A pipeline protection component layout method, system and medium based on smart gas internet of things

Abstract

Embodiments of the present application provide a pipeline protection component laying method and system based on smart gas Internet of Things, and a medium, belonging to the field of gas pipeline management. The method comprises: acquiring environmental information of a target area in a plurality of first preset time periods; acquiring biological information, climate information and facility information of the target area in the plurality of first preset time periods; determining vibration risk values, corrosion risk values and temperature risk values of the target area in the plurality of first preset time periods; determining a target risk distribution of the target area; based on the target risk distribution, determining target protection component information of collection points laid in the target area; based on the target risk distribution and a pipeline laying map of the target area, determining a laying density distribution of the target protection component; and based on the laying density distribution, generating a valve control instruction to adjust the gas delivery pressure of at least one gas pipeline in the target area. The method can ensure the service life of the gas pipeline and reduce the cost of pipeline replacement.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of gas pipeline management, and particularly relates to a pipeline protection component layout method and system based on smart gas Internet of Things and a medium. BACKGROUND

[0002] A gas pipeline is a main transportation facility for gas. During operation, external interference, including climate temperature variation, stress, vibration, freeze-thaw cycle, biological corrosion, etc., can reduce the service life of the gas pipeline, and even cause pipeline failure, resulting in safety hazards. The existing technology manages and maintains the gas pipeline mainly in a manner of combining regular inspection with post-maintenance, and lacks a means of early prevention during gas pipeline laying.

[0003] Therefore, it is necessary to provide a pipeline protection component layout method and system based on smart gas Internet of Things and a medium, which lays corresponding pipeline protection components in key protection areas according to actual conditions during pipeline laying, so as to improve the service life of the gas pipeline and ensure the safety of gas management and operation. SUMMARY

[0004] One or more embodiments of the present invention provide a method for deploying pipeline protection components based on a smart gas Internet of Things. The method is executed by a gas company management platform of a pipeline protection component deployment system, and the method includes: obtaining environmental information of a target area within a plurality of first preset time periods from a sensor device provided in a gas equipment object platform through a gas company sensor network platform, the environmental information including temperature information, humidity information, geological information and vibration information; obtaining biological information, climate information and facility information of the target area within the plurality of first preset time periods from a government safety supervision management platform through a government safety supervision sensor network platform; determining the vibration risk value of the target area in each of the plurality of first preset time periods based on the geological information, the facility information and the vibration information within the plurality of first preset time periods; determining the corrosion risk value of the target area in each of the plurality of first preset time periods based on the geological information, the biological information and the facility ...; determining the corrosion risk of the target area in each of the plurality of first preset time periods. The method comprises the following steps: determining the temperature risk values ​​of the target area in the multiple first preset time periods based on the climate information in the multiple first preset time periods; determining the target risk distribution of the target area based on the vibration risk value, the corrosion risk value and the temperature risk value in the multiple first preset time periods; determining the target protection component information laid at the collection point in the target area based on the target risk distribution, the target protection component information including the target protection component type and the corresponding first target protection level; determining the laying density distribution of the target protection component based on the target risk distribution and the pipeline laying map of the target area; and generating a valve control instruction based on the laying density distribution and sending it to the gas equipment object platform before performing the protection component laying operation, and / or during the execution of the protection component laying operation, so as to adjust the gas transmission pressure of at least one gas pipeline in the target area.

[0005] One or more embodiments of the present invention provide a pipeline protection component deployment system based on a smart gas Internet of Things. The pipeline protection component deployment 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, and a gas equipment object platform. The government safety supervision object platform includes a gas company management platform; the gas company management platform includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to achieve: through the gas company sensor network platform, obtain the environmental information of the target area within multiple first preset time periods from the sensor device set in the gas equipment object platform, the environmental information includes temperature information, humidity information, geological information and vibration information; through the government safety supervision sensor network platform, obtain the biological information, climate information and facility information of the target area within the multiple first preset time periods from the government safety supervision management platform; based on the geological information, the facility information and the vibration information within the multiple first preset time periods, determine the vibration wind speed of the target area in each of the multiple first preset time periods. risk value; determining the corrosion risk value of the target area in each of the multiple first preset time periods based on the geological information, the biological information and the facility information in the multiple first preset time periods; determining the temperature risk value of the target area in each of the multiple first preset time periods based on the climate information in the multiple first preset time periods; determining the target risk distribution of the target area based on the vibration risk value, the corrosion risk value and the temperature risk value in each of the multiple first preset time periods; determining the target protection component information laid at the collection points in the target area based on the target risk distribution, the target protection component information including the target protection component type and the corresponding first target protection level; determining the laying density distribution of the target protection component based on the target risk distribution and the pipeline laying map of the target area; and generating a valve control instruction based on the laying density distribution and sending it to the gas equipment object platform before performing the protection component laying operation and / or during the protection component laying operation, so as to adjust the gas transmission pressure of at least one gas pipeline in the target area.

[0006] One or more embodiments of the present invention 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 pipeline protection component deployment method based on a smart gas Internet of Things as described in any embodiment of the present invention.

[0007] The beneficial effects of the present invention include but are not limited to: when laying the pipeline, corresponding pipeline protection components are arranged in key protection areas according to actual conditions, thereby ensuring the service life of the gas pipeline; adjusting the gas delivery pressure of at least one gas pipeline in the target area according to valve control instructions can avoid failures, thereby ensuring the service life of the gas pipeline and reducing the cost of pipeline replacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The present invention will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] Figure 1 is an exemplary schematic diagram of a smart gas Internet of Things according to some embodiments of the present invention;

[0010] Figure 2 is an exemplary flow chart of a method for deploying pipeline protection components based on a smart gas Internet of Things according to some embodiments of the present invention;

[0011] Figure 3 This is an exemplary schematic diagram of determining target protection component information according to some embodiments of the present invention. DETAILED DESCRIPTION

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of the present invention. Those skilled in the art can apply the present invention to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0013] It should be understood that the terms "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 terms can achieve the same purpose, the terms may be replaced by other expressions.

[0014] As used herein and in the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0015] Flowcharts are used in this disclosure to illustrate the operations performed by systems according to embodiments of the present invention. It should be understood that the preceding and following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0016] Figure 1 1 is an exemplary schematic diagram of a smart gas Internet of Things according to some embodiments of the present invention. It should be noted that the following embodiments are only used to illustrate the present invention and do not constitute a limitation of the present invention.

[0017] like Figure 1 As shown, in some embodiments, the smart gas Internet of Things 100 may include a government safety supervision management platform 110, a government safety supervision sensor network platform 120, a government safety supervision object platform 130, a gas company sensor network platform 140 and a gas equipment object platform 150.

[0018] In some embodiments, one or more platforms in the smart gas Internet of Things 100 can exchange information and / or data via a network. In some embodiments, the network can be any one or more of a wired network or a wireless network.

[0019] The government safety supervision and management platform 110 is a comprehensive management platform for the government to conduct safety supervision and management. In some embodiments, the government safety supervision and management platform 110 can be configured to process and store data of the smart gas Internet of Things 100.

[0020] In some embodiments, the government security supervision management platform 110 may include a government supervision integrated database 110 - 1 , which is a database for data storage.

[0021] In some embodiments, the government safety supervision management platform 110 can be configured to obtain biological information, climate information, and facility information for the areas where multiple gas pipelines are located over multiple time periods in real time or at regular intervals, and store the obtained information in the government supervision integrated database 110-1. For more information about the government safety supervision management platform 110 in some embodiments, see the relevant description below.

[0022] The government security supervision sensor network platform 120 is a functional platform for sensor communication between the government security supervision management platform 110 and the government security supervision object platform 130. The government security supervision sensor network platform 120 can be configured as a communication network and a gateway.

[0023] The government safety supervision platform 130 is a platform for safety supervision of gas-related entities. For example, gas-related entities may include gas companies. In some embodiments, the government safety supervision platform 130 can exchange information with the government safety supervision sensor network platform 120 and the gas company sensor network platform 140.

[0024] In some embodiments, the government safety supervision platform 130 may include a gas company management platform 130-1. Gas company management platform 130-1 refers to the gas company's integrated information management platform. For example, gas company management platform 130-1 may be a gas company processor or server. In some embodiments, gas company management platform 130-1 may interact with the gas company sensor network platform 140 and the government safety supervision sensor network platform 120.

[0025] In some embodiments, the gas company management platform 130-1 can be configured to execute a pipeline protection component deployment method based on a smart gas Internet of Things as described in any embodiment of the present invention. For more information, see Figures 2-3 .

