Intelligent gas pipeline differential pressure safety monitoring Internet of Things system and method and storage medium

Abstract

The invention provides an intelligent gas pipeline differential pressure safety monitoring Internet of Things system and method and a storage medium. The Internet of Things system comprises a gas company management platform and a plurality of other platforms. The method is executed by a gas company management platform and comprises the following steps: acquiring a pressure difference data matrix of a current gas pipe network; based on the pressure difference data matrix, determining an abnormity judgment result of the current gas pipe network; determining anomaly probability distribution based on the differential pressure data matrix in response to the existence of the anomaly; generating an operation instruction set based on the abnormal probability distribution; and based on the differential pressure data matrix, generating a voltage regulation instruction, the voltage regulation instruction being configured to control a voltage regulation device to perform voltage regulation. The method can also be operated after a computer instruction stored in a computer readable storage medium is read. According to the Internet of Things system and method, real-time and accurate monitoring and analysis of the pressure difference of the gas pipeline can be realized, and safe and stable operation of a gas pipeline network is ensured.

Description

Technical Field

[0001] The present invention relates to the field of pipeline monitoring, and in particular to an intelligent gas pipeline pressure difference safety monitoring Internet of Things system, method and storage medium. Background Art

[0002] As an important infrastructure for modern energy transportation, gas pipelines are responsible for the efficient transportation of natural gas, and monitoring the pressure changes in gas pipelines is crucial to the safety assessment of gas pipeline networks. If there is an abnormal pressure difference between different gas pipelines at the same time and / or the same gas pipeline at different times, it means that there may be problems such as gas leakage.

[0003] Currently, there are many ways to monitor pressure difference (such as using pressure sensors for monitoring, etc.), but there is a lack of effective means to analyze whether the pressure difference is abnormal and the causes of the pressure difference.

[0004] Therefore, a smart gas pipeline pressure difference safety monitoring Internet of Things system, method and storage medium are provided, which can realize real-time and accurate monitoring and analysis of the gas pipeline pressure difference, ensure the safe and stable operation of the gas pipeline network, and safeguard the continuity and reliability of energy supply. Summary of the invention

[0005] In order to solve the problems of abnormal analysis of pressure difference and determination of the cause of pressure difference, the present invention provides an intelligent gas pipeline pressure difference safety monitoring Internet of Things system, method and storage medium.

[0006] The invention content includes a smart gas pipeline pressure difference safety monitoring Internet of Things system, the system includes a government safety supervision management platform, a government safety supervision sensor network platform, a government safety supervision object platform, a gas company sensor network platform, a gas equipment object platform and a gas maintenance object platform; the government safety supervision object platform includes a gas company management platform; the gas company management platform is configured to: obtain a pressure difference data matrix of the current gas pipeline network, the pressure difference data matrix includes the pressure difference data of the gas pipelines in the current gas pipeline network at different time periods; based on the pressure difference data matrix, determine the abnormal judgment result of the current gas pipeline network; in response to the abnormal judgment result being an abnormality, determine the abnormality based on the pressure difference data matrix. The abnormal probability distribution of the current gas pipeline network is described; based on the abnormal probability distribution, an operation instruction set is generated, and the operation instruction set includes operation instructions corresponding to the gas pipeline, and the operation instructions include: the monitoring and control instructions are configured to adjust the monitoring frequency of the pipeline monitoring equipment; the motion control instructions are configured to instruct the pipeline inspection equipment to inspect the target gas pipeline at a preset frequency; the reporting instructions are configured to receive and record the abnormal conditions of the current gas pipeline network; the maintenance instructions are configured to dispatch staff to maintain the current gas pipeline network; based on the pressure difference data matrix, a pressure regulation instruction is generated, and the pressure regulation instruction is configured to control the pressure regulation equipment to regulate the pressure of the abnormal gas pipeline in the current gas pipeline network.

[0007] The invention content includes a smart gas pipeline pressure difference safety monitoring method, which is executed by a gas company management platform, and the method includes: obtaining a pressure difference data matrix of the current gas pipeline network, wherein the pressure difference data matrix includes pressure difference data of gas pipelines in the current gas pipeline network at different time periods; based on the pressure difference data matrix, determining an abnormal judgment result of the current gas pipeline network; in response to the abnormal judgment result being an abnormality, determining an abnormal probability distribution of the current gas pipeline network based on the pressure difference data matrix; generating an operation instruction set based on the abnormal probability distribution, wherein the operation instruction set includes a corresponding The operation instructions of the gas pipeline include: the monitoring and control instructions are configured to adjust the monitoring frequency of the pipeline monitoring equipment; the motion control instructions are configured to instruct the pipeline inspection equipment to inspect the target gas pipeline at a preset frequency; the reporting instructions are configured to receive and record abnormal conditions of the current gas pipeline network; the maintenance instructions are configured to dispatch staff to maintain the current gas pipeline network; based on the pressure difference data matrix, a pressure regulation instruction is generated, and the pressure regulation instruction is configured to control the pressure regulation equipment to regulate the pressure of abnormal gas pipelines in the current gas pipeline network.

[0008] The invention content includes a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the smart gas pipeline pressure difference safety monitoring method.

[0009] The beneficial effects brought about by the above invention include but are not limited to: (1) constructing a pressure difference data matrix through the pressure difference data of each gas pipeline at different time periods, and then accurately judging whether there is an abnormality in the current gas pipeline network, and accurately determining the abnormal probability distribution of the gas pipeline network, so as to further generate corresponding operation instructions and pressure regulation instructions, which can timely and accurately evaluate the abnormal situation of the pipeline network, and carry out targeted control, inspection, maintenance and other operations to ensure the normal operation of the gas pipeline network; (2) according to the flow data and pressure difference data matrix of the current gas pipeline network, obtaining the flow characteristic map and pressure difference characteristic map of the current gas pipeline network, and further determining the abnormal probability distribution of the current gas pipeline network, which can fully consider the gas flow and pressure difference conditions in the gas pipeline, effectively avoid misjudgment of abnormal conditions, and improve the accuracy of identifying abnormal gas pipelines; (3) through the evaluation model, based on the pipeline location characteristics and abnormal probability distribution, determine the operation instruction set, which can use the learning ability of the machine learning model to accurately evaluate the operation instruction set, thereby improving the accuracy of abnormal maintenance of gas pipelines. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein: Figure 1 It is a schematic diagram of the platform structure of the smart gas pipeline pressure difference safety monitoring Internet of Things system according to some embodiments of this specification; Figure 2 is an exemplary flow chart of a smart gas pipeline pressure difference safety monitoring method according to some embodiments of this specification; Figure 3 is an exemplary flow chart of determining anomaly probability distribution according to some embodiments of this specification; Figure 4 is an exemplary flow chart of determining an operation instruction set according to some embodiments of this specification; Figure 5 is an exemplary schematic diagram of an evaluation model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0011] The following is a brief introduction to the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0012] The "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0013] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0014] When the operations performed in the embodiments of this specification are described in steps, unless otherwise specified, the order of the steps is interchangeable, steps may be omitted, and other steps may be included in the operation process.

[0015] Figure 1 It is a schematic diagram of the platform structure of the smart gas pipeline pressure difference safety monitoring Internet of Things system shown in some embodiments of this specification.

[0016] In some embodiments, Figure 1 As shown, the smart gas pipeline pressure difference safety monitoring Internet of Things system 100 may include a government safety supervision management platform 110, a government safety supervision sensor network platform 120, a government safety supervision object platform 130, a gas company sensor network platform 140, a gas equipment object platform 150 and a gas maintenance object platform 160.

