Pipeline Attachment Monitoring Method and System Based on Smart Gas Internet of Things

Abstract

The present invention provides a method and system for monitoring pipeline attachments based on the intelligent gas Internet of Things, relating to the technical field of the Internet of Things. The method includes: controlling sensors on gas pipelines or gas valves to collect basic perception data, and uploading the basic perception data to the gas company management platform through the gas equipment object platform; determining the attachment risk areas of the gas pipelines; determining the pipeline areas to be detected, controlling inspection robots to inspect the pipeline areas to be detected, and collecting the inspection results uploaded by the inspection robots; generating pigging data of the gas pipelines and sending it to the government safety supervision and management platform; and generating a pigging instruction based on the pigging confirmation data, and instructing to perform pigging operations on some gas pipelines according to the pigging instruction. The present invention can determine the influence relationship of attachments between different gas pipeline areas that conform to the actual situation, and can improve the accuracy of pipeline attachment monitoring.

Description

Technical Field

[0001] This specification relates to the field of Internet of Things technology, and particularly to a method and system for monitoring pipeline attachments based on the intelligent gas Internet of Things. Background Art

[0002] Due to factors such as changes in the composition of the gas source, wear and corrosion of the pipeline itself, as the service life of the gas pipeline continues to increase, the gas often entrains tiny particulate matters such as solid impurities during transportation. These particulate matters, including dust and other impurities, not only affect the gas quality but also pose a potential threat to the safe operation of the pipeline system. Therefore, it is necessary to estimate and evaluate the type and quantity of impurities in the gas pipeline to determine whether to clean the gas pipeline. The efficiency and safety of gas transportation are closely related to the cleanliness of the interior of the gas pipeline. Regular cleaning of the gas pipeline can not only ensure the stability of the gas transmission process but also extend the life of the gas pipeline.

[0003] Therefore, it is necessary to provide a method for monitoring pipeline attachments based on the intelligent gas Internet of Things, which can not only monitor the impurity distribution of each gas pipeline based on the distribution of the gas pipeline but also optimize the cleaning strategy of the gas pipeline based on the impurity distribution. Summary of the Invention <U+

[0004] In order to solve the problems of low accuracy in monitoring the attachments of different gas pipelines in the gas pipeline network and difficulty in identifying the potential relationship between impurities and gas pipelines in different regions, this specification provides a method and system for monitoring pipeline attachments based on the intelligent gas Internet of Things.

[0005] One or more embodiments of this specification provide a method for monitoring pipeline attachments based on the intelligent gas Internet of Things. This method is executed by the gas company management platform of the intelligent gas pipeline attachment monitoring system, and includes: issuing a data collection instruction, controlling sensors on the gas pipeline or gas valve to collect basic perception data, and transmitting it to the gas equipment object platform for summarization and storage. Through the gas equipment object platform according to the preset reporting rules, the basic perception data is uploaded to the gas company management platform through the gas company sensor network platform; determining the attachment risk area of the gas pipeline according to the basic perception data; determining the pipeline area to be detected according to the attachment risk area, generating a pipeline detection instruction and sending it to the gas pipeline network maintenance object platform; controlling the inspection robot by the gas pipeline network maintenance object platform to inspect the pipeline area to be detected, and collecting the inspection results uploaded by the inspection robot; receiving the inspection results collected by the gas pipeline network maintenance object platform, generating pigging data for the gas pipeline and sending it to the government safety supervision and management platform; and receiving the pigging confirmation data returned by the government safety supervision and management platform, generating a pigging instruction based on the pigging confirmation data, and instructing to perform pigging operations on some gas pipelines according to the pigging instruction.