[0026] The gas company sensor network platform 140 is a functional platform for sensory communication between the government safety supervision platform 130 and the gas equipment platform 150. The gas company sensor network platform 140 can be configured as a communication network and gateway. In some embodiments, the gas company sensor network platform 140 can also be a server located in the gas pipeline laying area.

[0027] In some embodiments, the gas company sensor network platform 140 can interact with the gas equipment object platform 150 and the gas company management platform 130-1. For example, the gas company sensor network platform 140 can obtain environmental information sent by the gas equipment object platform 150 and transmit the environmental information to the gas company management platform 130-1.

[0028] The gas equipment object platform 150 is a functional platform related to gas equipment and used for sensing information generation and controlling information execution.

[0029] In some embodiments, the gas equipment object platform 150 can be configured to interact with a variety of devices. These devices may include gas equipment (e.g., gas meters), gas monitoring equipment (e.g., gas pressure monitoring devices, temperature monitoring devices, flow monitoring devices), environmental protection facilities (e.g., exhaust gas treatment equipment, environmental monitoring equipment), and maintenance equipment (e.g., repair equipment, cleaning equipment). In some embodiments, the gas equipment object platform 150 may include multiple gas pipelines and sensor devices for collecting environmental information about the areas in which the gas pipelines are located.

[0030] In some embodiments, the gas equipment object platform 150 can interact with the gas company sensing network platform 140. For example, the gas equipment object platform 150 can obtain the valve control instruction issued by the gas company management platform 130-1 through the gas company sensing network platform 140, and adjust the gas delivery pressure of at least one gas pipeline in the target area according to the valve control instruction.

[0031] It should be noted that the above description of the smart gas IoT 100 is for the convenience of description, and cannot limit the present application to the scope of the embodiments.

[0032] Figure 2 is an exemplary flowchart of a pipeline protection component layout method based on a smart gas IoT according to some embodiments of the present application. In some embodiments, the flow 200 can be performed by the gas company management platform of the pipeline protection component layout system. For details of each platform, please refer to Figure 1 and the related description. As Figure 2 shown, the flow 200 includes the following steps.

[0033] Step 210, obtaining, by the gas company sensing network platform, the environmental information of the target area in a plurality of first preset time periods from the sensing devices set by the gas equipment object platform.

[0034] For related descriptions of the gas company sensing network platform and the gas equipment object platform, please refer to Figure 1 .

[0035] The target area refers to the area where the gas pipeline protection component is to be laid. The gas company management platform can determine the target area based on the pre-stored construction information in the database (for example, the government regulatory comprehensive database 110-1).

[0036] The first preset time period refers to a pre-set time period. The first preset time period can be a historical period before the current time. In some embodiments, the first preset time period can include a plurality of time points.

[0037] The environmental information refers to information related to the environment of the target area. The environmental information in the first preset time period can include information related to the environment of the target area obtained at a plurality of time points in the first preset time period. In some embodiments, the environmental information can include temperature information, humidity information, geological information, and vibration information.

[0038] The temperature information refers to information related to the temperature of the target area. In some embodiments, the temperature information can include an average temperature, a maximum temperature, and a minimum temperature. The average temperature refers to the average of the temperatures collected at multiple time points within the first preset time period. The maximum temperature refers to the highest temperature collected at multiple time points within the first preset time period. The minimum temperature refers to the lowest temperature collected at multiple time points within the first preset time period.

[0039] The humidity information refers to information related to the humidity of the target area. In some embodiments, the humidity information can include an average humidity, a maximum humidity, and a minimum humidity. The average humidity, the maximum humidity, and the minimum humidity are similar to the average temperature, the maximum temperature, and the minimum temperature, and will not be described here again.

[0040] The geological information refers to information related to the geology of the target area. In some embodiments, the geological information can include a soil density distribution and a soil pH distribution. The soil density distribution includes the average soil density of multiple collection points and corresponding position information collected at each time point within the first preset time period. The soil pH distribution includes the average soil pH of multiple collection points and corresponding position information collected at each time point within the first preset time period.

[0041] The collection point refers to a point for information collection. The collection point can be determined by user input.

[0042] For example, for the geological information, there are time points t1, t2, …, t n , and multiple collection points p1, …, p m in the preset collection path. If data is collected along the preset path at each time point within the first preset time period, the soil density distribution includes the average soil density collected at the collection point p1 at the time points t1, t2, …, t n , the average soil density collected at the collection point p2 at the time points t1, t2, …, t n , …, and the average soil density collected at the collection point p m at the time points t1, t2, …, t n .

[0043] The vibration information refers to information reflecting the vibration of the land in the target area. In some embodiments, the vibration information can include a vibration intensity distribution and a vibration frequency distribution. The vibration intensity distribution includes the average vibration intensity of multiple collection points and corresponding position information collected at each time point within the first preset time period. The vibration frequency distribution includes the average vibration frequency of multiple collection points and corresponding position information collected at each time point within the first preset time period.

[0044] In some embodiments, the gas equipment object platform can obtain environmental information of the target area in multiple first preset time periods through a set sensor device. The environmental information obtained by the gas equipment object platform in multiple first preset time periods can be transmitted to the gas company management platform through the gas company sensor network platform.

[0045] A sensing device is a detection device capable of measuring environmental information. In some embodiments, the sensing device may include a temperature acquisition device (e.g., a temperature sensor), a humidity acquisition device (e.g., a humidity sensor), a geological acquisition device (e.g., a soil detection instrument), a vibration acquisition device (e.g., a vibration sensor), etc.

[0046] In some embodiments, the sensing device can operate in various ways. For example, the sensing device can be set at a fixed location to detect data or loaded on a carrier (eg, a mobile carrier) to detect data.

[0047] In some embodiments, the sensing device may be mounted on a crawling robot. The crawling robot may be configured to collect data along a preset collection path.

[0048] A crawling robot is a robot that can crawl and carry objects (e.g., sensors). It can consist of a robot body and a control system, with its own power drive system, enabling autonomous movement. In some embodiments, the crawling robot can be positioned inside a gas pipeline or above the ground corresponding to the gas pipeline.

[0049] In some embodiments, the crawling robot may also be equipped with an image sensor, which may transmit detection data (eg, detection images) to a control system in real time.

[0050] In some embodiments, the crawling robot can collect environmental information within the target area according to a preset collection path.

[0051] The preset collection path refers to a preset path for the crawler robot to collect information. In some embodiments, the preset collection path may include multiple collection points.

[0052] In some embodiments, there may be multiple ways to determine the preset acquisition path.

[0053] In some embodiments, the gas company management platform may determine a preset collection path based on multiple gas pipeline transportation paths within a pipeline laying map.

[0054] A pipeline layout map is a schematic diagram of the gas pipeline layout. The pipeline layout map can indicate the pipeline's direction, dimensions, and other information. In some embodiments, the pipeline layout map can be user-entered or retrieved from pre-stored information in the government regulatory integrated database 110-1. The gas pipeline transportation path is the path of the gas pipeline laid underground and can be directly determined using the pipeline layout map. In some embodiments, the gas company management platform can determine the gas pipeline transportation path as a preset collection path.

[0055] In some embodiments, the gas company management platform can determine the collection parameters of the crawling robot based on the pipeline laying map and the pipeline importance levels of multiple gas pipeline sections; and determine a preset collection path based on the collection parameters of the crawling robot.

[0056] A gas pipeline segment refers to a section of a gas pipeline obtained by dividing it. A pipeline layout map may include multiple gas pipeline segments. In some embodiments, the gas pipeline segmentation can be performed by relevant personnel. In some embodiments, the gas company management platform can also divide the gas pipeline segments based on the length of the gas pipeline. For example, equidistant segmentation can be used to divide the gas pipeline into multiple gas pipeline segments of equal length.

[0057] The pipeline importance level refers to a level reflecting the importance of the gas pipeline segment. In some embodiments, the pipeline importance level can be preset by a technician based on prior knowledge or historical data.

[0058] The acquisition parameters of the crawling robot refer to the parameters when the crawling robot performs data acquisition. In some embodiments, the acquisition parameters of the crawling robot may include the acquisition points, sampling frequency, sampling amount, etc. during data acquisition.

[0059] In some embodiments, the gas company management platform can determine the number of collection points, sampling frequency, and corresponding sampling volume for each gas pipeline segment within a target area based on the pipeline importance level of the gas pipeline segment using a first preset table. The first preset table includes multiple pipeline importance levels and the corresponding collection parameters of the crawler robot (e.g., number of collection points, sampling frequency, and sampling volume) for each pipeline importance level. In some embodiments, the first preset table can be established by technical personnel based on experience. In some embodiments, the first preset table can be constructed based on prior knowledge or historical data (e.g., historical collection parameters of the crawler robot when collecting data from gas pipeline segments of different pipeline importance levels).

