Intelligent gas pipeline blockage point positioning method and Internet of Things system

Abstract

The invention provides an intelligent gas pipeline blocking point positioning method and an Internet of Things system, the method is executed by a gas company management platform of the intelligent gas pipeline blocking point positioning Internet of Things system, and the method comprises the steps that a monitoring point is determined based on historical blocking point positions, and the monitoring point is located in a gas pipeline of a gas pipeline network; constructing a gas operation map based on the monitoring data corresponding to the monitoring points; based on the gas operation map, determining a target blockage point location; determining cleaning parameters based on the target blocked point location, wherein the cleaning parameters comprise a to-be-cleaned point location; and generating a cleaning instruction based on the cleaning parameter, and sending the cleaning instruction to the cleaning robot to clean the gas pipeline corresponding to the to-be-cleaned point location. By means of the method and the Internet of Things system, the blockage point position can be accurately determined, blockage cleaning can be carried out in time, formation of the blockage point is effectively avoided, normal flowing of fuel gas is promoted, and the pipeline risk is reduced.

Description

Technical Field

[0001] This specification relates to the field of pipeline monitoring, and in particular to a smart gas pipeline blockage location method and an Internet of Things system. Background Art

[0002] With the acceleration of urbanization, the scale and complexity of gas pipeline networks are increasing, and the detection and treatment of pipeline blockage problems are becoming increasingly important. Gas pipeline blockage not only affects the normal supply of gas, but may also cause safety hazards. Traditional detection methods such as manual inspections, hardware detection methods, and software detection methods can detect and handle blockage problems to a certain extent, but they have limitations such as low efficiency, high cost, and lack of real-time performance. Therefore, it is urgent to develop more efficient and intelligent detection technologies to detect pipelines in a timely manner for cleaning.

[0003] In order to solve the problem of pipeline blockage detection, CN103644457B proposes a pipeline blockage positioning method and device, which mainly generates infrasound in the pipeline and uses the propagation characteristics of infrasound in the pipeline to detect and locate the blockage position. However, the infrasound sensor may be interfered by environmental noise, which may affect the accurate detection of the sound wave signal and thus affect the accuracy of the blockage positioning.

[0004] Therefore, it is hoped to provide a smart gas pipeline blockage location method and Internet of Things system to better achieve efficient and accurate detection of gas pipeline blockage problems, thereby improving the safe operation level of urban gas pipeline networks. Summary of the invention

[0005] The invention content includes a smart gas pipeline blockage location method, characterized in that the method is executed by a gas company management platform of a smart gas pipeline blockage location Internet of Things system, including: determining a monitoring point based on a historical blockage point, the monitoring point is located in a gas pipeline of a gas network, and the historical blockage point is determined based on historical blockage data corresponding to a preset historical period; constructing a gas operation map based on the monitoring data corresponding to the monitoring point, the monitoring data including at least one of pipeline pressure and gas flow rate; determining a target blockage point based on the gas operation map; determining cleaning parameters based on the target blockage point, the cleaning parameters including a point to be cleaned; generating a cleaning instruction based on the cleaning parameters, and sending the cleaning instruction to a cleaning robot to clean the gas pipeline corresponding to the point to be cleaned.

[0006] The invention content also includes an Internet of Things system for locating smart gas pipeline blockages, characterized in that the Internet of Things system includes a government safety supervision management platform, a government safety supervision sensor network platform, a gas company management platform, a gas company sensor network platform, and a smart gas equipment object platform; the gas company management platform is configured to execute the aforementioned smart gas pipeline blockage locating method.

[0007] The aforementioned smart gas pipeline blockage location method and Internet of Things system can achieve beneficial effects including but not limited to the following: based on the smart gas pipeline blockage location Internet of Things system, an information operation closed loop can be formed between the various functional platforms, and coordinated and operated regularly under the unified management of the gas company management platform, thereby realizing the informatization and intelligence of smart gas pipeline blockage location; by determining the monitoring points through historical blockage points, collecting monitoring data to construct a gas operation map, the blockage points can be accurately determined, and the blockages can be cleared in time, effectively avoiding the formation of blockage points, thereby promoting the normal flow of gas and reducing pipeline risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] 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 a smart gas pipeline blockage location Internet of Things system according to some embodiments of this specification; Figure 2 is an exemplary flow chart of a method for locating a blockage point in a smart gas pipeline according to some embodiments of this specification; Figure 3 is a schematic diagram of determining a blocking point according to some embodiments of this specification; Figure 4 is a flow chart for determining cleaning parameters according to some embodiments of this specification; Figure 5 It is a schematic diagram of a model determined according to the effects shown in some embodiments of this specification.

[0009] Explanation of the accompanying drawings: 100-smart gas pipeline blockage positioning Internet of Things system; 110-government safety supervision management platform; 120-government safety supervision sensor network platform; 130-government safety supervision object platform; 131-gas company management platform; 140-gas company sensor network platform; 150-smart gas equipment object platform; 310-gas operation map; 311-data completeness; 312-preset completeness conditions; 313-supplementary data; 314-update map; 320-candidate blockage section; 330-blockage detection result; 331-blockage prediction model; 332-estimated blockage point; 340-target blockage point; 510-cleaned data; 520-candidate configuration parameters; 530-blockage degree; 540-effect determination model; 550-estimated cleaning effect. DETAILED DESCRIPTION

[0010] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0011] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0012] 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 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.

[0013] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0014] Figure 1This is a schematic diagram of the platform structure of a smart gas pipeline blockage location IoT system according to some embodiments of this specification. A blockage point refers to a point where a blockage exists in a gas pipeline. In some embodiments of this specification, a blockage point may also be referred to as a blockage point or a blockage point.

[0015] like Figure 1 As shown, the smart gas pipeline blockage positioning Internet of Things system 100 may include a government safety supervision management platform 110, a government safety supervision sensor network platform 120, a gas company management platform 131, a gas company sensor network platform 140 and a smart gas equipment object platform 150.

[0016] The government safety supervision and management platform 110 refers to a platform for supervising and safely managing gas pipelines. In some embodiments, the government safety supervision and management platform 110 can be configured in a processor and / or a server to coordinate and coordinate the connection and collaboration between various functional platforms, and to gather all the information of the Internet of Things, and provide perception management and control management functions for the Internet of Things operation system.

[0017] In some embodiments, the government security supervision management platform 110 may exchange data with the government security supervision sensor network platform 120 .

[0018] The government security supervision sensor network platform 120 is a functional platform for managing government sensor communications. In some embodiments, the government security supervision sensor network platform 120 can be configured as a communication network or a gateway, etc., and can realize the functions of sensing information sensor communications and controlling information sensor communications.

[0019] In some embodiments, the government safety supervision sensor network platform 120 can interact with the government safety supervision management platform 110 upwards and interact with the gas company management platform 131 downwards. For example, the gas company management platform 131 can send the relevant data of the gas pipeline blockage location 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 interact with the government safety supervision sensor network platform 120 upwardly and with the gas company sensor network platform 140 downwardly.

[0022] The gas company management platform 131 refers to a comprehensive management platform for relevant information of the gas company. In some embodiments, the gas company management platform 131 can be configured to execute a smart gas pipeline blockage location method. For details of the smart gas pipeline blockage location method, please refer to the description later in this specification.

[0023] In some embodiments, the gas company management platform 131 may also include a processor. The processor may process data and / or information obtained from other platforms. The processor may execute program instructions based on the data, information and / or processing results to perform one or more functions described in this application.

