A smart gas pipeline network inspection method, an Internet of Things system and a medium

Abstract

This invention provides a smart gas pipeline network inspection method, an Internet of Things (IoT) system, and a medium. The method is implemented based on the smart gas pipeline network safety management platform of the smart gas pipeline network inspection IoT system. The method includes: acquiring the gas pipeline network distribution; determining at least one inspection sub-region based on the gas pipeline network distribution; and determining an inspection plan for each inspection sub-region within the at least one inspection sub-region based on the at least one inspection sub-region; wherein the inspection plan includes at least an inspection frequency.

Description

Technical Field

[0001] This manual relates to the field of gas pipeline inspection technology, and in particular to a smart gas pipeline inspection method, an Internet of Things system, and a medium. Background Technology

[0002] Damage to gas pipelines not only causes economic losses for gas companies but also affects the lives of urban residents, and in severe cases, can even threaten their personal safety. Therefore, gas companies need to arrange patrol personnel to inspect the gas pipeline network in order to detect and resolve problems in a timely manner. However, due to the large coverage area of ​​gas pipelines in cities, patrol personnel are prone to missing or repeating inspections, resulting in low inspection efficiency and poor inspection results.

[0003] Based on this, it is hoped that a smart gas pipeline inspection method, IoT system, and medium can be provided to improve inspection efficiency and effectiveness. Summary of the Invention

[0004] This invention provides a smart gas pipeline network inspection method, implemented based on a smart gas pipeline network safety management platform of a smart gas pipeline network inspection Internet of Things system. The method includes: acquiring the gas pipeline network distribution; determining at least one inspection sub-region based on the gas pipeline network distribution; determining an inspection plan for each inspection sub-region based on the at least one inspection sub-region; the inspection plan includes at least an inspection frequency.

[0005] This invention provides an IoT system for intelligent gas pipeline network inspection. The system includes: an intelligent gas user platform, an intelligent gas service platform, an intelligent gas pipeline network safety management platform, an intelligent gas sensor network platform, and an intelligent gas object platform. The intelligent gas object platform is used to acquire the gas pipeline network distribution and transmit the gas pipeline network distribution to the intelligent gas pipeline network safety management platform through the intelligent gas sensor network platform. The intelligent gas pipeline network safety management platform is configured to: determine at least one inspection sub-region based on the gas pipeline network distribution; determine an inspection plan for each inspection sub-region based on the at least one inspection sub-region; the inspection plan includes at least an inspection frequency; and the intelligent gas service platform is used to feed back the inspection plan to the intelligent gas user platform.

[0006] The present invention provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the aforementioned intelligent gas pipeline inspection method.

[0007] Beneficial effects:

[0008] In the invention, by using various methods such as pipeline network distribution, probability determination model, and preset sub-map segmentation, one or more inspection sub-areas are determined, and inspection plans for each inspection sub-area are determined. This makes the inspection plans more scientific and reasonable, which is conducive to improving inspection efficiency and inspection effect, so as to discover problems in time, prevent or deal with them in advance, and reduce the losses of gas companies. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is a schematic diagram of the structure of an intelligent gas pipeline inspection IoT system according to some embodiments of this specification;

[0011] Figure 2 This is an exemplary flowchart of a smart gas pipeline inspection method according to some embodiments of this specification;

[0012] Figure 3 This is an exemplary flowchart of a method for determining at least one patrol personnel station location according to some embodiments of this specification;

[0013] Figure 4 This is an exemplary flowchart of a method for determining at least one inspection sub-region according to some embodiments of this specification;

[0014] Figure 5 This is an exemplary schematic diagram of a method for determining inspection priority values ​​according to some embodiments of this specification. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0017] As indicated in this specification, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0019] Figure 1 This is a structural schematic diagram of an intelligent gas pipeline inspection IoT system according to some embodiments of this specification. The intelligent gas pipeline inspection IoT system 100 involved in the embodiments of this specification will be described in detail below. It should be noted that the following embodiments are only for explaining this specification and do not constitute a limitation thereof.

[0020] like Figure 1 As shown, the smart gas pipeline inspection IoT system 100 may include a smart gas user platform 110, a smart gas service platform 120, a smart gas pipeline safety management platform 130, a smart gas sensor network platform 140, and a smart gas object platform 150.

[0021] The smart gas user platform 110 can be user-centric, including a platform for acquiring user needs and providing information feedback to users. In some embodiments, the smart gas user platform 110 can be configured as a terminal device. For example, a desktop computer, tablet computer, laptop computer, mobile phone, or other intelligent electronic device that performs data processing and data communication.

[0022] In some embodiments, the smart gas user platform 110 may include a gas user sub-platform and a regulatory user sub-platform. The gas user sub-platform is for gas users and can be used to receive gas-related data and gas pipeline inspection reminders (e.g., inspection plans, inspection times, etc.) sent by the smart gas service sub-platform, as well as to send gas-related data query commands to the smart gas service sub-platform. The regulatory user sub-platform is for regulatory users (e.g., users under safety supervision) and can be used to receive gas pipeline inspection management information (e.g., inspection plans, etc.) sent by the smart regulatory service sub-platform, as well as to send gas pipeline inspection management information query commands to the smart regulatory service sub-platform.

[0023] The smart gas service platform 120 can be a platform for receiving and transmitting data and / or information. For example, the smart gas service platform 120 can be used to receive gas pipeline inspection management information uploaded by the smart gas data center 132 of the smart gas pipeline safety management platform 130, and to send the gas pipeline inspection management information to the smart gas user platform 110. In some embodiments, the smart gas service platform 120 can be used to receive query instructions (e.g., gas-related data query instructions, gas pipeline inspection management information query instructions, etc.) issued by the smart gas user platform 110, and to send query instructions to the smart gas data center 132 of the smart gas pipeline safety management platform 130.

[0024] In some embodiments, the smart gas service platform 120 may include a smart gas consumption service sub-platform and a smart regulatory service sub-platform. The smart gas consumption service sub-platform can receive gas-related data and gas pipeline inspection reminders uploaded by the smart gas data center 132, and send these data and reminders to the gas user sub-platform. It can also receive gas-related data query instructions from the gas user sub-platform and send these instructions to the smart gas data center 132. The smart regulatory service sub-platform can receive gas pipeline inspection management information uploaded by the smart gas data center 132 and transmit this information to the regulatory user sub-platform. It can also receive gas pipeline inspection management information query instructions from the regulatory user sub-platform and send these instructions to the smart gas data center 132.

[0025] The intelligent gas pipeline safety management platform 130 can refer to a platform that coordinates and integrates the connections and collaborations between various functional platforms, gathers all the information from the Internet of Things (IoT), and provides sensing, management, and control functions for the IoT operating system. For example, the intelligent gas pipeline safety management platform 130 can be used to receive relevant data (such as gas pipeline distribution, pipeline characteristics, etc.) from the intelligent gas sensor network platform 140, perform inspection management of the gas pipeline network, and determine inspection plans.

[0026] In some embodiments, the intelligent gas pipeline safety management platform 130 may include an intelligent gas pipeline inspection management sub-platform 131 and an intelligent gas data center 132. The intelligent gas pipeline inspection management sub-platform 131 may include an inspection plan management module, an inspection time early warning module, an inspection status management module, and an inspection problem management module.