[0006] One or more embodiments of this specification provide a system for monitoring pipeline attachments based on the intelligent gas Internet of Things. This system includes one or more of the gas company management platform, the gas equipment object platform, the gas pipeline network maintenance object platform, and the government safety supervision and management platform; the gas company management platform is configured to: issue a data collection instruction, control sensors on the gas pipeline or gas valve to collect basic perception data, and transmit it to the gas equipment object platform, and receive the basic perception data uploaded by the gas equipment object platform; determine the attachment risk area of the gas pipeline according to the basic perception data; determine the pipeline area to be detected according to the attachment risk area, generate a pipeline detection instruction and send it to the gas pipeline network maintenance object platform; receive the inspection results collected by the gas pipeline network maintenance object platform, generate pigging data for the gas pipeline and send it to the government safety supervision and management platform; receive the pigging confirmation data returned by the government safety supervision and management platform, generate a pigging instruction based on the pigging confirmation data, and instruct to perform pigging operations on some gas pipelines according to the pigging instruction; the gas equipment object platform is configured to: receive the basic perception data transmitted by the sensor, summarize and store it, and upload the basic perception data to the gas company management platform according to the preset reporting rules; the gas pipeline network maintenance object platform is configured to: receive the pipeline detection instruction sent by the gas company management platform, control the inspection robot to inspect the pipeline area to be detected, and collect the inspection results uploaded by the inspection robot, and send the inspection results to the gas company management platform; the government safety supervision and management platform is configured to: receive the pigging data sent by the gas company management platform, generate and send pigging confirmation data to the gas company management platform.

[0007] The beneficial effects brought by the above-mentioned invention content include, but are not limited to: (1) By determining the influence degree of the attachments, the influence relationship of the attachments between different gas pipeline areas that conform to the actual situation can be determined, and thus reliable data support can be provided for subsequent classification of the influence level of the attachments and determination of the attachment influence area. (2) By using the attachment analysis model based on the pipeline simulation atlas to predict the influence degree of the attachments on each gas pipeline, the attachment risk level of different gas pipelines can be more accurately evaluated, and the accuracy of pipeline attachment monitoring can be improved. Brief Description of the Drawings

[0008] This specification will further explain in the form of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0009] Figure 1 is a platform structure diagram of a pipeline attachment monitoring system based on the intelligent gas Internet of Things according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flowchart of a pipeline attachment monitoring method based on the intelligent gas Internet of Things according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flowchart of determining an attachment risk area according to some embodiments of this specification;

[0012] Figure 4 is an exemplary schematic diagram of determining an attachment risk level according to some embodiments of this specification;

[0013] Figure 5 is an exemplary schematic diagram of a prediction model according to some embodiments of this specification. Detailed Description of the Embodiments

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios according to these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the drawings represent the same structures or operations.

[0015] For different attachments distributed in the gas pipeline, different contents of different attachments, and the physical properties of different gas pipelines themselves, the fan should adopt reasonable cleaning strategies to better clean the gas pipeline.

[0016] In view of this, in some embodiments of this specification, it is desired to provide a method for monitoring pipeline attachments based on the intelligent gas Internet of Things, which can more intelligently plan the inspection sequence of gas pipelines and more reasonably plan the cleaning strategy for gas pipelines that need to be cleaned based on the location distribution relationship of gas management.

[0017] Figure 1 It is a platform structure diagram of a pipeline attachment monitoring system based on the intelligent gas Internet of Things shown in some embodiments of this specification. In some embodiments, as Figure 1 shown, the pipeline attachment monitoring system based on the intelligent gas Internet of Things may include a government safety supervision management platform 110, a government safety supervision sensor network platform 120, a gas company management platform 130, a gas company sensor network platform 140, a gas pipeline network maintenance object platform 150, and a gas equipment object platform 160.

[0018] The government safety supervision management platform 110 refers to a platform for providing government information and services. In some embodiments, the government safety supervision management platform 110 may be configured to receive the pigging data sent by the gas company management platform 130, generate and send pigging confirmation data to the gas company management platform 130.

[0019] The government safety supervision sensor network platform 120 is used to connect the government safety supervision management platform 110 and the gas company management platform 130 for information transmission.

[0020] The gas company management platform 130 refers to a platform for processing and storing data related to the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things. In some embodiments, the gas company management platform 130 can interact with the gas equipment object platform 160, the gas pipeline network maintenance object platform 150, and the government safety supervision management platform 110 respectively through the gas company sensor network platform 140. For example, the gas company management platform 130 can generate pigging data for gas pipelines and send it to the government safety supervision management platform 110. More content about the gas company management platform 130 can be referred to the relevant descriptions later.

[0021] In some embodiments, the gas company management platform 130 may include a processor and a storage unit.