[0024] The gas company sensor network platform 140 refers to a comprehensive management platform for sensor information of the gas company. In some embodiments, the gas company sensor network platform 140 can be configured as a communication network or a gateway, etc., and can realize the functions of sensing information sensor communication and control information sensor communication.

[0025] In some embodiments, the gas company sensor network platform 140 can interact with the gas company management platform 131 upwards and interact with the smart gas equipment object platform 150 downwards. For example, the gas company management platform 131 can upload the monitoring data corresponding to the monitoring points obtained by the smart gas equipment object platform 150 to the government safety supervision management platform 110 through the gas company sensor network platform 140.

[0026] The smart gas equipment object platform 150 refers to a functional platform for executing cleaning instructions and obtaining cleaning data. In some embodiments, the smart gas equipment object platform 150 may include at least one pipeline cleaning device and at least one pipeline monitoring device.

[0027] The pipeline cleaning device refers to a functional device for cleaning in a gas pipeline, such as a cleaning robot, etc. In some embodiments, the pipeline cleaning device can be used to clean a gas pipeline.

[0028] The pipeline monitoring device refers to a functional device for monitoring the blockage in the gas pipeline, for example, a pressure sensor, a flow sensor, a blockage detector, etc. In some embodiments, the pipeline monitoring device can be used to monitor the blockage in the gas pipeline.

[0029] In some embodiments, the smart gas equipment object platform 150 can exchange data with the gas company management platform 131 through the gas company sensor network platform 140 .

[0030] In some embodiments, the platform in the smart gas pipeline blockage location IoT system 100 can be divided into smart gas and Wanghe smart gas secondary network. Among them, the smart gas primary network refers to the network where government users supervise the operation of the gas pipeline network, and the smart gas secondary network is the network that includes the operation of the gas pipeline network. In some embodiments, the same platform in the smart gas pipeline blockage location IoT system 100 can play different roles in the smart gas primary network and the smart gas secondary network.

[0031] In some embodiments, the smart gas primary network may include at least a smart gas primary network management platform, a smart gas primary network sensor network platform, and a smart gas primary network object platform. The smart gas primary network management platform may include a government safety supervision management platform, the smart gas primary network sensor network platform may include a government safety supervision sensor network platform, and the smart gas primary network object platform may include a government safety supervision object platform. The government safety supervision object platform may be a gas company management platform.

[0032] In some embodiments, the smart gas secondary network may include at least a smart gas secondary network management platform, a smart gas secondary network sensor network platform and a smart gas secondary network object platform. The smart gas secondary network management platform may include a gas company management platform, the smart gas secondary network sensor network platform may include a gas company sensor network platform, and the smart gas secondary network object platform may include a gas equipment object platform.

[0033] For more information about the functions of the smart gas pipeline blockage location IoT system 100, please refer to this manual Figure 2-Figure 5 and related instructions.

[0034] In some embodiments of the present specification, based on the smart gas pipeline blockage location 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 blockage location.

[0035] In some embodiments, when implementing a smart gas pipeline blockage location method, the gas company management platform can determine monitoring points based on historical blockage points; construct a gas operation map based on monitoring data corresponding to the monitoring points; determine target blockage points based on the gas operation map; determine cleaning parameters based on the target blockage points; generate cleaning instructions based on the cleaning parameters, and send the cleaning instructions to the cleaning robot to clean the gas pipeline corresponding to the point to be cleaned.

[0036] Figure 2 is an exemplary flow chart of a method for locating a blockage point in a smart gas pipeline 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 executed by a gas company management platform.

[0037] Step 210, determining monitoring points based on historical congestion points.

[0038] The monitoring point is a monitoring point where monitoring equipment is arranged. In some embodiments, the monitoring point can be located in the gas pipeline of the gas pipeline network. For example, the bifurcation, intersection, bend or special facility of the gas pipeline (such as filtering facilities, pressure regulating facilities, etc.).

[0039] In some embodiments, the gas company management platform may determine monitoring points based on a set of historical congestion points.

[0040] The historical blocking point set refers to the set of all historical blocking points within a preset historical time. The blocking point refers to the point where the blocking event occurs in the gas pipeline. For example, the blocking point may include a main road pipeline, a pipeline branch, a pipeline interface, etc. The historical blocking point is the point where the gas pipeline has a blocking event in the historical data. In some embodiments, the blocking point and the historical blocking point can be represented by coordinates, wherein the coordinates may include but are not limited to at least one of geographic coordinates and custom coordinates.

[0041] In some embodiments, the historical congestion point set may be determined by the gas company management platform based on historical congestion data corresponding to a preset historical period, wherein the preset historical period may be set based on prior experience and / or actual demand.

[0042] Historical congestion data refers to all relevant information and data about congestion events that occurred in the smart gas pipeline congestion point positioning IoT system in the past period of time. For example, historical congestion data may include historical congestion points in historical time.

[0043] In some embodiments, historical blockage points may be obtained in a variety of ways, for example, through manual monitoring, by starting a pipeline crawling robot, etc.

[0044] In some embodiments, the duration of the preset historical period can be determined based on accident characteristics of preset historical accidents in the gas pipeline.

[0045] The preset historical accident refers to an accident whose historical occurrence frequency meets the preset frequency condition. The preset frequency condition may include the highest historical occurrence frequency, or the historical occurrence frequency is higher than the frequency threshold, etc. The aforementioned frequency threshold may be determined based on prior experience.

[0046] The accident feature is used to characterize the identifiable attributes related to the gas pipeline accident. For example, the accident feature may include but is not limited to at least one of whether the blockage point is easy to monitor, the number of monitoring times, the number of accidents, and the cause of the accident.

[0047] The preset historical accidents and their corresponding accident characteristics can reflect the overall situation of the gas pipeline. For example, if the accident characteristics corresponding to the preset historical accident show that the accident was caused by a parts problem, it can be inferred that the gas pipeline corresponding to the preset historical accident is old. For another example, if the accident characteristics corresponding to the preset historical accident show that the accident is easy to monitor, it can be determined that the gas pipeline corresponding to the preset historical accident is not prone to accident omissions.

[0048] In some embodiments, if the preset historical accident corresponding to the gas pipeline is easy to monitor, a shorter preset historical time length can be set for the gas pipeline to reduce the data processing volume and thus improve data processing efficiency; if the preset historical accident corresponding to the gas pipeline is not easy to monitor, a longer preset historical time length can be set for the gas pipeline to obtain sufficient data, thereby more accurately analyzing the blockage situation of the gas pipeline.

[0049] In some embodiments, the gas company management platform may determine the monitoring point based on the cleaning frequency of each historical congestion point in the historical congestion point set. For example, the gas company management platform may calculate the cleaning frequency of each historical congestion point, and count the points whose cleaning frequency is greater than the cleaning threshold into the monitoring point. The cleaning threshold represents the critical value of the cleaning frequency, which may be determined based on prior experience.

[0050] In some embodiments, the cleaning frequency of the historical congestion point is related to the number of times the historical congestion point is cleaned within a unit of historical time. For example, the gas company management platform can calculate the cleaning frequency by formula (1): F=N / T(1) Among them, F is the cleaning frequency, T is the preset historical period, and N is the number of cleaning times.

[0051] In some embodiments, the gas company management platform can selectively enable monitoring equipment. When the cleaning frequency of a historical blockage point is greater than the cleaning threshold, it is necessary to focus on monitoring the point. At this time, the gas company management platform can use the historical blockage point with a cleaning frequency greater than the cleaning threshold as a monitoring point and enable the monitoring equipment corresponding to the aforementioned historical blockage point.