[0060] In some embodiments, the gas company management platform can use a preset algorithm to obtain a path covering all the collection points and having the shortest length as the preset collection path. For example, the preset algorithm can be a path planning algorithm (e.g., Dijkstra algorithm, BFS (Best-First-Search) algorithm, A algorithm, etc.).

[0061] After determining the preset collection path, the gas company management platform can generate a movement instruction and send the movement instruction to the gas equipment object platform. The gas equipment object platform can send the movement instruction to the crawling robot.

[0062] The movement instruction is an instruction indicating the crawling robot to move. In some embodiments, the gas company management platform can generate a collection instruction based on the preset collection path of the crawling robot and send the collection instruction to the sensing device loaded on the crawling robot. When the crawling robot moves on the preset collection path, the sensing device loaded on the crawling robot can collect data based on the collection instruction.

[0063] In some embodiments of the present application, the sensing device is loaded on the crawling robot, and the preset collection path is determined based on the pipeline laying map and the pipeline importance of each gas pipeline segment. More information can be collected for gas pipeline segments with higher pipeline importance levels, and less information can be appropriately collected for gas pipeline segments with lower pipeline importance levels, so that the environmental information is more reasonably and efficiently collected.

[0064] In step 220, the government safety supervision sensing network platform obtains biological information, climate information, and facility information of the target region in a plurality of first preset time periods from the government safety supervision management platform.

[0065] The biological information refers to information related to the biology of the target region. In some embodiments, the biological information can include microbial density distribution, termite density distribution, and rodent quantity, etc. The microbial density distribution includes the average of the microbial density distribution of a plurality of collection points collected at each time point in the plurality of time points in the first preset time period and the corresponding position information. The termite density distribution includes the average of the termite density distribution of a plurality of collection points collected at each time point in the plurality of time points in the first preset time period and the corresponding position information. The rodent quantity refers to the average of the rodent quantity of a plurality of collection points collected at each time point in the plurality of time points in the first preset time period.

[0066] The climate information refers to information related to the climate of the target region. In some embodiments, the climate information can include the weather type of a plurality of time points in the first preset time period and the number of occurrences of each weather type.

[0067] The facility information refers to information related to facilities and equipment in the target area. In some embodiments, the facility information can include factory types, the number of factories corresponding to each factory type, and the number of installations. The facilities can include vehicles, mechanical equipment, sites, lines, communication equipment, signal signs, buildings, etc.

[0068] The factory types can include chemical plants, metallurgical processing plants, heavy machinery processing plants, etc. In some embodiments, the government safety supervision and management platform can obtain the factory types of all factories at multiple time points within a first preset time period, take the average of the number of each factory type obtained at the multiple time points within the first preset time period as the number of factories of the corresponding factory type, and take the average of the number of installations obtained at the multiple time points within the first preset time period as the number of installations.

[0069] In some embodiments, the government safety supervision and management platform can obtain biological information, climate information, and facility information of the target area within multiple first preset time periods and transmit them to the gas company management platform through the government safety supervision sensor network platform.

[0070] In some embodiments, the government safety supervision and management platform can periodically obtain biological information, climate information, and facility information of the target area and store them in the government supervision comprehensive database. For example, the government safety supervision and management platform can periodically perform biological statistics, industrial facility statistics, or facility statistics, etc., and determine the biological information and facility information according to the statistical results. The gas company management platform can call the biological information, climate information, and facility information corresponding to the first preset time period through the government safety supervision sensor network platform.

[0071] Step 230, based on the geological information, facility information, and vibration information within the multiple first preset time periods, determining vibration risk values of the target area in the multiple first preset time periods respectively.

[0072] The multiple first preset time periods can be multiple historical time periods before the current time. The lengths of the multiple first preset time periods can be the same. There can be no interval between the multiple first preset time periods, i.e., the end time point of the former first preset time period and the start time point of the latter first preset time period in the adjacent two first preset time periods coincide.

[0073] The vibration risk value refers to a numerical value measuring the degree of influence of ground vibration on the gas pipeline. In some embodiments, the vibration risk values of the target area in the multiple first preset time periods respectively can include vibration risk values of multiple collection points in the target area in the multiple first preset time periods respectively.

[0074] In some embodiments, the gas company management platform can determine the vibration risk values of the target area in the multiple first preset time periods respectively based on the geological information, facility information, and vibration information within the multiple first preset time periods through multiple ways.

[0075] In some embodiments, for each first preset time period, the gas company management platform can determine, based on the average soil density of each of the plurality of collection points, a vibration amplification coefficient corresponding to each of the plurality of collection points. For example, for each collection point, the gas company management platform can divide the vibration coefficient by the average soil density of the collection point to obtain the vibration amplification coefficient corresponding to the collection point. The vibration coefficient refers to the amplification coefficient of vibration under standard soil conditions. In some embodiments, the vibration coefficient can be set according to experience. The vibration amplification coefficient is the amplification coefficient of vibration under the actual soil conditions corresponding to the collection point. The average soil density can be the average of the soil densities collected at each time point in the soil density distribution of the first preset time period.

[0076] In some embodiments, for each first preset time period, the gas company management platform can determine, based on the vibration amplification coefficient, the average vibration intensity, the average vibration frequency, the average soil pH value, the facility information of the target area, and other parameters of each of the plurality of collection points, a vibration risk value of each of the plurality of collection points. The average soil pH value can be the average of the soil pH values collected at each time point in the soil pH value distribution within the first preset time period. The average vibration intensity and the average vibration frequency can be the average of the vibration intensities and the vibration frequencies collected at each time point in the vibration information within the first preset time period.

[0077] For example, for each collection point, the gas company management platform can determine the vibration risk value corresponding to the collection point according to formula (1):

[0078] (1)

[0079] wherein, represents the vibration risk value of the collection point in the first preset time period, represents the vibration amplification coefficient of the collection point, represents the average vibration intensity of the collection point, represents the average soil pH value of the collection point, represents the average vibration frequency of the collection point, represents the number of facilities, represents the number of installations. The number of facilities and the number of installations can be obtained from the facility information. , , , are weight coefficients of the plurality of parameters in calculating the vibration risk value. , , , may be set according to experience.

[0080] In some embodiments, the gas company management platform can determine the weight coefficients of the parameters in calculating the vibration risk value in multiple ways 、 、 、 For example, the gas company management platform can determine the weight coefficients of the parameters in calculating the vibration risk value by using a first preset regression algorithm.

[0081] In some embodiments, the gas company management platform can determine the labels of the parameters; and determine the weight coefficients of the parameters in calculating the vibration risk value by fitting the first preset regression algorithm according to the parameters and the corresponding labels.

[0082] For each parameter, the gas company management platform can take the number of times of failures of the gas pipeline caused by vibration corresponding to the parameter as the corresponding label. The first preset regression algorithm is similar to the third preset regression algorithm, and more details are described in step 250.

[0083] In step 240, the gas company management platform determines the corrosion risk values of the target region in the multiple first preset time periods based on the geological information, biological information and facility information in the multiple first preset time periods.

[0084] The corrosion risk value refers to a numerical value for measuring the risk degree of corrosion of the gas pipeline. In some embodiments, the corrosion risk values of the target region in the multiple first preset time periods can include the corrosion risk values of the multiple collection points in the target region in the multiple first preset time periods.

[0085] In some embodiments, the gas company management platform can determine the corrosion risk values of the target region in the multiple first preset time periods based on the geological information, biological information and facility information in the multiple first preset time periods in multiple ways.

[0086] In some embodiments, for each first preset time period, the gas company management platform can determine the soil acidity coefficients of the multiple collection points based on the average soil pH values of the multiple collection points. For example, for each collection point, the gas company management platform can subtract the average soil pH value of the collection point from 14 (the range of pH value) to obtain the soil acidity coefficient of the collection point. The soil acidity coefficient is a coefficient related to the soil pH value. The average soil pH value can be the average value of the soil pH values collected at each time point in the soil pH value distribution of the first preset time period.

[0087] In some embodiments, for each first preset time period, the gas company management platform can determine the corrosion risk value of each of the multiple collection points based on parameters such as the soil acidity coefficient, the number of factories producing corrosive gases and liquids, the average microbial density, the average termite density, and the average number of rodents. The average microbial density can be the average of the microbial densities collected at each time point within the first preset time period in the microbial density distribution. The average termite density can be the average of the termite densities collected at each time point within the first preset time period in the termite density distribution. The average number of rodents can be the average of the number of rodents collected at each time point within the first preset time period in the rodent count. The number of factories producing corrosive gases and liquids can be the number of factories corresponding to factories producing corrosive gases and liquids in the factory type.