[0022] The gas company sensing network platform 140 refers to a platform for managing communications. In some embodiments, the gas company sensing network platform 140 can implement the functions of sensing information sensing communication and control information sensing communication. In some embodiments, the gas company sensing network platform 140 can be used to interact with other modules in the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things. For example, the gas company management platform 130 can send pigging data to the gas company management platform 130 through the gas company sensing network platform 140. For another example, the gas company management platform 130 can send pipeline inspection instructions to the gas pipeline network maintenance object platform 150 through the gas company sensing network platform 140.

[0023] The gas pipeline network maintenance object platform 150 refers to a platform for controlling auxiliary facilities, pipeline maintenance equipment, and vehicles related to gas pipeline network maintenance. In some embodiments, the gas pipeline network maintenance object platform 150 can include a PLC controller, a data transmission device, and a storage unit, and is communicatively connected to pipeline maintenance equipment (such as inspection robots, pipeline locators, pipeline cleaning machines, combustible gas detectors, etc.).

[0024] In some embodiments, the gas pipeline network maintenance object platform 150 can be configured to receive pipeline inspection instructions sent by the gas company management platform 130, control the inspection robot to inspect the pipeline area to be detected, and collect the inspection results uploaded by the inspection robot, and send the inspection results to the gas company management platform 130. In some embodiments, the gas pipeline network maintenance object platform 150 can include a processor and a storage unit. More content about the gas pipeline network maintenance object platform 150 can be referred to the relevant descriptions later.

[0025] In some embodiments, the gas equipment object platform 160 can be configured to be communicatively connected to the gas pipeline network maintenance object platform 150 through the gas company sensing network platform 140. In some embodiments, the gas equipment object platform 160 can be configured to receive the basic sensing data transmitted by the sensor, summarize and store it, and upload the basic sensing data to the gas company management platform 130 according to the preset reporting rules. More content about the basic sensing data can be referred to the relevant descriptions later.

[0026] In some embodiments, the gas equipment object platform 160 can include a PLC controller, a data transmission device, and a storage unit, and is communicatively connected to the sensor, and can receive the basic sensing data collected by the sensor and summarize and store it.

[0027] In some embodiments, the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things may further include a processor ( Figure 1(not shown). For example, the gas company management platform 130 and / or the government safety supervision management platform 110 may include a processor. In some embodiments, the processor may process information and / or data related to the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things to perform one or more functions described in this specification. In some embodiments, the processor may include one or more engines (e.g., a single-chip processing engine or a multi-chip processing engine). By way of example only, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), etc., or any combination thereof. In some embodiments, the processor may interact with multiple platforms included in the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things (e.g., the government safety supervision management platform 110, the gas company management platform 130, the gas pipeline maintenance object platform 150, the gas equipment object platform 160, etc.).

[0028] In some embodiments, the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things may further include a storage unit ( Figure 1 (not shown). For example, one or more of the government safety supervision management platform 110, the gas company management platform 130, the gas pipeline maintenance object platform 150, and the gas equipment object platform 160 may include a storage unit. In some embodiments, the storage unit may store information and / or data related to the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things. For example, the gas pipeline maintenance object platform 150 may store the inspection results obtained by the inspection robot through the storage unit.

[0029] In some embodiments of this specification, the pipeline attachment monitoring system 100 based on the intelligent gas Internet of Things may form a closed-loop information operation among the functional platforms, coordinate and operate regularly, and realize the informatization and intelligence of the monitoring of the attachments on the gas pipeline.

[0030] Figure 2 is an exemplary flowchart of the pipeline attachment monitoring method based on the intelligent gas Internet of Things shown in some embodiments of this specification. As Figure 2 shown, the process 200 includes the following steps. In some embodiments, the process 200 may be executed by the gas company management platform.

[0031] Step 210, issue a data collection instruction, control the sensors on the gas pipeline or gas valve to collect basic perception data, and transmit it to the gas equipment object platform for aggregation and storage. The gas equipment object platform uploads the basic perception data to the gas company management platform according to the preset reporting rules.

[0032] Data collection instructions refer to instructions sent by the gas company management platform to the gas equipment object platform for data collection, aggregation, and storage.

