mn is the nth data point in the mth time subunit of the historical pressure value;

[0147] The Euclidean distance E(X m ,C m ) is compared with a preset threshold;

[0148] If the Euclidean distance E(X m ,C m ) is greater than or equal to the preset threshold, indicating that the corresponding operating data does not belong to normal periodic fluctuations;

[0149] If the Euclidean distance E(X m ,C m ) is less than the preset threshold, indicating that the corresponding operating data is a periodic normal fluctuation;

[0150] It should be noted that: by performing cluster analysis on the operating data of the gas pipeline network, the Euclidean distance between real-time data and historical data is calculated. The Euclidean distance reflects whether the current operating cycle is similar to the historical operating cycle and belongs to a normal operating cycle, thereby avoiding misjudgment of abnormalities.

[0151] If the operating data does not belong to normal periodic fluctuations, timely warnings will be issued and the gas network operation will be stopped. The unstable monitoring information of the gas network will be sent to the user client in a timely manner, and abnormalities will be checked.

[0152] Example 6

[0153] See also Figure 3 As shown, a gas pipeline network safety monitoring system based on the Internet of Things includes:

[0154] A data acquisition module, the data acquisition module is used to obtain the operation data of the gas pipeline network within the monitoring period, wherein the operation data includes: pressure data and temperature data;

[0155] A data accuracy analysis module, wherein the data accuracy analysis module compares and analyzes the operation data before transmission and the operation data after transmission to determine the accuracy of the operation data during the transmission process;

[0156] A data comprehensive analysis module, which is used to divide the monitoring period into a number of equal time sub-units, comprehensively analyze the pressure data and temperature data of each time sub-unit, and evaluate whether the gas pipeline network operation status in each time sub-unit is stable;

[0157] The comparison analysis and early warning module is used to compare and analyze the unstable time sub-unit with the historical normal monitoring cycle to determine whether there are normal periodic fluctuations. If so, the monitoring frequency is strengthened. If not, a timely warning is issued, and the gas pipeline network operation is stopped to conduct abnormality inspection.

[0158] The working principle of the present invention is as follows: the gas pipeline network operation data within the monitoring period is obtained through the data acquisition module, and the data before and after the transmission is compared and analyzed through the data accuracy analysis module to determine the data accuracy during the transmission process and ensure the authenticity and reliability of the data. The data comprehensive analysis module divides the monitoring period into several sub-units of the same time, and comprehensively analyzes the pressure data and temperature data in each sub-unit to evaluate whether its operating status is stable. On this basis, the comparative analysis and early warning module compares and analyzes the unstable time sub-unit with the historical normal monitoring period, and uses the K-means clustering algorithm to determine whether there is a periodic normal fluctuation. If so, the monitoring frequency is strengthened, otherwise, timely warning and stopping the gas pipeline network operation are carried out to conduct abnormal investigation. In addition, the present invention also uses the MQTT protocol to transmit data, and encrypts it through the national secret SM2 algorithm to ensure the security of data transmission; at the same time, with the help of the SCADA cloud platform and Docker technology, rapid deployment and cross-platform application are realized, which improves the flexibility and adaptability of the system. The entire monitoring system collects data in real time through the Internet of Things technology, and combines with advanced data analysis algorithms to achieve efficient monitoring and management of the operating status of the gas pipeline network, effectively preventing potential safety hazards.