[0052] By selectively enabling monitoring devices, the quality of monitoring data can be improved, the amount of invalid data can be reduced, and the operating efficiency of the system can be improved.

[0053] Step 220, constructing a gas operation map based on the monitoring data corresponding to the monitoring points.

[0054] The gas operation map is a map used to reflect the actual position relationship between monitoring points, pipeline nodes and pipelines.

[0055] In some embodiments, the gas operation graph may include nodes and edges.

[0056] Among them, the nodes of the gas operation map can be used to characterize the monitoring points and pipeline nodes in the gas pipeline network. Monitoring points refer to the points where monitoring equipment is installed, and pipeline nodes refer to the key parts in the pipeline system. Among them, key parts refer to the parts in the gas pipeline network that have a significant impact on the safe operation of the gas pipeline network, which may include but are not limited to the bifurcations, intersections, bends, and special facilities (such as filtering facilities, pressure regulating facilities, etc.) of the pipeline.

[0057] In some embodiments, the nodes of the gas operation map have node attributes. For example, for the node corresponding to the monitoring point, its node attribute may include monitoring data, which can be obtained by the monitoring equipment set at the monitoring point, and may include but not limited to at least one of pipeline pressure and gas flow rate; for another example, for the node corresponding to the pipeline node, its node attribute may include the type of the pipeline node, wherein the aforementioned type may include but not limited to the bifurcation, intersection, bend, special facility (such as filtering facility, pressure regulating facility, etc.) of the pipeline, which can be determined according to the actual situation of the pipeline node.

[0058] The edges of the gas operation graph can be used to characterize the gas pipelines connecting different nodes. In some embodiments, the edges of the gas operation graph have edge attributes, and the edge attributes are used to characterize the characteristics of the gas pipeline. Exemplarily, the edge attributes may include but are not limited to the pipeline length. The pipeline length can be obtained from the government safety supervision management platform.

[0059] In some embodiments, the gas company management platform can construct a gas operation map based on the gas pipeline network, key parts in the gas pipeline network, monitoring points, and monitoring data corresponding to the monitoring points. Exemplarily, the gas company management platform can use the monitoring points and pipeline nodes in the gas pipeline network as nodes of the gas operation map, and the monitoring data corresponding to the monitoring points and the node types of the pipeline nodes as node attributes; use the gas pipelines connected between the nodes as the edges of the gas operation map, and use the lengths of the gas pipelines between the nodes as edge attributes to obtain a constructed gas operation map.

[0060] Step 230, determining the target blockage point based on the gas operation map.

[0061] Target congestion points refer to points that require special attention and where clearing measures need to be taken.

[0062] In some embodiments, the gas company management platform can determine the target blockage point based on the gas operation map in a variety of ways. For example, the gas company management platform can determine the node that meets the preset conditions in the gas operation map as the target blockage point. The preset conditions may include that the node has corresponding monitoring data, and the pipeline pressure of the pipeline where the node is located is greater than the pressure threshold, and the gas flow rate is less than the flow rate threshold. The pressure threshold and the flow rate threshold can be determined based on prior experience.

[0063] In some embodiments, the gas company management platform can also determine the candidate congestion section based on the gas operation map; obtain the congestion detection result of the candidate congestion section; and determine the target congestion point based on the congestion detection result. For more detailed instructions, please refer to this manual Figure 3 and its related description.

[0064] Step 240, determining cleaning parameters based on the target blockage point.

[0065] In some embodiments, the cleaning parameter is a parameter for measuring the cleaning performance of the cleaning robot when performing pipeline cleaning.

[0066] In some embodiments, the cleaning parameters may include a point to be cleaned, which refers to a position in the gas pipeline that needs to be cleaned.

[0067] In some embodiments, the cleaning parameters may also include the moving speed, cleaning intensity, cleaning tools, etc. of the cleaning robot. In some embodiments, the gas company management platform may divide the cleaning parameters into different categories according to the parameter items corresponding to the cleaning parameters. For example, the cleaning parameters may be divided into moving parameters, configuration parameters, etc. Among them, the moving parameters may include the point to be cleaned and the moving speed, and the configuration parameters may include the cleaning intensity and cleaning tools. The aforementioned moving parameters and configuration parameters may also include other types of parameters, which may be determined according to the actual situation of the cleaning robot.

[0068] For more detailed information about movement parameters, configuration parameters, movement speed, cleaning intensity, and cleaning tools, see Figure 4 and related descriptions.

[0069] In some embodiments, the gas company management platform can determine the cleaning parameters according to the target blocking point. For example, the gas company management platform can determine the cleaning parameters by taking the target blocking point as the point to be cleaned.

[0070] In some embodiments, the gas company management platform can determine movement parameters based on the location to be cleaned and the moving speed, and determine configuration parameters based on the cleaning data.

[0071] For detailed information on cleaning data, as well as how to determine movement parameters, configuration parameters, movement speed, cleaning intensity, and cleaning tools, see Figure 4 and related descriptions.

[0072] Step 250, generating a cleaning instruction based on the cleaning parameters, and sending the cleaning instruction to the cleaning robot to clean the gas pipeline at the cleaning point.

[0073] Cleaning instructions refer to a series of specific operation commands issued from the gas company management platform during pipeline cleaning operations, which are used to guide cleaning robots or cleaning equipment to perform specific cleaning tasks. In some embodiments, cleaning instructions may include cleaning parameters. In some embodiments, according to the specific content of the cleaning instructions, cleaning instructions can be divided into movement instructions and configuration instructions. Among them, movement instructions are used to control the movement of the cleaning robot; configuration instructions are used to control the cleaning intensity of the cleaning robot and its configured cleaning tools. For more information about cleaning instructions, please refer to Figure 4 and related descriptions.

[0074] In some embodiments, the gas company management platform may generate a cleaning instruction based on the cleaning parameters. For example, the gas company management platform may generate a cleaning instruction including the cleaning parameters, such as cleaning the points to be cleaned in the gas pipeline.

[0075] In some embodiments, the gas company management platform can transmit the cleaning instructions to the smart gas equipment object platform through the gas company sensor network platform to control the cleaning robot in the smart gas equipment object platform to clean the gas pipeline according to the cleaning parameters.

[0076] Gas pipelines may form accumulated impurities due to gas impurities, pipeline corrosion, foreign matter intrusion, etc., thus forming blockage points and affecting the normal flow of gas. In some embodiments of this specification, the gas company management platform determines the monitoring points through historical blockage points, collects monitoring data to build a gas operation map, can accurately determine the blockage points, and clear the blockage in time, effectively avoiding the formation of blockage points, thereby promoting the normal flow of gas and reducing pipeline risks.

[0077] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0078] Figure 3 It is a schematic diagram of determining a blockage point according to some embodiments of this specification.

[0079] like Figure 3 As shown, in some embodiments, the gas company management platform can determine a candidate congestion section 320 based on the gas operation map 310 ; obtain a congestion detection result 330 of the candidate congestion section 320 ; and determine a target congestion point 340 based on the congestion detection result 330 .

[0080] The candidate blocked section refers to a pipeline section where a blockage point may exist. In some embodiments, the candidate blocked section may include at least one pipeline section where a blockage point may exist.