[0033] In some embodiments, the gas equipment object platform may collect basic sensing data through sensors on gas pipelines or gas valves based on data collection instructions.

[0034] Gas pipelines refer to pipeline facilities used to transport gas. Gas pipelines can be divided into different types based on their importance, such as trunk pipelines, secondary pipelines, and branch pipelines.

[0035] A gas valve is a valve installed on a gas pipeline. It can be used to adjust the gas flow rate and gas pressure in the pipeline.

[0036] Sensors are components used to collect and characterize gas-related parameters. For example, sensors include pressure sensors, temperature sensors, and flow rate sensors.

[0037] Basic sensing data refers to gas-related parameters collected by sensors. For example, basic sensing data can include gas temperature, gas flow rate, gas pressure, etc.

[0038] Preset reporting rules are data processing procedures predefined by the gas company management platform and executed by the gas equipment object platform. For example, preset reporting rules may include regular or irregular reporting. For example, regular reporting may be every 45 days, while irregular reporting may include immediate reporting of abnormal gas parameters. Abnormal gas parameters may include abnormal gas temperature, abnormal gas flow rate, or abnormal gas pressure.

[0039] In some embodiments, the preset reporting rules can be determined based on historical experience or the level of attachment risk. For example, if the gas company management platform determines that the attachment risk level is relatively low based on analysis of basic perception data when reporting every 14 days, the reporting period can be appropriately extended. For example, if the attachment risk level in different gas pipeline areas is consistently below the preset risk threshold, the reporting period can be doubled.

[0040] It is understandable that when the deposition risk level is relatively low, it means that the data analysis interval is relatively short and the accumulation of deposition in the pipeline is relatively slow.

[0041] For more information on the risk levels of deposits, see Figure 3 and related descriptions.

[0042] In some embodiments, the gas equipment object platform may acquire and aggregate basic sensing data by communicating with different sensors, and store the basic sensing data in a storage device.

[0043] For more descriptions about the gas company management platform and the gas equipment object platform, see Figure 1 and the related descriptions.

[0044] Step 220: Determine the attachment risk area of the gas pipeline according to the basic perception data.

[0045] The attachment risk area refers to the gas pipeline area where pipeline attachments may exist in the gas pipeline. Pipeline attachments refer to the residues accumulated on the inner wall of the pipeline during the gas transportation process of the gas pipeline. For example, the residues can include hydrates, oil stains, sand grains, etc.

[0046] The gas pipeline area refers to the area where there is a need to monitor pipeline attachments. In some embodiments, the gas pipeline area can be a section of the pipeline or a partial area of a section of the pipeline. In some embodiments, if there are multiple sensors on a section of the pipeline, the partial gas pipeline between every two adjacent sensors can be used as the gas pipeline area.

[0047] In some embodiments, the gas company management platform can determine the attachment risk area based on the basic perception data through various methods. For example, the gas company management platform can generate the difference between the basic perception data and the preset gas transportation parameters. If the difference is greater than the preset transportation difference threshold, the position where the sensor is located is determined as the attachment risk area.

[0048] The preset gas transportation parameters refer to the preset gas pipeline operation parameters. The preset gas transportation parameters can be determined during the construction or planning of the gas pipeline and are the gas pipeline operation parameters that ensure the normal transportation of downstream gas. For example, the preset gas transportation parameters can include the preset gas transportation rate range, the preset gas pressure range, the preset gas temperature range, etc.

[0049] In some embodiments, the preset transportation difference threshold can be statistically determined by the gas company management platform according to the historical inspection results. For example, among 10 historical inspection results where pipeline attachments are found, in 9 cases, the difference between the basic perception data of the pipeline and the preset gas transportation parameters is greater than a value (for example, 5%). Then this value is set as the preset transportation difference threshold.

[0050] For more descriptions about the historical inspection results, see Figure 2 the related descriptions of Step 230.

[0051] Step 230: Determine the pipeline area to be detected according to the attachment risk area, generate a pipeline detection instruction and send it to the gas pipeline network maintenance object platform; the gas pipeline network maintenance object platform controls the inspection robot to inspect the pipeline area to be detected based on the pipeline detection instruction and collect the inspection results uploaded by the inspection robot.

