A smart gas pipeline sampling monitoring method, Internet of Things system and storage medium

Abstract

The present invention provides a smart gas pipeline sampling and monitoring method, an Internet of Things system and a storage medium, and relates to the field of gas supervision technology. The method is executed by a government safety supervision management platform, and includes: obtaining pipeline sensing data; determining sampling parameters based on pipeline sensing data; in response to obtaining sampling data from a sampling device, determining a fault detection instruction based on the sampling data, and sending the fault detection instruction to a gas maintenance object platform to arrange manual inspection. The Internet of Things system includes a government safety supervision management platform, a government safety supervision sensor network platform, a government safety supervision object platform, a gas company sensor network platform, a gas equipment object platform and a gas maintenance object platform. The method can be run after being read by a computer instruction stored in a computer-readable storage medium. The present invention can realize reasonable sampling of gas in a pipeline, so that the status of pipeline operation can be accurately evaluated, which is conducive to maintaining the safety and stability of the pipeline.

Description

Technical Field

[0001] This specification relates to the field of gas supervision, and particularly to an intelligent gas pipeline sampling and monitoring method, an Internet of Things system, and a storage medium. Background Art

[0002] With the development of society, gas has become an indispensable part of people's daily lives. Ensuring the safety of gas use makes strict supervision of gas pipelines particularly important. The key point of this supervision process lies in sampling the gas inside the pipeline and deeply analyzing the data obtained from the sampling. However, the currently commonly used sampling method relies on manual operation of relevant equipment to complete. This method is not only time-consuming and laborious but may also introduce errors due to human factors, affecting the accuracy of the sampling data and thus misleading the accurate assessment of the pipeline operation status.

[0003] Therefore, it is necessary to provide an intelligent gas pipeline sampling and monitoring method, an Internet of Things system, and a storage medium to achieve dynamic adjustment of sampling parameters to complete reasonable sampling of the gas inside the pipeline, so as to accurately evaluate the pipeline operation status, which is beneficial to maintaining the safety and stability of the pipeline and ensuring the safety of gas transportation. Summary of the Invention

[0004] To solve the problem of how to reasonably sample the gas inside the gas pipeline to accurately evaluate the pipeline operation status, this specification provides an intelligent gas pipeline sampling and monitoring method, an Internet of Things system, and a storage medium.

[0005] The invention content includes an intelligent gas pipeline sampling and monitoring Internet of Things system, and the intelligent gas pipeline sampling and monitoring Internet of Things system includes: a government safety supervision management platform, a government safety supervision sensing network platform, a government safety supervision object platform, a gas company sensing network platform, a gas equipment object platform, and a gas maintenance object platform; the gas equipment object platform includes at least one sampling device and at least one pipeline monitoring device; the gas maintenance object platform includes at least one staff interaction device; the government safety supervision object platform includes the gas company management platform and key gas-using enterprises; the government safety supervision management platform is configured to: sequentially obtain, via the gas company sensing network platform, the gas company management platform, and the government safety supervision sensing network platform, the pipeline perception data of at least one pipeline collected and uploaded by the gas equipment object platform; determine sampling parameters based on the pipeline perception data of the at least one pipeline, send the sampling parameters to the government safety supervision object platform, and the government safety supervision object platform further sends them to the at least one sampling device; in response to obtaining at least one sampling data from the at least one sampling device, determine a fault detection instruction based on the at least one sampling data, send the fault detection instruction to the gas maintenance object platform, and the gas maintenance object platform arranges for manual inspection.

[0006] The invention content includes an intelligent gas pipeline sampling and monitoring method, and the method is implemented based on an intelligent gas pipeline sampling and monitoring Internet of Things system. The method is executed by the government safety supervision management platform in the intelligent gas pipeline sampling and monitoring Internet of Things system. The method includes: sequentially obtain, via the gas company sensing network platform, the gas company management platform, and the government safety supervision sensing network platform, the pipeline perception data of at least one pipeline collected and uploaded by the gas equipment object platform; determine sampling parameters based on the pipeline perception data of the at least one pipeline, send the sampling parameters to the government safety supervision object platform, and the government safety supervision object platform further sends them to the at least one sampling device; in response to obtaining at least one sampling data from the at least one sampling device, determine a fault detection instruction based on the at least one sampling data, send the fault detection instruction to the gas maintenance object platform, and the gas maintenance object platform arranges for manual inspection.

[0007] The invention content includes a computer-readable storage medium, and the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the intelligent gas pipeline sampling and monitoring method.

[0008] The beneficial effects brought by the above-mentioned invention content include but are not limited to: (1) By sensing data through the pipeline, sampling parameters can be reasonably determined, enabling the sampling device to accurately sample to obtain effective sampling data and analyze the sampling data to determine the fault detection instruction, which is beneficial to accurately evaluate the fault situation of pipeline operation, point out the direction for subsequent fault troubleshooting, and thus ensure the effective maintenance of the safety and stability of the pipeline; (2) By determining the abnormal pipeline and its corresponding abnormal area through the pipeline sensing data and then determining the sampling parameters, the sampling can be more targeted, the number of sampling devices to be turned on can be further reduced, and resource consumption can be reduced; (3) The automatic and accurate determination of the sampling detection ability of the sampling device can be achieved through the machine learning model; (4) By determining the pipeline sensing data for a period of time in the future based on the current pipeline sensing data and then determining the sampling time, the determined sampling time can be more reasonable, reducing the impact of sampling on the gas pipeline network and reducing the risks and economic losses brought by sampling. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will further illustrate in the form of exemplary embodiments, which will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0010] Figure 1 is a schematic diagram of the platform structure of the intelligent gas pipeline sampling and monitoring Internet of Things system shown in some embodiments of this specification;

[0011] Figure 2 is an exemplary flowchart of the intelligent gas pipeline sampling and monitoring method shown in some embodiments of this specification;

[0012] Figure 3 is an exemplary diagram for determining sampling parameters shown in some embodiments of this specification;

[0013] Figure 4 is an exemplary diagram of the detection ability evaluation model shown in some embodiments of this specification;

[0014] Figure 5 is an exemplary diagram for determining the sampling time shown in some embodiments of this specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] The following will briefly introduce the drawings required for the description of the embodiments. The drawings do not represent all embodiments.

[0016] As used herein, "system", "device", "unit" and / or "module" are a way to distinguish different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the said words can be replaced by other expressions.

[0017] Unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. A method or device may also include other steps or elements.

[0018] When the operations performed are described step by step in the embodiments of this specification, unless otherwise specified, the order of the steps can be adjusted, steps can be omitted, and other steps can also be included during the operation process.

[0019] Figure 1 It is a schematic diagram of the platform structure of the intelligent gas pipeline sampling and monitoring Internet of Things system shown in some embodiments of this specification.

[0020] In some embodiments, as Figure 1 shown, the intelligent gas pipeline sampling and monitoring Internet of Things system 100 may include a government safety supervision management platform 110, a government safety supervision sensing network platform 120, a government safety supervision object platform 130, a gas company sensing network platform 140, a gas equipment object platform 150, and a gas maintenance object platform 160.

[0021] The government safety supervision management platform 110 refers to a platform for supervising and managing the gas pipeline network. The government safety supervision management platform 110 can be used to evaluate various fault risks that may exist in the gas pipeline network.