[0088] [1] For example, for each collection point, the gas company management platform can determine the corrosion risk value corresponding to the collection point according to formula (2):

[0089] (2)

[0090] in, Indicates the corrosion risk value of the collection point in the first preset period, Indicates the soil acidity coefficient of the sampling point. Indicates the number of plants producing corrosive gases and liquids, represents the average microbial density, represents the average termite density, represents the average rodent population. 、 、 It is the weight coefficient of multiple parameters when calculating the corrosion risk value. 、 、 Can be set based on experience.

[0091] In some embodiments, the gas company management platform can determine the weight coefficients of multiple parameters when calculating the corrosion risk value in a variety of ways. 、 、 For example, the gas company management platform can determine the weight coefficients of multiple parameters when calculating the corrosion risk value through the second preset regression algorithm.

[0092] In some embodiments, the gas company management platform can determine labels for multiple parameters; based on the multiple parameters and corresponding labels, a second preset regression algorithm is used to fit and obtain weight coefficients for each parameter when calculating the corrosion risk value.

[0093] For each parameter, the gas company management platform can take the number of times the gas pipeline corresponding to the parameter fails due to corrosion as the corresponding label. The second preset regression algorithm is similar to the third preset regression algorithm, and more details are described in step 250.

[0094] In step 250, the temperature risk value of the target region in each of the plurality of first preset time periods is determined based on the climate information in the plurality of first preset time periods.

[0095] The temperature risk value refers to a numerical value that measures the risk degree of the gas pipeline from high temperature or low temperature, etc. In some embodiments, the temperature risk value of the target region in each of the plurality of first preset time periods can include the temperature risk value of each of the plurality of collection points in the target region in each of the plurality of first preset time periods.

[0096] In some embodiments, the gas company management platform can determine the temperature risk value of the target region in each of the plurality of first preset time periods based on the climate information in the plurality of first preset time periods in multiple ways.

[0097] In some embodiments, for each first preset time period, the gas company management platform can determine the temperature risk value of each of the plurality of collection points based on the average temperature, the maximum temperature, the minimum temperature, the average humidity, the weather risk coefficient, etc. of each of the plurality of collection points.

[0098] For example, for each collection point, the gas company management platform can determine the temperature risk value of the collection point according to formula (3):

[0099] (3)

[0100] wherein, T represents the temperature risk value of the collection point in the first preset time period, T represents the average temperature of the collection point in the first preset time period, T represents the maximum temperature of the collection point in the first preset time period, T represents the minimum temperature of the collection point in the first preset time period, T represents the average humidity of the collection point in the first preset time period, T represents the weather risk coefficient of the collection point. , , , are the weight coefficients of the plurality of parameters when calculating the temperature risk value. , , , may be set according to experience.

[0101] The weather risk coefficient is a mean value of the risk degree of each weather type and the corresponding frequency. In some embodiments, the risk degree of each weather type can be set empirically.

[0102] For example, the gas company management platform can set the weight coefficient according to experience.

[0103] In some embodiments, the gas company management platform can determine the weight coefficient of the parameters in calculating the temperature risk value in various ways 、 、 、 For example, the gas company management platform can determine the weight coefficient of the parameters in calculating the temperature risk value by a third preset regression algorithm.

[0104] In some embodiments, the first preset regression algorithm, the second preset regression algorithm, and the third preset regression algorithm can be the same or different. In some embodiments, the first preset regression algorithm, the second preset regression algorithm, and the third preset regression algorithm can include a linear regression algorithm, a polynomial regression algorithm, a support vector regression algorithm, etc.

[0105] In some embodiments, the gas company management platform can obtain temperature information and climate information around the gas pipeline in a plurality of first preset time periods corresponding to the length of the historical data.

[0106] In some embodiments, the gas company management platform can determine the labels of the plurality of temperature information and climate information; and according to the plurality of temperature information and climate information and the corresponding labels, the weight coefficients of the parameters in calculating the temperature risk value are fitted by the third preset regression algorithm.

[0107] For each temperature information and climate information, the gas company management platform can take the number of times of failure of the gas pipeline due to high or low temperature corresponding to the climate information as the corresponding label.

[0108] For example, assuming that the labels of information 1, information 2, and information 3 are y1, y2, and y3 respectively, the parameters included in the three information are respectively: information 1: average temperature , maximum temperature , minimum temperature , average humidity , weather risk coefficient ; information 2: average temperature , maximum temperature , minimum temperature , average humidity , weather risk coefficient ; information 3: average temperature , maximum temperature , minimum temperature , average humidity , weather risk factor Based on formula (3), the following three equations can be obtained. According to the following three equations, the gas company management platform can perform regression algorithms and fit the coefficients 、 、 、 .

[0109]

[0110]

[0111]

[0112] The process of calculating the weight coefficients corresponding to each parameter when calculating the corrosion risk value and the vibration risk value can be similar to that of the temperature risk value.

[0113] In some embodiments of the present invention, the weight coefficients of multiple parameters when calculating the vibration risk value / corrosion risk value / temperature risk value are determined through the first / second / third preset regression algorithm, which can improve the accuracy of the weight coefficients and thus improve the reliability of the calculated vibration risk value, corrosion risk value and temperature risk value.

[0114] In some embodiments, the gas company management platform may also determine a corrosion risk value based on the temperature risk value, geological information, biological information, and facility information.

[0115] In some embodiments, the gas company management platform may also consider the temperature risk value and the corresponding weight coefficient. For example, by adding a weighted term corresponding to the temperature risk value to formula (2), formula (4) is obtained:

[0116] (4)

[0117] in, is the temperature risk value of the collection point in the first preset period, is the weight coefficient corresponding to the temperature risk value.

[0118] In some embodiments, the gas company management platform can determine the weight coefficient corresponding to the temperature risk value in a variety of ways. For example, the gas company management platform can determine the proportion of the temperature risk value in the risk values ​​of three risk types (for example, vibration risk value, corrosion risk value and temperature risk value) as the weight coefficient corresponding to the temperature risk value. .

[0119] In some embodiments, the gas company management platform can also determine a vibration risk value based on the corrosion risk value, the geological information, the facility information, and the vibration information.

[0120] In some embodiments, the gas company management platform can also consider the corrosion risk value and a corresponding weight coefficient. For example, a weighted term corresponding to the corrosion risk value is added to Formula (1) to obtain Formula (5):

[0121] (5)

[0122] wherein, is the corrosion risk value of the collection point in the first preset time period, is the weight coefficient corresponding to the corrosion risk value.

[0123] In some embodiments, the gas company management platform can determine the weight coefficient corresponding to the corrosion risk value in multiple ways . For example, the gas company management platform can determine the proportion of the corrosion risk value in the risk values of the three risk types (e.g., the vibration risk value, the corrosion risk value, and the temperature risk value) as the weight coefficient corresponding to the corrosion risk value .

[0124] In some embodiments, the gas company management platform can determine the weight coefficient of the temperature risk value when calculating the corrosion risk value through a second preset regression algorithm, and / or determine the weight coefficient of the corrosion risk value when calculating the vibration risk value through a first preset regression algorithm.

[0125] That is, when determining the weight coefficients of multiple parameters when calculating the corrosion risk value through the second preset regression algorithm, the gas company management platform can also determine the label corresponding to the temperature risk value, and fit to obtain the weight coefficients of various parameters (including the temperature risk value) when calculating the corrosion risk value 、 、 when calculating the vibration risk value.

[0126] In some embodiments of the present application, determining the corrosion risk value based on the temperature risk value, the geological information, the biological information, and the facility information, and determining the vibration risk value based on the corrosion risk value, the geological information, the facility information, and the vibration information, can ensure that the corrosion risk value and the vibration risk value are more reliable, thereby ensuring the reliability of the target risk distribution.

[0127] Step 260, determining the target risk distribution of the target region based on the vibration risk value, the corrosion risk value, and the temperature risk value of each of the multiple first preset time periods.

[0128] The target risk distribution refers to various risk types (e.g., a vibration risk type, a corrosion risk type, and a temperature risk type) and corresponding risk characteristics of each collection point in the target region. The vibration risk type refers to a risk caused by vibration, the corrosion risk type refers to a risk caused by corrosion, and the temperature risk type refers to a risk caused by high or low temperature. The risk characteristics can include, for example, a mean value, a minimum value, and a maximum value of the risk values of each risk type of the collection point in the plurality of first preset time periods. For example, the risk characteristics can include a vibration risk mean value, a vibration risk minimum value, and a vibration risk maximum value of each collection point in the plurality of first preset time periods; a corrosion risk mean value, a corrosion risk minimum value, and a corrosion risk maximum value of each collection point in the plurality of first preset time periods; and a temperature risk mean value, a temperature risk minimum value, and a temperature risk maximum value of each collection point in the plurality of first preset time periods.