[0017] The government safety supervision and management platform 110 refers to a platform for supervision and safety management of the gas pipeline network, which can be used to coordinate the connection and collaboration between various functional platforms and provide perception management and control management functions for the Internet of Things operation system.

[0018] The government security supervision sensor network platform 120 refers to a functional platform for managing government sensor communications, and can be configured as a communication network or a gateway, etc.

[0019] In some embodiments, the government safety supervision sensor network platform 120 may interact with the government safety supervision management platform 110 upwards and interact with the government safety supervision object platform 130 downwards. For example, the government safety supervision object platform 130 may send a reporting instruction to the government safety supervision management platform 110 through the government safety supervision sensor network platform 120.

[0020] The government security supervision object platform 130 refers to an object platform for sensing information generation and controlling information execution.

[0021] In some embodiments, the government safety supervision object platform 130 may include a gas company management platform 131 .

[0022] The gas company management platform 131 refers to a comprehensive management platform for relevant information of the gas company, which can be used to manage gas companies and parameters related to pipeline pressure difference safety monitoring.

[0023] In some embodiments, the gas company management platform 131 can be configured to: obtain the pressure difference data matrix of the current gas pipeline network; determine the abnormal judgment result of the current gas pipeline network based on the pressure difference data matrix; in response to the abnormal judgment result being the existence of an abnormality, determine the abnormal probability distribution of the current gas pipeline network based on the pressure difference data matrix; based on the abnormal probability distribution, generate an operation instruction set; based on the pressure difference data matrix, generate a pressure regulation instruction.

[0024] In some embodiments, the gas company management platform 131 may be further configured to: in response to the number of abnormal gas pipelines in the pressure difference data matrix exceeding a first preset threshold, determine that the abnormality judgment result is that an abnormality exists.

[0025] In some embodiments, the gas company management platform 131 can be further configured to: obtain the flow data of the current gas pipeline network; determine the flow characteristic map of the current gas pipeline network based on the flow data; determine the pressure difference characteristic map of the current gas pipeline network based on the pressure difference data matrix and the flow data; determine the abnormal probability distribution of the current gas pipeline network based on the flow characteristic map and the pressure difference characteristic map.

[0026] In some embodiments, the gas company management platform 131 can be further configured to: determine a first probability distribution based on a flow characteristic map; determine a second probability distribution based on a pressure difference characteristic map; determine the abnormal probability distribution of the current gas pipeline network based on the first probability distribution and the second probability distribution.

[0027] In some embodiments, the gas company management platform 131 can be further configured to: generate multiple candidate instruction sets; for a candidate instruction set, determine the operating cost and operating efficiency of the candidate instruction set based on the pipeline location characteristics of the gas pipeline in the current gas pipeline network, the candidate instruction set and the abnormal probability distribution; determine the operating instruction set based on the operating cost and operating efficiency of the candidate instruction set.

[0028] In some embodiments, the gas company management platform 131 may be further configured to determine an operation instruction set through an evaluation model based on pipeline location characteristics and abnormal probability distribution of gas pipelines in the current gas pipeline network.

[0029] In some embodiments, the gas company management platform 131 may be further configured to: in response to the evaluation model being trained for a preset number of rounds, update the learning rate of the evaluation model based on a decay factor.

[0030] In some embodiments, the gas company management platform 131 may further include a processor. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-core processing device). As an example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), etc., or any combination thereof.

[0031] The gas company sensor network platform 140 refers to a comprehensive management platform for the gas company's sensor information, which can be configured as a communication network or a gateway, etc., for realizing the functions of perception information sensor communication and control information sensor communication.

[0032] In some embodiments, the gas company sensor network platform 140 may interact with the government safety supervision object platform 130 upwards, and interact with the gas equipment object platform 150 and the gas maintenance object platform 160 downwards. For example, the government safety supervision object platform 130 may send the acquired monitoring and control instructions, motion control instructions, and pressure regulation instructions to the gas equipment object platform 150 through the gas company sensor network platform 140, or send the acquired reporting instructions and maintenance instructions to the gas maintenance object platform 160.

[0033] The gas equipment object platform 150 refers to a functional platform for performing pipeline pressure difference monitoring, pressure difference regulation and pipeline inspection, and may include at least one pipeline monitoring device, at least one pipeline inspection device and at least one pressure regulating device.

[0034] The pipeline monitoring device refers to a functional device for monitoring the pressure difference in the gas pipeline, for example, a pressure sensor, etc. In some embodiments, the pipeline monitoring device can be used to obtain a pressure difference data matrix of the gas pipeline network.

[0035] The pipeline inspection equipment refers to a functional equipment for performing inspections in the gas pipeline, such as a pipeline crawling robot, etc. In some embodiments, the pipeline inspection equipment can be used to inspect the target gas pipeline at a preset frequency.

[0036] The pressure regulating device refers to a functional device for regulating the pressure in the gas pipeline, for example, a gas pipeline pressure regulator, etc. In some embodiments, the pressure regulating device can be used to regulate the pressure of an abnormal gas pipeline in the current gas pipeline network.

[0037] The gas maintenance object platform 160 is a platform for interacting with gas workers. The workers are people who are engaged in gas pipeline network related work, such as gas pipeline network safety officers, maintenance workers, etc.

[0038] The gas maintenance object platform 160 may include at least one interactive device, such as a mobile phone, a computer, etc. In some embodiments, the gas maintenance object platform may be used to receive maintenance instructions to deploy staff to perform maintenance on the current gas pipeline network.

[0039] For more information about the above platforms, please refer to Figure 2-Figure 5 and related instructions.

[0040] In some embodiments of the present specification, based on the smart gas pipeline pressure difference safety monitoring Internet of Things system 100, an information operation closed loop can be formed between various functional platforms, and coordinated and regularly operated under the unified management of the gas company management platform, thereby realizing the informatization and intelligence of smart gas pipeline pressure difference safety monitoring.

[0041] Figure 2 is an exemplary flow chart of a smart gas pipeline pressure difference safety monitoring method according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be implemented based on the smart gas pipeline pressure difference safety monitoring IoT system 100 and executed by the gas company management platform 131. For example, it is executed by a processor in the gas company management platform 131.

[0042] For more information about the gas company management platform 131 and the processor, see Figure 1 Related description.

[0043] Step S210, obtaining the pressure difference data matrix of the current gas pipeline network.

[0044] The current gas pipeline network refers to the gas pipeline network that currently needs to be monitored for pressure difference safety. The current gas pipeline network may include multiple gas pipelines.

[0045] The pressure difference data matrix refers to a matrix composed of pressure difference data. In some embodiments, the pressure difference data matrix may include pressure difference data of each gas pipeline in the current gas pipeline network at different time periods.

[0046] The different time periods may be set by default by the processor or pre-set by a technician according to needs, for example, multiple time periods within 24 hours.

[0047] The pressure difference data refers to data related to the difference in gas pipeline pressure. In some embodiments, the gas pipeline pressure can be monitored and acquired by a pipeline monitoring device (eg, a pressure sensor).

[0048] In some embodiments, each time period may include multiple time points, and two adjacent time points in each time period constitute a sub-period. For a gas pipeline, its pressure difference data in a time period may refer to the average value of its pressure difference data of all sub-periods in the time period. The pressure difference data of a sub-period may refer to the gas pipeline pressure at the end time point of the sub-period minus the gas pipeline pressure at the initial time point.