[0022] In some embodiments, the government safety supervision management platform 110 may be configured to: sequentially obtain, via the gas company sensing network platform 140, the gas company management platform 131, and the government safety supervision sensing network platform 120, the pipeline perception data of at least one section of pipeline collected and uploaded by the gas equipment object platform 150; determine sampling parameters based on the pipeline perception data of at least one section of pipeline, send the sampling parameters to the government safety supervision object platform 130, and further distribute them by the government safety supervision object platform 130 to at least one sampling device; in response to obtaining at least one sampling data from at least one sampling device, determine a fault detection instruction based on the at least one sampling data, and send the fault detection instruction to the gas maintenance object platform 160, and the gas maintenance object platform 160 arranges for manual inspection.

[0023] In some embodiments, the government safety supervision management platform 110 may be further configured to: determine abnormal data items based on the at least one sampling data and the standard sampling data; determine the detection content based on the abnormal data items, and determine the pipeline sampling position as the inspection pipeline position of the pipeline to be reinspected.

[0024] In some embodiments, the government safety supervision and management platform 110 may be further configured to: determine, as high-risk pipelines, the pipelines to be reinspected in the fault detection instruction whose pipeline in-degree is greater than a preset degree threshold; the preset degree threshold is related to the average in-degree of the gas pipeline network; increase the monitoring frequency of the pipeline monitoring devices of the high-risk pipelines within a preset future period.

[0025] In some embodiments, the government safety supervision and management platform 110 may be further configured to: determine at least one abnormal pipeline and its corresponding abnormal area based on the pipeline perception data of at least one pipeline; determine sampling parameters based on at least one abnormal pipeline and its corresponding abnormal area.

[0026] In some embodiments, the government safety supervision and management platform 110 may be further configured to: for an abnormal pipeline and its corresponding abnormal area, determine the sampling detection type based on the pipeline perception data of the abnormal pipeline and its corresponding abnormal area; in response to the existence of multiple sampling devices on the abnormal pipeline, evaluate the sampling detection capabilities of the sampling devices based on the pipeline perception data of the abnormal pipeline and the sampling detection type; determine to activate the sampling devices based on the sampling detection capabilities of at least one sampling device.

[0027] In some embodiments, the government safety supervision and management platform 110 may be further configured to: determine the sampling detection capabilities of the sampling devices through a detection capability evaluation model based on the pipeline perception data of the abnormal pipeline and the sampling detection type.

[0028] In some embodiments, the government safety supervision and management platform 110 may be further configured to: determine the pipeline perception data of at least one pipeline for a future period based on the pipeline perception data of at least one pipeline; determine the sampling time based on the pipeline perception data of at least one pipeline for a future period.

[0029] In some embodiments, the government safety supervision and management platform 110 may be further configured to: determine at least one candidate sampling time point; determine the sampling stability of at least one candidate sampling time point based on the pipeline perception data of at least one pipeline for a future period; determine the sampling time based on the sampling stability of at least one candidate sampling time point.

[0030] In some embodiments, the government safety supervision and management platform 110 may be further configured to: construct a gas pipeline network map; the nodes of the gas pipeline network map include gas pipelines, gas supply equipment, and gas consumption equipment, and the edges of the gas pipeline network map are the connection edges of the nodes where gas flows mutually; determine the sampling stability of at least one candidate sampling time point through a sampling stability evaluation model based on the gas pipeline network map.

[0031] In some embodiments, the government safety supervision management platform 110 interacts bidirectionally with the government safety supervision sensing network platform 120. For example, the government safety supervision management platform 110 can send sampling parameters to the government safety supervision sensing network platform 120 and obtain sampling data related to the sampling parameters from the government safety supervision sensing network platform 120.

[0032] In some embodiments, the government safety supervision management platform 110 may also include a processor. The processor can process data and / or information obtained from other platforms. The processor can execute program instructions based on this data, information, and / or processing results to perform one or more functions described in this application. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-chip processing device). By way of example only, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), etc. or any combination of the above.

[0033] The government safety supervision sensing network platform 120 refers to a functional platform for monitoring and transmitting data related to gas pipeline sampling. In some embodiments, the government safety supervision sensing network platform 120 can be configured as a communication base station, a router, a wireless device, etc. and operate based on a communication network.

[0034] In some embodiments, the government safety supervision sensing network platform 120 interacts bidirectionally with the government safety supervision object platform 130. For example, the government safety supervision sensing network platform 120 can send sampling parameters to the government safety supervision object platform 130.

[0035] The government safety supervision object platform 130 refers to an object platform for generating perception information and executing control information. In some embodiments, the government safety supervision object platform 130 can be used to store pipeline perception data and sampling data in the gas pipeline network, as well as the sampling parameters issued by the government safety supervision management platform 110.

[0036] In some embodiments, the government safety supervision object platform 130 may include a gas company management platform 131 and key gas-using enterprises 132.

[0037] The gas company management platform 131 refers to a comprehensive management platform for the relevant information of the gas company and can be used to manage the parameters related to pipeline sampling of the gas company.

[0038] The key gas-using enterprises 132 refer to the relevant enterprises that need to pay key attention to the gas usage situation. For example, chemical plants that use a large amount of gas, etc.

[0039] In some embodiments, the gas company management platform 131 can interact bidirectionally with the gas company sensing network platform 140.

[0040] The gas company's sensing network platform 140 refers to an integrated management platform for the sensing information of the gas company. In some embodiments, the gas company's sensing network platform 140 can be configured as a communication network or a gateway, etc.

[0041] In some embodiments, the gas company's sensing network platform 140 can interact bidirectionally with the gas company management platform 131 upwards and with the gas equipment object platform 150 and the gas maintenance object platform 160 downwards. For example, the gas company's sensing network platform 140 can obtain pipeline perception data of at least one section of pipeline from the gas equipment object platform 150. For another example, the gas company's sensing network platform 140 can send the obtained fault detection instructions to the gas maintenance object platform 160.

[0042] The gas equipment object platform 150 refers to a functional platform that performs pipeline monitoring and sampling. In some embodiments, the gas equipment object platform 150 can include at least one sampling device and at least one pipeline monitoring device.

[0043] The sampling device refers to a device that samples and inspects the gas in the gas pipeline and can be used to obtain sampling data. For example, the sampling device can integrate a temperature sensor, a flow rate detector, a pressure sensor, a concentration detector, a gas analysis instrument, etc.

[0044] In some embodiments, the sampling device can be deployed in a preset pipeline. The deployment location of the sampling device can be obtained through a positioning sensor installed on the sampling device or directly from relevant positioning records at the time of deployment and installation (such as the point records reserved when deploying the gas pipeline network).

[0045] In some embodiments, multiple sampling devices can be deployed on the gas pipeline network, and one or more sampling devices can be deployed on one section of pipeline. The sampling device can explore the pipeline conditions within the sampling range.

[0046] The pipeline monitoring device refers to a device that monitors the gas in the gas pipeline and can be used to obtain pipeline perception data. For example, the pipeline monitoring device can integrate a temperature sensor, a flow rate detector, a pressure sensor, etc.

[0047] The deployment situation of the pipeline monitoring device is similar to that of the sampling device and will not be elaborated here.