[0027] The inspection plan management module can be used to set and adjust pipeline equipment inspection plans, and distribute these plans to the smart gas pipeline inspection project object sub-platform via the smart gas data center 132 through the smart gas pipeline inspection project sensor network sub-platform. Inspection plans that may affect user gas consumption are also sent to the gas user sub-platform via the smart gas service sub-platform through the smart gas data center 132. The inspection time warning module can automatically arrange unexecuted inspection plans according to inspection time and issue warnings based on preset time thresholds. In some embodiments, managers can directly generate inspection reminder instructions through the inspection time warning module and distribute them to the smart gas pipeline inspection project object sub-platform via the smart gas data center 132 through the smart gas pipeline inspection project sensor network sub-platform. The inspection status management module can be used to view the execution status of pipeline equipment inspection plans and historical inspection plan execution status. The inspection problem management module can be used for viewing, remotely processing, and sending messages about inspection problems.

[0028] In some embodiments, the smart gas data center 132 can be used to receive information such as gas pipeline distribution and pipeline characteristics uploaded by the smart gas sensor network platform 140, and send the data to the smart gas pipeline safety management sub-platform for analysis and processing. After the smart gas pipeline safety management sub-platform completes the processing, it sends the data back to the smart gas data center 132. The smart gas data center 132 summarizes and stores the processed data and then uploads it to the smart gas service platform 120, which then transmits it to the smart gas user platform 110. In some embodiments, the smart gas data center 132 can also be used to receive query commands (such as gas-related data query commands, gas pipeline inspection management information query commands, etc.) issued by the smart gas service platform 120 and send them to the smart gas sensor network platform 140.

[0029] The intelligent gas sensor network platform 140 can refer to a platform for processing, storing, and transmitting data and / or information. For example, the intelligent gas sensor network platform 140 can be used to receive gas pipeline distribution, pipeline characteristics, etc., acquired by the intelligent gas object platform 150, and transmit them to the intelligent gas data center 132. In some embodiments, the intelligent gas sensor network platform 140 can be configured as a communication network and gateway.

[0030] In some embodiments, the intelligent gas sensor network platform 140 may include an intelligent gas pipeline equipment sensor network sub-platform and an intelligent gas pipeline inspection engineering sensor network sub-platform. The intelligent gas pipeline equipment sensor network sub-platform can receive relevant data from pipeline equipment, such as gas pipeline distribution and pipeline characteristics, and send it to the intelligent gas data center 132. It can also receive data query instructions related to pipeline equipment issued by the intelligent gas data center 132 and send them to the intelligent gas pipeline equipment object sub-platform. The intelligent gas pipeline inspection engineering sensor network sub-platform can receive inspection-related information (such as inspection plans and inspection reminder instructions) issued by the intelligent gas data center 132 and send it to the intelligent gas pipeline inspection engineering object sub-platform. It can also receive execution feedback on inspection-related information uploaded by the intelligent gas pipeline inspection engineering object sub-platform and send it to the intelligent gas data center 132.

[0031] The smart gas object platform 150 can be a functional platform for acquiring data and / or information related to pipeline objects. For example, the smart gas object platform 150 can be used to acquire relevant data of pipeline equipment and transmit it to the smart gas data center 132 through the smart gas sensor network platform 140. In some embodiments, the smart gas object platform 150 can be configured as various types of equipment, such as pipeline equipment (e.g., pipelines, gate stations, etc.) and inspection engineering related equipment (e.g., alarm devices, etc.).

[0032] In some embodiments, the smart gas object platform 150 may include a smart gas pipeline network equipment object sub-platform and a smart gas pipeline network inspection engineering object sub-platform. The smart gas pipeline network equipment object sub-platform can receive data query instructions related to pipeline network equipment transmitted by the smart gas sensor network platform 140, and after obtaining the relevant data of the pipeline network equipment, upload it to the smart gas data center 132 via the smart gas sensor network platform 140. The smart gas pipeline network inspection engineering object sub-platform can receive inspection-related information transmitted by the smart gas sensor network platform 140, perform corresponding inspection operations on the pipeline network equipment, and feed back the execution results to the smart gas data center 132 via the smart gas sensor network platform 140.

[0033] In some embodiments of this specification, the smart gas pipeline inspection IoT system built through the smart gas user platform, smart gas service platform, smart gas pipeline safety management platform, smart gas sensor network platform, and smart gas object platform can form a closed loop of smart gas pipeline inspection management information operation among gas pipeline equipment, pipeline inspection personnel, gas operators, and gas users, thereby realizing the informatization and intelligence of pipeline inspection management and making management more efficient.

[0034] It should be noted that the above description of the intelligent gas pipeline inspection IoT system 100 and its various components is for convenience only and should not be construed as limiting this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principle of the device, may arbitrarily combine the various components or construct subsystems connected to other components without departing from this principle.

[0035] Figure 2 This is an exemplary flowchart of a smart gas pipeline inspection method according to some embodiments of this specification.

[0036] In some embodiments, process 200 can be executed by the intelligent gas pipeline safety management platform 130. For example... Figure 2 As shown, process 200 may include the following steps:

[0037] Step 210: Obtain the distribution of the gas pipeline network.

[0038] Gas pipeline network distribution can refer to the distribution data of gas pipeline networks, such as the coverage area of ​​gas pipeline networks, the location of gas pipeline nodes, and the number of gas pipeline nodes.

[0039] The distribution of gas pipeline networks can be obtained in various ways. In some embodiments, the smart gas data center of the smart gas pipeline safety management platform 130 can obtain the gas pipeline network distribution based on the smart gas pipeline equipment object sub-platform of the smart gas object platform. The smart gas pipeline equipment object sub-platform can be configured with monitoring devices for pipeline equipment to obtain the pipeline network distribution. For example, the smart gas pipeline equipment object sub-platform can use the Global Positioning System (GPS) to obtain information such as the coverage area of ​​the gas pipeline network and the location of gas pipeline nodes.

[0040] Step 220: Based on the distribution of the gas pipeline network, determine at least one inspection sub-area.

[0041] An inspection sub-region can refer to any area within the gas pipeline network. For example, if the gas pipeline network is distributed across regions A, B, and C, then all three regions can be considered inspection sub-regions.

[0042] There are several ways to determine the inspection sub-regions. In some embodiments, the inspection sub-regions can be divided according to preset rules, such as dividing them by physical regions (e.g., city zones). The preset rules can be pre-defined division rules, or they can be determined based on historical experience, algorithms, etc.

[0043] In some embodiments, at least one patrol personnel station can be determined based on the distribution of the gas pipeline network, and at least one inspection sub-area can be determined based on the distribution of the gas pipeline network and the at least one patrol personnel station.

[0044] Patrol personnel outposts can refer to both the starting and stopping points of patrol personnel during their inspections. Patrol personnel outposts can be nodes in the gas pipeline network (such as gate stations, gas storage stations, etc.) or stations located at any point on the gas pipeline network (such as stations located at the midpoint of the pipeline).

[0045] There are several ways to determine the locations of patrol personnel. In some embodiments, several patrol personnel locations can be randomly generated based on the gas pipeline network distribution and preset conditions. These preset conditions can be pre-defined, such as a distance greater than a preset distance threshold. Specifically, based on the gas pipeline network distribution, a specific pipeline node can be used as a base point. Points whose distance from this pipeline node is greater than a preset distance threshold can be designated as a batch of patrol personnel locations. The relative distance between any two patrol personnel locations in this batch must be no less than the preset distance threshold. Then, using this batch of patrol personnel locations as a base point, other points whose distance is greater than the preset distance threshold can be designated as another batch of patrol personnel locations. This process is repeated until all patrol personnel locations for the gas pipeline network coverage area are determined. Here, the base point can be understood as a foundation point or starting point.

[0046] In some embodiments, a first pipeline network map can be constructed based on the gas pipeline network distribution. Based on the first pipeline network map, a probabilistic determination model is used to output the probability that a node and / or edge of the first pipeline network map is a patrol personnel's location. Then, based on the output of the nodes and edges of the first pipeline network map, at least one patrol personnel's location is determined. For details on how to determine at least one patrol personnel's location based on the gas pipeline network distribution using the first pipeline network map and the probabilistic determination model, please refer to [link to relevant documentation]. Figure 3 And its related descriptions.