[0129] In some embodiments, the gas company management platform can determine the target risk distribution of the target region based on the vibration risk values, the corrosion risk values, and the temperature risk values of each collection point in the plurality of first preset time periods, respectively, by various manners. For example, the gas company management platform can statistically process the risk values (e.g., including the vibration risk values, the corrosion risk values, and the temperature risk values) of each collection point in the plurality of first preset time periods to obtain the target risk distribution.

[0130] In some embodiments, the gas company management platform can determine the self-risk values corresponding to the vibration risk values, the corrosion risk values, and the temperature risk values based on the pipeline operation characteristics and the pipeline material characteristics.

[0131] The pipeline operation characteristics are characteristics representing a planned transportation condition of the pipeline. The pipeline planned transportation refers to a transportation plan based on the gas pipeline planning. In some embodiments, the pipeline operation characteristics can include a gas flow and a gas pressure of the pipeline planned transportation.

[0132] The pipeline material characteristics are characteristics representing conditions related to the material of the pipeline. In some embodiments, the pipeline material characteristics can include a pipeline wall material and a pipeline wall thickness.

[0133] In some embodiments, the gas company management platform can obtain the pipeline operation characteristics and the pipeline material characteristics based on a pipeline laying map.

[0134] The self-risk value is a numerical value for measuring the degree of risk generated by the operation (e.g., continuous transportation of high-pressure or high-flow gas, etc.) of the gas pipeline itself. In some embodiments, the self-risk value can include at least one or any combination of a vibration self-risk value corresponding to the vibration risk value, a corrosion self-risk value corresponding to the corrosion risk value, and a temperature self-risk value corresponding to the temperature risk value.

[0135] In some embodiments, the gas company management platform can construct a first feature vector based on the pipeline operation features and the pipeline material features, and match the vibration self-risk value, the corrosion self-risk value and the temperature self-risk value in the first vector database based on the first feature vector.

[0136] The first vector database includes a plurality of first reference vectors and corresponding first vector labels. The gas company management platform can construct the first reference vectors based on the pipeline operation features and the pipeline material features in the historical data. The first vector labels include at least one of the vibration self-risk value, the corrosion self-risk value and the temperature self-risk value corresponding to the first reference vectors.

[0137] In some embodiments, the gas company management platform can construct a plurality of first reference vectors based on the historical data, cluster the plurality of first reference vectors; count the number of gas pipelines in each category of the clustering result that fail (e.g., leak, rupture, etc.) due to each risk type (e.g., vibration, corrosion, temperature) respectively; and take the ratio of the number of gas pipelines that fail under each risk type to the total number of gas pipelines in the category as the first vector label corresponding to the first reference vector of the category. Since the causes of gas pipeline failures in the historical data can be traced back after pipeline maintenance.

[0138] In some embodiments, the gas company management platform can match the first reference vector with the highest vector similarity between the first feature vector in the first vector database, and determine the first vector label corresponding to the first reference vector with the highest vector similarity between the first feature vector as the self-risk value of each risk type, i.e., the vibration self-risk value, the corrosion self-risk value and the temperature self-risk value. Wherein, the vector similarity can be determined according to the vector distance. The vector similarity is negatively correlated with the vector distance.

[0139] In some embodiments, the gas company management platform can determine the target risk distribution through a plurality of ways based on the vibration risk value, the corrosion risk value, the temperature risk value and the respective self-risk values of the target region in a plurality of first preset time periods.

[0140] In some embodiments, for each data collection point, the gas company management platform may average the risk values ​​of each risk type determined in steps 230 to 250 for each data collection point over multiple first preset time periods, and then multiply the average by the corresponding intrinsic risk value, to obtain the average risk value corresponding to each risk type in the risk signature. For example, the gas company management platform may average the vibration risk values ​​corresponding to multiple first preset time periods, and then multiply the average by the intrinsic vibration risk value, to obtain the average vibration risk value; average the corrosion risk values ​​corresponding to multiple first preset time periods, and then multiply the average by the intrinsic corrosion risk value, to obtain the average corrosion risk value; and average the temperature risk values ​​corresponding to multiple first preset time periods, and then multiply the average by the intrinsic temperature risk value, to obtain the average temperature risk value.

[0141] In some embodiments, for each data collection point, the gas company management platform may directly use the highest and lowest risk values ​​of each risk type determined in steps 230 to 250 within multiple first preset time periods at the data collection point as the highest and lowest risk values ​​corresponding to each risk type in the risk signature. For example, the gas company management platform may use the highest and lowest vibration risk values ​​within multiple first preset time periods as the highest and lowest vibration risk values, respectively.

[0142] In the embodiment of the present invention, the target risk distribution is determined by the autologous risk value, and the probability of occurrence of the risk mean corresponding to the risk type can be estimated, so that the target risk distribution is more accurate.

[0143] In some embodiments, the gas company management platform may determine the target risk distribution based on the vibration risk value, corrosion risk value, temperature risk value, respective corresponding self-risk values ​​and their confidence levels of the target area.

[0144] The confidence level of the autologous risk value refers to the degree of certainty in the autologous risk value. For example, the higher the accuracy of the autologous risk value, the higher its confidence level.

[0145] The self-risk value can be determined in a variety of ways. In some embodiments, the gas company management platform can determine the vector similarity between the first feature vector and the first reference vector as the confidence level of the self-risk value. Methods for determining vector similarity include distance-based similarity calculation methods, angle cosine-based similarity calculation methods, and Pearson correlation coefficient-based similarity calculation methods.

[0146] In some embodiments, the gas company management platform may average the risk values ​​for each risk type determined in steps 230 to 250 over multiple first preset time periods, multiply the average by the corresponding auto-risk value, and then multiply the average by the confidence level corresponding to the auto-risk value, and use the calculated result as the risk average corresponding to each risk type in the risk signature. For example, the gas company management platform may average the vibration risk values ​​for multiple first preset time periods, multiply the average by the vibration auto-risk value, and then multiply the average by the confidence level corresponding to the vibration auto-risk value, and use the calculated result as the vibration risk average.

[0147] In the embodiment of the present invention, the target risk distribution is further determined by the confidence level of the autologous risk value, so that the obtained target risk distribution can be made more accurate.

[0148] Step 270 : Determine target protection component information of collection points laid in the target area based on the target risk distribution.

[0149] The target protection component information is information related to the deployed pipeline protection component. In some embodiments, the target protection component information may include the target protection component type and the corresponding first target protection level.

[0150] The target protection component type refers to the type of pipeline protection component installed in the target area. Target protection component types may include anti-corrosion components, thermal insulation components, and / or vibration-proof components. In some embodiments, for different risk types, the anti-corrosion component may address the corrosion risk type, the thermal insulation component may address the temperature risk type, and the vibration-proof component may address the vibration risk type.

[0151] The first target protection level refers to the protection level of the pipeline protection components laid in the target area. The protection level is divided according to the protection effect that the protection components can provide.

[0152] The first target protection level is related to the target protection component type. The first target protection level may include an anti-corrosion component protection level, a thermal insulation component protection level, and an anti-vibration component protection level, respectively indicating the level of anti-corrosion protection provided by the protection component, the level of thermal insulation protection provided by the protection component, and the level of anti-vibration protection provided by the protection component. In some embodiments, a higher first target protection level indicates better protection.

[0153] In some embodiments, the gas company management platform can determine the target protection component information of the collection points laid out in the target area through various methods based on the target risk distribution.

[0154] In some embodiments, for each data collection point, the gas company management platform can determine the target protection component type and the corresponding first target protection level deployed at that data collection point using a second preset table. The second preset table includes multiple target risk distributions and the corresponding first target protection level for each target risk distribution (for example, the protection level for corrosion protection components, thermal insulation component protection levels, and vibration isolation component protection levels). In some embodiments, the second preset table can be established by technical personnel based on experience. In some embodiments, the second preset table can be constructed based on prior knowledge or historical data (for example, the first target protection levels required for different target risk distributions).

[0155] For example, the gas company management platform can search the second preset table for the corresponding anti-corrosion component protection level, thermal insulation component protection level, and anti-vibration component protection level based on the target risk distribution.

[0156] For more information on determining target protection components, see Figure 3 and related instructions.

[0157] Step 280 : Determine the target protection component installation density distribution based on the target risk distribution and the pipeline installation map of the target area.