[0048] The gas maintenance object platform 160 refers to a platform related to gas maintenance. In some embodiments, the gas maintenance object platform 160 includes a staff interaction device.

[0049] A staff interaction device refers to a device that enables interaction with staff. For example, mobile phones, computers, etc. Staff refers to personnel engaged in work related to gas pipelines. For example, safety officers, maintenance workers, storage and transportation workers, etc. In some embodiments, the staff interaction device can obtain a fault detection instruction via the gas maintenance object platform 160 and arrange for a manual inspection.

[0050] For more descriptions of the above relevant parameters (such as, sampling data, pipeline perception data, fault detection instructions, etc.), reference can be made to Figures 2 to 5 the relevant descriptions.

[0051] In some embodiments of this specification, based on the intelligent gas pipeline sampling and monitoring Internet of Things system 100, an information operation closed-loop can be formed among various functional platforms, and coordinated and regular operation can be achieved under the unified management of the government safety supervision and management platform, realizing the informatization and intelligence of intelligent gas pipeline sampling.

[0052] Figure 2 is an exemplary flowchart of the intelligent gas pipeline sampling and monitoring method shown in some embodiments of this specification. As Figure 2 shown, process 200 includes the following steps S210 - step S230.

[0053] In some embodiments, the intelligent gas pipeline sampling and monitoring method can be implemented based on the intelligent gas pipeline sampling and monitoring Internet of Things system 100 and executed by the government safety supervision and management platform 110. For example, executed by a processor.

[0054] Step S210, sequentially obtain the pipeline perception data of at least one section of pipeline collected and uploaded by the gas equipment object platform via the gas company sensing network platform, the gas company management platform, and the government safety supervision sensing network platform.

[0055] Pipeline perception data refers to sensing data related to the pipeline. Among them, the pipeline can refer to a gas pipeline.

[0056] In some embodiments, the pipeline perception data can include pipeline temperature, pipeline air pressure, and pipeline gas flow rate.

[0057] Pipeline temperature, pipeline air pressure, and pipeline gas flow rate respectively refer to the temperature, air pressure, and gas flow rate inside the pipeline.

[0058] In some embodiments, the processor can obtain the pipeline perception data from the pipeline monitoring equipment in the gas equipment object platform via the gas company sensing network platform.

[0059] In some embodiments, one or more pipeline monitoring devices may be deployed in a section of pipeline. When there are multiple pipeline monitoring devices in a section of pipeline, the pipeline perception data of the pipeline may be a sequence composed of the pipeline perception data monitored and obtained by multiple pipeline monitoring devices.

[0060] Step S220: Determine sampling parameters based on the pipeline perception data of at least one section of pipeline, send the sampling parameters to the government safety supervision object platform, and further send them by the government safety supervision object platform to at least one sampling device.

[0061] The sampling parameters refer to the parameters related to the operation conditions of the sampling devices.

[0062] In some embodiments, the sampling parameters may at least include at least one activated sampling device and its corresponding pipeline sampling location.

[0063] An activated sampling device refers to a sampling device that needs to be in an activated state (i.e., capable of performing sampling operations).

[0064] The pipeline sampling location refers to the location in the pipeline where the activated sampling device performs sampling. For example, the deployment location of the activated sampling device.

[0065] In some embodiments, the processor may determine the sampling parameters based on the pipeline perception data of at least one section of pipeline in various ways. For example, the processor may calculate the respective data fluctuation values corresponding to the pipeline perception data of multiple pipelines (e.g., calculate the temperature fluctuation value of the pipeline temperature, the air pressure fluctuation value of the pipeline air pressure, and the gas flow velocity fluctuation value of the pipeline gas flow velocity), and determine the sampling parameters based on the data fluctuation values.

[0066] Among them, the data fluctuation value refers to a value reflecting the fluctuation situation of the pipeline perception data. In some embodiments, the data fluctuation value may be represented by the range or variance. For example, the temperature fluctuation value may be represented by the variance of the pipeline temperatures of all pipelines.

[0067] Exemplarily, if the respective data fluctuation values corresponding to the pipeline perception data are all not greater than the preset fluctuation threshold, sampling may not be performed, that is, the sampling parameters may be determined as 0 or null; if there is one or more data fluctuation values corresponding to one or more items of pipeline perception data that are greater than the preset fluctuation threshold, the sampling device of the default pipeline is activated for sampling, that is, the sampling device in the default pipeline is determined as the activated sampling device, and the corresponding pipeline sampling location is confirmed.

[0068] Among them, the default pipeline may refer to an important pipeline in the gas pipeline network. The preset fluctuation threshold refers to the minimum value of the data fluctuation value of the pipeline perception data set in advance. The default pipeline and the preset fluctuation threshold may be set by the system by default or evaluated and determined by technicians based on experience and with reference to historical data.

[0069] In some embodiments, the processor may also determine at least one abnormal pipeline and its corresponding abnormal area based on the pipeline perception data of at least one section of pipeline; and determine sampling parameters based on at least one abnormal pipeline and its corresponding abnormal area. For more content on this part, reference can be made to Figure 3 the corresponding description.

[0070] In some embodiments, the sampling parameters further include sampling time. The processor may also determine the pipeline perception data of at least one section of pipeline for a future period of time based on the pipeline perception data of at least one section of pipeline; and determine the sampling time based on the pipeline perception data of at least one section of pipeline for a future period of time. For more content on this part, reference can be made to Figure 5 the corresponding description.

[0071] Step S230: In response to obtaining at least one sampling data from at least one sampling device, determine a fault detection instruction based on the at least one sampling data, and send the fault detection instruction to the gas maintenance object platform, so that the gas maintenance object platform arranges for manual inspection.

[0072] Sampling data refers to gas-related data obtained by sampling devices. For example, at least one of gas flow rate, gas temperature, gas pressure, gas fuel concentration, and gas fuel composition.

[0073] Among them, the gas flow rate, gas temperature, and gas pressure in the sampling data may correspond to the pipeline gas flow rate, pipeline temperature, and pipeline gas pressure in the pipeline perception data respectively. The meanings of the two corresponding items are the same, but due to differences between the sampling device and the pipeline monitoring device (for example, it is assumed that the sampling device works normally continuously, while the pipeline monitoring device may malfunction, etc.), there may be numerical differences in the corresponding items.

[0074] Gas fuel concentration refers to the concentration of fuel inside the pipeline. For example, 5% etc.

[0075] Gas fuel composition refers to the fuel composition in the gas inside the pipeline. For example, the gas fuel composition in the pipeline transporting natural gas mainly includes methane, etc.

[0076] In some embodiments, the processor may obtain sampling data by turning on the sampling device.

[0077] A fault detection instruction refers to an instruction for guiding staff to conduct further fault inspections. In some embodiments, the fault detection instruction may include at least one pipeline to be reinspected, the inspection pipeline location of at least one pipeline to be reinspected, and the corresponding inspection content, etc.

[0078] A reinspection pipeline refers to a pipeline that needs to be inspected again. The inspection pipeline location refers to the location where the reinspection pipeline is inspected. For example, the inspection pipeline location can be the pipeline sampling location of the reinspection pipeline.

[0079] The inspection content refers to the item content that needs to be inspected. For example, pipeline sealing performance, etc.