[0052] The pipeline area to be detected refers to the gas pipeline area that needs on-site inspection. For example, the pipeline area to be detected can be the gas pipeline area inspected by detection equipment or inspection robots.

[0053] In some embodiments, the gas company management platform can determine the pipeline area to be detected through various methods based on the attachment risk area. For example, the gas company management platform can obtain the time interval between the current time and the last pigging time of a certain gas pipeline area. If the time interval is greater than the preset interval, it determines that the gas pipeline is the pipeline area to be detected. The preset interval can be a preset value input by the user to the gas company management platform.

[0054] In some embodiments, the gas company management platform can determine the pipeline area to be detected based on the difference between the basic perception data and the preset gas transmission parameters. For example, if the difference between the basic perception data and the preset gas transmission parameters of a certain gas pipeline area reaches 2 times the preset transmission difference threshold (for example, the preset transmission difference threshold is 5%, and the actual difference reaches 10% or more), it is determined as the pipeline area to be detected.

[0055] The pipeline detection instruction refers to the instruction related to pipeline detection communicated between the platform and the device in the intelligent gas pipeline attachment monitoring system. In some embodiments, the gas pipeline network maintenance object platform can send the pipeline detection instruction to the inspection robot.

[0056] The inspection robot refers to a robot equipped with inspection equipment. The inspection robot can be used to check whether there may be pipeline attachments and the content of attachments (such as the thickness of attachments, etc.) on the gas pipeline. For example, the inspection equipment can be an ultrasonic detector, a thickness gauge, etc.

[0057] The inspection result refers to the analysis data related to the inspection of the gas pipeline. For example, the inspection result can include whether there are pipeline attachments and the content of attachments in the pipeline area to be detected. For another example, the inspection result can also include whether pigging is performed.

[0058] In some embodiments, the gas pipeline network maintenance object platform can summarize the inspection results uploaded by the inspection robot to generate historical inspection results.

[0059] The content of attachments refers to the amount of pipeline attachments accumulated on the inner wall of the pipeline. For example, the content of attachments can include the thickness of attachments, the volume of attachments, etc.

[0060] In some embodiments, the gas company management platform can obtain the inspection results generated by one or more inspection robots through the gas pipeline network maintenance object platform.

[0061] In some embodiments, the gas company management platform can also generate a pipeline inspection sequence based on the risk level of attachments and the geographical location information of the gas pipeline area; and perform on-site inspections on the pipeline areas to be detected by the inspection robot according to the pipeline inspection sequence to obtain inspection results.

[0062] The risk level of attachments refers to the data reflecting the risk of pipeline attachments existing in different gas pipeline areas. For more descriptions about the risk level of attachments, see Figure 3 、 Figure 4 and related descriptions.

[0063] The geographical location information can refer to the geographical location where the gas pipeline area is located. For more descriptions about the geographical location information, see Figure 3 and related descriptions.

[0064] The pipeline inspection sequence includes the order of inspection for different pipeline areas to be detected. The pipeline inspection sequence can be represented by Arabic numerals or English letters. For example, (AB, 3) means that the pipeline inspection sequence for the gas pipeline area numbered AB is the 3rd. The pipeline inspection sequence can also include not performing inspections. For example, (BC, N) means not to perform inspections on the gas pipeline area numbered BC.

[0065] In some embodiments, the gas company management platform can generate one or more inspection groups. Each inspection group includes one or more adjacent pipeline areas to be detected. The pipeline inspection sequence of each inspection group is determined by sorting according to the average value of the risk levels of the attachments of the pipeline areas to be detected in each group. For example, the gas company management platform can divide different inspection routes according to the gas pipeline network. Each inspection route is used as an inspection group. Each inspection route includes several gas pipeline areas connected in sequence. The inspection route can have a preset maximum length (for example, 5 kilometers).

[0066] In some embodiments, the preset maximum length can be determined based on the battery life of the inspection robot (for example, the remaining power). The battery life can be determined according to historical inspection results. For example, in the previous historical inspection, the inspection robot stopped working due to insufficient power after moving 6 kilometers after charging. Then, before the next inspection, after confirming that the inspection robot is fully charged, the preset maximum length can be determined to be 5.5 kilometers, and the actual usage parameters of the inspection robot (for example, the maximum distance moved before the low battery warning is displayed) can be used as reference data for determining the preset maximum length next time.

