Gas pipe network remote valve regulation and control system and method based on intelligent internet of things

Abstract

The invention is suitable for the technical field of gas transmission and distribution and pipe network safety monitoring, and provides a gas pipe network remote valve regulation and control system and method based on intelligent Internet of Things, and the method comprises the steps: obtaining an initial backflow risk value of a target pipeline region and historical data of a downstream pipe section tail end valve corresponding to the target pipeline region, historical data are analyzed, and a plurality of valve turn-off action samples meeting stable working conditions are extracted; according to the method, a conjoint analysis mechanism based on the difference between the valve turn-off action duration change trend and the valve front pressure micro-drop value is constructed, and a correction factor generation mode of slope deviation judgment and the pressure micro-drop relative difference rate at a specific time node is introduced for the first time; and dynamic perception of the evolution state of the sealing performance of the tail end valve is realized.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of gas transmission and distribution and pipe network safety monitoring, and particularly relates to a gas pipe network remote valve regulation and control system and method based on intelligent Internet of Things. BACKGROUND

[0002] In the current operation and management of gas pipe networks, backflow risk, as one of the key hidden dangers affecting the safe operation of pipe networks, has long been widely concerned by the industry. In order to avoid the accident risks caused by gas backflow, the existing technology generally uses a fixed parameter threshold method to determine the backflow risk, such as using a preset lower limit of pipe section pressure or a valve pre-pressure drop threshold as a trigger condition. Once the preset value is exceeded, it is determined that there is a backflow risk, and a valve locking response is triggered. This kind of method has certain reference value under stable system conditions, and is especially suitable for scenes with simple structure and small environmental fluctuations, and can realize basic safety protection.

[0003] However, in the actual operation process of gas pipe networks, due to the influence of factors such as complex pipe network structure, gradual evolution of sealing performance of terminal valves due to long-term service, and frequent pressure disturbance, the fixed parameter threshold is difficult to accurately identify the risk change trend in many cases. On the one hand, the abnormal characteristics of the early stage of part of the sealing performance degradation are not obvious, and the threshold early warning is not triggered, which has the risk of missing judgment. On the other hand, short-time working condition fluctuations easily cause misjudgment, triggering unnecessary valve action and affecting system stability. Therefore, how to construct a method that can identify the evolution characteristics of the terminal valve state in real time and dynamically adjust the backflow risk determination strategy has become a key problem that the current technology urgently needs to break through. SUMMARY

[0004] The purpose of the present application is to provide a gas pipe network remote valve regulation and control system and method based on intelligent Internet of Things, which aims to solve the problems raised in the background art.

[0005] The present application is implemented as follows. The gas pipe network remote valve regulation and control method based on intelligent Internet of Things comprises:

[0006] obtaining an initial backflow risk value of a target pipe region and historical data of a downstream pipe section terminal valve corresponding to the target pipe region, analyzing the historical data, extracting a plurality of valve closing action samples that meet stable working condition conditions, obtaining a historical valve closing action duration corresponding to the valve closing action samples and a historical valve pre-pressure drop value within a preset time period after the valve closing action is completed;

[0007] calling a preset reference model to obtain a standard valve closing action duration change trend consistent with the type of the target pipe region and the downstream pipe section terminal valve;

[0008] a deviation between the average change slope of the historical valve closing action duration change trend and the average change slope of the standard valve closing action duration change trend is analyzed, and it is determined whether the deviation is greater than a preset slope deviation threshold value;

[0009] If the condition that the deviation is greater than the preset slope deviation threshold value is met, a plurality of specific time nodes are selected, and corresponding historical valve front pressure drop values and standard valve front pressure drop values in each specific time node are extracted;

[0010] A relative difference rate between the valve front pressure drop values at each specific time node is calculated, and a correction factor is generated based on the set of relative difference rates. The initial backflow risk value is corrected using the correction factor to obtain a corrected backflow risk value, which is used to regulate the remote valve locking strategy of the target pipeline region.

[0011] As a further limitation of the technical scheme of the embodiments of the present application, the standard valve action trend model is formed by collecting a plurality of sample data formed during the execution of a plurality of closing actions over time under normal loss conditions for different types of pipeline regions and corresponding downstream pipe segment end valves. The sample data includes the duration of each closing action and the valve front pressure drop value within a preset time period after the completion of the closing action. The standard valve action trend model is constructed based on the above-mentioned samples and is used to represent the standard change trend of the valve closing action duration of the corresponding downstream pipe segment end valve of the target pipeline region over time.

[0012] As a further limitation of the technical scheme of the embodiments of the present application, the step of analyzing the deviation between the average change slope of the historical valve closing action duration change trend and the average change slope of the standard valve closing action duration change trend includes:

[0013] All historical valve closing action samples of the downstream pipe segment end valve corresponding to the target pipeline region from the start of use to the current time point are selected from the historical data, and the historical valve closing action durations corresponding to the historical valve closing action samples are arranged in chronological order to construct the historical valve closing action duration change trend;

[0014] The standard valve closing action duration change trend corresponding to the above-mentioned running time period is extracted from the standard valve action trend model;

[0015] The first average change slope of the historical valve closing action duration change trend and the second average change slope of the standard valve closing action duration change trend are calculated respectively;

[0016] The deviation amplitude is determined by subtracting the second average change slope from the first average change slope, and dividing the difference by the second average change slope.

[0017] As a further limitation of the technical scheme of the embodiment of the application, if the deviation amplitude is greater than the preset slope deviation threshold, a plurality of specific time nodes are selected, and the steps of extracting the corresponding historical valve pre-pressure micro-drop value and the standard valve pre-pressure micro-drop value at each specific time node include:

[0018] On the premise that the deviation amplitude is greater than the preset slope deviation threshold, a plurality of specific time nodes are selected based on the historical valve closing action duration change trend, and the specific time nodes need to satisfy any one of the following conditions: the historical action duration change rate at the node jumps significantly compared to the previous node, or the corresponding historical valve pre-pressure micro-drop value has a fluctuation surge or a sudden drop.

[0019] The historical valve pre-pressure micro-drop value and the standard valve pre-pressure micro-drop value corresponding to each specific time node are extracted from the historical valve closing action duration change trend and the standard valve closing action duration change trend, respectively.