[0049] In some embodiments, the processor can obtain the pressure difference data of the gas pipelines in the current gas pipeline network at different time periods from the gas equipment object platform, and construct a pressure difference data matrix with the pressure difference data of a gas pipeline in a time period as an element, the pressure difference data of different gas pipelines in the same time period as a row vector, and the pressure difference data of the same gas pipeline at different time periods as a column vector. For example, the pressure difference data matrix can be expressed as ,in, Represents the number of gas pipelines in the current gas network, represents the number of time periods, Represents gas pipeline In the period Pressure difference data , the row vector Representative period Different gas pipelines (gas pipeline 1-gas pipeline ), column vector Represents gas pipeline In different time periods (period 1-period ) of the pressure difference data.

[0050] Step S220, determining the abnormality judgment result of the current gas pipeline network based on the pressure difference data matrix.

[0051] The abnormality judgment result refers to the judgment result of whether the pressure difference data of the gas pipeline network is abnormal, which may include the existence of an abnormality or the absence of an abnormality.

[0052] In some embodiments, the processor may determine the abnormality judgment result of the gas pipeline network through a variety of methods based on the pressure difference data matrix.

[0053] In some embodiments, in response to the presence of pressure difference data higher than a preset pressure difference threshold in the pressure difference data matrix, the processor may determine that the abnormality judgment result is that an abnormality exists. The preset pressure difference threshold may refer to the maximum value of the pressure difference data when there is no abnormality, which may be set by default by the processor or by a technician based on historical experience.

[0054] In some embodiments, in response to the number of abnormal gas pipelines in the pressure difference data matrix exceeding a first preset threshold, the abnormality judgment result is determined to be the presence of an abnormality.

[0055] An abnormal gas pipeline refers to a gas pipeline with abnormal pressure difference data. For a gas pipeline, if its pressure difference data in one or more time periods is abnormal, it is an abnormal gas pipeline.

[0056] In some embodiments, the pressure difference data abnormality may refer to the pressure difference data exceeding the normal pressure difference range. The normal pressure difference range may be determined by the processor and / or technicians based on historical data statistics, and the normal pressure difference ranges of different gas pipelines at different times may be the same or different. (Gas pipeline In the period Differential pressure data), based on multiple historical monitoring, gas pipeline In the period The average of multiple historical pressure difference data is the center of the range, which is determined according to the preset range size. The corresponding normal pressure difference range, the preset range size can be set by the processor by default or by the technician based on historical experience. For example, the center of the range is , the preset range size is , the normal pressure difference range is .

[0057] The first preset threshold refers to the maximum value of the number of abnormal gas pipelines allowed to exist when there is no abnormality.

[0058] In some embodiments, the first preset threshold may be set by default by the processor or by a technician based on historical experience.

[0059] In some embodiments, the first preset threshold may also be related to the number of abnormalities of the current gas network within a historical period.

[0060] The historical period refers to the period before the current period. Wherein, the current period may be a period in the pressure difference data matrix, and the historical period may be a period before the earliest period in the pressure difference data matrix.

[0061] The number of abnormalities refers to the number of times the abnormality judgment result of the gas pipeline network is that an abnormality exists. The number of abnormalities of the current gas pipeline network in the historical period can be obtained by the processor or the technician based on historical data statistics.

[0062] In some embodiments, the first preset threshold value may be negatively correlated with the number of abnormalities. The more abnormalities the current gas pipeline network has in the historical period, the more unstable the current gas pipeline network is, and the corresponding first preset threshold value may be smaller to ensure that abnormalities in the current gas pipeline network can be discovered in time.

[0063] In some embodiments of the present specification, the abnormal judgment result of the current gas pipeline network can be accurately determined by checking whether the number of abnormal gas pipelines in the pressure difference data matrix exceeds a first preset threshold, which is conducive to timely detection of pipeline network abnormalities.

[0064] Step S230, in response to the abnormality judgment result being that an abnormality exists, determining the abnormal probability distribution of the current gas pipeline network based on the pressure difference data matrix.

[0065] The abnormal probability distribution refers to the distribution of abnormal conditions in the current gas pipeline network. In some embodiments, the abnormal probability distribution may include multiple abnormal condition combinations in the current gas pipeline network and multiple probabilities corresponding thereto.

[0066] Among them, abnormal conditions refer to abnormal events that may occur during the transportation of gas in the pipeline network, such as gas pipeline leakage, gas pipeline blockage, and related equipment failure. Abnormal condition combination refers to a combination of multiple abnormal gas pipelines and their corresponding multiple abnormal conditions.

[0067] As an example only, the current gas pipeline network includes abnormal gas pipeline 1 and abnormal gas pipeline 2, and the abnormal situation includes abnormal situation 1 and abnormal situation 2 (such as gas pipeline leakage and gas pipeline blockage). Then the abnormal situation combination may include , , , , They represent abnormal gas pipeline 1 and abnormal gas pipeline 2 respectively. Represent abnormal situation 1 and abnormal situation 2 respectively. Represents 4 abnormal situation combinations respectively. It represents that abnormal gas pipeline 1 has abnormal situation 1 and abnormal gas pipeline 2 has abnormal situation 1, and the rest are similar.

[0068] Correspondingly, the abnormal probability distribution can be expressed as , , , , Represents abnormal situation combinations The probability of occurrence, It can be the product of the probability that abnormal gas pipeline 1 will have abnormal situation 1 and the probability that abnormal gas pipeline 2 will send abnormal situation 1, and the rest are similar.

[0069] In some embodiments, the processor can determine the abnormal probability distribution based on the pressure difference data matrix by a variety of methods. For example, the processor can determine the corresponding abnormal probability distribution based on the pressure difference data matrix by looking up the first preset table. The first preset table may include a corresponding relationship between the pressure difference data matrix and the abnormal probability distribution. The first preset table can be constructed by the processor and / or a technician based on historical data.

[0070] In some embodiments, the processor can also obtain the flow data of the current gas pipeline network from the government safety supervision management platform; determine the flow characteristic map of the current gas pipeline network based on the flow data; determine the pressure difference characteristic map of the current gas pipeline network based on the pressure difference data matrix and the flow data; determine the abnormal probability distribution of the current gas pipeline network based on the flow characteristic map and the pressure difference characteristic map. For more information about this part, please refer to Figure 3 Related description.

[0071] Step S240, generating an operation instruction set based on the abnormal probability distribution.

[0072] An operation instruction set refers to a collection of operation instructions.

[0073] Operation instructions refer to instructions used to operate gas pipeline pressure difference safety monitoring, which may include monitoring and control instructions, motion control instructions, reporting instructions and / or maintenance instructions.

[0074] Monitoring and control instructions are instructions for regulating pipeline monitoring equipment. Monitoring and control instructions can be sent to the gas equipment object platform to regulate the monitoring frequency of pipeline monitoring equipment.

[0075] In some embodiments, the monitoring and control instructions can also be used to add pipeline monitoring equipment.

[0076] The motion control instruction is an instruction used to control the motion of the pipeline inspection equipment. The motion control instruction can be sent to the gas equipment object platform to instruct the pipeline inspection equipment to inspect the target gas pipeline at a preset frequency.

[0077] The target gas pipeline refers to a gas pipeline that needs to be inspected. In some embodiments, the processor can determine the abnormal gas pipeline and the upstream and downstream gas pipelines connected to the abnormal gas pipeline as the target gas pipeline.