[0081] Candidate blocked sections can be determined in a variety of ways. In some embodiments, the gas company management platform can determine candidate blocked sections based on the gas operation map. For example, the gas company management platform can determine the pipeline where the node that meets the preset conditions is located, and the upstream and downstream gas pipelines of the node as candidate blocked sections. Among them, the preset conditions may include the existence of corresponding monitoring data in the stage, and the pipeline pressure of the gas pipeline where the node is located is greater than the pressure threshold, and the gas flow rate is less than the flow rate threshold.

[0082] In some embodiments, the gas company management platform can also evaluate the data completeness 311 of the gas operation map 310, and in response to the data completeness 311 not satisfying the preset completeness condition 312: determine the data request, and send the data request to the government safety supervision management platform to obtain supplementary data 313; based on the acquisition of the supplementary data, update the gas operation map to obtain an updated map 314; based on the updated map 314, determine the candidate blocked section 320.

[0083] In some cases, due to data permissions, untimely data collection or other possible reasons, the government safety supervision and management platform is unable to send all the data required to build the gas operation map to the gas company management platform in the first time. At this time, the gas company management platform can first build a gas operation map based on the obtained data, and determine whether it is necessary to further obtain data from the government safety supervision and management platform by evaluating the data completeness.

[0084] Data completeness is a value that represents the degree of completeness of the attribute data corresponding to the node in the gas operation map. The higher the data completeness, the more complete the attribute data corresponding to the node in the gas operation map.

[0085] In some embodiments, the data completeness may include the degree of perfection of the detection data corresponding to the monitoring points in the gas operation map. Exemplarily, the gas company management platform may evaluate the data completeness of the gas operation map based on the number of nodes with monitoring data in the gas operation map and the total number of nodes representing the monitoring points in the gas operation map. The more nodes with monitoring data, the higher the data completeness. Exemplarily, the data completeness is determined based on the percentage of the number of nodes with monitoring data to the total number of nodes representing the monitoring points.

[0086] In some embodiments, the preset completeness condition may be that the data completeness is not less than a completeness threshold.

[0087] The completeness threshold is a numerical value that characterizes the minimum standard of data completeness. In some embodiments, the completeness threshold can be set based on prior experience and / or actual needs.

[0088] In some embodiments, the completeness threshold is positively correlated with the area of ​​the gas network. For example, the larger the area of ​​the gas network, the higher the completeness threshold. In some embodiments, the area of ​​the gas network can be obtained from the government safety supervision management platform by the gas company management platform through the government safety supervision sensor network platform.

[0089] Since the larger the area of ​​the region, the wider the range of the pipeline in the region, by setting a completeness threshold that is positively correlated with the area of ​​the region, the comprehensiveness of the data can be improved, thereby more accurately judging the blockage situation of the gas pipeline network.

[0090] In some embodiments, in response to the data completeness of the gas operation map not meeting a preset completeness condition, the gas company management platform may determine a data request and send the data request to the government safety supervision management platform through the government safety supervision sensor network platform.

[0091] A data request is a message used to request additional data.

[0092] The supplementary data is data used to supplement the missing node attributes in the gas operation map. In some embodiments, the supplementary data can be used to improve the data completeness of the existing monitoring data.

[0093] In some embodiments, the gas company management platform may send a data request to the government safety supervision management platform through the government safety supervision sensor network platform to request to obtain supplementary data.

[0094] In some embodiments, the gas company management platform may update the gas operation map based on the acquisition of supplementary data to obtain an updated map.

[0095] The updated graph refers to a new gas operation graph obtained by improving the missing node attributes in the gas operation graph. The missing node attributes refer to the missing monitoring data of the node corresponding to the monitoring point in the gas operation graph.

[0096] In some embodiments, in response to obtaining the supplementary data, the gas company management platform may update the gas operation map based on the supplementary data to obtain an updated gas operation map. For example, the gas company management platform may supplement the missing node attributes in the gas operation map based on the supplementary data, and in response to the data completeness of the gas operation map after the data supplementation meets the preset completeness condition, the gas company management platform may determine the gas operation map after the data supplementation as an updated map.

[0097] In some embodiments, in response to the data completeness of the gas operation map after data supplementation still not meeting the preset completeness condition, the gas company management platform can process the gas operation map after data supplementation through a preset method to determine the estimated value of the missing monitoring data, and further improve the gas operation map based on the estimated value to obtain an updated map. The aforementioned preset method can be an interpolation method, and the detailed description of the interpolation method can be found in the relevant description below.

[0098] In some embodiments, in response to failure to obtain supplementary data, the gas company management platform may determine estimated monitoring data based on the gas operation map; update the gas operation map based on the estimated monitoring data, and obtain an updated gas operation map.

[0099] The estimated monitoring data is the estimated value of the missing monitoring data in the gas operation map. For example, in the gas operation map node, the estimated monitoring data may include one of the monitoring node and the pipeline node.

[0100] In some embodiments, the gas company management platform may determine the estimated monitoring data based on the gas operation map by a preset method, wherein the preset algorithm may be an interpolation method.

[0101] In some embodiments, determining the estimated monitoring data by interpolation method may include the following: the gas company management platform can obtain the actual position coordinates of the nodes in the gas operation map, determine multiple discrete scattered points based on the nodes with monitoring data, and perform interpolation calculations based on the multiple discrete points to obtain the estimated monitoring data corresponding to the nodes that do not have monitoring data.

[0102] There may be multiple types of interpolation methods, for example, at least one of Lagrange algorithm and Newton interpolation, and other algorithms capable of implementing interpolation calculations.

[0103] In some embodiments, in response to obtaining blockage data of at least one blockage point, the gas company management platform may update the gas operation map.

[0104] The blockage data is data characterizing the components of the blockage, and may include component information of at least one component causing the blockage, and the ratio of each component.

[0105] In some embodiments, the blocking point may be a node in the gas operation map or a point that does not belong to the gas operation map. In response to the aforementioned blocking point being a node in the gas operation map, the gas company management platform may add its corresponding blocking object data as a new node attribute to the gas operation map; in response to the aforementioned blocking point being a point that does not belong to the gas operation map, the gas company management platform may add the blocking point as a supplementary node to the gas operation map, and determine the connection relationship between the supplementary node and other nodes based on the gas pipeline where the blocking point is located, and then determine the newly added edge between the supplementary node and the original node in the gas operation map, wherein the node attribute corresponding to the supplementary node is the blocking object data corresponding to the blocking point, and the edge feature corresponding to the newly added edge is the length of the gas pipeline corresponding to the newly added edge.

[0106] Based on the data of the blockage points and their corresponding blockage objects in the gas pipeline, the nodes and node attributes in the gas operation map are expanded, so that a gas operation map with richer data can be obtained, thereby obtaining a more extensive and accurate candidate blockage interval determination result.

[0107] In some embodiments, in response to the data completeness of the gas operation map meeting the preset completeness conditions, the gas company management platform can determine the candidate congestion sections based on the gas operation map; in response to the data completeness of the gas operation map not meeting the preset completeness conditions, the gas company management platform can determine the candidate congestion sections based on the updated map.

[0108] In some embodiments, the gas company management platform can determine the candidate blocked sections based on the node attributes of each node in the gas operation map or update map. For example, the gas company management platform can determine the node with monitoring data, pipeline pressure greater than the pressure threshold, and gas flow rate less than the flow rate threshold as the target node, and determine the target node and its upstream and downstream pipelines as the candidate blocked sections.