[0020] As a further limitation of the technical scheme of the embodiment of the application, the relative difference rate between the valve pre-pressure micro-drop values at each specific time node is calculated, and a correction factor is generated based on the relative difference rate set. The initial backflow risk value is corrected using the correction factor to obtain a corrected backflow risk value, which is used to regulate the remote valve locking strategy of the target pipeline region.

[0021] The relative difference rate between the historical valve pre-pressure micro-drop value and the standard valve pre-pressure micro-drop value at each specific time node is calculated, and the relative difference rates are collected to obtain a relative difference rate set;

[0022] The average value of all relative difference rates in the relative difference rate set is calculated and used as a correction factor;

[0023] The preset backflow risk value correction function is retrieved, and the initial backflow risk value is corrected in combination with the correction factor to obtain a corrected backflow risk value;

[0024] The corrected backflow risk value is compared with the risk determination threshold, and the remote valve locking response strategy of the target pipeline region is dynamically adjusted to achieve preventive regulation of backflow risk.

[0025] As a further limitation of the technical scheme of the embodiment of the application, the backflow risk value correction function is:

[0026] ;

[0027] wherein, denotes the revised backflow risk value, denotes the initial backflow risk value, denotes the total number of specific time nodes, denotes the historical pre-valve pressure micro-drop value corresponding to the th specific time node, denotes the historical pre-valve pressure micro-drop value corresponding to the th specific time node, denotes the standard pre-valve pressure micro-drop value corresponding to the th specific time node;

[0028] denotes the relative difference rate between the historical pre-valve pressure micro-drop value and the standard pre-valve pressure micro-drop value at the th specific time node, denotes the revision factor, which is the average value of the relative difference rates corresponding to all specific time nodes, denotes the adjustment coefficient of the revision factor, and is greater than 0.

[0029] The intelligent Internet of Things-based remote valve control system for gas pipeline network comprises a data acquisition module, a standard trend extraction module, a deviation amplitude judgment module, a specific data extraction module, and a revision module, wherein:

[0030] The data acquisition module is configured to acquire an initial backflow risk value of a target pipeline region and historical data of a downstream pipe section end valve corresponding to the target pipeline region, analyze the historical data, extract a plurality of valve closing action samples under stable working conditions, and acquire historical valve closing action duration and historical pre-valve pressure micro-drop values within a preset time period after the valve closing action is completed.

[0031] The standard trend extraction module is configured to call a preset reference model to acquire a standard valve closing action duration change trend consistent with the target pipeline region and the type of the downstream pipe section end valve. The standard valve action trend model is constructed based on sample data collected under normal loss conditions, and is used to represent the standard change trend of the valve closing action duration of the downstream pipe section end valve corresponding to the target pipeline region over time.

[0032] ​​The deviation amplitude judgment module is configured to analyze a deviation amplitude between the average change slope of the historical valve closing action duration change trend and the average change slope of the standard valve closing action duration change trend, and determine whether the deviation amplitude is greater than a preset slope deviation threshold value;

[0033] The specific data extraction module is configured to select a plurality of specific time nodes and extract the historical valve front pressure micro-drop value and the standard valve front pressure micro-drop value corresponding to each specific time node if the condition that the deviation amplitude is greater than the preset slope deviation threshold value is met.

[0034] The correction module is configured to calculate a relative difference rate between the valve front pressure micro-drop values at each specific time node, generate a correction factor based on a set of the relative difference rates, correct the initial backflow risk value by using the correction factor, and obtain a corrected backflow risk value for use in regulating a remote valve closing strategy for the target pipeline region.

[0035] As a further limitation of the technical scheme of the embodiment of the present application, the deviation amplitude judgment module specifically comprises:

[0036] The historical trend construction unit is configured to select all historical valve closing action samples of the downstream pipe section end valve of the target pipeline region from the historical data, from when the valve was put into use to the current time point, and arrange the historical valve closing action durations corresponding to the historical valve closing action samples in chronological order to construct a historical valve closing action duration change trend.

[0037] The standard trend extraction unit is configured to extract a standard valve closing action duration change trend corresponding to the above-mentioned operation time period from the standard valve action trend model.

[0038] The slope calculation unit is configured to calculate a first average change slope of the historical valve closing action duration change trend and a second average change slope of the standard valve closing action duration change trend, respectively.

[0039] The deviation judgment unit is configured to obtain a difference value by subtracting the second average change slope from the first average change slope, and obtain a deviation amplitude by dividing the difference value by the second average change slope, and determine whether the deviation amplitude exceeds the preset slope deviation threshold value.

[0040] As a further limitation of the technical scheme of the embodiment of the present application, the specific data extraction module specifically comprises:

[0041] The node screening unit is configured to select a plurality of specific time nodes based on the historical valve closing action duration change trend on the premise that the deviation amplitude is greater than the preset slope deviation threshold, and the specific time nodes need to meet any one of the following conditions: the historical action duration change rate at the node significantly jumps compared with the previous node, or the corresponding historical valve front pressure micro-drop value has a feature of sudden increase or sudden decrease.

[0042] The data extraction unit is configured to extract the historical valve front pressure micro-drop value and the standard valve front pressure micro-drop value corresponding to each specific time node from the historical valve closing action duration change trend and the standard valve closing action duration change trend, respectively.

[0043] As a further limitation of the technical scheme of the embodiment of the present application, the correction module specifically includes:

[0044] The relative difference calculation unit is configured to calculate the relative difference rate between the historical valve front pressure micro-drop value and the standard valve front pressure micro-drop value at each specific time node, and collect these relative difference rates to obtain a relative difference rate set;

[0045] The correction factor generation unit is configured to calculate the average value of all relative difference rates in the relative difference rate set, and take it as a correction factor;

[0046] The risk value correction unit is configured to call a preset backflow risk value correction function, and correct the initial backflow risk value in combination with the correction factor to obtain a corrected backflow risk value;

[0047] The strategy regulation unit is configured to compare the corrected backflow risk value with a risk judgment threshold, dynamically adjust the remote valve locking response strategy of the target pipeline region, and realize preventive regulation of the backflow risk;

[0048] The backflow risk value correction function is:

[0049] ;

[0050] Wherein, denotes the corrected backflow risk value, denotes the initial backflow risk value, denotes the total number of specific time nodes, denotes the historical valve front pressure micro-drop value corresponding to the i-th specific time node, denotes the standard valve front pressure micro-drop value corresponding to the i-th specific time node.