[0078] Reporting instructions are instructions used to convey relevant information. Reporting instructions can be sent to the government safety supervision management platform to receive and record abnormal conditions of the current gas pipeline network.

[0079] Maintenance instructions refer to instructions for gas pipeline maintenance. They may include the geographical location of the abnormal gas pipeline and the number of corresponding staff assigned. Maintenance instructions can be sent to the gas maintenance object platform to deploy staff to maintain the current gas pipeline network.

[0080] In some embodiments, the processor may generate an operation instruction set based on the abnormal probability distribution by a variety of methods.

[0081] In some embodiments, the processor may determine the abnormal situation combination with the highest probability of occurrence based on the abnormal probability distribution, and determine the operation instruction set corresponding to the abnormal situation combination by querying the second preset table. The second preset table may include the correspondence between the abnormal situation combination and the operation instruction set. The second preset table may be pre-constructed by the processor and / or technicians based on historical data and / or historical experience.

[0082] In some embodiments, the processor may generate multiple candidate instruction sets; for a candidate instruction set, based on the pipeline location characteristics of the gas pipeline in the current gas pipeline network, the candidate instruction set and the abnormal probability distribution, determine the operating cost and operating efficiency of the candidate instruction set; based on the operating cost and operating efficiency of the candidate instruction set, determine the operating instruction set. For more information about this section, please refer to Figure 4 and its related description.

[0083] Step S250: generating a pressure adjustment instruction based on the pressure difference data matrix.

[0084] Pressure regulation instructions are instructions for regulating the pressure of gas pipelines. Pressure regulation instructions can be sent to the gas equipment object platform to control the pressure regulating equipment to regulate the pressure of abnormal gas pipelines in the current gas network. For more information about pressure regulating equipment, see Figure 1 Related description.

[0085] In some embodiments, the processor can determine the abnormal gas pipeline and the time period corresponding to the abnormal pressure difference data based on the pressure difference data matrix, and then generate corresponding pressure regulation instructions to continuously control the abnormal gas pipeline to keep the pressure difference within the normal pressure difference range during the time period corresponding to the abnormal pressure difference data.

[0086] In some embodiments of the present specification, a pressure difference data matrix is ​​constructed through the pressure difference data of each gas pipeline at different time periods, so as to accurately judge whether there is any abnormality in the current gas pipeline network, and accurately determine the abnormal probability distribution of the gas pipeline network, so as to further generate corresponding operation instructions and pressure regulation instructions, so as to timely and accurately evaluate the abnormal situation of the pipeline network, and carry out targeted control, inspection, maintenance and other operations to ensure the normal operation of the gas pipeline network.

[0087] Figure 3FIG. 1 is an exemplary flow chart of determining an abnormal probability distribution according to some embodiments of this specification. Figure 3 As shown, the process 300 may include the following steps. In some embodiments, the process 300 may be executed by the gas company management platform 131. For example, the process 300 may be executed by a processor in the gas company management platform 131.

[0088] Step S310, obtaining the flow data of the current gas network.

[0089] Flow data refers to data related to the gas flow in the gas pipeline. For example, the flow data of the current gas pipeline network may include average flow data of each gas pipeline at different time periods.

[0090] Average flow data refers to the average value of the gas flow in a gas pipeline within a period of time. The average flow data of a gas pipeline in a period of time can be represented by the average value of the instantaneous flow data at multiple time points in the period of time. Among them, the instantaneous flow data can refer to the amount of gas passing through the cross section of the gas pipeline at a certain moment, which can be obtained by a flow sensor (such as an ultrasonic flow meter, a turbine flow meter, etc.).

[0091] For example, a gas pipeline The average flow data can be expressed as , Represents gas pipeline In the period Average traffic data .about See also Figure 2 Related description in the pressure difference data matrix.

[0092] In some embodiments, the processor may obtain flow data of each gas pipeline from a government safety supervision management platform via a government safety supervision sensor network platform.

[0093] Step S320, based on the flow data, determine the flow characteristic map of the current gas pipeline network.

[0094] The flow characteristic map refers to a map that characterizes the relevant characteristics of the flow data of the current gas pipeline network, and can be composed of multiple nodes and multiple edges. In some embodiments, the processor can establish a flow characteristic map based on the connection relationship between each gas pipeline in the current gas pipeline network and the flow data of each gas pipeline.

[0095] The nodes of the flow characteristic map may be various gas pipelines of the current gas network, and one node of the flow characteristic map corresponds to one gas pipeline. The node feature of a node of the flow characteristic map may be the average flow data of the gas pipeline corresponding to the node at different time periods.

[0096] In some embodiments, if the gas pipelines corresponding to two nodes in the flow characteristic map are connected, there is an edge of the flow characteristic map between the two nodes. The edge of the flow characteristic map is a directed edge, and the direction of the edge can be from the upstream gas pipeline to the downstream gas pipeline.

[0097] The edge feature of the traffic feature map may be a sequence of influences of the upstream node corresponding to the edge on the downstream node.

[0098] The influence degree sequence refers to a sequence consisting of multiple influence degrees corresponding to multiple time periods. The influence degree refers to the degree of influence of the upstream node on the downstream node in a certain period of time.

[0099] In some embodiments, for an edge of a traffic feature map, its influence corresponding to a certain time period can be represented by the ratio of the average traffic data of the upstream node of the edge in the time period to the sum of the average traffic data of all upstream nodes of the downstream node of the edge.

[0100] For example, for gas pipelines Pointing to the gas pipeline The side of the gas pipeline is the upstream node, gas pipeline As the downstream node, the gas pipeline There are 3 edges that are downstream nodes, and the upstream nodes corresponding to the other 2 edges are gas pipelines. and gas pipelines , then the gas pipeline Pointing to the gas pipeline The edge of the period The influence of , , , Represents gas pipelines , , In the period Average flow data for gas pipelines , , For gas pipeline All upstream gas pipelines.

[0101] Step S330, determining the pressure difference characteristic map of the current gas pipeline network based on the pressure difference data matrix and the flow data.

[0102] The pressure difference characteristic map refers to a map that characterizes the relevant characteristics of the pressure difference data of the gas pipelines in the current gas pipeline network, and can be composed of multiple nodes and multiple edges. In some embodiments, the processor can establish the pressure difference characteristic map based on the connection relationship between the gas pipelines in the current gas pipeline network, the flow data of the current gas pipeline network, and the pressure difference data matrix.

[0103] The nodes of the pressure difference characteristic map are the same as the nodes of the flow characteristic map, and the node feature of a node of the pressure difference characteristic map may be the pressure difference data of the gas pipeline corresponding to the node at different time periods.

[0104] In some embodiments, the processor may directly extract the pressure difference data of the gas pipeline at different time periods from the pressure difference data matrix as the pressure difference node feature.

[0105] The edge of the pressure difference characteristic map is the same as the edge of the flow characteristic map, and the edge feature of the pressure difference characteristic map may be a sensitivity sequence of the upstream node corresponding to the edge to the downstream node.

[0106] Among them, the sensitivity sequence refers to a sequence composed of multiple sensitivities corresponding to multiple time periods. Sensitivity refers to the sensitivity of the downstream node to the changes of the upstream node in a certain period of time. The greater the sensitivity, the greater the impact of the flow of the upstream gas pipeline on the pressure of the downstream gas pipeline.

[0107] In some embodiments, for an edge of the pressure difference characteristic graph, its sensitivity corresponding to a certain time period can be represented by the ratio of the pressure difference data of the downstream node of the edge in the time period to the average flow data of the upstream node of the edge in the time period.