[0067] In some embodiments of this specification, by determining the preset maximum length according to the battery life of the inspection robot, the actual load can be ensured, and the inspection efficiency can be guaranteed.

[0068] In some embodiments, the gas company management platform may determine whether to inspect a pipeline area to be inspected based on the historical inspection results of the pipeline area to be inspected where the risk level of the attachment is equal to or approximately equal to a preset risk threshold. For example, if in the historical inspection results of a pipeline area to be inspected, the proportion of the number of times without pigging is greater than a preset proportion (e.g., 0.9) pre-entered by the user into the system, then the pipeline area to be inspected is determined as the area not to be inspected this time.

[0069] For more descriptions of the preset risk threshold, see Figure 3 and related descriptions.

[0070] In some embodiments, in response to the inspection result of a pipeline area to be inspected indicating that the content of the attachment meets the preset content condition, the gas company management platform may adjust the pipeline inspection order of non-target pipelines.

[0071] Non-target pipelines may refer to gas pipeline areas associated with the pipeline area to be inspected. In some embodiments, non-target pipelines may be determined based on the influence degree of the attachment.

[0072] In some embodiments, the gas company management platform may determine non-target pipelines according to the edges of the pipe network simulation atlas.

[0073] It can be understood that only the downstream pipelines of the pipeline area to be inspected are associated with the pipeline area to be inspected, that is, the downstream pipelines of the pipeline area to be inspected may be affected by the transfer and accumulation of pipeline attachments in the upstream pipeline.

[0074] For more descriptions of the influence degree of the attachment and the pipe network simulation atlas, see Figure 3 、 Figure 4 and related descriptions.

[0075] The preset content condition may include a judgment condition for determining whether to adjust the inspection order of non-target pipelines. For example, the preset content condition may include that the content of the attachment (such as the thickness of the attachment, etc.) is lower than a preset content threshold (such as 3 mm). In some embodiments, the preset content condition may further include a judgment condition for determining whether to perform pigging.

[0076] In some embodiments, the gas company management platform may preset the preset content threshold according to historical basic perception data. For example, the gas company management platform may obtain the gas transmission rate in the basic perception data of multiple time periods after determining not to perform pigging in the historical data, and use the lowest attachment thickness when the gas transmission efficiency (such as gas flow) decreases due to non-pigging as the preset content threshold.

[0077] In some embodiments, the gas company management platform can also use a preset algorithm to determine a preset content threshold. For example, the gas company management platform can also determine multiple associated groups based on the historical sensing data and historical attachment risk levels of different pipeline areas at different times.

[0078] An associated group can include a gas pipeline area with an inspection result of unclear pigging, and two adjacent gas pipeline areas downstream of this gas pipeline area with an adjacent degree less than or equal to 2. For example, in A - B - C - D - E, AB, BC, CD, and DE are 4 sequentially connected gas pipeline areas. If AB is a gas pipeline area with an inspection result of unclear pigging, then AB, BC, and CD can be determined as an associated group.

[0079] The adjacent degree is a value reflecting the relative position relationship of different gas pipeline areas. For example, an adjacent degree of 2 means that there is one gas pipeline area (such as BC) between two gas pipeline areas (such as AB and CD).

[0080] In some embodiments, the gas company management platform can generate an association ratio of the number of associated groups in which the attachment risk level increases continuously twice to the total number of associated groups. Here, the attachment risk level increasing continuously twice means that the attachment risk levels of the downstream gas pipeline areas (such as BC and CD) within the associated group increase continuously twice.

[0081] For example, associated group A includes the gas pipeline area AB with an inspection result of unclear pigging, and two adjacent gas pipeline areas BC and CD downstream of it with an adjacent degree less than or equal to 2. In the subsequent 2 analysis results for the attachment risk level, the attachment risk levels of BC and CD increase each time, such as increasing by 2 levels and 3 levels respectively. Then, it is considered that associated group A is an associated group in which the attachment risk level increases continuously twice.