[0051] denotes the historical valve front pressure micro-drop value corresponding to the i-th specific time node, ​​a relative difference rate between the historical pre-valve pressure drop value and the standard pre-valve pressure drop value at a specific time node, refers to a correction factor, i.e., an average value of the relative difference rates corresponding to all specific time nodes, refers to a regulation coefficient of the correction factor, and is greater than 0.

[0052] Compared with the prior art, the present application has the following beneficial effects:

[0053] The present application realizes dynamic perception of the evolution state of the sealing performance of the terminal valve by constructing a joint analysis mechanism based on the difference between the change trend of the valve closing action duration and the pre-valve pressure drop value, first introducing a slope deviation judgment and a correction factor generation mode of the pressure drop relative difference rate at a specific time node. Compared with the existing backflow risk evaluation method based on fixed parameter threshold, the present application can complete risk discrimination at an early stage of abnormal trend and quantitatively correct the backflow risk value, thereby promoting intelligent adjustment of the remote valve locking strategy. The method has good adaptability, real-time performance and engineering application value, and can effectively improve the safety regulation and control capability of the gas pipeline network. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The flowchart of the method provided for the embodiment of the present application;

[0055] Figure 2 The flowchart of the trend deviation identification based on the slope deviation amplitude judgment in the method provided for the embodiment of the present application;

[0056] Figure 3 The flowchart of the pressure drop feature positioning based on the specific time node extraction in the method provided for the embodiment of the present application;

[0057] Figure 4 The flowchart of the correction factor generation based on the relative difference rate and the correction of the backflow risk value in the method provided for the embodiment of the present application;

[0058] Figure 5 The application architecture diagram of the system provided for the embodiment of the present application;

[0059] Figure 6 The structural block diagram of the deviation amplitude judgment module in the system provided for the embodiment of the present application;

[0060] Figure 7 The structural block diagram of the specific data extraction module in the system provided for the embodiment of the present application;

[0061] Figure 8 The structural block diagram of the correction module in the system provided for the embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0063] Figure 1 A flow chart of the method provided by the embodiment of the present application is shown.

[0064] Specifically, a gas pipeline network remote valve control method based on intelligent Internet of Things, the method specifically comprises the following steps:

[0065] In step S100, the initial backflow risk value of the target pipeline region and the historical data of the downstream pipe segment end valve corresponding to the target pipeline region are obtained, the historical data is analyzed, a plurality of valve closing action samples under stable working condition are extracted, the historical valve closing action duration corresponding to the valve closing action samples and the historical pre-valve pressure drop value within a preset time period after the valve closing action is completed are obtained.

[0066] In the embodiment of the present application, the target pipeline region refers to a specific delivery paragraph set as a potential backflow risk monitoring object in the current gas pipeline network structure. The region is usually upstream of a certain gas supply subarea or pressure regulating node in the dispatching control system, and its operating state may be affected by the reverse influence of the downstream structure or the end valve state change, and has the physical conditions of backflow risk triggering.

[0067] The initial backflow risk value refers to the original backflow risk level evaluated according to the basic operating state, structural characteristics and existing model rules of the current target pipeline region before risk correction. It is used as the starting basis for risk judgment, and is used to reflect the backflow tendency of the target region under normal model analysis. In the prior art, the initial backflow risk value is usually generated based on static working condition simulation, negative pressure response model or experience criterion library evaluation. For example, some systems will use expert systems or rule-based scoring methods to calculate the value according to the pressure drop rate detected by the pressure sensor, the frequency of end valve operation, the flow mutation mode and other data. The initial backflow risk value is often compared with the system preset risk judgment threshold value, when it is higher than the threshold value, the system may start the early warning mechanism, close part of the pipe segment, or adjust the gas supply strategy, so as to avoid potential backflow events.

[0068] Downstream pipe section end valve refers to the end control valve in the downstream branch adjacent to the target pipeline area, closest to the end position of the target area. The valve is usually located near the inlet of the end-use gas facility or regulating equipment, and its closed state has a key impact on the gas flow stability of the target area. The present invention focuses on the possible decline in sealing performance of such end valve after long-term operation (such as valve core aging, valve seat wear, etc.), which may cause micro-leakage of the valve in the nominal "closed" state, triggering the reversal of the pressure difference inside the target pipeline area and causing the risk of backflow.

[0069] Historical data refers to the operation information associated with the target area and its downstream end valve collected and stored during the past operation period, typically including: historical valve operation log (including opening and closing actions and duration), pressure sensor record (including pre-valve pressure time series), gas flow rate change record, event trigger timestamp, environmental temperature / humidity, etc. Data sources may include SCADA systems, edge node controllers, local intelligent sensor modules, and cloud scheduling databases, etc.

[0070] Stable working condition refers to the operation state of the target pipeline area within a certain time period without being disturbed by sudden events, such as the absence of external construction disturbance, large-scale pressure regulation operation, pipe section switching, gas use peak impact, etc. Only data extracted under such working conditions can reflect the real influence of the end valve on the backflow trend, avoiding interference from atypical external factors.

[0071] Valve closure refers to the operation cycle of the system issuing a closing instruction to the downstream pipe section end valve and executing it. The action process is usually initiated by the control module, implemented by electromagnetic actuators or pneumatic devices, and finally confirmed by the sensor through the valve position state.

[0072] Historical valve closure action duration refers to the time interval from the start of the valve closing instruction to the system confirming its complete closing state, reflecting the response efficiency and indirect characteristics of the sealing performance of the valve in specific operation. This indicator can usually be obtained through valve position sensors, actuator feedback signals, or control instruction time sequence records in intelligent control systems.

[0073] Historical pre-valve pressure drop value refers to the small drop value of the pressure in the pre-valve pipe network in the target area within a preset observation period after the valve executes the closing operation, reflecting the internal pressure release trend or reverse leakage trend of the area after the valve is closed. Its value can be obtained by high-precision pressure sensors, which is the data that can be routinely obtained in existing intelligent gas monitoring systems.