[0047] In some embodiments, the inspection sub-regions can be initially divided based on the gas pipeline network distribution and according to preset rules, and then further determined by combining the locations of patrol personnel. For example, the inspection sub-regions can be initially divided according to physical areas (e.g., city zones) (e.g., Zone A, Zone B, Zone C). If there are no patrol personnel in Zone A, but patrol personnel are stationed in Zones B and C, then Zone A can be merged into the area where the patrol personnel station closest to Zone A is located (e.g., Zone C). Thus, Zone B and Zone A + Zone C can be determined as the final two inspection sub-regions. It should be noted that this method is only an example and is not intended to limit the method of dividing by preset distances.

[0048] In some embodiments, a second pipeline network map can be constructed based on the gas pipeline network distribution and at least one patrol personnel station; based on the second pipeline network map, at least one second pipeline network sub-map is determined using a preset sub-map segmentation method; and then, based on the at least one second pipeline network sub-map, at least one inspection sub-area is determined. For details on how to determine at least one inspection sub-area based on the gas pipeline network distribution and at least one patrol personnel station using the second pipeline network map and the preset sub-map segmentation method, please refer to [link to relevant documentation]. Figure 4 And its related descriptions.

[0049] In some embodiments of this specification, at least one patrol personnel station is determined based on the distribution of the gas pipeline network. Then, based on the distribution of the gas pipeline network and at least one patrol personnel station, at least one inspection sub-area is determined. This ensures that each inspection sub-area has at least one patrol personnel station, thereby ensuring the normal inspection of the inspection area.

[0050] Step 230: Based on at least one inspection sub-region, determine the inspection plan for each inspection sub-region within the at least one inspection sub-region.

[0051] An inspection plan can refer to the methods that inspection personnel should adopt when inspecting a gas pipeline network, including but not limited to the inspection cycle and related operations. For example, when the relevant data of the pipeline equipment shows abnormal fluctuations, the inspection plan may be a new plan obtained by extending the inspection cycle or changing the inspection route based on the original inspection plan. In some embodiments, the inspection plan includes at least the inspection frequency.

[0052] Inspection frequency refers to the number of inspections conducted on a specific sub-area within a certain period. For example, the inspection frequency could be 10 times / day, 20 times / week, etc. Inspection frequency can be determined manually and randomly, or it can be determined based on historical data and other methods. For instance, the inspection frequency can be determined based on the frequency of gas pipeline accidents in the historical accident data of a specific sub-area; the higher the accident frequency, the higher the corresponding inspection frequency.

[0053] In some embodiments, the smart gas data center transmits relevant data of pipeline equipment to the smart gas pipeline inspection and management sub-platform. The smart gas pipeline inspection and management sub-platform can determine the inspection plan in various ways. For example, the smart gas pipeline inspection and management sub-platform can match relevant data of pipeline equipment in the inspection sub-area (e.g., gas pipeline distribution, pipeline characteristics, etc.) with historical pipeline data, and then use the historical pipeline data with the highest similarity as reference data, and the corresponding historical reference inspection plan as the inspection plan for the inspection sub-area. Here, historical pipeline data can refer to a collection of historical relevant data of pipeline equipment, such as historical gas pipeline distribution, historical pipeline characteristics, etc.; reference data can refer to the data in historical pipeline data that has the highest similarity to the relevant data of the current pipeline equipment; and historical reference inspection plan can be the inspection plan adopted by the pipeline equipment when it is running under the parameters of the reference data.

[0054] In some embodiments, the inspection plan may also include an inspection route; the inspection sub-area may also include a patrol personnel station and at least one inspection point.

[0055] In some embodiments, the inspection plan for the inspection sub-region can be determined based on the route taken from the patrol personnel's station to each patrol point in at least one patrol point within the identified inspection sub-region.

[0056] An inspection point can refer to the destination of an inspection. An inspection point can be a section of pipeline in a pipeline network, a node at the opposite end of the pipeline, or a point on the pipeline, etc.

[0057] Inspection points can be determined in several ways. In some embodiments, inspection points can be determined based on historical inspection data. For example, the top 10 historical inspection points ranked by the number of inspections from highest to lowest can be used as inspection points. Historical inspection points can refer to pipeline nodes or pipelines that have previously served as inspection points. In some embodiments, inspection points can also be determined based on actual conditions. For example, the node opposite to an abnormal pipeline can be used as an inspection point. An abnormal pipeline can refer to a section of a gas pipeline whose characteristics exceed a preset characteristic threshold, such as a pipeline where the gas pressure exceeds a preset gas pressure threshold or a pipeline where the number of repairs exceeds a preset maintenance threshold.

[0058] The inspection route can refer to the route that inspection personnel should take during the inspection. For example, the route from pipeline node A to pipeline node B; or, for example, from pipeline node A through pipeline node B to the middle of pipeline c, etc.

[0059] Inspection routes can be determined in various ways, such as randomly determining the route. In some embodiments, inspection routes can be generated according to a preset method. For example, the top 10 historical inspection points ranked by the number of inspections from highest to lowest in historical inspection data can be used as inspection points. Starting from the inspection point furthest from the others, the remaining inspection points can be connected sequentially according to the principle of minimizing the distance. The principle of minimizing the distance can be determined based on algorithms or other methods.

[0060] In some embodiments, each inspection point in at least one inspection point has an inspection priority value; the inspection route is determined based on the inspection priority value of each inspection point. For details regarding inspection priority values ​​and how to determine the inspection route based on the inspection priority value of each inspection point, please refer to [link to relevant documentation]. Figure 5 And its related descriptions.

[0061] In some embodiments, an inspection plan for a sub-region can be determined based on the inspection route. For example, after determining the inspection route, the inspection frequency can be determined based on the pipeline characteristics corresponding to the inspection points along the route, thereby determining the inspection plan. The pipeline characteristics can be features related to the pipeline itself, such as pipe diameter and pipeline service life. Specifically, when it is found that the service life of the pipeline corresponding to an inspection point in the inspection route exceeds a service life threshold, the inspection frequency can be increased based on the original inspection plan to obtain a new inspection plan. The service life threshold can refer to a pre-set service life value, which can be determined based on historical experience, simulation experiments, and other methods.

[0062] In some embodiments of this specification, by determining the inspection route and then determining the inspection plan based on the inspection route, not only can the workload of the inspection personnel be reduced, but it is also conducive to the unified scheduling and management of the inspection personnel, clarifying the scope of responsibility and saving management costs.

[0063] In some embodiments of this specification, by using various methods such as pipeline network distribution, pipeline map, probability determination model, and preset sub-map segmentation, one or more inspection sub-areas are determined, and inspection plans for each inspection sub-area are determined. This makes the inspection plans more scientific and reasonable, which is conducive to improving inspection efficiency and inspection effect, so as to detect problems in time, prevent or deal with them in advance, and reduce the losses of gas companies.

[0064] Figure 3 This is an exemplary flowchart illustrating a method for determining at least one patrol personnel station location according to some embodiments of this specification.

[0065] In some embodiments, process 300 can be executed by the intelligent gas pipeline safety management platform 130. For example... Figure 3 As shown, process 300 may include the following steps:

[0066] Step 310: Construct a first pipeline network map based on the gas pipeline network distribution. The nodes of the first pipeline network map correspond to the branches of the gas pipeline network distribution; the edges of the first pipeline network map correspond to the pipes in the gas pipeline network distribution; and one edge of the first pipeline network map corresponds to a pipe connecting two branches of the gas pipeline network.