[0108] For example, for gas pipelines Pointing to the gas pipeline The side of the gas pipeline is the upstream node, gas pipeline is a downstream node, then the edge is in the period The sensitivity can be , Represents gas pipeline In the period Average flow data, Represents gas pipeline In the period The pressure difference data.

[0109] Step S340, determining the abnormal probability distribution of the current gas pipeline network based on the flow characteristic map and the pressure difference characteristic map.

[0110] In some embodiments, the processor may determine the abnormal probability distribution of the current gas network based on the flow characteristic map and the pressure difference characteristic map through an abnormal monitoring algorithm, wherein the abnormal monitoring algorithm may include but is not limited to clustering algorithms, machine learning, density statistics, etc.

[0111] In some embodiments, the processor may determine a first probability distribution based on a flow characteristic map; determine a second probability distribution based on a pressure difference characteristic map; and determine an abnormal probability distribution of the current gas network based on the first probability distribution and the second probability distribution.

[0112] The first probability distribution refers to the abnormal probability distribution of the nodes of the flow characteristic map, that is, the distribution of abnormal conditions in the gas pipeline in the flow characteristic map. The first probability distribution may include multiple abnormal condition combinations in the flow characteristic map and their corresponding multiple probabilities.

[0113] The abnormal situation combination in the traffic characteristic map refers to the combination of multiple first abnormal nodes and their corresponding multiple abnormal situations. For more information about abnormal situations and abnormal situation combinations, please refer to Figure 2 Related description.

[0114] The first abnormal node refers to an abnormal gas pipeline with abnormal conditions in the flow characteristic map. In some embodiments, the processor may determine a node in the flow characteristic map that satisfies at least two preset conditions in the first preset condition group as the first abnormal node.

[0115] The first preset condition group may correspond to the abnormal situations one by one, and each abnormal situation has its own corresponding flow abnormality range.

[0116] The flow abnormality range refers to the range in which the average flow data is not within the normal flow range, that is, the flow abnormality range is included in the complement of the normal flow range. The flow abnormality ranges of different abnormal situations are different. The determination of the normal flow range can refer to the determination process of the normal pressure difference range above, which will not be repeated here. The flow abnormality range can be determined by the processor and / or technicians based on historical data and / or historical experience.

[0117] In some embodiments, the first preset condition group may include a first preset condition, a second preset condition, and a third preset condition. For a node in an abnormal situation, the corresponding first preset condition may be that in a preset number of adjacent time periods, multiple average flow data of the node are within the flow abnormality range corresponding to the abnormal situation; the second preset condition may be that in the most recent time period, the average flow data of at least one downstream node of the node is within the flow abnormality range corresponding to the abnormal situation; the third preset condition may be that the average flow data of the upstream node of the edge with the greatest influence corresponding to the node in the most recent time period is within the flow abnormality range corresponding to the abnormal situation.

[0118] The adjacent time period refers to a time period adjacent to the current time. For example, the current time period is time period 10, and the adjacent time periods may include time period 9, time period 8, etc., which are before time period 10 and adjacent to time period 10.

[0119] In some embodiments, the preset number of adjacent time periods in the first preset condition may be set by default by the processor or may be preset by a technician based on experience.

[0120] In some embodiments, the processor may determine a preset number of adjacent time periods in the first preset condition based on an operation instruction sequence of the gas pipeline corresponding to a node of the flow characteristic map.

[0121] An operation instruction sequence refers to a sequence consisting of multiple time periods and their corresponding operation instructions. In some embodiments, the processor may determine the operation instruction sequence based on historical data.

[0122] In some embodiments, for a node in the traffic characteristic map, the processor can determine the historical period corresponding to the last execution of the motion control instruction and the historical period corresponding to the last execution of the maintenance instruction based on the operation instruction sequence, determine the historical period closest to the current period, and determine the number of periods between it and the current period as a preset number. For more information about operation instructions, motion control instructions, maintenance instructions, etc., please refer to Figure 2 Related description.

[0123] In some embodiments of the present specification, a preset number of adjacent time periods is determined based on an operation instruction sequence, which can cover a time period that has not been monitored after the last execution of an operation instruction (including motion control instructions and / or maintenance instructions), thereby avoiding misjudgment due to lack of relevant data and improving the accuracy of determining the first abnormal node in the traffic characteristic map.

[0124] In some embodiments, a first abnormal node in the flow characteristic map may have one or more abnormal conditions at the same time. If a first abnormal node has one abnormal condition, the probability corresponding to the abnormal condition is 1. If a first abnormal node has multiple abnormal conditions, the probability of each abnormal condition corresponding to the node is the same. For example, if there are 10 abnormal conditions in the gas pipeline 1 in the flow characteristic map, the probability of each abnormal condition is 1 / 10.

[0125] As an example only, the flow characteristic map includes the first abnormal node 1 and the first abnormal node 2 (e.g., abnormal gas pipeline 1 and abnormal gas pipeline 2), the abnormal situation of the first abnormal node 1 includes abnormal situation 1 and abnormal situation 2, and the abnormal situation of the first abnormal node 2 includes abnormal situation 1, then the abnormal situation combination may include , , They represent the first abnormal node 1 and the second abnormal node 2 respectively. Represent abnormal situation 1 and abnormal situation 2 respectively. , Represents two abnormal situation combinations respectively. It means that the first abnormal node 1 has abnormal situation 1 and the first abnormal node 2 has abnormal situation 1, and the rest are similar.

[0126] Correspondingly, the first probability distribution can be expressed as , , Represents abnormal situation combinations , The probability of occurrence, It may be the product of the probability that the first abnormal node 1 occurs the abnormal situation 1 and the probability that the first abnormal node 2 sends the abnormal situation 1, and the rest are similar.

[0127] The second probability distribution refers to the abnormal probability distribution of the nodes of the pressure difference characteristic map, that is, the distribution of abnormal conditions of the abnormal gas pipeline in the pressure difference characteristic map. In some embodiments, the second probability distribution may include multiple abnormal condition combinations in the pressure difference characteristic map and their corresponding multiple probabilities.

[0128] The abnormal situation combination in the pressure difference characteristic map refers to a combination of multiple second abnormal nodes and multiple abnormal situations corresponding thereto.

[0129] The second abnormal node refers to an abnormal gas pipeline with abnormal conditions in the pressure difference characteristic map. In some embodiments, the processor may determine a node in the pressure difference characteristic map that meets at least two preset conditions in the second preset condition group as the second abnormal node.

[0130] The second preset condition group may correspond to the abnormal situation one by one, and each abnormal situation has its own corresponding abnormal pressure difference range. That is, one abnormal situation may correspond to one abnormal flow range and one abnormal pressure difference range.

[0131] The abnormal pressure difference range refers to the range where the pressure difference data is not within the normal pressure difference range, that is, the abnormal pressure difference range is included in the complement of the normal pressure difference range. The abnormal pressure difference ranges for different abnormal situations are different, and the abnormal pressure difference ranges can be determined by the processor and / or technicians based on historical data and / or historical experience. For more information about the normal pressure difference range and pressure difference data, please refer to Figure 2 Related description.