[0109] Since the gas operation map before the update is incomplete, the gas company management platform determines whether the gas operation map data before the update is complete by evaluating the data completeness. In some embodiments of this specification, the gas operation map with incomplete data is supplemented by the gas operation map to obtain a more complete updated map; determining the candidate blocked section in the gas pipeline based on the updated map can obtain more extensive and accurate results.

[0110] In some embodiments, the gas company management platform may obtain the congestion detection results of the candidate congestion sections.

[0111] The congestion detection result is a data sequence used to reflect the congestion situation in the candidate congestion section. In some embodiments, the congestion detection result may include a sound wave reflection duration sequence of at least one position in the candidate congestion section.

[0112] In some embodiments, the gas company management platform can control the sound wave transmitting device outside the candidate blockage section to transmit sound wave signals, and use the receiving device to capture and analyze the reflection, scattering or attenuation characteristics of the sound waves when propagating inside the pipeline, so as to obtain the blockage detection results.

[0113] In some embodiments, the gas company management platform can determine the target congestion point based on the congestion detection result. In some embodiments, the gas company management platform can calculate the gradient of adjacent sound wave reflection time in the sound wave reflection time sequence for each congestion detection result, and use the position corresponding to the point with the largest gradient change as the target congestion point of the candidate congestion section.

[0114] In some embodiments, the target congestion point may further include an estimated congestion point where congestion may occur in the future.

[0115] In some embodiments, the gas company management platform may determine an estimated congestion point 332 within a future period of time based on the congestion detection result 330 through a congestion prediction model 331 .

[0116] The congestion prediction model refers to a model used to determine the estimated congestion points and their corresponding congestion levels within a period of time in the future. In some embodiments, the congestion prediction model may be a machine learning model, such as a deep neural network (DNN) model.

[0117] In some embodiments, the input of the congestion prediction model may include the congestion detection result, and the output of the congestion prediction model may include the estimated congestion point in the gas pipeline network in the future period of time. The future period of time can be set based on actual needs. For a detailed description of the congestion detection result, please refer to this specification Figure 2 Related description in .

[0118] The estimated blockage point refers to at least one point in the gas pipeline network where blockage may occur within a period of time in the future.

[0119] The degree of blockage refers to the proportion of space inside the gas pipeline occupied by the blockage. In some embodiments, the degree of blockage can be represented by a numerical value, and the larger the numerical value, the higher the degree of blockage.

[0120] In some embodiments, the congestion prediction model can be obtained by training the initial prediction model based on a large number of first training samples with first labels. The gas company management platform can input multiple first training samples with first labels into the initial prediction model, construct a loss function through the first labels and the output results of the initial prediction model, and iteratively update the initial prediction model based on the loss function. When the end condition is met, the training is completed and a trained congestion prediction model is obtained. The preset conditions may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0121] In some embodiments, the first training sample may be a sample detection result of a sample congestion section at a first historical time in historical data. The sample detection result refers to a congestion detection result in historical data.

[0122] In some embodiments, the first label may be a historical blockage point detected by the sample blockage section at a second historical time in the historical data, wherein the second historical time is later than the first historical time.

[0123] In some embodiments of the present specification, through the congestion prediction model, the congestion pattern can be learned from historical data, thereby improving the accuracy of predicting future congestion events, facilitating early regulation of possible congestion points, and reducing the possibility of accidents.

[0124] In some embodiments of this specification, the gas company management platform uses the gas operation map to perform a preliminary assessment of the section that may be blocked, and by further detecting the internal conditions of the section that may be blocked, more accurate results can be obtained to optimize maintenance work.

[0125] Figure 4 1 is a flow chart of determining cleaning parameters according to some embodiments of this specification. Figure 4 As shown, the process 400 includes the following steps 410 to 450. In some embodiments, the process 400 may be executed by a gas company management platform.

[0126] In some embodiments, the processor can determine the movement parameters based on the point to be cleaned and the moving speed, and control the cleaning robot to clean the point to be cleaned based on the movement parameters; in response to the cleaning robot arriving at the point to be cleaned, control the cleaning robot to perform preliminary cleaning according to a preset configuration; in response to obtaining the cleaning data fed back by the cleaning robot, determine the configuration parameters based on the cleaning data; generate a configuration update instruction based on the configuration parameters, and send the configuration update instruction to the cleaning robot.

[0127] In some embodiments, controlling a cleaning robot to clean a location to be cleaned based on movement parameters may include: sending the movement parameters to a government security supervision and management platform; in response to obtaining a confirmed cleaning instruction from the government security supervision and management platform, generating a movement instruction based on the movement parameters, and sending it to the cleaning robot to control the cleaning robot to clean the location to be cleaned.

[0128] Step 410, determining the movement parameters of the cleaning robot based on the location to be cleaned and the movement speed, and sending the movement parameters to the government safety supervision management platform.

[0129] The movement parameters are parameters used to characterize the movement characteristics of the cleaning robot. In some embodiments, the movement parameters may include the points to be cleaned and the movement speed. For detailed descriptions of the points to be cleaned and their determination, see Figure 2 Related description in .

[0130] The moving speed refers to the speed at which the cleaning robot moves in the gas pipeline network during cleaning operations.

[0131] In some embodiments, the gas company management platform may determine the moving speed of the cleaning robot based on prior experience or actual needs.

[0132] In some embodiments, the moving speed may be related to the distribution sparseness of the points to be cleaned in the area where the points to be cleaned are located. The greater the distribution sparseness, the slower the moving speed of the cleaning robot in the area.

[0133] Distribution sparsity refers to the degree of distribution sparsity of the points to be cleaned. In some embodiments, the distribution sparsity can be represented by a numerical value, where a larger numerical value indicates a more sparse distribution of the points to be cleaned, and a smaller numerical value indicates a more dense distribution of the points to be cleaned.

[0134] In some embodiments, the gas company management platform can determine the distribution sparsity based on the point distance between the points to be cleaned. For example, the gas company management platform can count the point distance between every two points to be cleaned among multiple points to be cleaned, and calculate the mean value based on all the point distances corresponding to the multiple points to be cleaned, and the calculated mean value is the distribution sparsity.

[0135] In some embodiments of the present specification, evaluating the moving speed based on the distribution sparsity is helpful to improve the cleaning efficiency. The larger the distribution sparsity, the more dispersed the points to be cleaned are, and the higher the probability of blockage between the points to be cleaned. Based on the larger distribution sparsity, appropriately reducing the moving speed of the cleaning robot can enable the cleaning robot to perform more detailed cleaning between two points to be cleaned.

[0136] In some embodiments, the gas company management platform processor can determine the movement parameters of the cleaning robot based on the points to be cleaned and the moving speed. For example, the gas company management platform can directly use the determined points to be cleaned and the moving speed as the movement parameters.

[0137] In some embodiments, the gas company management platform can send the mobile parameters to the smart gas equipment object platform through the gas company sensor network platform. For more information about the gas company management platform and the smart gas equipment object platform, please refer to Figure 1 Related description.

[0138] Step 420, in response to obtaining a confirmed cleaning instruction from the government security supervision management platform, generating a movement instruction based on the movement parameters, and sending the movement instruction to the cleaning robot to control the cleaning robot to clean the point to be cleaned.

[0139] Confirming a cleaning instruction refers to confirming the instruction to clean the points to be cleaned.

[0140] In some embodiments, the gas company management platform can obtain confirmation and cleanup instructions from the government safety supervision management platform through the government safety supervision sensor network platform. For more information about the government safety supervision management platform and the government safety supervision sensor network platform, please refer to Figure 1 Related description.