[0067] The first pipeline network map can refer to a map determined based on gas pipeline network distribution information, which can represent the distribution information of gas pipelines, gate stations, gas storage stations, and other pipeline network equipment in various areas of the city. In some embodiments, the intelligent gas pipeline network safety management platform 130 can obtain gas pipeline network distribution information from the intelligent gas data center based on the intelligent gas pipeline network inspection and management sub-platform to construct the first pipeline network map.

[0068] In some embodiments, the intelligent gas pipeline safety management platform 130 can construct a first pipeline map 312 based on the gas pipeline distribution 311.

[0069] The nodes of the first pipeline network map can be used to represent branches of the gas pipeline network. Examples include pipeline inflection points, gate stations, and gas storage stations. The nodes of the first pipeline network map can be determined according to preset rules. For example, the nodes can be determined based on the number, density, location, and importance of pipeline inflection points, gate stations, and gas storage stations in the gas pipeline network distribution, or they can be preset based on experience.

[0070] In some embodiments, the nodes in the first pipeline network diagram 312 include node n1, node n2, node n12, etc.

[0071] The characteristics of nodes in the first pipeline network map can include various types of information. In some embodiments, the characteristics of nodes in the first pipeline network map can include the node type corresponding to the node. Node types can include various types, such as gate station type, gas storage station type, pipeline bend type, etc. The characteristics of nodes in the first pipeline network map can also include other information about the corresponding node, such as the number of times it has been inspected in history, failure rate, etc. In some embodiments, the characteristics of nodes in the first pipeline network map can also include whether the node is a patrol personnel station. For relevant information on patrol personnel stations, please refer to [link to relevant content]. Figure 2 And its description.

[0072] The edges of the first pipeline network diagram can be used to represent pipelines in the gas pipeline network distribution. In some embodiments, the edges of the first pipeline network diagram can connect two nodes of the first pipeline network diagram, which can characterize the relationship between the two connected nodes. For example, adjacency relationship, distance relationship, etc. It is understood that there can be multiple gas pipelines between two nodes of the first pipeline network diagram (e.g., two gas storage stations). As an example only, a gas storage station may have multiple gas pipelines (e.g., 2 or 3) laid at different angles or directions, which converge at the same gas storage station. In this case, in the first pipeline network diagram, the two nodes corresponding to the two gas storage stations can be connected by multiple edges (e.g., 2 or 3) depending on the number of gas pipelines.

[0073] In some embodiments, the edges in the first pipeline network diagram 312 include edges A, B, Q, etc. In some embodiments, the edges of the first pipeline network diagram can be directed edges, and the direction of the edge can indicate the direction of gas transmission. For example, edge A can indicate that the gas is transmitted from node n1 to node n2.

[0074] The features of the edges of the first pipeline network map can include various information. In some embodiments, the features of the edges of the first pipeline network map can include the length of the gas pipeline corresponding to the edge, for example, 50m. The features of the edges of the first pipeline network map can also include other information, such as the service life of the gas pipeline, the number of times it has been inspected in history, the failure rate, etc. In some embodiments, the features of the edges of the first pipeline network map can also include whether the edge is a patrol personnel station.

[0075] Step 320: Based on the first pipeline network map, and using a probability determination model, output the probability that the nodes and / or edges of the first pipeline network map are the locations where patrol personnel are stationed.

[0076] A patrol personnel outpost refers to a location where patrol personnel can stay and conduct inspections of gas pipelines. Patrol personnel outposts can be set up near gate stations, gas storage stations, or pipelines within the gas pipeline network. In some embodiments, a patrol personnel outpost can correspond to a node or edge of a first pipeline network map; that is, multiple nodes or edges of the first pipeline network map can be designated as patrol personnel outposts. It should be noted that when an edge of the first pipeline network map is designated as a patrol personnel outpost, that outpost can be represented based on the midpoint of that edge or in other forms.

[0077] In some embodiments, the location of patrol personnel can be determined based on preset rules. For example, at least one patrol personnel location can be randomly determined, and using the at least one patrol personnel location as a center, a node or edge outside a preset radius threshold (e.g., 200m) that is closest to the at least one patrol personnel location can be selected as a new patrol personnel location.

[0078] The probability of each node or edge in the first pipeline network map being designated as a patrol personnel station can be different. In some embodiments, the intelligent gas pipeline safety management platform 130 can determine the probability of a patrol personnel station using a probabilistic deterministic model.

[0079] A probabilistic deterministic model can refer to a model used to determine the probability that a node and / or edge in a first pipeline network map is a patrol personnel's post. In some embodiments, the probabilistic deterministic model can be a trained machine learning model. For example, the probabilistic deterministic model can include any one or a combination of recurrent neural network models, convolutional neural networks, or other custom model structures.

[0080] In some embodiments, the probability determination model 321 can be a trained graph neural network model. For example... Figure 3 As shown, the intelligent gas pipeline safety management platform 130 can input the first pipeline map 312 into the probability determination model 321, process the first pipeline map 312 through the probability determination model 321, and output the probability 322 of each node and / or each edge of the first pipeline map being a patrol personnel station based on the nodes and / or edges of the first pipeline map. For example, based on node n1, output the probability that node n1 is a patrol personnel station; based on node n3, output the probability that node n13 is a patrol personnel station; based on edge Q, output the probability that edge Q is a patrol personnel station, etc.

[0081] In some embodiments, the probabilistic determination model can be obtained by training multiple labeled sample pipeline network maps. These sample pipeline network maps can be multiple historical pipeline network maps, and the labels can be determined based on whether a node or edge in the sample pipeline network map is a historical patrol personnel station. For example, if a node or edge is a historical patrol personnel station, the label corresponding to that node or edge is 1; otherwise, it is 0. In some embodiments, the labels can also be determined based on historical inspection information of nodes or edges in the sample pipeline network map. For example, the lower the historical inspection failure rate, the higher the probability of it being identified as a patrol personnel station. The labels can be annotated manually or by other methods.

[0082] During the initial training of the probabilistic deterministic model, the intelligent gas pipeline safety management platform 130 can input each sample pipeline map into the model. Through processing by the model, it outputs the probability values ​​of each node and edge being a patrol personnel's station based on the nodes and edges in the sample pipeline map. The intelligent gas pipeline safety management platform 130 can construct a loss function based on the label of each sample pipeline map and the output of the probabilistic deterministic model. Iteratively updating the parameters of the probabilistic deterministic model based on the loss function continues until preset conditions are met, resulting in a trained probabilistic deterministic model. These preset conditions can include the loss function being less than a threshold, convergence, or the training period reaching a threshold.

[0083] In some embodiments, the label setting method may also be: in the sample pipeline network map, the label of the node or edge that is actually set as the station of the patrol personnel is set to 1, and the label value of the remaining nodes / edges is set based on the preset attenuation degree, such as the label value is set to a value in the range of [0, 1].

[0084] For example, the label values ​​of other nodes / edges can be determined based on the algorithm L = 1 - k * degree. Here, k represents a preset decay rate (e.g., 0.1), and degree represents the adjacency or distance (e.g., 1, 2) of the other node or edge to the patrol personnel's station. For instance, if a node is adjacent to the patrol personnel's station (adjacency of 1), then the label value of that node is L = 1 - 0.1 * 1 = 0.9.

[0085] In some embodiments, if a node or edge obtains multiple node labels based on different patrol personnel stations, the final label value of the node or edge can be determined based on its corresponding multiple node labels, such as the final label value being the average or weighted sum of multiple node labels.

[0086] In some embodiments of this specification, since there are a large number of nodes and edges, setting the label when training the probability determination model by setting the decay degree can improve the training efficiency of the probability determination model.