[0074] The reason for selecting these two data is that the valve closing action duration directly reflects the actual operating condition and response agility of the valve, and if there is a continuous increase, it may indicate that the closing efficiency is decreased or the mechanical resistance is increased; and the historical valve front pressure drop value reveals whether there is an abnormal pressure difference evolution in the "closing" state, especially in the background of sealing wear, the value may be abnormally enlarged, becoming an early signal of the reverse flow trend. Therefore, the two indicators can cooperatively depict the evolution trend of the valve performance, and assist in identifying the condition that needs to further correct the reverse flow risk value.

[0075] Further, the gas pipeline network remote valve control method based on intelligent Internet of Things further comprises the following steps:

[0076] In step S200, a preset reference model is called to obtain a standard valve closing action duration change trend consistent with the target pipeline region and the type of the downstream pipe section end valve.

[0077] The standard valve action trend model is a structured time evolution model constructed by collecting and analyzing representative historical operation samples under ideal working conditions. The model has a clear source of acquisition and implementation basis, and can be applied to an actual gas pipeline network control system to provide a standard reference for early identification and dynamic correction of reverse flow risk.

[0078] In the embodiment of the present application, the full name of the preset reference model is a standard valve action trend model. This model is a structured time evolution model constructed by collecting and analyzing representative historical operation samples under ideal working conditions. The model has a clear source of acquisition and implementation basis, and can be applied to an actual gas pipeline network control system to provide a standard reference for early identification and dynamic correction of reverse flow risk.

[0079] The standard valve action trend model is derived from long-term operation data collection and structured analysis of different types of target pipeline regions and their downstream pipe section end valves. Specifically, in the model construction process, first, a number of standard sample regions with excellent running state, no significant leakage, and no influence of wear are selected, which require to contain multiple valve closing action records and cover a typical period from the initial investment to the medium-term service stage. On this basis, the action duration of each closing action of the valve in each sample region is called, and the valve front pressure drop value in a preset time period after each closing action is formed into a complete structured sample data set.

[0080] The model is mainly constructed by applying time series analysis and trend normalization processing technology. After the sample collection is completed, firstly, the sequence of the duration of the shutdown action is smoothed and the first derivative is extracted to identify the evolution trend of the average response time; then the data collected in different samples are normalized and aligned, and the sliding window method is used to eliminate the influence of short-term fluctuations, and finally the average change trend of the valve under standard working conditions is extracted as the running time changes. The whole modeling process supports automatic completion through the industrial big data platform, gas scheduling system or historical monitoring log platform, has a stable engineering implementation path, and has good compatibility with the existing SCADA system and IoT sensing network.

[0081] The core content reflected by the standard valve action trend model is: under the premise that there is no interference of abnormal wear, leakage, aging and other factors, how does the action response behavior of the valve at the end of the downstream pipe section of a specific type evolve over time in long-period operation, especially whether there is a natural growth trend in the duration of the shutdown action of the valve, and the slope change characteristics of the trend. By comparing the actual collected historical valve shutdown action duration in the target pipeline area with the standard trend, it can be identified whether the current valve has shown signs of deviation from the standard model, and then it can be judged whether the reverse flow risk assessment of the region is underestimated, thereby supporting the subsequent dynamic correction process. Therefore, the model not only has significant engineering usability, but also logically constitutes the core discriminant criterion in the dynamic identification mechanism of reverse flow risk.

[0082] Further, the gas pipeline network remote valve control method based on intelligent Internet of Things further comprises the following steps:

[0083] Step S300, analyze the deviation amplitude between the average change slope of the historical valve shutdown action duration change trend and the average change slope of the standard valve shutdown action duration change trend, and determine whether it is greater than the preset slope deviation threshold.

[0084] Specifically, Figure 2 A flowchart of trend deviation identification based on slope deviation amplitude judgment is shown.

[0085] Among them, analyzing the deviation amplitude between the average change slope of the historical valve shutdown action duration change trend and the average change slope of the standard valve shutdown action duration change trend, and determining whether it is greater than the preset slope deviation threshold specifically comprises the following steps:

[0086] Step S301, select all historical valve shutdown action samples of the downstream pipe section end valve corresponding to the target pipeline area from the start of use to the current time point from the historical data, and arrange the historical valve shutdown action duration corresponding to the historical valve shutdown action sample in chronological order to construct the historical valve shutdown action duration change trend;

[0087] Step S302, extracting the standard valve closing action duration change trend corresponding to the above-mentioned operation time period from the standard valve action trend model;

[0088] Step S303, respectively calculating the first average change slope of the historical valve closing action duration change trend and the second average change slope of the standard valve closing action duration change trend;

[0089] Step S304, obtaining the difference value by subtracting the second average change slope from the first average change slope, and obtaining the deviation amplitude by dividing the difference value by the second average change slope, and judging whether the deviation amplitude exceeds the preset slope deviation threshold.

[0090] In the embodiment of the present application, the specific process of step S303 is that the historical valve closing action duration change trend constructed is first processed, the action duration of each historical sample point is recognized through time series analysis means, and a trend line is constructed in time sequence based on these samples, and then the average change rate of the trend line in the whole cycle range is calculated as the first average change slope. Similarly, the average change rate of the standard valve closing action duration change trend extracted from the standard valve action trend model is also calculated in the same way as the second average change slope.

[0091] In step S304, by comparing the deviation between the above-mentioned two average change slopes, a deviation amplitude for measuring the change trend deviation is calculated, and it is judged whether the deviation amplitude exceeds the slope deviation threshold set by the system in advance. The purpose of this judgment is to identify whether the valve operating state in the target pipeline region has deviated significantly from the standard evolution trend.

[0092] The judgment process reflects whether there is a potential risk of sealing performance aging, wear aggravation or action imbalance in the actual operation of the valve in the target region. Through the identification of the evolution trend rate, abnormal signals that are not easy to directly perceive can be found early, which has good foresight and intervention value.

[0093] The setting of the preset slope deviation threshold is usually based on a large number of standard operation samples, and the normal change rate range of each sample is extracted for normalized statistics, and then combined with the sensitivity requirement of the system for risk control, the final threshold is determined by artificial experience or data-driven model to balance the possibility of false positives and missed judgments.

[0094] In addition, in the deviation amplitude judgment mode, in addition to the currently adopted slope ratio mode, the absolute deviation comparison of historical trend and standard trend, sliding window difference accumulation value analysis, or trend direction comparison through similarity matching algorithm can also be used. These alternative modes can be selected according to specific working conditions to enhance the recognition ability of the system to different risk modes.