[0132] In some embodiments, the second preset condition group may include a fourth preset condition, a fifth preset condition, and a sixth preset condition. For a node in an abnormal situation, the corresponding fourth preset condition may be that in multiple adjacent time periods, multiple pressure difference data of the node are all within the pressure difference normal range corresponding to the abnormal situation; the fifth preset condition may be that in the most recent time period, the pressure difference data of at least one downstream node of the node is within the pressure difference normal range corresponding to the abnormal situation; the sixth preset condition may be that the pressure difference data of the upstream node of the edge with the greatest sensitivity corresponding to the node in the most recent time period is within the pressure difference normal range corresponding to the abnormal situation.

[0133] In some embodiments, a second abnormal node in the pressure difference characteristic map may also have one or more abnormal conditions at the same time. For the probability corresponding to the abnormal condition of the second abnormal node, refer to the probability corresponding to the abnormal condition of the first abnormal node in the flow characteristic map. That is, the content of determining the second probability distribution based on the pressure difference characteristic map can refer to the relevant description of determining the first probability distribution based on the flow characteristic map. The principle is the same and will not be repeated here.

[0134] In some embodiments, the processor may determine the abnormal probability distribution of the current gas network through weighted processing based on the first probability distribution and the second probability distribution.

[0135] In some embodiments, the weight size relationship of weighted processing can be determined based on the flow characteristic map and the pressure difference characteristic map. For example, for each time period, the processor can count the number of nodes in the flow characteristic map whose average flow data is within the flow abnormal range as the number of flow abnormal nodes in the time period, and then calculate the variance of the multiple flow abnormal node numbers corresponding to each time period, recorded as the first variance; for each time period, the processor can count the number of nodes in the pressure difference characteristic map whose pressure difference data is within the pressure difference abnormal range as the number of pressure difference abnormal nodes in the time period, and then calculate the variance of the multiple pressure difference abnormal node numbers corresponding to each time period, recorded as the second variance; the processor can determine the weight size relationship of the first probability distribution and the second probability distribution in the weighted processing based on the size relationship between the first variance and the second variance.

[0136] Exemplarily, if the first variance is greater than the second variance, it means that the number of abnormal pressure difference nodes corresponding to each time period fluctuates more than the number of abnormal flow nodes, then the weight of the first probability distribution can be appropriately increased, that is, the weight of the first probability distribution is greater than the weight of the second probability distribution; similarly, if the first variance is less than (or equal to) the second variance, then the weight of the first probability distribution is less than (or equal to) the weight of the second probability distribution.

[0137] In some embodiments of the present specification, a first probability distribution and a second probability distribution are obtained based on a flow characteristic map and a pressure difference characteristic map, respectively, and based on the relationship between the variance of the number of abnormal pressure difference nodes and the variance of the number of abnormal flow nodes corresponding to each time period, accurate weights are assigned to the first probability distribution and the second probability distribution, which is facilitating accurate determination of the abnormal probability distribution of the current gas pipeline network.

[0138] In some embodiments of the present specification, based on the flow data and pressure difference data matrix of the current gas pipeline network, the flow characteristic map and pressure difference characteristic map of the current gas pipeline network are obtained, and the abnormal probability distribution of the current gas pipeline network is further determined. This can fully consider the gas flow and pressure difference conditions in the gas pipeline, effectively avoid misjudgment of abnormal conditions, and improve the accuracy of identifying abnormal gas pipelines.

[0139] Figure 4 FIG. 1 is an exemplary flow chart of determining an operation instruction set according to some embodiments of this specification. Figure 4 As shown, the process 400 includes the following steps. In some embodiments, the process 400 may be executed by the gas company management platform 131. For example, the process 400 may be executed by a processor in the gas company management platform 131.

[0140] Step S410: generating multiple candidate instruction sets.

[0141] A candidate instruction set refers to a set consisting of multiple candidate instructions, and the candidate instruction set can be used for a candidate operation instruction set.

[0142] In some embodiments, the processor may randomly compose one or more candidate instruction sets based on the one or more candidate instructions.

[0143] Candidate instructions refer to candidate operation instructions. A candidate instruction set may include one or more candidate instructions from candidate monitoring and control instructions, candidate motion control instructions, candidate maintenance instructions, candidate reporting instructions, etc. In some embodiments, the candidate instructions may be randomly generated by the processor or set by a technician based on experience.

[0144] For more information about the above instructions, see Figure 2 Related description.

[0145] Step S420, for a candidate instruction set, based on the pipeline location characteristics of the gas pipeline in the current gas pipeline network, the candidate instruction set and the abnormal probability distribution, determine the operation cost and operation efficiency of the candidate instruction set.

[0146] The pipeline location feature refers to the location feature of the gas pipeline, which may include the geographical location of the current gas pipeline.

[0147] In some embodiments, the processor may directly retrieve the geographical location of the gas pipeline uploaded in advance.

[0148] The operating cost refers to the cost required to execute the candidate instruction set, which may include the total number of workers and / or working equipment, the total working time, the total distance between each gas pipeline and the working center, etc.

[0149] Among them, the staff may include pipeline maintenance personnel, and the working equipment may include pipeline inspection equipment. In some embodiments, the processor can determine the number of working equipment based on motion control instructions and determine the assigned number of staff based on maintenance instructions, thereby determining the total number of staff and / or working equipment.

[0150] The total working time may be the sum of the maintenance time of the staff and / or the inspection time of the working equipment. In some embodiments, the processor may statistically calculate the average value of multiple historical total working times and use it as the total working time.

[0151] The work center may be a gathering place for staff and / or work equipment. The work center may include a maintenance center and an inspection center. The distance between the gas pipeline and the work center may be determined by the processor based on the geographical location of the work center and the pipeline location characteristics.

[0152] In some embodiments, the processor may determine the operating cost by weighted summation based on the total number of workers and / or working equipment, the total working time, and the total distance between each gas pipeline and the working center, wherein the weighted weight may be set by default by the processor or pre-set by the technician based on experience.

[0153] Operational efficiency refers to the candidate instruction set's ability to troubleshoot anomalies and / or resolve risks in the gas network.

[0154] In some embodiments, the processor may determine the operating efficiency based on the operating coefficient, the standard instruction set, and the candidate instruction set. For each abnormal situation combination in the abnormal probability distribution, there is a corresponding standard instruction set. The standard instruction set and the operating coefficient may be set by default by the processor or pre-set by the technician based on experience.

[0155] Exemplarily, for a combination of abnormal situations, the processor may determine the gap between the standard instruction set and a candidate instruction set, and determine the ratio of the operating coefficient to the gap as the operating efficiency of the candidate instruction set.

[0156] In some embodiments, the gap between the standard instruction set and the candidate instruction set can be represented by a vector distance. For example, for a gas pipeline, the processor can calculate the vector distance between the standard operating instruction corresponding to the gas pipeline in the standard instruction set and the candidate operating instruction corresponding to the gas pipeline in the candidate instruction set, and statistically calculate the average of each vector distance corresponding to each gas pipeline in the current gas pipeline network, and use it as the gap between the standard instruction set and the candidate instruction set. Among them, the vector distance may refer to the distance between the standard vector corresponding to the standard operating instruction and the candidate vector corresponding to the candidate operating instruction. For example, Euclidean distance, etc. The vector elements of the standard vector may include the monitoring frequency and the standard number of additional pipeline monitoring equipment in the standard monitoring and control instructions, the preset frequency in the standard motion control instructions, the quantized value of the standard reporting instruction (quantized as 1 if there is a standard reporting instruction, and quantized as 0 if there is no standard reporting instruction), the geographical location of the gas pipeline in the standard maintenance instruction and the number of staff assigned, and the candidate vector is the same.