[0087] Step 330: Based on the output of the nodes and edges of the first pipeline network map, determine at least one patrol personnel station.

[0088] In some embodiments, after processing the first pipeline network map using a probabilistic deterministic model, the intelligent gas pipeline safety management platform 130 can determine at least one patrol personnel station based on the patrol personnel station probability values ​​output from the nodes and edges of the first pipeline network map, according to preset rules. As an example only, the X nodes and / or edges with the highest patrol personnel station probability values ​​can be used as patrol personnel station locations, wherein the distance between these X nodes and / or edges can be greater than a preset distance threshold to ensure a more uniform distribution of patrol personnel station locations.

[0089] In some embodiments, the intelligent gas pipeline safety management platform 130 can sort (e.g., descending order) the probability values ​​of patrol personnel stationing points and select the first M preset nodes / edges as candidate patrol personnel stationing points. From these M candidate patrol personnel stationing points, N candidate patrol personnel stationing points that meet preset constraints are randomly selected as target patrol personnel stationing points. The preset constraints may include ensuring that the distance (e.g., the length of the gas pipeline) between any two candidate patrol personnel stationing points is greater than a preset distance threshold (e.g., 200m).

[0090] like Figure 3 As shown, after processing the first pipeline network map 312 based on the probabilistic determination model 321, the probability values ​​of patrol personnel stationing points output based on the nodes and edges of the first pipeline network map are sorted in descending order. This determines that the three patrol personnel stationing points satisfying the aforementioned preset constraints can be nodes n1, n9, and n12. This is merely an example and is not intended to be limiting. For example, there could be four, five, etc.

[0091] The number N of patrol personnel stationed at various locations can be determined based on actual needs or various suitable methods. For example, the number of patrol personnel stationed at various locations can be determined based on one or more combinations of factors such as the proportion of the total number of nodes and edges in the first pipeline network map (e.g., 10%), the number of divisions in the pipeline network distribution, and the actual number of patrol personnel. For example, if the actual number of patrol personnel is 20, the number of patrol personnel stationed at various locations can be set to less than 20 (e.g., 18).

[0092] In some embodiments, the number of patrol personnel stationed at each location can be determined based on the average subgraph complexity of multiple subgraphs after the pipeline subgraph has been segmented. Each pipeline subgraph corresponds to an inspection area; the higher the subgraph complexity, the more nodes / edges represent that subgraph. It is understood that the higher the complexity of each individual subgraph, the higher the average subgraph complexity of all subgraphs, and consequently, the greater the inspection workload for the patrol personnel.

[0093] In some embodiments, an average threshold can be preset. The intelligent gas pipeline safety management platform 130 can increase the number of patrol personnel stations to make the average subgraph complexity of multiple subgraphs lower than the preset average threshold, thereby determining the corresponding number of patrol personnel stations. For example, if the current number of patrol personnel stations is 3, and the number of nodes and edges in each of the 3 determined subgraphs is relatively large (e.g., exceeding the preset number threshold), meaning the average subgraph complexity is relatively large, then the current number of patrol personnel stations can be increased (e.g., by adding 1), thus increasing the number of subgraphs (e.g., by adding 1 accordingly). At the same time, the number of nodes and edges in each subgraph decreases accordingly, meaning the subgraph complexity of each subgraph decreases accordingly. When the average subgraph complexity of all subgraphs is less than the preset average threshold or the sum of the number of nodes and edges in each subgraph is less than the preset number threshold, the increase of the current number of patrol personnel stations can be stopped, and the current number of patrol personnel stations can be determined as the final number of patrol personnel stations.

[0094] For more information on network subgraphs and their complexity, please refer to [link to relevant documentation]. Figure 4 And its description.

[0095] Some embodiments in this specification, which combine the inspection workload to determine the number of patrol personnel stationed at each location, can effectively reduce the inspection pressure and make the method of determining the patrol personnel stationed at each location more user-friendly.

[0096] Some embodiments in this specification determine the probability of patrol personnel being stationed at a location using a probability determination model, and then determine the location of patrol personnel based on the probability of their stationing. This can make the results more accurate and improve the efficiency of determining the location of patrol personnel.

[0097] Figure 4 This is an exemplary flowchart of a method for determining at least one inspection sub-region according to some embodiments of this specification.

[0098] In some embodiments, process 400 can be executed by the intelligent gas pipeline safety management platform 130. For example... Figure 4 As shown, process 400 may include the following steps:

[0099] Step 410: Based on the distribution of the gas pipeline network and at least one patrol personnel station, construct a second pipeline network map.

[0100] The second pipeline network map can refer to a map determined based on the distribution of gas pipeline networks and the information on patrol personnel's locations. It can represent the distribution information of gas pipelines, gate stations, gas storage stations, and other pipeline equipment, as well as the locations of patrol personnel, in various areas of the city. In some embodiments, the intelligent gas pipeline network safety management platform 130 can determine the second pipeline network map by obtaining gas pipeline network distribution information and at least one patrol personnel's location information from the intelligent gas data center based on the intelligent gas pipeline network inspection management sub-platform.

[0101] In some embodiments, the intelligent gas pipeline safety management platform 130 can construct a second pipeline map 413 based on the gas pipeline distribution 411 and at least one patrol personnel station 412. The second pipeline map 413 includes patrol personnel stations (i.e., solid nodes): node n1, node n9, node n12; non-patrol personnel stations (i.e., hollow nodes): node n2, node n3, node n4, etc.; and edges: edge A, edge B, edge C, etc. For details on the characteristics of nodes and edges, see [link to relevant documentation]. Figure 3 And its related descriptions.

[0102] It should be noted that when the patrol personnel's station is a certain edge, the patrol personnel's station can be set as the midpoint of that edge or other preset points. In the characteristics of the patrol personnel's station, the type of the station can be set to "gas pipeline", and other characteristics of the original edge can be set as the characteristics of the patrol personnel's station (such as the number of historical inspections, failure rate, etc.). In addition, the original edge is divided into two edges, and the characteristics of the two edges also change accordingly. For example, if the patrol personnel's station is set as the midpoint of a certain edge, and the length value in the characteristics of the original edge is L, then the length values ​​in the characteristics of the two edges after division are both adjusted to L*1 / 2.

[0103] Step 420: Based on the second pipeline network map, at least one second pipeline network sub-map is determined by a preset sub-map segmentation method.

[0104] The second subgraph can refer to a graph consisting of at least some of the nodes and / or edges in the second subgraph.

[0105] In some embodiments, the intelligent gas pipeline safety management platform 130 can determine at least one second pipeline sub-map of the second pipeline map based on the physical or administrative planning of the urban area. For example, if the city includes areas A, B, and C, the intelligent gas pipeline safety management platform 130 can correspondingly divide the second pipeline map into three second pipeline sub-maps: the second pipeline sub-map corresponding to area A, the second pipeline sub-map corresponding to area B, and the second pipeline sub-map corresponding to area C.

[0106] In some embodiments, the intelligent gas pipeline safety management platform 130 can segment the second pipeline map based on a preset sub-map segmentation method to determine at least one second pipeline sub-map.

[0107] In some embodiments, the intelligent gas pipeline safety management platform 130 can perform multiple rounds of iterative segmentation of the second pipeline map based on a preset sub-map segmentation method, and ultimately determine at least one second pipeline sub-map. For example... Figure 4 As shown, at least one second pipeline sub-graphite can be determined as second pipeline sub-graphite 421, second pipeline sub-graphite 422, or second pipeline sub-graphite 423. The intelligent gas pipeline safety management platform 130 can be set with an iteration counter to record the time or iteration round of the current iteration, and to record the nodes and / or edges assigned to the second pipeline sub-graphite in each iteration round. For example, the time / iteration round t for a node to be assigned to a certain second pipeline sub-graphite is 2. Each iteration round can include the following:

[0108] The preset subgraph segmentation method may include the following steps S1 to S5:

[0109] Step S1: Based on the stationary nodes of the second pipeline network map, determine at least one initial second pipeline network sub-map, where each initial second pipeline network sub-map contains a stationary node.