[0141] The movement instruction refers to the instruction for controlling the cleaning robot to move.

[0142] In some embodiments, in response to obtaining a confirmed cleaning instruction from the government safety supervision management platform, the gas company management platform can generate a movement instruction based on the movement parameters. For example, the processor generates a movement instruction based on the movement parameters through path planning technology, and the movement instruction may include at least one to-be-cleaned point that the cleaning robot needs to reach, the order in which the at least one to-be-cleaned point is cleaned, and the movement speed from the current to-be-cleaned point to the next to-be-cleaned point, etc.

[0143] In some embodiments, the gas company management platform can send movement instructions to the smart gas equipment object platform through the gas company sensor network platform to control the cleaning robot in the smart gas equipment object platform to reach the cleaning point based on the aforementioned movement instructions to clean the blocked location in the gas pipeline network. For more information about the smart gas equipment object platform, please refer to Figure 1 Related description.

[0144] Step 430, in response to the cleaning robot arriving at the point to be cleaned, controlling the cleaning robot to perform preliminary cleaning according to a preset configuration.

[0145] The preset configuration refers to a preset cleaning configuration of the cleaning robot. In some embodiments, the preset configuration may include at least one of a preset cleaning intensity and a preset cleaning tool. Wherein, the preset cleaning intensity refers to a preset cleaning intensity, and the preset cleaning tool refers to a preset tool for cleaning.

[0146] In some embodiments, the intensity of cleaning can be represented by a numerical value of 1-10, and a larger numerical value indicates a higher preset cleaning intensity. In some embodiments, the preset cleaning tool can include but is not limited to one or more of a brush, a scraper, a high-pressure nozzle, etc.

[0147] In some embodiments, the preset configuration may be set based on a priori experience.

[0148] Initial cleaning refers to the first round of cleaning performed by the cleaning robot on the cleaning point.

[0149] In some embodiments, the gas company management platform can send the preset configuration to the smart gas equipment object platform through the gas company sensor network platform to control the cleaning robot in the smart gas equipment object platform to perform preliminary cleaning of the blocked locations in the gas pipeline network according to the preset configuration.

[0150] Step 440, in response to obtaining the cleaning data fed back by the cleaning robot, determining configuration parameters based on the cleaning data.

[0151] The cleaning data refers to the data on the blockage situation fed back by the cleaning robot after the first round of cleaning of the points to be cleaned. In some embodiments, the cleaning data may include the distribution of the components of the blockage at the points to be cleaned.

[0152] In some embodiments, the gas company management platform can perform component analysis on the cleared obstruction to determine the clearing data, wherein the obstruction refers to an object that blocks the gas pipeline.

[0153] Configuration parameters are parameters that characterize the configuration of the cleaning robot. In some embodiments, the configuration parameters may include at least one of cleaning intensity and cleaning tools. The cleaning intensity may be represented by a numerical value, the larger the numerical value, the greater the cleaning intensity, and the type of cleaning tool is similar to the preset cleaning tool, and the relevant description can be found in the above text.

[0154] In some embodiments, in response to obtaining the cleaning data fed back by the cleaning robot, the gas company management platform can determine the configuration parameters in a variety of ways based on the cleaning data.

[0155] Exemplarily, the gas company management platform can determine the configuration parameters of the cleaning robot based on the cleaning data by matching in a reference configuration database.

[0156] In some embodiments, the gas company management platform can determine candidate reference data based on historical data of the gas pipeline network, and screen the candidate reference data according to preset screening criteria to determine the reference data. The candidate reference data may include at least one piece of data representing the historical cleaning situation, and the reference data may include at least one piece of data representing the historical cleaning situation after screening. Each piece of data may include the historical congestion degree after historical cleaning, historical cleaning data, historical configuration parameters, and the historical congestion degree after cleaning.

[0157] The preset screening standard may be that the rate of change of the degree of congestion is greater than a threshold value of the rate of change. The rate of change of the degree of congestion may be determined based on the ratio of the change value of the degree of congestion at the point to be cleaned to the initial degree of congestion before cleaning, the change value of the degree of congestion may be determined based on the difference between the initial degree of congestion before cleaning and the historical degree of congestion after cleaning, and the threshold value of the rate of change may be determined based on prior experience.

[0158] In some embodiments, the gas company management platform can construct at least one vector to be clustered based on the historical cleanup data in the reference data and its corresponding historical configuration parameters, cluster the at least one vector to be clustered, and obtain a preset number of cluster centers. The gas company management platform can determine the historical cleanup data corresponding to the cluster center as the reference cleanup data, and determine the historical configuration parameters corresponding to the cluster center as the reference configuration parameters. The preset number can be set based on prior experience and / or actual needs.

[0159] In some embodiments, the gas company management platform can build a reference configuration database based on reference cleansing data and reference configuration parameters, and match the cleansing data provided by the cleansers and their feedback in the reference configuration database to obtain the reference cleansing data with the highest similarity to the cleansing data, and determine the reference configuration parameters corresponding to the reference cleansing data as the configuration parameters corresponding to the cleansing data.

[0160] In some embodiments, the gas company management platform can also obtain candidate configuration parameters based on historical cleaning data; determine the estimated cleaning effect of the candidate configuration parameters based on the cleaning data; and determine the candidate configuration parameters whose estimated cleaning effect meets the preset cleaning target as configuration parameters.

[0161] Historical data refers to the relevant data when the cleaning robot performs historical cleaning operations. In some embodiments, the historical data may include at least one piece of data representing the historical cleaning situation, and each piece of data may include the historical congestion degree after historical cleaning, historical cleaning data, historical configuration parameters, and the historical congestion degree after cleaning.

[0162] Candidate configuration parameters refer to alternative configuration parameters.

[0163] In some embodiments, the gas company management platform can filter the historical data according to the preset filtering criteria to obtain at least one candidate data, and determine the historical cleanup data with a number of occurrences greater than the number threshold in the candidate data as the candidate configuration parameter. For detailed description of the preset filtering criteria, please refer to the above description.

[0164] The estimated cleaning effect refers to the estimated effect after cleaning. In some embodiments, the estimated cleaning effect can be represented by a numerical value of 1-10, and a larger numerical value indicates a better estimated cleaning effect.

[0165] In some embodiments, the gas company management platform may determine the estimated cleaning effect corresponding to the candidate configuration parameters in a variety of ways.

[0166] Exemplarily, the processor may determine the estimated cleaning effect by querying a cleaning effect evaluation table based on the cleaning data and the candidate configuration parameters, wherein the cleaning effect evaluation table includes at least one reference evaluation data, each reference evaluation data including reference cleaning data, reference configuration parameters, and their corresponding reference cleaning effect.

[0167] In some embodiments, the cleaning effect evaluation table can be constructed based on reference data. Exemplarily, the gas company management platform can construct a cleaning vector based on the historical cleaning data, historical configuration parameters and the rate of change of the degree of congestion in the reference data, and cluster the cleaning vector to form a preset number of cluster centers, and determine the historical cleaning data and historical configuration parameters corresponding to the cluster centers as reference cleaning data and reference configuration parameters, and determine the rate of change of the degree of congestion corresponding to the cluster centers as the corresponding reference cleaning effect. For the acquisition of reference data, please refer to the relevant description above.

[0168] In some embodiments, the gas company management platform can query in the cleaning effect evaluation table based on the cleaning parameters and candidate configuration parameters to determine the closest reference cleaning data and reference configuration parameters, and determine the reference cleaning effect corresponding to the reference cleaning data and reference configuration parameters as the estimated cleaning effect corresponding to the candidate configuration parameters.