[0159] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0160] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0161] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0162] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0163] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A gas pipeline network safety monitoring method based on the Internet of Things, It is characterized in that The following steps are involved: S1: Obtain the operation data of the gas pipeline network within the monitoring period, compare and analyze the operation data before and after transmission, and determine the accuracy of the operation data during the transmission process; Wherein, the operation data includes: pressure data and temperature data; S2: marking the transmitted operation data according to the analysis result, and dividing the operation data into accurate operation data and inaccurate operation data; S3: Based on accurate data, the monitoring period is divided into several equal time sub-units, and the pressure data and temperature data of each time sub-unit are comprehensively analyzed to evaluate whether the operation status of the gas pipeline network in each time sub-unit is stable; S4: According to the analysis results, the real-time operation status of the gas pipeline network in all time sub-units is marked, and the time sub-units are divided into stable time sub-units and unstable time sub-units; S5: Compare and analyze the unstable time sub-unit with the historical normal monitoring cycle to determine whether there are normal periodic fluctuations. If so, increase the monitoring frequency. If not, issue a timely warning, stop the gas pipeline network operation, and conduct abnormal investigation.

2. According to the method for gas pipeline network safety monitoring based on the Internet of Things according to claim 1, It is characterized in that The operation data before transmission and the operation data after transmission are compared and analyzed, and the data accuracy index is calculated to determine the accuracy of the operation data during the transmission process; The data accuracy index acquisition process is as follows: Get the running data before transmission, denoted as D b ; Get the running data after transmission, denoted as D a ; The operation data before the transmission is recorded as one set of data, and the operation data after the transmission is recorded as another set of data; Get the mean and standard deviation of each group of data respectively; Set the running data to normal distribution and set the prior distribution to In the formula, P(D b ) is the prior probability distribution, μ b is the mean value of the data before transmission, σ b is the standard deviation of the data before transmission; For each transmitted data point D a , calculate its likelihood under the prior distribution; The likelihood calculation expression under the prior distribution is: In the formula, P(D a |D b ) represents the probability of the data after transmission given the data before transmission, i represents the number of running data during transmission, represents the actual value of the i-th data, μ b represents the mean value of the data before transmission, σ a represents the standard deviation of the data after transmission, and exp represents an exponential function with e as the low value; Compute the posterior distribution according to Bayes’ theorem; The Bayesian theorem calculates the posterior distribution expression as: P(D b |D b )∝P(D a |D b )*P(D b ); In the formula, P(D b |D a ) represents the probability of the data before transmission given the data before transmission, P(D b ) represents the prior probability distribution; The probability of the data after transmission is calculated by the ratio of the probability of the data before transmission to obtain the data accuracy index.

3. According to the method for gas pipeline network safety monitoring based on the Internet of Things as described in claim 1, It is characterized in that The operation data after transmission is marked according to the analysis result, and the operation data is divided into accurate operation data and inaccurate operation data, specifically including: Determine whether the data accuracy index is greater than or equal to the preset data accuracy index threshold. If so, record it as accurate data; if not, record it as inaccurate data.

4. According to claim 1, a gas pipeline network safety monitoring method based on the Internet of Things, It is characterized in that The monitoring period is divided into a number of equal time sub-units, the pressure data and temperature data of each time sub-unit are comprehensively analyzed, and the abnormal fluctuation coefficient of each time sub-unit is calculated, specifically including: For the pressure data and temperature data in each time subunit, an ARIMA model is constructed respectively, and the pressure fluctuation coefficient and the temperature fluctuation coefficient are calculated according to the ARIMA model; The pressure fluctuation coefficient and the temperature fluctuation coefficient are normalized, and the abnormal fluctuation coefficient of each time subunit is calculated.

5. According to the method for monitoring gas pipeline network safety based on the Internet of Things according to claim 4, It is characterized in that The pressure fluctuation coefficient acquisition process is as follows: According to the ARIMA forecasting model, obtain the predicted value of the pressure at time t by the ARIMA model; For each time subunit, the predicted value of the pressure at time t by the ARIMA model is processed with the time pressure value to calculate the pressure fluctuation coefficient within the subunit; The pressure fluctuation coefficient calculation expression is: Where γj represents the pressure fluctuation coefficient of the jth time subunit, j represents the number of time subunits, j is a positive integer greater than 0, Δt is the length of each time subunit, P(t) is the pressure value at time t, and Pz(t) is the pressure prediction value of the ARIMA model at time t.