[0110] The initial second pipeline sub-map can refer to the second pipeline sub-map obtained when the second pipeline map is segmented in each iteration. In some embodiments, the intelligent gas pipeline safety management platform 130 can use each of the at least one patrol personnel station as the starting node or reference node of the corresponding at least one initial second pipeline sub-map.

[0111] like Figure 4 As shown, the stationed nodes in the second pipeline network map 413 include nodes n1, n9, and n12, thus determining three initial second pipeline network sub-maps. Each initial second pipeline network sub-map contains at least its corresponding stationed node, such as the stationed node n9 in the initial second pipeline network sub-map 421. It can be understood that the number of patrol personnel stationed at each location determines the number of initial second pipeline network sub-maps. For example, the aforementioned three patrol personnel stationed locations determine that the number of initial second pipeline network sub-maps will be three.

[0112] Step S2: Select a target node from the network nodes of the second network map as nodes to be assigned, based on a preset filtering method.

[0113] The node to be assigned can refer to a second network sub-map node that has not yet been assigned to the initial second network sub-map.

[0114] The target node can refer to the node to be assigned that has been selected to be included in the initial second network sub-graph.

[0115] In some embodiments, the intelligent gas pipeline safety management platform 130 can select at least one node as the target node from the nodes to be assigned based on a preset strategy. For example, it can select several nodes near the patrol personnel's post (e.g., less than a preset distance threshold) as target nodes based on a random selection strategy.

[0116] In some embodiments, the intelligent gas pipeline safety management platform 130 can select a target node from the nodes to be assigned based on a preset screening method.

[0117] The preset filtering method can be to select the target node based on the current preferred value of the node to be assigned. The current preferred value is related to the first distance between the node and the subgraph with the smallest complexity of the current subgraph, and the second distance between the previous target node and the node.

[0118] The preferred value can be used to determine the probability that a node to be assigned will be selected as a target node. The preferred value can be a value in the range [0, 1], for example, 0.8. The larger the preferred value, the higher the priority it is in determining the initial second pipeline sub-graph. The preferred value can also be other representations, such as level 1, level 2, level 3, etc. In some embodiments, the intelligent gas pipeline safety management platform 130 can determine the preferred value of each node to be assigned based on a first distance between the node to be assigned and the sub-graph with the lowest complexity of the current sub-graph, and a second distance between the previous target node and the node.

[0119] Subgraph complexity refers to the complexity of the current initial second network subgraph. Subgraph complexity can be a numerical value, such as 0.8 or 5. A higher value indicates greater complexity. Subgraph complexity can be determined based on the number of nodes and edges in the current initial second network subgraph. As an example only, subgraph complexity can be equal to the sum of the number of nodes and edges in the subgraph.

[0120] In some embodiments, the first distance can be determined based on the distance between the current node to be assigned and the reference node of the initial second pipeline subgraph with the lowest complexity of the current subgraph (i.e., the patrol personnel's post in the initial second pipeline subgraph). For example, it can be determined based on the sum of the lengths of the edges corresponding to the shortest path connecting the current node to be assigned and the reference node.

[0121] like Figure 4As shown, if the initial second network subgraph with the lowest complexity is the second network subgraph 421, then the first distance between the node to be assigned n5 and the reference node n9 of the second network subgraph 421 can be determined based on the sum of the lengths of edge M and edge F. The length of edge M can be determined by the length feature value (e.g., 200m) in the characteristics of edge M, and the same applies to edge F.

[0122] In some embodiments, the second distance can be determined based on the length of the edge corresponding to the shortest path connecting the current node to be assigned and the previous target node. The previous target node can be the last target node assigned to the initial second network subgraph in the previous round of subgraph segmentation. For example, if node n7 was the target node in the previous round of subgraph segmentation, and node n5 is the node to be assigned in this round of subgraph segmentation, then the second distance corresponding to node n5 is the length of edge F.

[0123] In some embodiments, the intelligent gas pipeline safety management platform 130 further determines the initial second pipeline sub-map with the smallest sub-map complexity based on the sub-map complexity of each initial second pipeline sub-map, and determines the preferred value of each node to be assigned based on the first distance and the second distance of each node to be assigned. The smaller the first distance, the larger the preferred value; the larger the second distance, the larger the preferred value. In some embodiments, the intelligent gas pipeline safety management platform 130 can determine a first preferred value based on the first distance of the node to be assigned, determine a second preferred value based on the second distance of the node to be assigned, and then determine the final preferred value of the node to be assigned based on the average of the first and second preferred values ​​of the node to be assigned.

[0124] In some embodiments, the intelligent gas pipeline safety management platform 130 can sort the preferred values ​​of each node to be assigned (e.g., in descending order) and select the node with the largest preferred value as the target node.

[0125] Some embodiments in this specification, through a preset screening method, can help balance the complexity of each second network sub-map and prevent size imbalances between the second network sub-maps.

[0126] Step S3: Determine the initial second pipeline sub-graph to which the target node belongs based on the objective function value of the target node relative to each initial second pipeline sub-graph.

[0127] The objective function value is a probability value used to determine the final allocation of the target node selected in step S2 to one of the initial second network subgraphs. The objective function value can be related to the subgraph complexity of the initial second network subgraph and the first distance between the target node and the initial second network subgraph.

[0128] In some embodiments, the objective function may be a preset algorithm or formula. For example, the objective function value F = k1*d1 + k2*d2. Here, k1 and k2 are preset coefficients. For example, k1 = 0.5, k2 = 0.3; d1 is the subgraph complexity, which can represent the complexity of the initial second network subgraph to which the target node is to be assigned; d2 is the first distance between the target node and the initial second network subgraph to which the target node is to be assigned.

[0129] In some embodiments, the intelligent gas pipeline safety management platform 130 can determine the function value of the target node when it is assigned to each initial second pipeline sub-map based on the aforementioned method, and determine the initial second pipeline sub-map corresponding to the minimum target function value F when the target node is assigned to it.

[0130] In some embodiments, the objective function value is also related to the increment of the variance of the inspection priority values ​​of nodes and edges in the initial second pipeline subgraph after the target node is assigned to the initial second pipeline subgraph. The larger the increment of this variance, the smaller the objective function value. For example, the initial objective function value can be determined based on the aforementioned method, then an adjustment value can be determined based on the increment of the variance, and finally, the objective function value can be determined based on the initial objective function value and the adjustment value.

[0131] Understandably, the inspection priority values ​​of each node and edge in the initial second pipeline subgraph can differ. As the number of iterations increases, the number of nodes and edges in each initial second pipeline subgraph also increases. Correspondingly, the variance of the inspection priority values ​​of each node and edge in the current iteration versus the previous iteration fluctuates. Smaller fluctuations indicate that the inspection priority values ​​of each node and edge in the initial second pipeline subgraph are closer, leading to greater uncertainty and error in subsequent actual inspection routes or sequences. Conversely, larger fluctuations indicate greater differences in the inspection priority values ​​of each node and edge in the initial second pipeline subgraph, resulting in clearer determination of subsequent actual inspection routes or sequences and smaller errors.

[0132] S4, determine the new target node, repeat the above operation until all nodes to be assigned have determined their initial second pipeline sub-map.

[0133] The new target node can refer to the node to be assigned in the current iteration of subgraph segmentation after the previous round of subgraph segmentation. For specific selection methods, please refer to the scheme in step S2 above.