[0080] In some embodiments, the processor can determine a fault detection instruction in various ways based on at least one sampling data. For example, the processor can, based on the current sampling data, search in the historical data for historical sampling data with a relatively high first data similarity to the current sampling data, and use the fault detection instruction corresponding to the historical sampling data as the current fault detection instruction. Among them, the first data similarity can be represented by a vector distance.

[0081] In some embodiments, the processor can determine abnormal data items based on at least one sampling data and standard sampling data; based on the abnormal data items, determine the inspection content, and determine the pipeline sampling location as the inspection pipeline location of the reinspection pipeline.

[0082] The standard sampling data refers to the sampling data under normal conditions. For example, the standard sampling data can include standard gas flow rate, standard gas temperature, standard gas pressure, standard gas fuel concentration, and standard gas fuel composition, etc.

[0083] In some embodiments, the standard sampling data can be set by the system default or by a technician according to historical data. For example, the processor or the technician can select the historical sampling parameter with a relatively high similarity to the current sampling parameter, and among the corresponding historical sampling data, the historical gas flow rate with the highest occurrence frequency is used as the standard gas flow rate.

[0084] The abnormal sampling data can be sampling data with a similarity lower than a preset similarity threshold to the standard sampling data.

[0085] In some embodiments, the processor can calculate the similarity between each sampling data and the standard sampling data, and determine the sampling data with a similarity lower than the preset similarity threshold as the abnormal sampling data. The similarity can be represented by a vector distance, etc. The preset similarity threshold can be a preset distance threshold. For example, if the vector distance between the sampling data and the standard sampling data is lower than the preset distance threshold, then the sampling data is abnormal sampling data.

[0086] In some embodiments, the preset similarity threshold can be related to the average in-degree of the gas pipeline network. For example, the larger the average in-degree of the gas pipeline network, the larger the preset similarity threshold can be.

[0087] The average in-degree of the gas pipeline network refers to the average of the pipeline in-degrees of each pipeline in the gas pipeline network. For example, 3, etc.

[0088] The pipe in-degree of the current pipe refers to the number of other pipes from which gas converges into the current pipe.

[0089] An abnormal data item refers to a specific data item with an abnormality in the abnormal sampling data.

[0090] In some embodiments, the processor may calculate a first difference between each data item in the abnormal sampling data and the corresponding data item in the standard sampling data, and determine the data item with the first difference greater than the corresponding first difference threshold as the abnormal data item.

[0091] In some embodiments, the first difference may include a gas flow rate difference, a gas temperature difference, a gas pressure difference, a gas concentration difference, and a gas component difference, and the first difference threshold may include a gas flow rate difference threshold, a gas temperature difference threshold, a gas pressure difference threshold, a gas concentration difference threshold, and a gas component difference threshold.

[0092] Among them, the gas flow rate difference may refer to the absolute value of the difference between the gas flow rate in the abnormal sampling data and the standard gas flow rate in the standard sampling data. The gas temperature difference and gas pressure difference are the same. The gas component difference may refer to the difference in the number of component types between the gas fuel components in the abnormal sampling data and the standard gas fuel components in the standard sampling data.

[0093] The gas flow rate difference threshold may refer to the maximum value of the gas flow rate difference under normal conditions. The gas temperature difference threshold, gas pressure difference threshold, gas concentration difference threshold, and gas component difference threshold are the same.

[0094] In some embodiments, the processor may determine the detection content based on the abnormal data item by querying a first preset relationship table. The first preset relationship table includes abnormal data items and their corresponding detection content. The first preset relationship table may be constructed based on historical data. For example, for a historical abnormal data item in the historical data, the processor may count one or more subsequent actual historical detection contents corresponding to it, and determine the historical detection content with the highest occurrence frequency as the historical detection content corresponding to the historical abnormal data item. By traversing multiple historical abnormal data items, the first preset relationship table is constructed.

[0095] In some embodiments, the processor may determine the sampling device that is turned on corresponding to the abnormal sampling data, and determine the pipe sampling position corresponding to the turned-on sampling device as the inspection pipe position of the pipe to be reinspected.

[0096] In some embodiments of this specification, by calculating the similarity between sampled data and standard sampled data, abnormal sampled data and abnormal data items can be accurately determined. At the same time, according to the average in-degree of the gas pipeline network, the preset similarity threshold can be flexibly adjusted to identify subtle differences and improve the reliability of the reinspected pipelines identified.

[0097] In some embodiments, the processor can also determine the reinspected pipelines with a pipeline in-degree greater than the preset degree threshold in the fault detection instruction as high-risk pipelines, and increase the monitoring frequency of the pipeline monitoring devices for high-risk pipelines within a preset future period.

[0098] The preset degree threshold refers to the maximum value of the pipeline in-degree set in advance. For example, 8, etc.

[0099] In some embodiments, the preset degree threshold can be related to the average in-degree of the gas pipeline network. For example, the preset degree threshold can be equal to the average in-degree of the gas pipeline network. Or, the preset degree threshold can be positively correlated with the average in-degree of the gas pipeline network.

[0100] A high-risk pipeline refers to a pipeline with a relatively high risk of pipeline failure. Among them, pipeline failures can include pipeline gas leakage, pipeline blockage, etc.

[0101] In some embodiments, the preset future period can be a fixed future time period default set by the processor or preset manually in advance. For example, the next 6 hours after the current moment. In some embodiments, the preset future period can also refer to the time period from the current moment to when the pipeline failure is eliminated.

[0102] The monitoring frequency refers to the frequency at which the pipeline monitoring device monitors the pipeline to obtain pipeline perception data. For example, 30 times per minute, etc.

[0103] In some embodiments, after determining the high-risk pipelines, the processor can increase the monitoring frequency of the pipeline monitoring devices for high-risk pipelines within a preset future period based on a preset increase amount. Among them, the preset increase amount can be a fixed increase amount default set by the processor or preset manually in advance. For example, 5 times per minute. The preset increase amount can also be a dynamic increase amount determined by the processor based on the average value of the pipeline in-degree of the high-risk pipelines. For example, the preset increase amount can be positively correlated with the average value of the pipeline in-degree of the high-risk pipelines.

[0104] In some embodiments of this specification, by determining whether the pipeline in-degree of the reinspected pipeline is greater than the preset degree threshold, it can be effectively determined whether the reinspected pipeline is a high-risk pipeline. Furthermore, by increasing the monitoring frequency of the pipeline monitoring devices for high-risk pipelines, it can be further ensured that pipeline failures in the pipeline can be detected in a timely manner.

[0105] In some embodiments of this specification, by sensing data through pipelines, sampling parameters can be reasonably determined, enabling sampling devices to accurately sample to obtain effective sampling data, and analyzing the sampling data to determine fault detection instructions, which is conducive to accurately evaluating the fault conditions of pipeline operation, indicating the direction for subsequent fault troubleshooting, and thus ensuring the effective maintenance of the safety and stability of pipelines.

[0106] It should be noted that the above description of process 200 is only for illustration and explanation, and does not limit the scope of application of the present invention. For those skilled in the art, various modifications and changes can be made to process 200 under the guidance of the present invention. However, these modifications and changes are still within the scope of the present invention.

[0107] Figure 3 It is an exemplary schematic diagram of determining sampling parameters shown in some embodiments of this specification.