[0095] Further, the intelligent Internet of Things based gas pipe network remote valve regulation method further comprises the following steps:

[0096] Step S400, if the condition that the deviation amplitude is greater than the preset slope deviation threshold is met, a plurality of specific time nodes are selected, and the corresponding historical valve front pressure micro-drop value and standard valve front pressure micro-drop value in each specific time node are extracted.

[0097] Specifically, Figure 3 A flow chart of pressure micro-drop feature positioning based on specific time node extraction is shown.

[0098] If the condition that the deviation amplitude is greater than the preset slope deviation threshold is met, a plurality of specific time nodes are selected, and the corresponding historical valve front pressure micro-drop value and standard valve front pressure micro-drop value in each specific time node are extracted, specifically including the following steps:

[0099] Step S401, on the premise that the deviation amplitude is greater than the preset slope deviation threshold, a plurality of specific time nodes are selected based on the historical valve closing action duration change trend, and the specific time nodes need to meet any of the following conditions: the historical action duration change rate at the node jumps significantly compared with the previous node, or the corresponding historical valve front pressure micro-drop value has a fluctuation surge or a sudden drop;

[0100] Step S402, the historical valve front pressure micro-drop value and the standard valve front pressure micro-drop value corresponding to each specific time node are extracted from the historical valve closing action duration change trend and the standard valve closing action duration change trend, respectively.

[0101] In the embodiment of the application, the selection of the specific time node aims to accurately identify the abnormal change period that may appear in the running trend of the downstream pipe section end valve in the target pipe region, so as to subsequently extract and analyze the valve front pressure micro-drop value.

[0102] The selection conditions of the specific time node include the following two types:

[0103] One category is that the change rate of the action duration at the node is significantly different from the previous node, that is, the duration change gradient at the location of the node is significantly higher or lower than the previous node, indicating that the time response characteristic of the valve closing action at this stage has changed abruptly, which may correspond to the rapid deterioration of the sealing performance, the resistance change or the abnormal response mechanism of the system.

[0104] Another category is that the historical pressure drop value before the valve corresponding to the node shows a sudden increase or decrease in fluctuation characteristics. This type of pressure drop value anomaly usually reflects the abnormal pressure difference feedback of the valve during the closing process, which may be related to factors such as valve wear, seal deformation or internal flow structure change. Therefore, the identification of such nodes is of key significance for capturing early abnormal risks.

[0105] The above two types of nodes can be screened by setting a change rate threshold and a fluctuation detection index to ensure that the selected specific time nodes reflect the key variation information in the running trend, improving the response accuracy of the subsequent correction factor.

[0106] In step S402, for each specific time node that has been determined, the historical pressure drop value before the valve corresponding to the time node is read from the historical valve closing action duration change trend, and the standard pressure drop value before the valve corresponding to the time node is read from the standard valve action trend model. To ensure correspondence, time axis unified mapping processing can be performed on the two types of trend curves to ensure that each node has a clear bidirectional value reference. The extracted two types of data will be used to calculate the relative difference rate as the basis for the subsequent correction factor. This process is usually implemented with the help of structured data indexing technology or timestamp-based matching algorithm, which has a clear and practical engineering implementation path.

[0107] Further, the gas pipeline network remote valve control method based on intelligent Internet of Things further comprises the following steps:

[0108] Step S500, calculate the relative difference rate between the pressure drop values before the valve at each specific time node, and generate a correction factor based on the set of relative difference rates. The initial backflow risk value is corrected using the correction factor to obtain a corrected backflow risk value for the remote valve locking strategy of the target pipeline area.

[0109] Specifically, Figure 4 A flowchart for generating a correction factor based on a relative difference rate and correcting a backflow risk value is shown.

[0110] Among them, calculating the relative difference rate between the pressure drop values before the valve at each specific time node, and generating a correction factor based on the set of relative difference rates. The initial backflow risk value is corrected using the correction factor to obtain a corrected backflow risk value for the remote valve locking strategy of the target pipeline area specifically includes the following steps:

[0111] Step S501, calculating the relative difference rate between the historical valve inlet pressure drop value and the standard valve inlet pressure drop value at each specific time node, and collecting these relative difference rates to obtain a relative difference rate set;

[0112] Step S502, calculating the average of all relative difference rates in the relative difference rate set and using it as a correction factor;

[0113] Step S503: Retrieve a preset backflow risk value correction function, and correct the initial backflow risk value in combination with the correction factor to obtain a corrected backflow risk value;

[0114] Step S504 : comparing the corrected backflow risk value with the risk determination threshold, and dynamically adjusting the remote valve locking response strategy of the target pipeline area to achieve preventive control of the backflow risk.

[0115] The backflow risk value correction function is:

[0116] ;

[0117] in, Refers to the corrected backflow risk value, Refers to the initial backflow risk value, Refers to the total number of nodes at a specific time. Refers to the The historical pressure drop value before the valve corresponding to a specific time node, Refers to the The standard valve front pressure drop value corresponding to a specific time node;

[0118] Refers to the The relative difference rate between the historical valve front pressure drop value and the standard valve front pressure drop value at a specific time node, Refers to the correction factor, which is the average value of the relative difference rate corresponding to all specific time nodes. is the adjustment coefficient of the correction factor, and Greater than 0.

[0119] In the embodiment of the present application, the reason why the relative difference rate between the historical valve pre-pressure micro-drop value and the standard valve pre-pressure micro-drop value is selected as the key basis for constructing the correction factor is mainly because the relative difference rate can directly reflect the difference between the actual sealing state of the valve at the end of the downstream pipe section and the ideal sealing state thereof. In the ideal sealing working condition, after the valve completes the closing action, the pre-valve pressure should show a regular micro-decrease in a short time. If there is a sealing fatigue or leakage hidden danger, the decrease amplitude often shows an atypical fluctuation, thereby causing a deviation between the historical micro-drop value and the standard value. Therefore, by constructing the relative difference rate, the early deviation signal in the gradual attenuation process of the valve performance can be sensitively captured.