[0134] In some embodiments, the intelligent gas pipeline safety management platform 130 can repeat the operations of steps S1 to S3 in each iteration, gradually assigning unassigned nodes and edges in the second pipeline map to the initial second pipeline sub-map, until all unassigned nodes in the second pipeline map are assigned to their respective initial second pipeline sub-maps, at which point the iteration terminates.

[0135] It should be noted that when one edge in the second pipeline network diagram (such as...) Figure 4 The two nodes to be assigned connected by edge D) (e.g. Figure 4 Nodes n2 and n5 are assigned to two different second network sub-maps (e.g., ... Figure 4 When the second pipeline sub-map 422 and the second pipeline sub-map 421 are used, edge D can belong to both of the second pipeline sub-maps simultaneously. In this case, the intelligent gas pipeline safety management platform 130 can mark or prompt edge D. When patrol personnel inspect the inspection sub-areas corresponding to the second pipeline sub-map 422 and the second pipeline sub-map 421, the gas pipeline corresponding to edge D can be inspected by patrol personnel in the inspection sub-area corresponding to the second pipeline sub-map 422, or by patrol personnel in the inspection sub-area corresponding to the second pipeline sub-map 421. In some embodiments, the intelligent gas pipeline safety management platform 130 can also determine the sub-map to which edge D belongs based on the direction of edge D, such as assigning edge D to the sub-map where its arrow originates, that is, it can be inspected by patrol personnel in the inspection sub-area corresponding to the second pipeline sub-map 422. In some embodiments, other methods can also be adopted, such as random assignment.

[0136] Step S5: The initial second pipeline sub-maps after the aforementioned operations are completed are used as the final second pipeline sub-maps to determine their corresponding inspection sub-regions.

[0137] like Figure 4 As shown, when the iteration terminates, all nodes and edges in the second network graph are divided, thereby determining the nodes and edges contained in the final three second network subgraphs, such as second network subgraph 421, second network subgraph 422 and second network subgraph 423.

[0138] It should be noted that the preset subgraph segmentation methods can include segmentation by nodes or segmentation by edges, etc. The above-mentioned preset subgraph segmentation method uses node-based segmentation as an example and is not intended to limit the scope of the method.

[0139] Step 430: Based on at least one second pipeline sub-map, determine at least one inspection sub-region.

[0140] The inspection sub-region can refer to the physical inspection area corresponding to the second pipeline sub-map.

[0141] In some embodiments, when performing step 430, the intelligent gas pipeline safety management platform 130 can determine the inspection sub-area based on the second pipeline sub-map determined by the preset sub-map segmentation method.

[0142] For example, the intelligent gas pipeline safety management platform 130 will determine each of the second pipeline sub-maps in the final second pipeline sub-map as an inspection sub-area.

[0143] like Figure 4 As shown, the final second pipeline sub-maps 421, 422, and 423 correspond to three different inspection sub-regions. It can be understood that each final second pipeline sub-map corresponds to the actual gas pipeline network distribution. Accordingly, referring to the final second pipeline sub-maps, the intelligent gas pipeline safety management platform 130 can map the pipeline equipment (e.g., gas pipelines, gate stations, gas storage stations) corresponding to the nodes or edges in each final second pipeline sub-map to the actual regions, thereby generating the inspection sub-regions.

[0144] Some embodiments in this specification use a preset sub-map segmentation method to automatically segment the second pipeline network map, improving the efficiency of segmenting the second pipeline network sub-map. At the same time, it takes into account the complexity of the sub-map when dividing the second pipeline network sub-map, which helps to make the segmented second pipeline network sub-map more balanced and facilitates a more balanced inspection workload for the further determined inspection sub-regions.

[0145] It should be noted that the descriptions of processes 200, 300, and 400 above are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the processes under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0146] Figure 5 This is an exemplary schematic diagram of a method for determining inspection priority values ​​according to some embodiments of this specification.

[0147] In some embodiments, each inspection point in at least one inspection point has an inspection priority value, and the inspection route is determined based on the inspection priority value of each inspection point.

[0148] The inspection priority value refers to the priority value for patrol personnel to inspect inspection points. The inspection priority value can be a value in the range [0, 1], for example, 0.3, 0.8. The higher the inspection priority value of an inspection point, the higher the priority that inspection point should be inspected.

[0149] In some embodiments, the inspection priority value can be determined based on the pipeline characteristics corresponding to the inspection point.

[0150] Pipeline characteristics refer to the attributes or information of a gas pipeline. These characteristics can include physical parameters such as material, length, thickness, diameter, and region. Operating parameters include the gas composition, flow rate, pressure rating, and frequency of gas delivery. Other pre-defined information may also be included, such as historical inspection frequency, failure rate, and maintenance records.

[0151] In some embodiments, the intelligent gas pipeline safety management platform 130 can acquire gas pipeline-related information (e.g., physical parameters, operating parameters, etc.) stored in the intelligent gas data center, and determine pipeline characteristics based on this information. In some embodiments, pipeline characteristics can be represented in various forms; for example, they can be represented by, but are not limited to, vectors or vector matrices. For instance, pipeline characteristics can be represented by a vector (a, b, c, d, e), where the first element a represents the inspection sub-area where the gas pipeline is located, the second element b represents the length of the gas pipeline, the third element c represents the average daily gas flow rate, the fourth element d represents the gas pressure level, and the fifth element e represents the failure rate.

[0152] In some embodiments, the intelligent gas pipeline safety management platform 130 can determine the inspection priority value of the inspection point based on the pipeline characteristics corresponding to the inspection point and through a feature determination model.

[0153] A feature determination model can refer to a model used to determine the inspection priority value of inspection points. The feature determination model can be a trained machine learning model. For example, it can include any one or a combination of recurrent neural network models, convolutional neural networks, or other custom model structures.

[0154] like Figure 5 As shown, the input of the feature determination model 520 may include the pipeline feature 510 corresponding to the inspection point, and the output of the inspection priority value 530 corresponding to the inspection point is based on the processing of the feature determination model 520.

[0155] In some embodiments, the feature determination model can be obtained by training a large number of labeled first training samples. The first training samples include sample pipeline historical feature vectors constructed based on multiple sets of historical gas pipeline information. These multiple sets of gas pipeline information can be obtained from historical data stored in a smart gas data center. The labels of the first training samples can be the inspection priority values ​​of the inspection points corresponding to each set of sample pipeline historical feature vectors. Labels can be generated manually or through other feasible methods.

[0156] When training the feature determination model, the intelligent gas pipeline safety management platform 130 can input the historical feature vectors of sample pipelines into the feature determination model, construct a loss function based on the output of the feature determination model and the label of the first training sample, and iteratively update the parameters of the initial feature determination model based on the loss function until the preset conditions are met and training is completed, resulting in a trained feature determination model. The preset conditions can be that the loss function is less than a threshold, convergence, or the training period reaches a threshold.

[0157] In some embodiments, the inspection priority value of an inspection point is also related to the time and / or round in which the node and / or edge corresponding to the inspection point in the second pipeline map is divided into a sub-map during sub-map segmentation.

[0158] It should be noted that the pipeline characteristics corresponding to different inspection points can be the same, and the inspection priority values ​​output by the feature-based determination model 520 can also be the same. In some embodiments, the inspection priority values ​​output by the feature-based determination model 520 can be used as candidate inspection priority values.

[0159] In some embodiments, the intelligent gas pipeline safety management platform 130 can determine the final inspection priority value 530 of an inspection point based on preset rules, the time and / or round 540 when the inspection point is assigned to the second pipeline sub-map, and the aforementioned candidate inspection priority values. The time and / or round when the inspection point is assigned to the second pipeline sub-map can be obtained based on the iteration counter records of the sub-map segmentation method during iteration.