[0169] In some embodiments, the gas company management platform can also determine the estimated cleaning effect of the candidate configuration parameters based on the cleaning data through the effect determination model. For a detailed description of the effect determination model, please refer to this specification Figure 5 and its related description.

[0170] In some embodiments, the gas company management platform may determine the configuration parameters based on the estimated cleaning effects of the candidate configuration parameters. For example, the gas company management platform may determine the candidate configuration parameters whose estimated cleaning effects meet the preset cleaning targets as the configuration parameters.

[0171] The preset cleaning target refers to the preset cleaning effect that is expected to be achieved. In some embodiments, the preset cleaning target can be represented by a change rate threshold. When the blockage degree changes and is greater than the change rate threshold, the preset cleaning target can be considered to be achieved. The change rate threshold represents the minimum expected value of the change rate of the blockage degree of the gas pipeline and / or the gas pipeline to be cleaned. In some embodiments, the preset cleaning target can be set based on prior experience and / or actual needs.

[0172] In some embodiments, the gas company management platform determines the candidate configuration parameters whose estimated cleaning effects are not less than the change rate threshold as configuration parameters.

[0173] In some embodiments of the present specification, candidate configuration parameters are determined based on historical cleaning data, the cleaning effect is determined based on the cleaning parameters and the candidate configuration parameters, and the configuration parameters are further determined, which is conducive to selecting the configuration parameters with the best effect, thereby better ensuring the cleaning effect of the cleaning robot.

[0174] Step 450: Generate a configuration update instruction based on the configuration parameters, and send the configuration update instruction to the cleaning robot.

[0175] Configuration update instructions are instructions for updating the cleaning robot configuration.

[0176] In some embodiments, the processor may generate corresponding configuration update instructions based on the configuration parameters to control the cleaning robot to update relevant configurations.

[0177] In some embodiments, the processor may send a configuration update instruction based on the smart gas device object platform. For more information about the smart gas device object platform, see Figure 1 Related description.

[0178] In some embodiments of the present specification, movement parameters are determined based on the cleaning point and the moving speed, and movement instructions are generated based on the movement parameters to control the cleaning robot to reach the cleaning point and control the cleaning robot to perform preliminary cleaning according to the preset configuration. Configuration parameters are determined based on the cleaning data fed back by the cleaning robot, and configuration update instructions are further determined. This is conducive to ensuring the compliance and safety of the cleaning process, and is conducive to determining configuration update instructions suitable for pipeline cleaning, ensuring the use of optimal cleaning tools and cleaning volume, reducing unnecessary cleaning times of the cleaning robot, and thereby avoiding damage to the gas pipeline while maintaining energy saving and high efficiency.

[0179] It should be noted that the above description of the process 200 and the process 400 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 and the process 400 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0180] Figure 5 It is a schematic diagram of a model determined according to the effects shown in some embodiments of this specification.

[0181] In some embodiments, the gas company management platform may determine the estimated cleaning effects of the candidate configuration parameters based on the cleaning data through an effect determination model.

[0182] For more information about cleaning data, candidate configuration parameters, and estimated cleaning effects, see Figure 2 and Figure 4 Related description.

[0183] The effect determination model refers to a model used to determine the estimated cleaning effect. In some embodiments, the effect determination model can be a machine learning model, such as a deep neural network (DNN), a graph neural network (GNN), etc.

[0184] In some embodiments, Figure 5 As shown, the input of the effect determination model 540 may include cleaning data 510 and candidate configuration parameters 520 , and the output may be an estimated cleaning effect 550 .

[0185] In some embodiments, the effect determination model can be obtained by training in a variety of ways. For example, the effect determination model can be obtained by training the initial determination model through multiple sets of training samples with training labels. A set of training samples for training the effect determination model can include sample cleaning data and sample configuration parameters, and the training labels corresponding to the training samples are historical cleaning effects when cleaning based on the sample cleaning data and sample configuration parameters.

[0186] In some embodiments, training samples and their corresponding training labels can be obtained based on historical data. For example, historical cleaning data and historical configuration parameters corresponding to at least one cleaning operation in historical data are obtained, and the historical cleaning effect is determined based on the difference between the degree of congestion before cleaning and the degree of congestion after cleaning. The gas company management platform can determine the historical cleaning data and historical configuration parameters as sample cleaning data and sample configuration parameters, and determine the historical cleaning effect as a training label. For an explanation of the degree of congestion, please refer to the relevant description above.

[0187] In some embodiments, the gas company management platform can perform multiple rounds of iterative training on the initial effect determination model based on multiple sets of training samples with training labels. The training process is similar to the training process of the congestion prediction model, which can be seen in Figure 3 See the relevant instructions in .

[0188] In some embodiments, Figure 5As shown, the input of the effect determination model 540 may also include the estimated congestion point 332 and the corresponding congestion degree 530 within a future period of time.

[0189] For more information on estimating congestion points and congestion levels, see Figure 3 See the relevant instructions in .

[0190] In some embodiments, the training samples of the training effect determination model may further include sample blockage points and sample blockage degrees, and the sample blockage points and sample blockage degrees may be acquired based on historical data.

[0191] In some embodiments, the gas company management platform can train the effect determination model based on training samples including sample blockage points, sample blockage degrees, sample cleaning data, and sample candidate configuration parameters. For the training method of the effect determination model, please refer to the relevant description above.

[0192] In some embodiments of the present specification, the blockage point and the degree of major blockage are used as inputs to the effect determination model, and the generation rate of gas pipeline blockages can be considered, thereby improving the accuracy of the effect determination model in determining the cleaning effect, providing more accurate reference data for subsequent cleaning operations, and making cleaning more effective.

[0193] In some embodiments, the gas company management platform can split the sample data set according to a preset ratio to obtain a training set, a validation set, and a test set; use the training set, the validation set, and the test set to train the initial effect determination model to obtain an effect determination model.

[0194] The preset ratio refers to the ratio of the training set, validation set and test set to the sample data set. For example, the ratio of the training set, validation set and test set to the sample data set may be 8:1:1.

[0195] In some embodiments, the preset ratio may be pre-set by the gas company management platform based on default settings or prior experience.

[0196] The sample data set is historical data that can be used as training samples. In some embodiments, the sample data set may include historical cleaning data and historical configuration parameters corresponding to the gas pipeline in at least one historical time period.

[0197] In some embodiments, the sample data set may be extracted from a storage device by the gas company management platform based on default settings or based on prior experience.

[0198] In some embodiments, the processor splits the sample data set based on a preset ratio to obtain a training set, a validation set, and a test set.

[0199] The splitting method may include sampling statistics, and the sampling statistics may include but are not limited to random sampling, stratified sampling, etc. In some embodiments, the gas company management platform may also split the sample data set in other ways.

[0200] The training set refers to the data set used to train the effect determination model.

[0201] The test set is the data set used to evaluate the performance of the effect determination model.

[0202] The validation set is the data set used to select the best performing model.

[0203] There is no data overlap between the training set, validation set, and test set obtained by splitting, that is, there is no duplicate data between any two of the training set, validation set, and test set.