[0158] The laying density distribution includes the number of pipeline protection components laid in the gas pipeline section at each collection point in the target area.

[0159] In some embodiments, the gas company management platform can determine the laying density distribution of the target protection components in a variety of ways based on the target risk distribution and the pipeline laying map of the target area.

[0160] In some embodiments, for each collection point, the gas company management platform can cluster the collection points in multiple gas pipeline laying areas in the historical data based on the risk characteristics of the collection point, and find multiple collection points in the target area that belong to the same category as the collection point in the clustering results, and use the average number of protection components of each component type actually used at these collection points as the laying number of pipeline protection components in the collection point.

[0161] Step 290, before executing the protection component deployment operation, and / or during executing the protection component deployment operation, based on the laying density distribution, generate a valve control instruction and send it to the gas equipment object platform to adjust the gas delivery pressure of at least one gas pipeline in the target area.

[0162] The valve control instruction is used to instruct the regulating valve in the gas pipeline to adjust the pressure.

[0163] In some embodiments, the gas company management platform can generate valve control instructions in various ways based on the distribution of laying density. For example, for collection points with a small number of protection components, the possibility of failure is relatively high, and a valve control instruction can be generated to reduce the pressure in the gas pipeline.

[0164] In some embodiments, for collection points where the number of protective components laid exceeds a preset density threshold, the gas company management platform can generate valve control instructions for regulation at preset intervals to ensure that the pressure in the gas pipeline corresponding to the collection point remains within the standard range.

[0165] In some embodiments, the preset density threshold and the preset duration can be set based on historical construction experience. For example, the gas company management platform can select the density threshold corresponding to the historical construction process without any failure as the current preset density threshold.

[0166] The standard range refers to the standard range of gas pipeline pressure. In some embodiments, the standard range can be set by technicians based on experience.

[0167] In some embodiments, the gas company management platform can send the generated valve control instruction to the gas equipment object platform via the gas company sensor network platform. The gas equipment object platform can adjust the gas delivery pressure of at least one gas pipeline within the target area based on the valve control instruction. Specifically, the gas equipment object platform can control the regulating valve within the gas pipeline to adjust the pressure.

[0168] In some embodiments of the present invention, corresponding pipeline protection components are arranged in key protection areas according to actual conditions when laying the pipeline, so as to ensure the service life of the gas pipeline; the gas delivery pressure of at least one gas pipeline in the target area is adjusted according to the valve control instruction, so as to avoid failures, thereby ensuring the service life of the gas pipeline and reducing the cost of pipeline replacement.

[0169] It should be noted that the above description of process 200 is for illustrative purposes only and does not limit the scope of the present invention. Those skilled in the art will appreciate that various modifications and variations to process 200 can be made under the guidance of the present invention. However, such modifications and variations remain within the scope of the present invention. For example, steps 230, 240, and 250 may be performed simultaneously.

[0170] Figure 3 This is an exemplary schematic diagram of determining target protection component information according to some embodiments of the present invention.

[0171] In some embodiments, as Figure 3As shown, the gas company management platform can determine the pipeline protection strength 320 of the collection point based on the pipeline material characteristics 310 of the collection point; determine the risk protection level 340 of the collection point based on the pipeline protection strength 320 of the collection point and the target risk distribution 330 of the target area; and determine the second target protection level 350 of the collection point based on the risk protection level 340 of the collection point.

[0172] For details on collection points, pipeline material characteristics, target areas, and target risk distribution, see Figure 2 .

[0173] The pipeline protection strength refers to the protection level of the gas pipeline itself against various risk types. In some embodiments, the pipeline protection strength may include vibration protection level, corrosion protection level, and high temperature protection level.

[0174] In some embodiments, the gas company management platform can determine the pipeline protection strength using a third preset table. The third preset table includes multiple pipeline wall materials and multiple pipeline wall thicknesses and corresponding pipeline protection strengths. The pipeline wall thickness can be a range of values.

[0175] In some embodiments, the third preset table can be set by technicians based on experience. In some embodiments, the third preset table can be constructed based on prior knowledge or historical data (e.g., historically correlated pipeline protection strengths for different pipeline wall materials and thicknesses). The gas company management platform can search the third preset table for the corresponding pipeline protection strength based on the pipeline wall material and thickness in the pipeline material feature.

[0176] The risk protection level refers to the degree to which the collection point needs to be protected.

[0177] The risk protection level can be determined in a variety of ways. In some embodiments, for each collection point, the gas company management platform can calculate the risk protection level for the collection point by subtracting the corresponding protection level in the pipeline protection strength of the collection point from the first target protection level determined in step 270 according to the second preset table.

[0178] The second target protection level is the protection level of each target protection component type obtained by modifying the first target protection level according to the pipeline protection strength. In some embodiments, if the second target protection level is determined based on the first target protection level, the target protection component information includes the target protection component type and the corresponding second target protection level.

[0179] The second target protection level can be determined in a variety of ways. In some embodiments, for each collection point, the gas company management platform can determine the risk protection level of the collection point as the second target protection level of the collection point.

[0180] In the embodiment of the present invention, the second target protection level is determined by determining the pipeline protection strength and the risk protection level. The target protection levels of different risk types can be specifically determined according to the pipeline material characteristics.

[0181] In some embodiments, as Figure 3 As shown, the gas company management platform can determine a second target protection level 350 of the collection point based on the risk protection level 340 and the component joint protection information 360 of multiple target protection components.

[0182] The component joint protection information includes the protection level of the protection component for each risk type. For example, the component joint protection information may include the vibration protection level, corrosion protection level, and thermal insulation protection level corresponding to the protection component.

[0183] Different types of protective components, while fulfilling their respective protective functions, can also achieve certain other protective functions due to their inherent structure. As an example, level 3 insulation material can achieve level 3 insulation, and due to its thickness, it also provides certain vibration and corrosion protection. For example, it can achieve level 1 vibration protection and level 2 corrosion protection. If level 1 vibration protection and level 3 insulation are actually required, then level 3 insulation material can be used directly to achieve both vibration and insulation requirements.

[0184] In some embodiments, the gas company management platform can obtain the risk type with the largest risk value in the target risk distribution, and obtain the protection level of the protection component corresponding to the risk type for each risk type; according to the protection level of the protection component for each risk type, adjust the protection level of the protection component in other risk types.

[0185] In an embodiment of the present invention, the second target protection level of the collection point is further determined by combining component protection information, so that the protection component can protect other smaller risk types while protecting the risk type with the highest risk value, thereby saving protection costs.

[0186] In some embodiments, as Figure 3As shown, the gas company management platform can construct a first risk characteristic map 332 of the target area based on the target risk distribution 330 and the pipeline laying map 331 of the target area; generate multiple candidate protection component combinations 370 corresponding to the collection points based on the first risk characteristic map 332, the risk protection level 340 and the component joint protection information 360; for each candidate protection component combination 370, update the first risk characteristic map 332 based on the candidate protection component combination 370 to obtain a second risk characteristic map 333 corresponding to the candidate protection component combination; based on the second risk characteristic map 333, determine the protection effect 335 corresponding to the candidate protection component combination 370 through the prediction model 334; determine the target protection component combination 380 based on the protection effects 335 corresponding to each of the multiple candidate protection component combinations 370; and determine the target protection component information 390 of the collection point based on the target protection component combination 380.

[0187] For more information on pipeline laying diagrams, please refer to Figure 2 And related instructions.

[0188] The first risk feature map is a directed graph structure constructed based on the connection relationships between the various gas pipelines within the pipeline layout map. The first risk feature map can be represented by nodes and edges connecting the nodes. The nodes in the graph are collection points. The node characteristics represent the risk type and corresponding risk characteristics of the point, namely the average, minimum, and maximum risk values ​​corresponding to multiple first preset time periods. The edges in the graph represent the connection relationships between the various nodes. If the gas pipelines where the two nodes are located are directly connected or the two nodes are in the same gas pipeline, there is an edge between the two nodes pointing from the upstream pipeline to the downstream pipeline.

[0189] The candidate protective component combination is a combination of protective components of three risk types with different levels and different materials.

[0190] In some embodiments, for each node in the first risk profile, the gas company management platform can randomly generate a large number of candidate protection component combinations that meet the risk protection level of the collection point corresponding to the node. Meeting the risk protection level means that the protection level of a certain protection component type plus the protection levels of other protection component types for the risk type can meet the risk protection level.

[0191] The second risk profile is a risk profile updated based on the candidate protection component combinations on the first risk profile. Each candidate protection component combination may correspond to a second risk profile.