[0160] In some embodiments, a weighting coefficient for the candidate inspection priority value can also be set. This weighting coefficient can be inversely proportional to the time and / or round when the inspection point is assigned to the second pipeline sub-map. For example, the time and / or round when the inspection point is assigned to the second pipeline sub-map is t, the weighting coefficient k = 1 / t, and the final inspection priority value V = k * V'; V' is the candidate inspection priority value output by the feature-based determination model 520.

[0161] For example, such as Figure 4 As shown, the current patrol personnel are located at node n7 and can proceed to either node n5 or node n8. If the pipeline characteristics of nodes n5 and n8 are completely identical, and if, during the iterative processing of the subgraph segmentation method, node n8 is selected first as the node to be assigned to the second pipeline subgraph 421, then node n8 has a higher inspection priority. In this case, the patrol personnel's inspection route is the route from node n7 to node n8, i.e., the pipeline corresponding to edge L.

[0162] Understandably, by introducing the time and / or round when inspection points are assigned to the second pipeline sub-map, when the inspection priority values ​​of inspection points determined based on pipeline characteristics are the same in the same second pipeline sub-map, the inspection point that is assigned to the second pipeline sub-map first can have a higher inspection priority, thereby eliminating the uncertainty of the inspection order.

[0163] Some embodiments in this specification determine the inspection priority value of inspection points through a feature determination model. This can automatically and in real time determine the inspection priority value of inspection points, which helps to improve efficiency. At the same time, by introducing the time and / or round when the inspection point is divided into a sub-map, the interference of inspection priority order caused by the same pipeline features can be eliminated, which helps to make the inspection sequence of inspection points clearer and more explicit.

[0164] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0165] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0166] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0167] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0168] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0169] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0170] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A smart gas pipeline network inspection method, characterized in that, The intelligent gas pipeline safety management platform based on the intelligent gas pipeline inspection IoT system is implemented, and the method includes: Obtain the distribution of the gas pipeline network; Based on the gas pipeline network distribution, a first pipeline network map is constructed; The nodes of the first pipeline network map correspond to the branches of the gas pipeline network distribution; the edges of the first pipeline network map correspond to the pipes in the gas pipeline network distribution; wherein, one edge of the first pipeline network map corresponds to a pipe connecting two branches of the gas pipeline network. Based on the first pipeline network map, a probability determination model is used to output the probability that the nodes and / or edges of the first pipeline network map are patrol personnel's posts, based on the nodes and / or edges of the first pipeline network map; the probability determination model is a trained machine learning model. Based on the output of the nodes and edges of the first pipeline network map, at least one patrol personnel station is determined. Based on the gas pipeline network distribution and the at least one patrol personnel station, a second pipeline network map is constructed. The nodes of the second pipeline network map include pipeline network nodes and station nodes; the pipeline network nodes correspond to the pipeline branches in the gas pipeline network distribution; the station nodes correspond to the patrol personnel's station locations; the edges of the second pipeline network map correspond to the pipelines in the gas pipeline network distribution. Based on the second pipeline network map, at least one second pipeline network sub-map is determined by a preset sub-map segmentation method; Based on the at least one second pipeline sub-map, at least one inspection sub-region is determined; Based on the at least one inspection sub-region, an inspection plan is determined for each inspection sub-region within the at least one inspection sub-region; the inspection plan includes at least the inspection frequency.

2. The method according to claim 1, characterized in that, The inspection plan also includes an inspection route; the inspection sub-area includes a patrol personnel station and at least one inspection point. The process of determining the inspection plan for each inspection sub-region in the at least one inspection sub-region includes: The inspection route is defined as the route that starts from the patrol personnel's post and traverses each of the at least one inspection point within the inspection sub-region. Based on the inspection route, the inspection plan for the inspection sub-area is determined.

3. The method according to claim 2, wherein each of the at least one inspection point has an inspection priority value; The inspection route is determined based on the inspection priority value of each of the inspection points; The inspection priority value is determined based on the pipeline characteristics corresponding to the inspection point.

4. The method according to claim 1, wherein the intelligent gas pipeline inspection IoT system further comprises: Smart gas user platform, smart gas service platform, smart gas sensor network platform, smart gas object platform; The smart gas object platform is used to acquire the gas pipeline network distribution and transmit the gas pipeline network distribution to the smart gas pipeline network safety management platform through the smart gas sensor network platform. The method further includes: The inspection plan is fed back to the smart gas user platform based on the smart gas service platform.

5. The method according to claim 4, wherein the smart gas user platform includes a gas user sub-platform and a regulatory user sub-platform; The smart gas service platform includes a smart gas consumption service sub-platform corresponding to the gas user sub-platform and a smart regulatory service sub-platform corresponding to the regulatory user sub-platform. The intelligent gas pipeline safety management platform includes an intelligent gas pipeline inspection management sub-platform and an intelligent gas data center; wherein... The intelligent gas pipeline inspection management sub-platform includes an inspection plan management module, an inspection time early warning module, an inspection status management module, and an inspection problem management module. The intelligent gas sensing network platform includes an intelligent gas pipeline equipment sensing network sub-platform and an intelligent gas pipeline inspection engineering sensing network sub-platform. The intelligent gas platform includes an intelligent gas pipeline equipment platform and an intelligent gas pipeline inspection engineering platform.

6. A smart gas pipeline network inspection IoT system, characterized in that, The system includes: a smart gas user platform, a smart gas service platform, a smart gas pipeline safety management platform, a smart gas sensor network platform, and a smart gas object platform; The smart gas object platform is used to acquire the gas pipeline network distribution and transmit the gas pipeline network distribution to the smart gas pipeline network safety management platform through the smart gas sensor network platform. The intelligent gas pipeline safety management platform is configured as follows: Based on the gas pipeline network distribution, a first pipeline network map is constructed; The nodes of the first pipeline network map correspond to the branches of the gas pipeline network distribution; the edges of the first pipeline network map correspond to the pipes in the gas pipeline network distribution; wherein, one edge of the first pipeline network map corresponds to a pipe connecting two branches of the gas pipeline network. Based on the first pipeline network map, a probability determination model is used to output the probability that the nodes and / or edges of the first pipeline network map are patrol personnel's posts, based on the nodes and / or edges of the first pipeline network map; the probability determination model is a trained machine learning model. Based on the output of the nodes and edges of the first pipeline network map, at least one patrol personnel station is determined. Based on the gas pipeline network distribution and the at least one patrol personnel station, a second pipeline network map is constructed. The nodes of the second pipeline network map include pipeline network nodes and station nodes; the pipeline network nodes correspond to the pipeline branches in the gas pipeline network distribution; the station nodes correspond to the patrol personnel's station locations; the edges of the second pipeline network map correspond to the pipelines in the gas pipeline network distribution. Based on the second pipeline network map, at least one second pipeline network sub-map is determined by a preset sub-map segmentation method; Based on the at least one second pipeline sub-map, at least one inspection sub-region is determined; Based on the at least one inspection sub-region, an inspection plan is determined for each inspection sub-region within the at least one inspection sub-region; the inspection plan includes at least the inspection frequency; The smart gas service platform is used to feed back the inspection plan to the smart gas user platform.

7. The system according to claim 6, characterized in that, The inspection plan also includes an inspection route; the inspection sub-area includes a patrol personnel station and at least one inspection point. The intelligent gas pipeline safety management platform is further used for: The inspection route is defined as the route that starts from the patrol personnel's post and traverses each of the at least one inspection point within the inspection sub-region. Based on the inspection route, the inspection plan for the inspection sub-area is determined.

8. 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 intelligent gas pipeline inspection method as described in any one of claims 1 to 5.

Images