[0120] The average of the above relative difference rates is taken to generate the correction factor, which has two important significances: one is that the individual fluctuation reflected by each specific time node can be balanced, and the stability and anti-interference ability of the overall evaluation are improved; the other is that the distortion of the correction result caused by the extreme data of an abnormal time point is avoided, thereby ensuring that the generated correction factor can more truly reflect the deviation trend of the overall risk level of the target region at the current stage.

[0121] In specific application, the correction factor will act on the initial backflow risk value to weight and amplify it. For example, if the initial backflow risk value is 0.45 and the correction factor is 0.2, the risk value calculated after weighting by the adjustment coefficient will be increased to about 0.54. In this way, the potential backflow risk rising trend caused by the abnormal sealing performance of the downstream valve can be effectively identified, and a higher level of lockout response strategy of the subsequent remote control system to the region is prompted.

[0122] The step S504 is introduced just to feed back the above correction result to the control strategy layer. After obtaining the corrected backflow risk value, the system compares it with the preset risk judgment threshold. For example, if the risk threshold is set to 0.5, and the above correction result is 0.54, it means that there is a warning signal of too high backflow risk in the current region. At this time, the system will trigger the measures to improve the level of valve lockout, including but not limited to the control actions such as closing the warning pipe section in advance, prolonging the valve holding time, activating the backup on-off path, etc., so as to intervene in the risk scenario that may evolve into an accident in advance, and realize the goal of "preventive regulation".

[0123] In summary, the present application dynamically corrects the backflow risk value by comparing the difference between the historical data and the standard model, effectively makes up for the deficiency that the existing static evaluation method cannot identify the evolution trend of sealing fatigue, and has significant technical advantages and engineering practical value in ensuring the safe operation of the pipe network.

[0124] Further, Figure 5 The application architecture diagram of the system provided by the embodiment of the present application is shown.

[0125] In a further preferred embodiment provided by the present application, a gas pipeline network remote valve control system based on intelligent Internet of Things comprises:

[0126] The data acquisition module 100 is configured to acquire an initial backflow risk value of a target pipeline region and historical data of a downstream pipe section end valve corresponding to the target pipeline region, analyze the historical data, extract a plurality of valve closing action samples under stable working condition conditions, and acquire a historical valve closing action duration corresponding to the valve closing action samples and a historical pre-valve pressure drop value within a preset time period after completion of the valve closing action.

[0127] Further, the gas pipeline network remote valve control system based on intelligent Internet of Things further comprises:

[0128] The standard trend extraction module 200 is configured to call a preset reference model to acquire a standard valve closing action duration change trend consistent with the target pipeline region and the downstream pipe section end valve type.

[0129] The standard valve action trend model is a plurality of sample data formed in the process of performing a plurality of closing actions over time under normal loss state for different types of pipeline regions and downstream pipe section end valves corresponding thereto under ideal working conditions. The sample data includes the duration of each closing action and the pre-valve pressure drop value within a preset time period after completion of the closing action.

[0130] The standard valve action trend model is constructed based on the above-mentioned sample data and is used to represent the standard change trend of the valve closing action duration of the downstream pipe section end valve corresponding to the target pipeline region over the running time.

[0131] Further, the gas pipeline network remote valve control system based on intelligent Internet of Things further comprises:

[0132] The deviation amplitude judgment module 300 is configured to analyze the deviation amplitude between the average change slope of the historical valve closing action duration change trend and the average change slope of the standard valve closing action duration change trend, and judge whether it is greater than a preset slope deviation threshold.

[0133] Specifically, Figure 6 The structure block diagram of the deviation amplitude judgment module 300 in the system provided by the embodiment of the present application is shown.

[0134] In a preferred embodiment provided by the present application, the deviation amplitude judgment module 300 specifically comprises:

[0135] The historical trend construction unit 301 is configured to select all historical valve closing action samples of the valve at the end of the downstream pipe section corresponding to the target pipe area from the historical data from when the valve was put into use to the current time point, and arrange the historical valve closing action duration corresponding to the historical valve closing action samples in chronological order to construct a historical valve closing action duration change trend.

[0136] The standard trend extraction unit 302 is configured to extract a standard valve closing action duration change trend corresponding to the above running time period from the standard valve action trend model.

[0137] The slope calculation unit 303 is configured to calculate a first average change slope of the historical valve closing action duration change trend and a second average change slope of the standard valve closing action duration change trend, respectively.

[0138] The deviation judgment unit 304 is configured to obtain a difference value by subtracting the second average change slope from the first average change slope, and obtain a deviation amplitude by dividing the difference value by the second average change slope, and judge whether the deviation amplitude exceeds a preset slope deviation threshold.

[0139] Further, the gas pipe network remote valve regulation system based on intelligent Internet of Things further comprises:

[0140] The specific data extraction module 400 is configured to select a plurality of specific time nodes and extract the historical valve pre-pressure micro-decrease value and the standard valve pre-pressure micro-decrease value corresponding to each specific time node if the condition that the deviation amplitude is greater than the preset slope deviation threshold is met.

[0141] Specifically, Figure 7 The structure block diagram of the specific data extraction module 400 in the system provided by the embodiment of the application is shown.

[0142] In the preferred embodiment provided by the application, the specific data extraction module 400 specifically comprises:

[0143] The node screening unit 401 is configured to select a plurality of specific time nodes based on the historical valve closing action duration change trend on the premise that the deviation amplitude is greater than the preset slope deviation threshold, and the specific time node needs to meet any one of the following conditions: the historical action duration change rate at the node significantly jumps compared with the previous node, or the corresponding historical valve pre-pressure micro-decrease value has the characteristics of sudden increase or sudden decrease.

[0144] The data extraction unit 402 is configured to extract the historical valve pre-pressure micro-decrease value and the standard valve pre-pressure micro-decrease value corresponding to each specific time node from the historical valve closing action duration change trend and the standard valve closing action duration change trend, respectively.

[0145] Furthermore, the gas pipe network remote valve control system based on intelligent Internet of Things also includes:

[0146] Correction module 500 is used to calculate the relative difference rate between the valve front pressure drop values ​​at each specific time node, and generate a correction factor based on the relative difference rate set. The correction factor is used to correct the initial backflow risk value to obtain a corrected backflow risk value for regulating the remote valve locking strategy of the target pipeline area.

[0147] Specifically, Figure 8 FIG. 5 shows a structural block diagram of the correction module 500 in the system provided by an embodiment of the present invention.