[0192] The difference between the second risk profile and the first risk profile includes different node characteristics. In some embodiments, compared to the first risk profile, the node characteristics of the second risk profile may also include the type of candidate protection components used by the node and the component combination protection information of the candidate protection components used by the node. The type of candidate protection components used by the node can be obtained based on the component combination protection information of the candidate protection component combination corresponding to the second risk profile.

[0193] In some embodiments, compared to the first risk characteristic map, the node characteristics of the second risk characteristic map may further include future autologous risk values ​​of the collection points corresponding to the nodes.

[0194] The future self-risk value refers to the self-risk value within a preset future period. The preset future period refers to the period after the gas pipeline is completed. For example, it can be one day after the gas pipeline is completed, one week after the gas pipeline is completed, etc.

[0195] In some embodiments, the gas company management platform can obtain the change value of the pipeline material characteristics in a preset future time period through the second vector database based on environmental information and pipeline material characteristics; and determine the future self-risk value through the second vector database based on the change value of the pipeline material characteristics in the preset future time period.

[0196] The change value of the pipe material characteristic refers to the change value of the pipe wall thickness.

[0197] In some embodiments, the gas company management platform can construct a second feature vector based on environmental information and pipeline material characteristics, and obtain a change value of the pipeline material characteristics in a preset future period by matching the second feature vector in a second vector database.

[0198] The second vector database includes multiple second reference vectors and corresponding second vector labels. The gas company management platform can construct a second reference vector based on environmental information surrounding the gas pipeline and pipeline material characteristics in historical data. The second vector label includes the change value of the pipeline material characteristic corresponding to the second reference vector. In some embodiments, the gas company management platform can use the actual change value of the gas pipeline wall corresponding to the second reference vector in the historical data after a predetermined future time period as the second vector label corresponding to the reference second characteristic vector.

[0199] In some embodiments, the gas company management platform can match the second reference vector with the highest vector similarity with the second feature vector in the second vector database, and use the second vector label corresponding to the second reference vector with the highest vector similarity with the second feature vector as the change value of the pipeline material characteristics in a preset future time period.

[0200] In the embodiment of the present invention, since the gas pipeline generally ages over time, when predicting the protection effect of the protection component, it is necessary to consider the inherent risk value of the gas pipeline after aging to ensure the accuracy of the model prediction.

[0201] The effectiveness of a candidate protection component combination can be measured by the predicted service life of the gas pipeline and the predicted number of failures during its service life. For example, the longer the predicted service life of the gas pipeline and the fewer the predicted failures during its service life, the better the protection effect, and vice versa.

[0202] In some embodiments, for each candidate protection component combination, the gas company management platform can predict the protection effect of each node in the second risk characteristic map through a prediction model based on the second risk characteristic map, thereby obtaining the protection effect of the candidate protection component combination.

[0203] In some embodiments, the prediction model is a machine learning model, such as a neural network model, a graph neural network model (GNN), etc.

[0204] In some embodiments, as Figure 3 As shown, the input of the prediction model 334 may include the second risk characteristic map 333 , and the output of the prediction model 334 may include the protection effect 335 of each node in the second risk characteristic map 333 .

[0205] In some embodiments, the prediction model can be obtained by training based on training data.

[0206] In some embodiments, the gas company management platform may obtain multiple labeled training samples to form a training sample set, and perform multiple rounds of iterations based on the training sample set.

[0207] The training sample may include a sample second risk characteristic map. The training sample may be a sample second risk characteristic map corresponding to multiple gas pipeline laying areas in historical data. The gas company management platform may first obtain a sample first risk characteristic map based on the historical risk conditions and pipeline laying map corresponding to the historical data; then, based on the protection component combinations actually selected in the historical data, update the node features to obtain a sample second risk characteristic map.

[0208] The label can be the actual protection effect corresponding to the second risk signature map of the training sample. The label is the actual service life and number of failures during the future period of each gas pipeline in the gas pipeline laying area corresponding to the training sample in the historical data. The future period of the historical moment is still a time that has already occurred.

[0209] In some embodiments, the gas company management platform can input the training sample set into the initial prediction model to perform multiple rounds of iterations. At least one round of iteration includes: selecting one or more training samples from the training sample set, inputting the one or more training samples into the initial prediction model to obtain model prediction outputs corresponding to the one or more training samples; substituting the model prediction outputs corresponding to the one or more training samples and labels of the one or more training samples into a formula of a predefined loss function to calculate a value of the loss function; iteratively updating model parameters in the initial prediction model according to the value of the loss function until an iteration end condition is met, ending the iteration, and obtaining a trained prediction model. The iteration end condition can include convergence of the loss function, the number of iterations reaching a threshold, etc.

[0210] In the embodiments of the present application, the protection effect is determined by the prediction model, the self-learning ability of the machine learning model is used to find the rules from a large amount of historical data, the relationship between the second risk feature spectrum and the protection effect of the candidate protection component combination is obtained, the accuracy and efficiency of determining the protection effect are improved, and the protection component combination with better protection effect is determined.

[0211] In some embodiments, in the training sample set of the prediction model, the number of training samples of any environment type in the plurality of environment types needs to be greater than a preset number threshold corresponding to the environment type.

[0212] The environment type is the environment type in which the collection point corresponding to the node is located. The environment type can include residential areas, industrial areas, commercial areas, etc. The complexity of the environment information in each environment type refers to the sum of the microbial density, termite density, rodent number, factory type number, and facility type number included in the environment information.

[0213] In some embodiments, the preset number threshold is positively correlated with the complexity of the environment information in the environment type.

[0214] In the embodiments of the present application, since the environment directly affects the protection effect of the protection component, the greater the complexity of the environment information, the greater the amount of information contained in the environment information. At this time, more training sample numbers are needed for this type of environment, which can ensure that the model is fully trained, thereby improving the accuracy of model prediction.

[0215] In some embodiments, the gas company management platform can determine the protection effect of the candidate protection component combination corresponding to the second risk feature spectrum according to the protection effect of each node output by the prediction model. For example, the gas company management platform can take the average of the protection effect of each node to obtain the protection effect corresponding to the candidate protection component combination.

[0216] In some embodiments, the gas company management platform may select a candidate protection component combination with the best protection effect as the target protection component combination.

[0217] In some embodiments, the gas company management platform can determine the target protection component type and the corresponding second target protection level for each point based on the relevant information of the protection components recommended for use at each point included in the target protection component combination (including the target protection component type and protection level), thereby determining the target protection component information of the collection point.

[0218] In an embodiment of the present invention, a risk characteristic map is constructed to predict the protection effect of candidate protection component combinations, thereby determining the target protection component combination with the best protection effect. More appropriate target protection component information can be determined to ensure the service life of the gas pipeline.

[0219] One or more embodiments of the present invention provide a pipeline protection component deployment system based on a smart gas internet of things. The system includes a government safety supervision management platform, a government safety supervision sensor network platform, a government safety supervision target platform, a gas company sensor network platform, and a gas equipment target platform. The government safety supervision target platform includes a gas company management platform. The gas company management platform includes at least one processor and at least one memory; the at least one memory is configured to store computer instructions; and the at least one processor is configured to execute at least some of the computer instructions to implement a pipeline protection component deployment method based on a smart gas internet of things as described in any of the aforementioned embodiments. The pipeline protection component deployment system based on a smart gas internet of things can be part of the smart gas internet of things.

[0220] One or more embodiments of the present invention 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 pipeline protection component deployment method based on a smart gas Internet of Things as described in any one of the above embodiments.

[0221] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit the present invention. Although not explicitly described herein, those skilled in the art may make various modifications, improvements, and revisions to the present invention. Such modifications, improvements, and revisions are suggested in the present invention and remain within the spirit and scope of the exemplary embodiments of the present invention.

[0222] At the same time, the present invention uses specific terms to describe embodiments of the present invention. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic associated with at least one embodiment of the present invention. Therefore, it should be emphasized and noted that the use of "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or more in different places in the present invention does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the present invention may be appropriately combined.

[0223] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in the present invention are not intended to limit the order of the processes and methods of the present invention. Although the above disclosure discusses some embodiments of the invention that are currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and 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 are consistent with the spirit 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 by software solutions, such as installing the described system on an existing server or mobile device.

[0224] Similarly, it should be noted that, in order to simplify the presentation of the present disclosure and facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of the invention sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of the invention requires more features than those recited in the claims. In practice, an embodiment may have fewer features than the totality of the features of a single embodiment disclosed above.

[0225] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present invention are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0226] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited herein is hereby incorporated by reference in its entirety. This excludes any application history that is inconsistent with or conflicts with the present disclosure, including any document (currently or subsequently appended to this disclosure) that limits the broadest scope of the claims of this disclosure. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the present disclosure, the descriptions, definitions, and / or terminology used in this disclosure will control.