6. According to claim 4, a gas pipeline network safety monitoring method based on the Internet of Things, It is characterized in that The temperature fluctuation coefficient acquisition process is as follows: According to the ARIMA prediction model, obtain the predicted value of the temperature at time t by the ARIMA model; The predicted value of the temperature at time t by the ARIMA model and the actual temperature value are processed to calculate the temperature fluctuation coefficient; The temperature fluctuation coefficient calculation expression is: In the formula, δ j represents the temperature fluctuation coefficient of the jth time subunit, j represents the number of time subunits, j is a positive integer greater than 0, Δt is the length of each time subunit, T(t) is the temperature value at time t, and Tz(t) is the temperature prediction value of the ARIMA model at time t.

7. According to claim 1, a gas pipeline network safety monitoring method based on the Internet of Things, It is characterized in that According to the analysis results, the real-time operation status of the gas pipeline network in all time sub-units is marked, and the time sub-units are divided into stable time sub-units and unstable time sub-units, specifically including: Get the abnormal fluctuation coefficient ε of each time subunit j , determine the abnormal fluctuation coefficient ε j Whether it is greater than or equal to the preset abnormal fluctuation coefficient threshold, if so, it is recorded as an unstable time sub-unit, if not, it is recorded as a stable time sub-unit.

8. According to the method for monitoring gas pipeline network safety based on the Internet of Things in claim 1, It is characterized in that The unstable time sub-unit is compared and analyzed with the historical normal monitoring period to determine whether there is a periodic normal fluctuation, specifically including: The K-means clustering algorithm is used to analyze the fluctuation of the operating data in the current unstable time subunit and the fluctuation of the corresponding historical operating data, calculate the Euclidean distance between the real-time operating data and the historical operating data, and judge whether there is periodic normal fluctuation based on the comparison between the Euclidean distance and the preset threshold.

9. According to the method for gas pipeline network safety monitoring based on the Internet of Things as claimed in claim 8, It is characterized in that The process of obtaining the Euclidean distance between the real-time operation data and the historical operation data is as follows: Obtaining the operation data of the unstable time subunit and the historical operation data in the corresponding historical time subunit; Construct a feature vector for the running data in each time sub-unit in real time, denoted as X m ; Construct a feature vector for the running data in each time sub-unit of history as the initial centroid, denoted as C m ; For each abnormal time subunit, the Euclidean distance between the feature vector of the running data set and the initial centroid of the historical running data is calculated; The Euclidean distance calculation formula is: In the formula, E(X m ,C m ) indicates X m With C m The Euclidean distance between them, m represents the number of time subunits, n represents the number of selected data points in the time subunit, X mn is the nth data point in the mth time subunit of the real-time pressure value, C mn It is the nth data point in the mth time subunit of the historical pressure value.

10. A gas pipeline network safety monitoring system based on the Internet of Things, It is characterized in that A gas pipeline network safety monitoring method based on the Internet of Things for use in claims 1-9, comprising: A data acquisition module, the data acquisition module is used to obtain the operation data of the gas pipeline network within the monitoring period, wherein the operation data includes: pressure data and temperature data; A data accuracy analysis module, wherein the data accuracy analysis module compares and analyzes the operation data before transmission and the operation data after transmission to determine the accuracy of the operation data during the transmission process; A data comprehensive analysis module, which is used to divide the monitoring period into a number of equal time sub-units, comprehensively analyze the pressure data and temperature data of each time sub-unit, and evaluate whether the operation status of the gas pipeline network in each time sub-unit is stable; The comparison analysis and early warning module is used to compare and analyze the unstable time sub-unit with the historical normal monitoring cycle to determine whether there are normal periodic fluctuations. If so, the monitoring frequency is strengthened. If not, a timely warning is issued, and the gas pipeline network operation is stopped to conduct abnormality inspection.

Images