[0148] In a preferred embodiment of the present invention, the correction module 500 specifically includes:

[0149] The relative difference calculation unit 501 is used to calculate the relative difference rate between the historical pre-valve pressure drop value and the standard pre-valve pressure drop value at each specific time node, and collect these relative difference rates to obtain a relative difference rate set;

[0150] The correction factor generating unit 502 is used to calculate the average value of all relative difference rates in the relative difference rate set and use it as the correction factor;

[0151] The risk value correction unit 503 is used to call a preset backflow risk value correction function and correct the initial backflow risk value in combination with the correction factor to obtain a corrected backflow risk value;

[0152] The strategy control unit 504 is used to compare the corrected backflow risk value with the risk determination threshold and dynamically adjust the remote valve locking response strategy of the target pipeline area to achieve preventive control of the backflow risk;

[0153] The backflow risk value correction function is:

[0154] ;

[0155] in, Refers to the corrected backflow risk value, Refers to the initial backflow risk value, Refers to the total number of nodes at a specific time. Refers to the The historical pressure drop value before the valve corresponding to a specific time node, Refers to the The standard valve front pressure drop value corresponding to a specific time node;

[0156] Refers to the a relative difference rate between the historical pre-valve pressure drop value and the standard pre-valve pressure drop value at a specific time node, refers to a correction factor, i.e., an average of the relative difference rates corresponding to all specific time nodes, refers to a regulation coefficient of the correction factor, and is greater than 0.

[0157] It should be understood that although each step in the flowchart of each embodiment of the present application is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless explicitly stated herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least a part of other steps or sub-steps or stages of other steps.

[0158] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments of each method. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0159] Each technical feature of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of each technical feature in the above-mentioned embodiments are described, however, as long as the combination of these technical features does not exist contradictory, it should be considered as the scope of the present application.

[0160] The above embodiments only express several implementation manners of the present application, which are described in a more specific and detailed manner, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

[0161] The above only describes the preferred embodiments of the present application, and should not be used to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A remote valve control method for a gas pipeline network based on intelligent Internet of Things, characterized in that: The method comprises: Obtain the initial backflow risk value of the target pipeline area and the historical data of the valve at the end of the downstream pipe section corresponding to the target pipeline area, analyze the historical data, extract several valve closing action samples that meet stable operating conditions, obtain the historical valve closing action duration corresponding to the valve closing action samples, and the historical valve inlet pressure drop value within a preset time period after the valve closing action is completed; Call the preset reference model to obtain the duration change trend of the standard valve shut-off action that is consistent with the valve type at the end of the target pipeline area and the downstream pipe section; Analyze the deviation between the average change slope of the historical valve closing action duration change trend and the average change slope of the standard valve closing action duration change trend, and determine whether it is greater than a preset slope deviation threshold; If the deviation amplitude is greater than the preset slope deviation threshold, a number of specific time nodes are selected, and the historical valve inlet pressure drop value and the standard valve inlet pressure drop value corresponding to each specific time node are extracted; The relative difference rate between the slight drop values ​​of the valve front pressure at each specific time node is calculated, and a correction factor is generated based on the relative difference rate set. The correction factor is used to correct the initial backflow risk value to obtain the corrected backflow risk value for regulating the remote valve locking strategy of the target pipeline area.

2. The method for remote valve control of a gas pipeline network based on intelligent Internet of Things according to claim 1 is characterized in that: The standard valve action trend model is a model that, under ideal operating conditions, collects a number of sample data generated during the execution of several shut-off actions over time under normal loss conditions for different types of pipeline areas and corresponding downstream pipe end valve types. The sample data includes the duration of each shut-off action and the slight drop in the valve front pressure within a preset time period after the shut-off action is completed. The standard valve action trend model is constructed based on the above samples and is used to characterize the standard change trend of the duration of the valve shut-off action of the downstream pipe end valve corresponding to the target pipeline area as the operating time evolves.

3. The method for remote valve control of a gas pipeline network based on intelligent Internet of Things according to claim 2 is characterized in that: The steps of analyzing the deviation between the average change slope of the historical valve closing action duration change trend and the average change slope of the standard valve closing action duration change trend, and determining whether the deviation is greater than a preset slope deviation threshold include: Select all historical valve shut-off action samples from the downstream end valve of the target pipeline area from the time it was put into use to the current time point from the historical data, and arrange the historical valve shut-off action durations corresponding to the historical valve shut-off action samples in chronological order to construct a trend of changes in the historical valve shut-off action durations; Extracting the duration change trend of the standard valve shut-off action corresponding to the above-mentioned operating time period from the standard valve action trend model; Calculate the first average change slope of the historical valve closing action duration change trend and the second average change slope of the standard valve closing action duration change trend respectively; A difference is obtained by subtracting the second average change slope from the first average change slope, and the difference is divided by the second average change slope to obtain a deviation amplitude, and it is determined whether the deviation amplitude exceeds a preset slope deviation threshold.

4. The method for remote valve control of a gas pipeline network based on intelligent Internet of Things according to claim 3 is characterized in that: If the condition that the deviation amplitude is greater than the preset slope deviation threshold is met, the steps of selecting several specific time nodes and extracting the historical valve inlet pressure slight drop value and the standard valve inlet pressure slight drop value corresponding to each specific time node include: On the premise of confirming that the deviation amplitude is greater than the preset slope deviation threshold, a number of specific time nodes are selected based on the historical valve closing action duration change trend. The specific time nodes must meet any of the following conditions: the historical action duration change rate at this node has a significant jump compared with the previous node, or the corresponding historical valve front pressure drop value has a sudden increase or decrease in fluctuation; The historical valve inlet pressure drop value and the standard valve inlet pressure drop value corresponding to each specific time node are extracted from the historical valve closing action duration change trend and the standard valve closing action duration change trend respectively.