[0157] In some embodiments, for a combination of abnormal situations, the processor may determine the product of its corresponding probability and operating efficiency, and determine the sum of the products corresponding to various combinations of abnormal situations included in the candidate instruction set as the operating efficiency corresponding to the candidate instruction set.

[0158] Step S430: determining an operating instruction set based on the operating cost and operating efficiency of the candidate instruction sets.

[0159] In some embodiments, the processor may perform a weighted summation of the operating cost and operating efficiency of the candidate instruction sets, and determine the candidate instruction set with the highest weighted summation value as the operating instruction set. The weight coefficient of the operating cost is a negative number, and the weights of the operating cost and operating efficiency may be set by default by the processor or pre-set by a technician based on experience.

[0160] In some embodiments of the present specification, by evaluating the operating cost and operating efficiency of the candidate instruction sets, the operating instruction set can be accurately and quickly determined from the candidate instructions, which is beneficial to the safe operation of the gas pipeline network.

[0161] In some embodiments, the operation instruction set may also include operation instruction sequences for each gas pipeline in the current gas pipeline network at different time periods. The processor may also determine the operation instruction set through an evaluation model based on the pipeline location characteristics and abnormal probability distribution of the gas pipelines in the current gas pipeline network.

[0162] For more information about the operation instruction set, current gas pipeline network, different time periods, operation instruction sequence, pipeline location characteristics, and abnormal probability distribution, please refer to Figure 2-Figure 4 Related description.

[0163] The evaluation model refers to a model used to determine the operation instruction set. In some embodiments, the evaluation model can be a machine learning model, such as a deep neural network (DNN), a graph neural network (GNN), etc.

[0164] In some embodiments, Figure 5 As shown, the input of the assessment model 550 may include pipeline location features 510 and abnormal probability distribution 520 , and the output may be an operation instruction set 560 .

[0165] In some embodiments, the evaluation model can be obtained by training in a variety of ways. For example, the evaluation model can be obtained by training a plurality of training samples with training labels. A set of training samples for training the evaluation model may include sample pipeline location features and sample abnormal conditions of a sample gas pipeline. The training labels corresponding to a set of training samples are actual operating instruction sets with the best operating effect.

[0166] In some embodiments, the processor can obtain multiple groups of training samples based on historical data, wherein the historical pipeline location characteristics and historical abnormal conditions of each historical gas pipeline in a historical gas pipeline network can be used as a group of training samples; construct multiple historical vectors based on multiple groups of training samples, and the historical vectors include historical pipeline location characteristics and historical abnormal conditions; cluster multiple historical vectors to determine one or more cluster clusters; for each cluster cluster, the processor can use the historical actual operation instruction set with the best operating effect in multiple historical actual operation instruction sets corresponding to multiple groups of training samples in the cluster cluster as the training label corresponding to all training samples in the cluster cluster. Among them, clustering methods include but are not limited to K-means clustering, mean shift clustering, etc. The best operating effect can refer to that in multiple time periods after the execution of the historical actual operation instruction set, the historical pressure difference data of each historical gas pipeline in the corresponding historical gas pipeline network are all within the normal pressure difference range, and the historical pressure difference data fluctuates minimally.

[0167] For more information about abnormal conditions, pressure difference data, and normal pressure difference range, please refer to Figure 2 Related description.

[0168] In some embodiments, the processor may perform multiple rounds of iterative training on the initial evaluation model based on multiple groups of training samples with training labels (including historical sample pipeline location features and historical sample anomalies). One round of iterative training includes: inputting a group of training samples with training labels into the initial evaluation model, determining the loss function value through the training labels and the output results of the initial evaluation model, and iteratively updating the parameters of the initial evaluation model based on the loss function value. When multiple rounds of iterations are performed until the iteration conditions are met, the training of the initial evaluation model is completed and a trained evaluation model is obtained. Among them, the iteration method may include but is not limited to the gradient descent method, and the iteration conditions may include the convergence of the loss function and the number of iterations reaching a preset number threshold.

[0169] In some embodiments, Figure 5 As shown, the input of the evaluation model 550 may also include a flow characteristic map 530 and a pressure difference characteristic map 540 .

[0170] For more information about flow characteristic graphs and pressure difference characteristic graphs, please refer to Figure 3 Related description.

[0171] In some embodiments, the training samples of the training evaluation model may also include a sample flow characteristic map and a sample pressure difference characteristic map, and the sample flow characteristic map and the sample pressure difference characteristic map may be acquired based on historical data.

[0172] In some embodiments, the processor can train the evaluation model based on training samples including sample flow characteristic maps, sample pressure difference characteristic maps, sample pipeline position features, and sample abnormal probability distribution. For the training method of the evaluation model, please refer to the relevant description above.

[0173] In some embodiments of the present specification, using a flow characteristic map and a pressure difference characteristic map as inputs to an evaluation model can improve the accuracy of the evaluation model in determining an operating instruction set.

[0174] In some embodiments, in response to the evaluation model being trained for a preset number of rounds, the processor may update the learning rate of the evaluation model based on a decay factor.

[0175] The preset number of rounds refers to the preset number of training rounds, for example, the preset number of iterations.

[0176] In some embodiments, the processor may determine the preset number of rounds based on the complexity of the pressure difference characteristic map.

[0177] Since the higher the complexity of the pressure difference feature map, the more complex the connection method of the gas pipeline in the current gas pipeline network is, the higher the potential instability in the current gas pipeline network is, and the greater the amount of information included in the training sample is. Therefore, the complexity of the pressure difference feature map can be positively correlated with the preset number of rounds, that is, the higher the complexity of the pressure difference feature map, the larger the preset number of rounds, so as to delay the time of learning rate decay, so that the evaluation model can accurately learn the data characteristics of the training samples.

[0178] The complexity of the pressure difference characteristic map refers to the complexity of the pressure difference characteristic map. The complexity of the pressure difference characteristic map can be represented by a value of 0-10, and a larger value indicates a higher complexity.

[0179] In some embodiments, the processor may determine the pipeline in-degree and pipeline out-degree of each node in the pressure difference characteristic map, further calculate the variance of the pipeline in-degree of all nodes and the variance of the pipeline out-degree of all nodes, and determine the mean of the above two variances as the complexity of the pressure difference characteristic map. Wherein, the pipeline in-degree refers to the number of pipelines flowing to the node, and the pipeline out-degree refers to the number of pipelines flowing out of the node. The pipeline in-degree and pipeline out-degree can be obtained by the processor based on the pressure difference characteristic map.

[0180] The decay factor refers to a parameter of the decay evaluation model learning rate, and can be represented by a value between 0 and 1. In some embodiments, the decay factor can be set by default by the processor and / or pre-set by a technician based on experience.

[0181] The learning rate refers to a parameter that controls the update of the evaluation model. For example, the search step size of the gradient descent method in iterative training. In some embodiments, in response to the evaluation model being trained for a preset number of rounds, the processor can update the learning rate of the evaluation model based on the decay factor. For example, the learning rate is multiplied by the decay factor to update to a new learning rate.

[0182] In some embodiments of the present specification, the preset number of rounds is determined according to the complexity of the pressure difference characteristic map, and the learning rate is updated based on the attenuation factor after the preset number of rounds of training. This can help the model better converge to the optimal solution, avoid oscillation or failure to converge during the model training process, and enable the model to be fully learned, which is conducive to the accurate acquisition of the operating instruction set.