[0227] Finally, it should be understood that the embodiments described herein are intended only to illustrate the principles of the present invention. Other variations may also fall within the scope of the present invention. Therefore, by way of example and not limitation, alternative configurations of the embodiments of the present invention may be considered consistent with the teachings of the present invention. Accordingly, the embodiments of the present invention are not limited to the embodiments explicitly described and illustrated herein.

Claims

1. A method for deploying pipeline protection components based on smart gas Internet of Things, characterized in that: The method is executed by a gas company management platform of a pipeline protection component deployment system, and the method includes: Obtaining, through the gas company's sensor network platform, environmental information of the target area within a plurality of first preset time periods from a sensor device provided in the gas equipment object platform, the environmental information including temperature information, humidity information, geological information, and vibration information; Obtaining biological information, climate information, and facility information of the target area within the plurality of first preset time periods from a government safety supervision management platform via a government safety supervision sensor network platform; determining, based on the geological information, the facility information, and the vibration information within the plurality of first preset time periods, a vibration risk value of the target area in each of the plurality of first preset time periods; Determining, based on the geological information, the biological information, and the facility information within the plurality of first preset time periods, a corrosion risk value of the target area in each of the plurality of first preset time periods; determining, based on the climate information within the plurality of first preset time periods, a temperature risk value of the target area in each of the plurality of first preset time periods; determining a target risk distribution of the target area based on the vibration risk value, the corrosion risk value, and the temperature risk value of each of the plurality of first preset time periods; Based on the target risk distribution, target protection component information of the collection points laid in the target area is determined, the target protection component information including a target protection component type and a corresponding first target protection level, the first target protection level being the protection level of the pipeline protection component laid in the target area; wherein, based on the target risk distribution, determining the target protection component information of the collection points laid in the target area includes: Constructing a first risk characteristic map of the target area based on the target risk distribution and the pipeline laying map of the target area; generating a plurality of candidate protection component combinations corresponding to the collection point based on the first risk characteristic map, the risk protection level of the collection point, and component joint protection information of a plurality of target protection components; For each of the candidate protection component combinations, Updating the first risk characteristic map based on the candidate protection component combination to obtain a second risk characteristic map corresponding to the candidate protection component combination; Based on the second risk feature map, determining the protection effect corresponding to the candidate protection component combination through a prediction model, wherein the prediction model is a machine learning model; Determining a target protection component combination based on the protection effects corresponding to each of the plurality of candidate protection component combinations; Determining target protection component information of the collection point based on the target protection component combination; Determining the laying density distribution of the target protection components based on the target risk distribution and the pipeline laying map; and Before executing the protection component deployment operation, and / or during executing the protection component deployment operation, based on the deployment density distribution, a valve control instruction is generated and sent to the gas equipment object platform to adjust the gas delivery pressure of at least one gas pipeline in the target area.

2. The method for deploying pipeline protection components based on the smart gas Internet of Things according to claim 1 is characterized in that: The method further comprises: Based on pipeline operation characteristics and pipeline material characteristics, determining the self-risk value corresponding to each of the vibration risk value, the corrosion risk value, and the temperature risk value, wherein the self-risk value is used to measure the risk level generated by the operation of the gas pipeline itself; The determining the target risk distribution of the target area based on the vibration risk value, the corrosion risk value, and the temperature risk value of each of the plurality of first preset time periods includes: The target risk distribution is determined based on the vibration risk value, the corrosion risk value, the temperature risk value of the target area in the plurality of first preset time periods and the corresponding self-risk value.

3. The method for deploying pipeline protection components based on the smart gas Internet of Things according to claim 1 is characterized in that: The determining, based on the target risk distribution, target protection component information of the collection points laid in the target area includes: Determining the pipeline protection strength at the collection point based on the pipeline material characteristics at the collection point; Determining the risk protection level of the collection point based on the pipeline protection strength of the collection point and the target risk distribution of the target area; Based on the risk protection level of the collection point, a second target protection level of the collection point is determined. The second target protection level is the protection level corresponding to each target protection component type obtained by modifying the first target protection level according to the pipeline protection strength.

4. The method for deploying pipeline protection components based on the smart gas Internet of Things according to claim 3 is characterized in that: Determining the second target protection level of the collection point based on the risk protection level of the collection point includes: The second target protection level of the collection point is determined based on the risk protection level and the component joint protection information of the multiple target protection components.

5. A pipeline protection component deployment system based on smart gas Internet of Things, characterized by: The pipeline protection component deployment 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, and a gas equipment object platform. The government safety supervision object platform includes a gas company management platform; the gas company management platform includes at least one processor and at least one memory; The at least one memory is for storing computer instructions; The at least one processor is configured to execute at least some of the computer instructions to implement: Obtaining, through the gas company's sensor network platform, environmental information of the target area within a plurality of first preset time periods from a sensor device provided in the gas equipment object platform, the environmental information including temperature information, humidity information, geological information, and vibration information; Obtaining biological information, climate information, and facility information of the target area within the plurality of first preset time periods from a government safety supervision management platform via a government safety supervision sensor network platform; determining, based on the geological information, the facility information, and the vibration information within the plurality of first preset time periods, a vibration risk value of the target area in each of the plurality of first preset time periods; Determining, based on the geological information, the biological information, and the facility information within the plurality of first preset time periods, a corrosion risk value of the target area in each of the plurality of first preset time periods; determining, based on the climate information within the plurality of first preset time periods, a temperature risk value of the target area in each of the plurality of first preset time periods; determining a target risk distribution of the target area based on the vibration risk value, the corrosion risk value, and the temperature risk value of each of the plurality of first preset time periods; Based on the target risk distribution, target protection component information of the collection points laid in the target area is determined, the target protection component information including a target protection component type and a corresponding first target protection level, the first target protection level being the protection level of the pipeline protection component laid in the target area; wherein, based on the target risk distribution, determining the target protection component information of the collection points laid in the target area includes: Constructing a first risk characteristic map of the target area based on the target risk distribution and the pipeline laying map of the target area; generating a plurality of candidate protection component combinations corresponding to the collection point based on the first risk characteristic map, the risk protection level of the collection point, and component joint protection information of a plurality of target protection components; For each of the candidate protection component combinations, Updating the first risk characteristic map based on the candidate protection component combination to obtain a second risk characteristic map corresponding to the candidate protection component combination; Based on the second risk feature map, determining the protection effect corresponding to the candidate protection component combination through a prediction model, wherein the prediction model is a machine learning model; Determining a target protection component combination based on the protection effects corresponding to each of the plurality of candidate protection component combinations; Determining target protection component information of the collection point based on the target protection component combination; Determining the laying density distribution of the target protection components based on the target risk distribution and the pipeline laying map; and Before executing the protection component deployment operation, and / or during executing the protection component deployment operation, based on the deployment density distribution, a valve control instruction is generated and sent to the gas equipment object platform to adjust the gas delivery pressure of at least one gas pipeline in the target area.

6. The pipeline protection component deployment system based on the smart gas Internet of Things according to claim 5 is characterized in that: The at least one processor is further configured to implement: Based on pipeline operation characteristics and pipeline material characteristics, determining the self-risk value corresponding to each of the vibration risk value, the corrosion risk value, and the temperature risk value, wherein the self-risk value is used to measure the risk level generated by the operation of the gas pipeline itself; The determining the target risk distribution of the target area based on the vibration risk value, the corrosion risk value, and the temperature risk value of each of the plurality of first preset time periods includes: The target risk distribution is determined based on the vibration risk value, the corrosion risk value, the temperature risk value of the target area in the plurality of first preset time periods and the corresponding self-risk value.

7. The pipeline protection component deployment system based on the smart gas Internet of Things according to claim 5 is characterized in that: The at least one processor is further configured to implement: Determining the pipeline protection strength at the collection point based on the pipeline material characteristics at the collection point; Determining the risk protection level of the collection point based on the pipeline protection strength of the collection point and the target risk distribution of the target area; Based on the risk protection level of the collection point, a second target protection level of the collection point is determined. The second target protection level is the protection level corresponding to each target protection component type obtained by modifying the first target protection level according to the pipeline protection strength.

8. The pipeline protection component deployment system based on the smart gas Internet of Things according to claim 7 is characterized in that: The at least one processor is further configured to implement: The second target protection level of the collection point is determined based on the risk protection level and the component joint protection information of the multiple target protection components.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by the processor, the pipeline protection component deployment method based on the smart gas Internet of Things as described in claim 1 is implemented.

Images