5. The method for remote valve control of a gas pipeline network based on intelligent Internet of Things according to claim 4 is characterized in that: The steps of calculating the relative difference rate between the slight drop values ​​of the valve front pressure at each specific time node, generating a correction factor based on the relative difference rate set, and using the correction factor to correct the initial backflow risk value to obtain a corrected backflow risk value for controlling the remote valve locking strategy of the target pipeline area include: Calculate the relative difference rate between the historical valve inlet pressure drop value and the standard valve inlet pressure drop value at each specific time node, and collect these relative difference rates to obtain a relative difference rate set; Calculate the average of all relative difference rates in the relative difference rate set and use it as a correction factor; Retrieve a preset backflow risk value correction function, and correct the initial backflow risk value in combination with the correction factor to obtain a corrected backflow risk value; The corrected backflow risk value is compared with the risk judgment threshold, and the remote valve locking response strategy of the target pipeline area is dynamically adjusted to achieve preventive control of the backflow risk.

6. The method for remote valve control of a gas pipeline network based on intelligent Internet of Things according to claim 5 is characterized in that: The backflow risk value correction function is: ； in, Refers to the corrected backflow risk value, Refers to the initial backflow risk value, Refers to the total number of nodes at a specific time. Refers to the The historical pressure drop value before the valve corresponding to a specific time node, Refers to the The standard valve front pressure drop value corresponding to a specific time node; Refers to the The relative difference rate between the historical valve front pressure drop value and the standard valve front pressure drop value at a specific time node, Refers to the correction factor, which is the average value of the relative difference rate corresponding to all specific time nodes. is the adjustment coefficient of the correction factor, and Greater than 0.

7. The gas pipe network remote valve control system based on intelligent Internet of Things is characterized by: The system includes: a data acquisition module, a standard trend extraction module, a deviation amplitude judgment module, a specific data extraction module and a correction module, wherein: A data acquisition module is used to obtain the initial backflow risk value of the target pipeline area and the historical data of the valve at the end of the downstream pipe section corresponding to the target pipeline area, analyze the historical data, extract several valve closing action samples that meet stable operating conditions, and obtain the historical valve closing action duration corresponding to the valve closing action samples and the historical valve inlet pressure drop value within a preset time period after the valve closing action is completed; A standard trend extraction module is used to call a preset reference model to obtain a standard valve shut-off action duration variation trend consistent with the target pipeline area and the downstream pipe segment end valve type; the standard valve action trend model is a model that, under ideal operating conditions, collects a number of sample data generated during the execution of a number of shut-off actions over time under normal loss conditions for different types of pipeline areas and their corresponding downstream pipe segment end valve types. The sample data includes the action duration of each shut-off action and the slight drop in valve front-valve pressure within a preset time period after the completion of the shut-off action. The standard valve action trend model is constructed based on the above samples and is used to characterize the standard variation trend of the valve shut-off action duration of the downstream pipe segment end valve corresponding to the target pipeline area over the operating time; The deviation amplitude judgment module is used to analyze the deviation amplitude between the average change slope of the historical valve closing action duration change trend and the average change slope of the standard valve closing action duration change trend, and judge whether it is greater than a preset slope deviation threshold; A specific data extraction module is used to select a number of specific time nodes if the deviation amplitude is greater than a preset slope deviation threshold, and extract the historical valve inlet pressure drop value and the standard valve inlet pressure drop value corresponding to each specific time node; The correction module is used to calculate the relative difference rate between the slight drop values ​​of the valve front pressure at each specific time node, and generate a correction factor based on the relative difference rate set. The correction factor is used to correct the initial backflow risk value to obtain the corrected backflow risk value for regulating the remote valve locking strategy of the target pipeline area.

8. The gas pipe network remote valve control system based on intelligent Internet of Things according to claim 7 is characterized in that: The deviation amplitude judgment module specifically includes: A historical trend construction unit is used to select all historical valve shut-off action samples of the downstream pipe section end valve corresponding to the target pipeline area from the start of use to the current time point from the historical data, and arrange the historical valve shut-off action durations corresponding to the historical valve shut-off action samples in chronological order to construct a trend of changes in the historical valve shut-off action durations; A standard trend extraction unit is used to extract a standard valve shut-off action duration change trend corresponding to the above-mentioned operating time period from a standard valve action trend model; a slope calculation unit, for respectively calculating a first average change slope of a change trend of a historical valve closing action duration and a second average change slope of a change trend of a standard valve closing action duration; The deviation judgment unit is used to obtain a difference by subtracting the second average change slope from the first average change slope, and divide the difference by the second average change slope to obtain a deviation amplitude, and judge whether the deviation amplitude exceeds a preset slope deviation threshold.

9. The gas pipe network remote valve control system based on intelligent Internet of Things according to claim 8 is characterized in that: The specific data extraction module specifically includes: The node screening unit is used to select several specific time nodes based on the historical valve closing action duration change trend, on the premise of confirming that the deviation amplitude is greater than the preset slope deviation threshold. The specific time nodes must meet any of the following conditions: the historical action duration change rate at the node has a significant jump compared with the previous node, or the corresponding historical valve pre-pressure drop value has the characteristics of a sudden increase or decrease in fluctuation. The data extraction unit is used to extract the historical valve inlet pressure slight drop value and the standard valve inlet pressure slight drop value corresponding to each specific time node from the historical valve closing action duration change trend and the standard valve closing action duration change trend respectively.

10. The gas pipe network remote valve control system based on intelligent Internet of Things according to claim 9 is characterized in that: The correction module specifically includes: The relative difference calculation unit is used to calculate the relative difference rate between the historical valve inlet pressure drop value and the standard valve inlet pressure drop value at each specific time node, and collect these relative difference rates to obtain a relative difference rate set; A correction factor generating unit, used for calculating an average value of all relative difference rates in the relative difference rate set and using the average value as a correction factor; The risk value correction unit is used to call a preset backflow risk value correction function and correct the initial backflow risk value in combination with the correction factor to obtain a corrected backflow risk value; A strategy control unit is used to compare the corrected backflow risk value with the risk determination threshold and dynamically adjust the remote valve locking response strategy of the target pipeline area to achieve preventive control of the backflow risk; The backflow risk value correction function is: ； in, Refers to the corrected backflow risk value, Refers to the initial backflow risk value, Refers to the total number of nodes at a specific time. Refers to the The historical pressure drop value before the valve corresponding to a specific time node, Refers to the The standard valve front pressure drop value corresponding to a specific time node; Refers to the The relative difference rate between the historical valve front pressure drop value and the standard valve front pressure drop value at a specific time node, Refers to the correction factor, which is the average value of the relative difference rate corresponding to all specific time nodes. is the adjustment coefficient of the correction factor, and Greater than 0.

Images