[0183] In some embodiments of the present specification, an evaluation model is used to determine an operating instruction set based on pipeline location characteristics and abnormal probability distribution, and the learning ability of a machine learning model can be used to accurately evaluate the operating instruction set, thereby improving the accuracy of abnormal maintenance of gas pipelines.

[0184] One or more embodiments of the present specification provide a smart gas pipeline pressure difference safety monitoring device, the device comprising at least one memory and at least one processor, the at least one memory being used to store computer instructions, and the at least one processor executing the computer instructions or part of the instructions to implement a smart gas pipeline pressure difference safety monitoring method.

[0185] One or more embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a smart gas pipeline pressure difference safety monitoring method.

[0186] The embodiments of the present invention are only for illustration and explanation, and do not limit the scope of application of the present invention. For those skilled in the art, various modifications and changes that can be made under the guidance of the present invention are still within the scope of the present invention. In addition, some features, structures or characteristics in one or more embodiments of the present invention can be appropriately combined.

[0187] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the referenced materials of this invention and the contents of this invention, the descriptions, definitions, and / or usage of terms in this invention shall prevail.

[0188] Finally, it should be understood that the embodiments described in the present invention are only used to illustrate the principles of the embodiments of the present invention. Other variations may also fall within the scope of the present invention. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present invention may be considered consistent with the teachings of the present invention. Accordingly, the embodiments of the present invention are not limited to the embodiments explicitly introduced and described in the present invention.

Claims

1. A smart gas pipeline pressure difference safety monitoring Internet of Things system, characterized by: The system includes a gas company management platform; The gas company management platform is configured as follows: Acquire a pressure difference data matrix of the current gas pipeline network, wherein the pressure difference data matrix includes pressure difference data of gas pipelines in the current gas pipeline network at different time periods; Based on the pressure difference data matrix, determining an abnormality judgment result of the current gas pipeline network; In response to the abnormality judgment result being that an abnormality exists, determining an abnormal probability distribution of the current gas pipeline network based on the pressure difference data matrix; Based on the abnormal probability distribution, an operation instruction set is generated, wherein the operation instruction set includes operation instructions corresponding to the gas pipeline, and the operation instructions include: A monitoring and control instruction is configured to control the monitoring frequency of the pipeline monitoring device; The motion control instruction is configured to instruct the pipeline inspection equipment to inspect the target gas pipeline at a preset frequency; A reporting instruction is configured to receive and record the abnormal situation of the current gas pipeline network; A maintenance instruction is configured to dispatch personnel to perform maintenance on the current gas pipeline network; Based on the pressure difference data matrix, a pressure regulation instruction is generated, and the pressure regulation instruction is configured to control the pressure regulation device to regulate the pressure of the abnormal gas pipeline in the current gas pipeline network.

2. The Internet of Things system according to claim 1, characterized in that: The gas company management platform is further configured as follows: Obtaining flow data of the current gas pipeline network; Based on the flow data, determining a flow characteristic map of the current gas pipeline network; Determine a pressure difference characteristic map of the current gas pipeline network based on the pressure difference data matrix and the flow data; Based on the flow characteristic map and the pressure difference characteristic map, the abnormal probability distribution of the current gas pipeline network is determined.

3. The Internet of Things system according to claim 1, characterized in that: The gas company management platform is further configured as follows: generating a plurality of candidate instruction sets; For one of the candidate instruction sets, based on the pipeline location characteristics of the gas pipeline in the current gas pipeline network, the candidate instruction set and the abnormal probability distribution, determining the operation cost and operation efficiency of the candidate instruction set; The operating instruction set is determined based on the operating cost and the operating efficiency of the candidate instruction set.

4. The Internet of Things system according to claim 1, characterized in that: The operation instruction set also includes a sequence of operation instructions for gas pipelines in the current gas pipeline network at different time periods, and the gas company management platform is further configured as follows: Based on the pipeline position characteristics of the gas pipeline in the current gas pipeline network and the abnormal probability distribution, the operation instruction set is determined through an evaluation model, and the evaluation model is a machine learning model.

5. The Internet of Things system according to claim 1, characterized in that: The system also includes a government safety supervision management platform, a government safety supervision sensor network platform, a government safety supervision object platform, a gas company sensor network platform, a gas equipment object platform and a gas maintenance object platform; wherein the government safety supervision object platform includes the gas company management platform; The government safety supervision management platform is connected to the government safety supervision object platform through the government safety supervision sensor network platform; The government safety supervision object platform is connected to the gas equipment object platform and the gas maintenance object platform through the gas company sensor network platform; The monitoring and control instructions are sent to the gas equipment object platform, the motion control instructions are sent to the gas equipment object platform, the reporting instructions are sent to the government safety supervision and management platform, the maintenance instructions are sent to the gas maintenance object platform, and the pressure regulation instructions are sent to the gas equipment object platform.

6. A smart gas pipeline pressure difference safety monitoring method, characterized in that: The method is executed by a gas company management platform, and the method includes: Acquire a pressure difference data matrix of the current gas pipeline network, wherein the pressure difference data matrix includes pressure difference data of gas pipelines in the current gas pipeline network at different time periods; Based on the pressure difference data matrix, determining an abnormality judgment result of the current gas pipeline network; In response to the abnormality judgment result being that an abnormality exists, determining an abnormal probability distribution of the current gas pipeline network based on the pressure difference data matrix; Based on the abnormal probability distribution, an operation instruction set is generated, wherein the operation instruction set includes operation instructions corresponding to the gas pipeline, and the operation instructions include: A monitoring and control instruction is configured to control the monitoring frequency of the pipeline monitoring device; The motion control instruction is configured to instruct the pipeline inspection equipment to inspect the target gas pipeline at a preset frequency; A reporting instruction is configured to receive and record the abnormal situation of the current gas pipeline network; A maintenance instruction is configured to dispatch staff to perform maintenance on the current gas pipeline network; Based on the pressure difference data matrix, a pressure regulation instruction is generated, and the pressure regulation instruction is configured to control the pressure regulation device to regulate the pressure of the abnormal gas pipeline in the current gas pipeline network.

7. The method according to claim 6, characterized in that The determining, based on the pressure difference data matrix, the abnormal probability distribution of the current gas pipeline network includes: Obtaining flow data of the current gas pipeline network; Based on the flow data, determining a flow characteristic map of the current gas pipeline network; Determine a pressure difference characteristic map of the current gas pipeline network based on the pressure difference data matrix and the flow data; Based on the flow characteristic map and the pressure difference characteristic map, the abnormal probability distribution of the current gas pipeline network is determined.

8. The method according to claim 6, characterized in that The generating an operation instruction set based on the abnormal probability distribution includes: generating a plurality of candidate instruction sets; For one of the candidate instruction sets, based on the pipeline location characteristics of the gas pipeline in the current gas pipeline network, the candidate instruction set and the abnormal probability distribution, determining the operation cost and operation efficiency of the candidate instruction set; The operating instruction set is determined based on the operating cost and the operating efficiency of the candidate instruction set.

9. The method according to claim 6, characterized in that The operation instruction set also includes a sequence of operation instructions for gas pipelines in the current gas pipeline network at different time periods. The generating of the operation instruction set based on the abnormal probability distribution also includes: Based on the pipeline position characteristics of the gas pipeline in the current gas pipeline network and the abnormal probability distribution, the operation instruction set is determined through an evaluation model, and the evaluation model is a machine learning model.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the smart gas pipeline pressure difference safety monitoring method as described in any one of claims 6-9.

Images