[0108] In some embodiments, as Figure 3 shown, the processor can determine at least one abnormal pipeline 320 and its corresponding abnormal area 330 based on the pipeline sensing data 310 of at least one section of pipeline; and determine sampling parameters 340 based on at least one abnormal pipeline 320 and its corresponding abnormal area 330.

[0109] An abnormal pipeline refers to a pipeline with abnormal corresponding pipeline sensing data. An abnormal area refers to an area on the pipeline where abnormalities exist.

[0110] In some embodiments, the processor can calculate the second difference between each data item in the pipeline sensing data and each data item of the standard pipeline sensing data of the pipeline. If the second difference of a certain data item is greater than the second difference threshold, it is determined that the data item is an abnormal data item of the pipeline, and the pipeline is determined to be an abnormal pipeline.

[0111] In some embodiments, the second difference can include the pipeline temperature difference, the pipeline air pressure difference, and the pipeline gas flow rate difference, and the second difference threshold can include the pipeline temperature difference threshold, the pipeline air pressure difference threshold, and the pipeline gas flow rate difference threshold.

[0112] Among them, the pipeline temperature difference refers to the absolute value of the difference between the pipeline temperature in the pipeline sensing data and the standard pipeline temperature in the standard pipeline sensing data. The pipeline air pressure difference and the pipeline gas flow rate difference are the same.

[0113] The pipeline temperature difference threshold refers to the maximum value of the pipeline temperature difference under normal circumstances. The pipeline air pressure difference threshold and the pipeline gas flow rate difference threshold are the same.

[0114] Standard pipeline perception data refers to pipeline perception data under normal circumstances. For example, standard pipeline perception data may include standard pipeline temperature, standard pipeline air pressure, standard pipeline gas flow rate, etc. In some embodiments, the standard pipeline perception data may be set by the system by default or determined by technicians based on historical data. For example, among the historical pipeline perception data of the same pipeline in the historical data, the historical pipeline perception data with the highest frequency of occurrence may be determined as the standard pipeline perception data.

[0115] In some embodiments, the processor may determine the abnormal area based on the abnormal pipeline by querying the second preset relationship table. The second preset relationship table includes the abnormal pipeline and the corresponding abnormal area. The second preset relationship table may be constructed based on historical data. For example, for a historical abnormal pipeline in the historical data, the processor may count one or more historical abnormal areas corresponding to it, and determine the historical abnormal area with the highest number of occurrences as the historical abnormal area corresponding to the historical abnormal pipeline. By traversing multiple historical abnormal pipelines, the second preset relationship table is constructed.

[0116] In some embodiments, the processor may determine the sampling parameters based on at least one section of abnormal pipeline and its corresponding abnormal area in various ways. For example, the processor may determine the center position of the abnormal area as the pipeline sampling position, and use the sampling devices within a preset range corresponding to the pipeline sampling position as the sampling devices to be activated. The preset range may refer to a range not exceeding a preset distance threshold from the pipeline sampling position.

[0117] In some embodiments, the sampling parameters may further include the sampling detection type.

[0118] The sampling detection type refers to the type of the way the sampling device performs sampling. In some embodiments, the sampling detection type may include sampling detection and non-sampling detection.

[0119] Sampling detection refers to a detection method that requires extracting the gas in the pipeline for sample detection. Non-sampling detection refers to a detection method that directly performs detection without extracting the gas in the pipeline.

[0120] In some embodiments, for a section of abnormal pipeline and its corresponding abnormal area, the processor may determine the sampling detection type based on the pipeline perception data of the abnormal pipeline and its corresponding abnormal area; in response to the presence of multiple sampling devices on the abnormal pipeline, evaluate the sampling detection capabilities of the sampling devices based on the pipeline perception data and the sampling detection type of the abnormal pipeline; and determine the sampling devices to be activated based on the sampling detection capabilities of at least one sampling device.

[0121] In some embodiments, the processor may determine the sampling detection type in various ways based on the pipeline perception data of the exception pipeline and its corresponding exception area. For example, the processor may determine the sampling detection type by querying a third preset relationship table.

[0122] The third preset relationship table includes the exception area of the exception pipeline, the exception data items, and the corresponding sampling detection types. The third preset relationship table may be constructed based on historical data. For example, for the exception area of a historical exception pipeline and the exception data items in the historical data, the processor may count one or more historical sampling detection types actually used subsequently, and determine the historical sampling detection type with the highest occurrence times as the historical sampling detection type corresponding to the exception area of the historical exception pipeline and the exception data items. By traversing multiple historical exception pipelines, the third preset relationship table is constructed.

[0123] The sampling detection ability refers to the ability of the sampling device to obtain sampling data that can accurately reflect the pipeline fault problem. In some embodiments, the sampling detection ability may be represented by a numerical value. The higher the numerical value, the greater the sampling detection ability.

[0124] In some embodiments, the processor may evaluate the sampling detection ability of the sampling device in various ways based on the pipeline perception data of the exception pipeline and the sampling detection type. For example, the processor may determine the sampling detection ability of the sampling device by means of vector matching.

[0125] Merely by way of example, the processor may construct a first standard vector library. The first standard vector library may include multiple first standard vectors and their corresponding multiple first labels. Among them, the first standard vector may include pipeline perception data and sampling detection type, and the first label may be the sampling detection ability of the corresponding sampling device.

[0126] In some embodiments, the processor may construct a first clustering vector based on the historical pipeline perception data, historical sampling detection type, and their corresponding historical sampling detection ability in the historical data, cluster multiple first clustering vectors, construct a first standard vector based on the historical pipeline perception data and historical sampling detection type corresponding to the clustering center formed by clustering, and use the historical sampling detection ability corresponding to the clustering center as the first label of the first standard vector.

[0127] In some embodiments, the processor may calculate the fault similarity between the historical fault detection instruction corresponding to the historical sampling data and the historical pipeline fault information actually monitored, and determine the fault similarity as the historical sampling detection ability.

[0128] The fault similarity may refer to the degree of similarity between the historical fault detection instruction and the historical pipeline fault information actually monitored. The fault similarity may be represented by cosine similarity, Euclidean distance, etc.

[0129] In some embodiments, the processor may construct a first vector to be matched based on the pipeline perception data of the current exception pipeline and the sampling detection type, match the first vector to be matched with the first standard vectors in the first standard vector library, calculate the vector similarities between the first vector to be matched and multiple first standard vectors, and determine the first label corresponding to the first standard vector with the highest vector similarity as the sampling detection capability of the current sampling device. Among them, the vector similarity may be represented by cosine similarity, Euclidean distance, etc.

[0130] In some embodiments, the processor may determine the sampling detection capability of the sampling device based on the pipeline perception data of the exception pipeline and the sampling detection type through a detection capability evaluation model. For more content on this part, reference can be made to Figure 4 the corresponding description.

[0131] In some embodiments, the processor may determine to activate the sampling device in multiple ways based on the sampling detection capability. For example, the processor may select one or more sampling devices with the maximum sampling detection capability as the activated sampling devices.

[0132] In some embodiments of this specification, determining a suitable sampling detection type for the pipeline perception data with anomalies can improve the sampling efficiency. By evaluating the sampling detection capability of the sampling device, sampling devices with better sampling effects can be effectively selected, which helps reduce resource consumption during the sampling process and also reduces the impact of the sampling device on the pipeline.