[0204] In some embodiments, the gas company management platform can train the initial effect determination model based on the training set, the validation set and the test set to obtain the effect determination model. The training process includes multiple stages of training. Among them, one stage of training includes: inputting the training set into the initial effect determination model, constructing a loss function based on the training label and the output of the initial effect determination model, and updating the parameters of the initial effect determination model through multiple rounds of iterations based on the loss function; in the aforementioned training process, based on a pre-set validation frequency, the trained initial effect determination model is verified through the validation set, and the initial learning rate or the learning rate in the initial effect determination model training process after this round of training is adjusted based on the validation results. A variety of strategies can be used to adjust the learning rate, such as one or more of the methods such as the learning rate attenuation strategy, the learning rate preheating, the cyclic learning rate, and the use of an adaptive learning rate adjustment algorithm.

[0205] The verification frequency refers to the frequency of verifying the initial effect determination model after training, for example, the model is verified after every n rounds of training; in response to the verification condition being met, an intermediate model is obtained, and the intermediate model is tested through a test set to evaluate the performance of the intermediate model obtained by the training of this stage, wherein the intermediate model refers to the effect determination model obtained after stage training, and the performance of the intermediate model can refer to the accuracy of the intermediate model output, and the verification condition refers to the condition for verifying the current training result, which can include one or more of the number of iterations reaching a threshold, the loss function converging, and the value of the loss function being less than a preset threshold. Perform multiple stages of training, and use the effect determination model with the best performance as the trained effect determination model.

[0206] The learning rate refers to the parameter that controls the step size when updating model parameters during model training. It determines the amplitude of updating parameters along the direction of the fastest decrease of the loss function during the process of model training by gradient descent (or other optimization algorithms) to determine the initial effect.

[0207] In some embodiments, different initial learning rates may be used when training a model using different sample data sets, and the initial learning rate of each sample data set is related to the sample statistical difference of the sample data set. In some embodiments, the gas company management platform may determine the initial learning rate of the model based on the sample statistical difference. For example, the larger the sample statistical difference, the smaller the initial learning rate.

[0208] Generally, the greater the statistical difference of the samples, the higher the uncertainty of the results of pipeline cleaning and the greater the influence of potential factors. Therefore, a smaller learning rate should be determined for such samples to better explore the implicit rules in the samples.

[0209] The sample statistical difference refers to the degree of difference of the samples in the sample data set. In some embodiments, the greater the sample statistical difference, the greater the diversity of the sample.

[0210] In some embodiments, the gas company management platform can calculate the sample statistical difference in a variety of ways. For example, the gas company management platform can collect the sample data, quantify the cleaning data, configuration parameters, and cleaning effect of each sample data into numerical values, correspond each sample data to a numerical vector, calculate the vector distance (e.g., cosine distance) between every two numerical vectors in the sample data set, and calculate the variance of the obtained multiple vector distances. The larger the variance, the greater the sample statistical difference.

[0211] In some embodiments of the present specification, the effect determination model is trained based on the training set, the test set and the validation set, which is beneficial to improve the robustness of the effect determination model and prevent the effect determination model from overfitting. When the statistical difference of the samples is too large, the learning rate is appropriately increased so that the model can be fully learned, which is beneficial to the accurate acquisition of the cleaning effect.

[0212] In some embodiments of the present specification, the cleaning effect is determined by an effect determination model based on cleaning data and configuration parameters, and the cleaning effect can be accurately evaluated by utilizing the learning ability of the machine learning model, thereby improving the efficiency of gas pipeline blockage cleaning.

[0213] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, 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, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0214] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0215] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0216] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0217] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0218] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A smart gas pipeline blockage location method, characterized in that: The method is executed by a gas company management platform of a smart gas pipeline blockage location IoT system, and includes: Determine a monitoring point based on a historical blockage point set, wherein the monitoring point is located in a gas pipeline of a gas pipeline network; Constructing a gas operation map based on the monitoring data corresponding to the monitoring points; Based on the gas operation map, determining a target blockage point; Determine cleaning parameters based on the target blocking point, the cleaning parameters including the point to be cleaned; A cleaning instruction is generated based on the cleaning parameters, and the cleaning instruction is sent to a cleaning robot to clean the gas pipeline corresponding to the point to be cleaned.

2. The method according to claim 1, characterized in that The step of determining a target blocking point based on the gas operation map includes: Determining a candidate blocked section based on the gas operation map; Obtaining a congestion detection result of the candidate congestion section; Based on the blockage detection result, the target blockage point is determined.

3. The method according to claim 2, characterized in that The determining of a candidate blocked section based on the gas operation map includes: Evaluating data completeness of the gas operation map, in response to the data completeness not satisfying a preset completeness condition: Determine a data request and send the data request to the government security supervision management platform to obtain additional data; Based on the acquisition of the supplementary data, the gas operation map is updated to obtain an updated map; Based on the updated map, the candidate congested section is determined.

4. The method according to claim 1, characterized in that The determining of the cleaning parameters based on the target blocking point includes: Determining movement parameters of the cleaning robot based on the points to be cleaned and the movement speed, and controlling the cleaning robot to clean the points to be cleaned based on the movement parameters; In response to the cleaning robot arriving at the point to be cleaned, controlling the cleaning robot to perform preliminary cleaning according to a preset configuration; In response to obtaining cleaning data fed back by the cleaning robot, determining configuration parameters based on the cleaning data; A configuration update instruction is generated based on the configuration parameters, and the configuration update instruction is sent to the cleaning robot.

5. The method according to claim 4, characterized in that The determining of configuration parameters based on the cleaned data includes: Based on historical data, candidate configuration parameters are obtained; Based on the cleaning data, determining an estimated cleaning effect of the candidate configuration parameters; The candidate configuration parameters whose estimated cleaning effects satisfy preset cleaning targets are determined as the configuration parameters.

6. A smart gas pipeline blockage location Internet of Things system, characterized by: The Internet of Things system includes a government safety supervision management platform, a government safety supervision sensor network platform, a gas company management platform, a gas company sensor network platform, and a smart gas equipment object platform; The gas company management platform is configured to execute the smart gas pipeline blockage location method as described in claim 1.

7. The Internet of Things system according to claim 6, characterized in that: The gas company management platform is further configured as follows: Based on the gas operation map, determine the candidate blocking section; Obtaining a congestion detection result of the candidate congestion section; Based on the blockage detection result, a target blockage point is determined.

8. The Internet of Things system according to claim 7, characterized in that: The gas company management platform is further configured as follows: Evaluating data completeness of the gas operation map, in response to the data completeness not satisfying a preset completeness condition: Determining a data request and sending the data request to the government security supervision management platform to obtain supplementary data; Based on the acquisition of the supplementary data, the gas operation map is updated to obtain an updated map; Based on the updated map, the candidate congested section is determined.

9. The Internet of Things system according to claim 6, characterized in that: The gas company management platform is further configured as follows: Determine the movement parameters of the cleaning robot based on the point to be cleaned and the movement speed, and control the cleaning robot to clean the point to be cleaned based on the movement parameters; In response to the cleaning robot arriving at the point to be cleaned, controlling the cleaning robot to perform preliminary cleaning according to a preset configuration; In response to obtaining cleaning data fed back by the cleaning robot, determining configuration parameters based on the cleaning data; A configuration update instruction is generated based on the configuration parameters, and the configuration update instruction is sent to the cleaning robot.

10. The Internet of Things system according to claim 9, characterized in that: The gas company management platform is further configured as follows: Based on historical data, candidate configuration parameters are obtained; Based on the cleaning data, determining an estimated cleaning effect of the candidate configuration parameters; The candidate configuration parameters whose estimated cleaning effects satisfy preset cleaning targets are determined as the configuration parameters.

Images