[0133] In some embodiments of this specification, by determining the exception pipeline and its corresponding exception region through the pipeline perception data and then determining the sampling parameters, the sampling can be more targeted, which can further reduce the number of activated sampling devices and reduce resource consumption.

[0134] Figure 4 is an exemplary schematic diagram of the detection capability evaluation model shown in some embodiments of this specification.

[0135] In some embodiments, as Figure 4 shown, the processor may determine the sampling detection capability 430 of the sampling device based on the pipeline perception data 310 of the exception pipeline and the sampling detection type 410 through the detection capability evaluation model 420.

[0136] For more content on the exception pipeline, pipeline perception data, sampling detection type, sampling detection capability, and sampling device, reference can be made to Figures 1 to 3 the relevant description.

[0137] The detection capability evaluation model refers to a model used to determine the sampling detection capability. In some embodiments, the detection capability evaluation model can be a machine learning model. For example, a neural network (NN), etc.

[0138] In some embodiments, as Figure 4 shown, the input of the detection capability evaluation model 420 can include the pipeline perception data 310 of the abnormal pipeline and the sampling detection type 410, and the output can be the sampling detection capability 430 of the sampling device.

[0139] In some embodiments, the detection capability evaluation model can be obtained through training in various ways. For example, it can be obtained by training with a plurality of first training samples with first training labels, etc. A set of first training samples for training can include the sample pipeline perception data of the sample abnormal pipeline and the sample sampling detection type. The first training label corresponding to a set of first training samples is the actual sampling detection capability of the sample sampling device.

[0140] In some embodiments, the processor can select the historical pipeline perception data and the historical sampling detection type of a historical abnormal pipeline as a set of first training samples, and use the historical sampling detection capability of the historical sampling device corresponding to this set of first training samples as the first training label of this set of first training samples. For the process of obtaining the first training label, reference can be made to Figure 3 the relevant description of the process of obtaining the first label in the first standard vector library, which will not be elaborated here.

[0141] In some embodiments, the processor can input the sample pipeline perception data and the sample sampling detection type of the sample abnormal pipeline into the initial detection capability evaluation model, construct a first loss function based on the sampling detection capability of the sampling device output by the initial detection capability evaluation model and the first training label, update the initial detection capability evaluation model based on the first loss function, and when the first preset condition is met, the initial detection capability evaluation model is trained and completed to obtain a trained detection capability evaluation model. Among them, the first preset condition can be that the first loss function converges, the number of iterations reaches a threshold, etc.

[0142] In some embodiments, as Figure 4 shown, the input of the detection capability evaluation model 420 further includes the pipeline in-degree 440, the pipeline out-degree 450, and the number of upstream and downstream users of the pipeline 460.

[0143] For more content about the pipeline in-degree, reference can be made to Figure 2 the corresponding description.

[0144] The pipeline out-degree of the current pipeline refers to the number of other pipelines into which the gas flows after flowing out of the current pipeline.

[0145] The number of users upstream and downstream of the pipeline refers to the number of users connected upstream and downstream of the pipeline. A user refers to a gas user. In some embodiments, the number of users upstream and downstream of the pipeline may be composed of the number of users upstream of the pipeline and the number of users downstream of the pipeline.

[0146] In some embodiments of this specification, taking the pipeline in-degree, pipeline out-degree, and the number of users upstream and downstream of the pipeline as the inputs of the detection ability evaluation model can effectively consider the influence of the surrounding pipeline environment of the pipeline on the measurement, making the evaluation of the sampling detection ability more accurate.

[0147] In some embodiments, the detection ability evaluation model may include the training in the first stage. The training in the first stage may include training based on the first training set, validating based on the first validation set, and testing based on the first test set. The first training set, the first validation set, and the first test set are data sets composed of historical pipeline perception data, historical sampling detection types, historical numbers of upstream and downstream pipelines of the pipeline, and historical numbers of users upstream and downstream of the pipeline. The data volumes of the first training set, the first validation set, and the first test set form a first preset ratio, and there is no data intersection among the first training set, the first validation set, and the first test set. The sample statistical difference of the first training set is greater than the preset difference threshold, and the preset difference threshold is related to the accident frequency of historical sampling accidents.

[0148] The first training set refers to the data set used to train the internal parameters of the model.

[0149] The first validation set refers to the data set used to verify the state and convergence of the model during the training process.

[0150] The first test set refers to the data set used to test the generalization ability of the model.

[0151] In some embodiments, one historical pipeline perception data and the corresponding one historical sampling detection type, one historical number of upstream and downstream pipelines of the pipeline, and one historical number of users upstream and downstream of the pipeline form a data group. The first training set, the first validation set, and the first test set are all composed of multiple data groups.

[0152] The first preset ratio can be set by the system default or by technicians according to experience. For example, the first preset ratio can be 8:1:1.

[0153] Data intersection means that there is the same data in different sets, that is, the same data is used in multiple sets. In some embodiments, there is no data intersection among the first training set, the first validation set, and the first test set.

[0154] The sample statistical difference refers to the overall difference of sample data. In some embodiments, the processor may digitally quantify each sample data in the first training set; calculate the vector distances between pairwise sample data in the first training set; calculate the variance of the multiple vector distances; and determine the sample statistical difference based on the variance.

[0155] Among them, digital quantization may refer to corresponding one data group to one digital vector. Among them, the sampling detection in the historical sampling detection type may be assigned a value of 1 and the non-sampling detection may be assigned a value of 0, and other data are all numerical data and can be directly used. The vector distance between pairwise sample data can be represented by the cosine distance between pairwise digital vectors. The greater the variance of the multiple vector distances, the greater the sample statistical difference.

[0156] A sampling accident refers to an accident caused by sampling. For example, poor sampling data quality, quality problems in the pipeline caused by sampling, etc. In some embodiments, the accident frequency of historical sampling accidents may refer to the frequency of historical sampling accidents in a large number of historical samplings. The greater the accident frequency of historical sampling accidents, the greater the preset difference threshold may be.

[0157] In some embodiments of this specification, the model is trained in the first stage through the first training set, the first validation set, and the first test set, and the preset difference threshold corresponding to the sample statistical difference of the first training set is determined through the accident frequency of historical sampling accidents, which can make the sample data distribution in model training more extensive. Referring to the sample statistical difference can make the model more robust, prevent the model from overfitting, and is beneficial for the model to accurately learn the prediction of the sampling detection ability.

[0158] In some embodiments of this specification, the automated and accurate determination of the sampling detection ability of the sampling device can be achieved through a machine learning model.

[0159] Figure 5 It is another exemplary schematic diagram for determining sampling parameters as shown in some embodiments of this specification.

[0160] In some embodiments, the sampling parameter may further include the sampling time.

[0161] The sampling time refers to the time point when the sampling device starts sampling. The sampling time is a future time point of the current time point.

[0162] In some embodiments, as Figure 5 shown, the processor may determine the pipeline perception data 510 of at least one section of pipeline in a future period based on the pipeline perception data 310 of at least one section of pipeline; and determine the sampling time 520 based on the pipeline perception data 510 of at least one section of pipeline in a future period.

[0163] The future period refers to a period of time after the current time point.

[0164] In some embodiments, the processor may determine the pipeline perception data of at least one pipeline for a future period in various ways based on the pipeline perception data of at least one pipeline.

[0165] For example, the processor may calculate a plurality of first similarities between the pipeline perception data at the current time point and the historical pipeline perception data at a plurality of historical time points in the historical data, determine the historical time point corresponding to the historical pipeline perception data with the highest first similarity, and use the historical pipeline perception data for a subsequent period of time at that historical time point as the pipeline perception data for the future period of time at the current time point. Wherein, the subsequent period of time at the historical time point is the same as the future period of time at the current time point. The first similarity may be represented by a vector distance.

[0166] In some embodiments, the processor may determine the sampling time in various ways based on the pipeline perception data of at least one pipeline for a future period. For example, the processor may select a plurality of future time points within the future period. For each future time point, calculate the gradient between the pipeline perception data of each pipeline at that future time point and the pipeline perception data of the adjacent pipeline, determine the average gradient corresponding to all pipelines in the gas pipeline network at that future time point. One future time point corresponds to one average gradient. Among the plurality of average gradients corresponding to the plurality of future time points, the future time point with the smallest average gradient is determined as the sampling time.

[0167] Wherein, the selection method of the plurality of future time points within the future period can refer to the determination method of candidate sampling time points in the following text, which will not be elaborated here.

[0168] In some embodiments, the processor may determine at least one candidate sampling time point; determine the sampling stability of at least one candidate sampling time point based on the pipeline perception data of at least one pipeline for a future period; and determine the sampling time based on the sampling stability of at least one candidate sampling time point.

[0169] In some embodiments, the processor may determine the candidate sampling time point in various ways. For example, the processor may divide the future period according to a preset length to obtain a plurality of sub-periods, and use the start time point or the end time point of each sub-period as the candidate sampling time point. The preset length is negatively correlated with the number of candidate sampling time points. The larger the preset length, the fewer the number of candidate sampling time points. The number of candidate sampling time points may be set by default in the system or set by a technician according to actual needs.

[0170] Sampling stability refers to the stability of the gas pipeline network corresponding to the sampling time. In some embodiments, sampling stability may be affected by the sampling behavior or the gas pipeline network itself. For example, at a certain point in time, multiple large chemical enterprises start using gas, and the gas in the gas pipeline network fluctuates greatly, and the corresponding sampling stability may be poor. Another example is that when the sampling equipment conducts sampling, due to non-standard operations, a large amount of gas overflows, which in turn leads to the instability of the gas pipeline network.

[0171] In some embodiments, the processor can determine the sampling stability of at least one candidate sampling time point in multiple ways based on the pipeline perception data of at least one pipeline for a future period of time. For example, the processor can determine the sampling stability of at least one candidate sampling time point by means of vector matching.

[0172] Merely by way of example, the processor can construct a second standard vector library. The second standard vector library can include multiple second standard vectors and their corresponding multiple second tags. Among them, the second standard vector can include pipeline perception data and sampling time, and the second tag can be the sampling stability of the corresponding sampling time.

[0173] In some embodiments, the processor can construct a second clustering vector based on the historical pipeline perception data, historical sampling time and their corresponding historical sampling stability in the historical data, cluster the multiple second clustering vectors, construct a second standard vector based on the historical pipeline perception data and historical sampling time corresponding to the clustering center formed by clustering, and use the historical sampling stability corresponding to the clustering center as the second tag of the second standard vector.

[0174] In some embodiments, the processor can calculate the second similarity between the pipeline perception data before the historical sampling time and the pipeline perception data after the historical sampling time, and determine the historical sampling stability based on the second similarity (for example, using 1 minus the second similarity as the historical sampling stability). The second similarity can be represented by cosine similarity, Euclidean distance, etc.

[0175] In some embodiments, the processor can construct a second vector to be matched based on the current pipeline perception data for a future period of time and the candidate sampling time point, match the second vector to be matched with the second standard vectors in the second standard vector library, calculate the multiple vector similarities between the second vector to be matched and the multiple second standard vectors, and determine the second tag corresponding to the second standard vector with the highest vector similarity as the sampling stability of the candidate sampling time point. Among them, the vector similarity can be represented by cosine similarity, Euclidean distance, etc.

[0176] In some embodiments, such as Figure 5As shown, the processor can construct a gas pipeline network atlas 540; based on the gas pipeline network atlas 540, the sampling stability 530 of at least one candidate sampling time point can be determined through the sampling stability evaluation model 550.

[0177] The gas pipeline network atlas refers to an atlas that can reflect the connection relationship between each pipeline and equipment in the gas pipeline network. In some embodiments, the gas pipeline network atlas is composed of nodes and edges.

[0178] In some embodiments, the nodes of the gas pipeline network atlas can include gas pipeline nodes, gas supply equipment nodes, and gas consumption equipment nodes.

[0179] The gas pipeline node takes the gas pipeline as the node; the gas supply equipment node takes the gas supply equipment as the node; the gas consumption equipment node takes the gas consumption equipment as the node. The gas supply equipment refers to the equipment that provides gas, such as a mixer, a gas pressure regulating box, etc. The gas consumption equipment refers to the terminal equipment that uses gas, such as residential gas consumption equipment, etc.

[0180] In some embodiments, the node attributes of the gas pipeline node can include the current pipeline perception data of the pipeline and the pipeline perception data for a period of time in the future; the node attributes of the gas supply equipment node can include the gas supply arrangement; the node attributes of the gas consumption equipment can include the gas consumption equipment information and the current gas consumption rate.

[0181] Among them, the gas supply arrangement refers to the output parameters of the gas at each time point. For example, the output flow rate, output volume, output gas pressure, output gas concentration, output gas composition, etc. In some embodiments, the processor can obtain the gas supply arrangement from the gas company management platform. The gas consumption equipment information refers to the information related to the gas consumption equipment. For example, the type of the gas consumption equipment, etc. The current gas consumption rate refers to the rate of using gas currently, such as 5m / s, etc.

[0182] In some embodiments, the node attributes of the gas pipeline node in the gas pipeline network atlas can also include the in-degree of the gas pipeline node.

[0183] In some embodiments of this specification, the node attributes of the gas pipeline node also consider the in-degree of the pipeline. Through the in-degree of the pipeline, the complexity of the gas pipeline network can be characterized, and the accuracy of subsequent determination of sampling stability can be improved.

[0184] In some embodiments, the edges of the gas pipeline network atlas can be the connection edges of the nodes where the gas flows mutually. The edge attributes of the gas pipeline network atlas can include the gas flow direction and the gas flow rate. The gas flow direction can refer to the direction from the node where the gas flows out to the node where the gas flows in.

[0185] The sampling stability evaluation model is a model used to determine the sampling stability of candidate sampling time points. In some embodiments, the sampling stability evaluation model can be a machine learning model. For example, a Graph Neural Networks (GNN) model, etc.

[0186] In some embodiments, the input of the sampling stability evaluation model can include a gas pipeline network map and candidate sampling time points, and the output can be the sampling stability of the candidate sampling time points.

[0187] In some embodiments, the processor can train the sampling stability evaluation model based on multiple second training samples with second training labels. The training process can refer to Figure 4 the training process of the detection ability evaluation model in, which will not be elaborated here.

[0188] A set of second training samples can include a sample gas pipeline network map and sample candidate sampling time points, and the second training label corresponding to a set of second training samples can be the sampling stability of the sample candidate sampling time points corresponding to the training samples.

[0189] In some embodiments, the processor can select a historical gas pipeline network map and a historical sampling time as a set of second training samples, and use the historical sampling stability of the historical sampling time corresponding to this set of second training samples as the second training label of this set of second training samples. For the acquisition process of the second training label, reference can be made to the relevant description of the acquisition process of the second label of the second standard vector library in the above text, which will not be elaborated here.

[0190] In some embodiments of this specification, through the machine learning model, the sampling stability of candidate sampling time points can be accurately determined, and then the appropriate sampling time can be determined to sample the gas pipeline, improving work efficiency.

[0191] In some embodiments, the processor can determine the sampling time in various ways based on the sampling stability of at least one candidate sampling time point. For example, the processor can sort the sampling stabilities of multiple candidate sampling time points and select one or more candidate sampling time points with the highest sampling stability as the sampling time.

[0192] In some embodiments of this specification, by measuring the stability of candidate sampling time points, the impact of different sampling times on the gas pipeline network can be measured more precisely, which is conducive to further reducing the risks and benefit losses brought by sampling.

[0193] In some embodiments of this specification, based on the current pipeline perception data, the pipeline perception data for a future period of time can be determined, and then the sampling time can be determined, which can make the determined sampling time more reasonable, reduce the impact of sampling on the gas pipeline network, and reduce the risks and economic benefit losses brought by sampling.

[0194] One or more embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a smart gas pipeline sampling and monitoring method.

[0195] Certain features, structures, or characteristics in one or more embodiments of the present invention may be appropriately combined.

[0196] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numerical letters, or the use of other names in the present invention are not used to limit the order of the processes and methods of the present invention. Although some currently useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details are for illustrative purposes only. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of the present invention. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0197] If there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the materials cited in the present invention and the content described in the present invention, the descriptions, definitions, and / or uses of terms in the present invention shall prevail.

Claims

1. A smart gas pipeline sampling and monitoring Internet of Things system, characterized in that: The smart gas pipeline sampling and monitoring IoT system includes a government safety supervision management platform, a government safety supervision sensor network platform, a government safety supervision object platform, a gas company sensor network platform, a gas equipment object platform, and a gas maintenance object platform; The gas equipment object platform includes at least one sampling device and at least one pipeline monitoring device; The gas maintenance object platform includes at least one staff interaction device; The government safety supervision object platform includes the gas company management platform and key gas-using enterprises; The government security supervision management platform is configured as follows: Obtaining pipeline sensing data of at least one section of the pipeline collected and uploaded by the gas equipment object platform via the gas company sensor network platform, the gas company management platform, and the government safety supervision sensor network platform in sequence; Determine sampling parameters based on the pipeline sensing data of the at least one section of the pipeline, and send the sampling parameters from the government safety supervision object platform to the at least one sampling device; the sampling parameters include at least one open sampling device and a corresponding pipeline sampling position, and a sampling time; the government safety supervision management platform is further configured as follows: Determining pipeline sensing data of the at least one section of the pipeline for a period of time in the future based on the pipeline sensing data of the at least one section of the pipeline; Determine candidate sampling time points; Determining the sampling stability of the candidate sampling time point based on the pipeline sensing data for the future period of time; Determining the sampling time based on the sampling stability of the candidate sampling time points; In response to acquiring at least one sampling data from the at least one sampling device, a fault detection instruction is determined based on the at least one sampling data, and the fault detection instruction is sent to the gas maintenance object platform to arrange a manual inspection.

2. The Internet of Things system according to claim 1, characterized in that: The government security supervision management platform is further configured as follows: Based on the pipeline sensing data of the at least one section of the pipeline, determining at least one section of abnormal pipeline and its corresponding abnormal area; Based on the at least one abnormal pipeline section and its corresponding abnormal area, the at least one sampling device to be started and the corresponding pipeline sampling position are determined.

3. The Internet of Things system according to claim 2, characterized in that: The sampling parameters also include a sampling detection type, and the sampling detection type includes sampling detection and non-sampling detection; The government security supervision management platform is further configured as follows: For a section of abnormal pipeline and its corresponding abnormal area, Determining the sampling detection type based on the pipeline sensing data of the abnormal pipeline and the corresponding abnormal area; In response to the presence of a plurality of the sampling devices on the abnormal pipeline, based on the pipeline sensing data of the abnormal pipeline and the sampling detection type, evaluating the sampling detection capability of the sampling device; The starting of the sampling device is determined based on the sampling detection capability of the at least one sampling device.

4. A smart gas pipeline sampling and monitoring method, characterized in that: The method is implemented based on a smart gas pipeline sampling and monitoring Internet of Things system, which includes a government safety supervision management platform, a government safety supervision sensor network platform, a government safety supervision object platform, a gas company sensor network platform, a gas equipment object platform, and a gas maintenance object platform; The method is performed by the government security supervision management platform, and the method includes: Obtaining pipeline sensing data of at least one section of the pipeline collected and uploaded by the gas equipment object platform via the gas company sensor network platform, the gas company management platform, and the government safety supervision sensor network platform in sequence; Determine sampling parameters based on the pipeline sensing data of the at least one section of the pipeline, send the sampling parameters to the government safety supervision object platform, and further send them to at least one sampling device by the government safety supervision object platform; the sampling parameters include at least one open sampling device and a corresponding pipeline sampling position; In response to acquiring at least one sampling data from the at least one sampling device, determining a fault detection instruction based on the at least one sampling data, sending the fault detection instruction to the gas maintenance object platform, and the gas maintenance object platform arranging a manual inspection; The sampling parameters also include sampling time, and the determining of the sampling parameters based on the pipeline sensing data of the at least one section of the pipeline includes: Determining pipeline sensing data of the at least one section of the pipeline for a period of time in the future based on the pipeline sensing data of the at least one section of the pipeline; Determine candidate sampling time points; Determining the sampling stability of the candidate sampling time point based on the pipeline sensing data for the future period of time; The sampling time is determined based on the sampling stability of the candidate sampling time points.

5. The method according to claim 4, characterized in that The determining of sampling parameters based on the pipeline sensing data of the at least one section of the pipeline includes: Based on the pipeline sensing data of the at least one section of the pipeline, determining at least one section of abnormal pipeline and its corresponding abnormal area; Based on the at least one abnormal pipeline section and its corresponding abnormal area, the at least one sampling device to be started and the corresponding pipeline sampling position are determined.

6. The method according to claim 5, characterized in that The sampling parameters also include a sampling detection type, and the sampling detection type includes sampling detection and non-sampling detection; The step of determining the sampling parameters based on the at least one abnormal pipeline section and its corresponding abnormal area includes: For a section of abnormal pipeline and its corresponding abnormal area, Determining the sampling detection type based on the pipeline sensing data of the abnormal pipeline and the corresponding abnormal area; In response to the presence of a plurality of the sampling devices on the abnormal pipeline, based on the pipeline sensing data of the abnormal pipeline and the sampling detection type, evaluating the sampling detection capability of the sampling device; The starting of the sampling device is determined based on the sampling detection capability of the at least one sampling device.

7. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the smart gas pipeline sampling and monitoring method as described in any one of claims 4-6.

Images