[0082] In some embodiments, if there is one or more associated groups with an association ratio greater than a preset association threshold, the gas company management platform can determine these associated groups as frequently associated groups. In some embodiments, the gas company management platform can determine the average value of the minimum attachment thickness of the gas pipeline areas (such as pipeline AB) with an inspection result of unclear pigging in these associated groups as the preset content threshold.

[0083] In some embodiments, in response to the inspection result of a to-be-detected pipeline area indicating that the attachment content meets the preset content condition, the gas company management platform can determine, among the downstream adjacent pipelines of this to-be-detected pipeline area, the gas pipeline areas with a non-zero attachment influence degree and that have been determined as to-be-detected pipeline areas as non-target pipelines, and then adjust the inspection order of the non-target pipelines. For more descriptions about the attachment influence degree, see Figure 3 and related descriptions.

[0084] Adjusting the inspection order may include delaying the inspection order of the pipeline area to be inspected or not conducting the inspection. In some embodiments, adjusting the inspection order may further include: if there are other pipeline areas to be detected around a non-target pipeline (e.g., other gas pipeline areas adjacent to the non-target pipeline), the gas company management platform may issue a pipeline detection instruction, and through the inspection robot, inspect the non-target pipeline whose inspection order has been adjusted.

[0085] In some embodiments, the gas company management platform may determine the pipeline areas to be detected or non-target pipelines corresponding to the edges in the pipeline network simulation atlas, and then determine the adjusted inspection order according to the adjacency between different pipeline areas to be detected and non-target pipelines, and the influence degree of the attachments in the gas pipeline area adjacent to the downstream of the pipeline area to be detected. For example, the gas company management platform may adjust the inspection order of non-target pipelines with an adjacency less than or equal to 2 to the pipeline area to be detected, and no longer adjust the inspection order of non-target pipelines with an adjacency greater than 2 to the pipeline area to be detected.

[0086] In some embodiments, the gas company management platform may determine the attachment risk level of the adjusted non-target pipeline, and then re-determine the pipeline inspection order according to the size of the adjusted attachment risk level.

[0087] For example, the gas company management platform may determine the adjusted attachment risk level through a preset algorithm according to the current attachment influence level of the non-target pipeline and the positive correlation of the attachment influence degree. For example, the gas company management platform may calculate and determine the adjusted attachment risk level of the non-target pipeline through formula (1):

[0088] N = O α (1)

[0089] Wherein, N is the adjusted attachment risk level of the non-target pipeline, O is the current attachment risk level of the non-target pipeline, and α is the attachment influence degree of the current non-target pipeline.

[0090] For more descriptions about the pipeline network simulation atlas, edges, and attachment risk levels, see Figure 3 、 Figure 4 and related descriptions.

[0091] In some embodiments of this specification, when the inspectors and material equipment required for pipeline network inspection are limited, and the inspection time is restricted, by determining a reasonable pipeline inspection order, the pipeline inspection efficiency can be improved, and the inspection requirements of the pipeline areas to be inspected with greater risks can be preferentially met.

[0092] In some embodiments of this specification, by adjusting the inspection order based on the impact of attachments, the inspection order of downstream pipelines can be reasonably adjusted according to the inspection results of upstream pipelines, which can improve the inspection efficiency to a certain extent and extend the endurance of the inspection robot.

[0093] Step 240: Receive the inspection results collected by the gas pipeline network maintenance object platform, generate gas pipeline cleaning data and send it to the government safety supervision and management platform.

[0094] Pigging data refers to data related to gas pipeline cleaning. For example, it can include information such as whether a gas pipeline section has been pigged and the pigging time. Pigging data can be represented as sequence data related to pigging for multiple pipelines. For example, (AB, Y, 1.3; BC, N, N; CD, Y, 3) indicates that the gas pipeline sections AB and CD require pigging (Y indicates pigging is required, N indicates not pigging is not required), with the pigging timelines being 1.3 and 3 days, respectively; the gas pipeline section BC does not require pigging.

[0095] In some embodiments, the gas company management platform can generate pigging data based on inspection results using various methods. For example, the gas company management platform can determine whether to pig the pipeline and the pigging area based on the thickness of the deposits in the inspection results. For example, if the deposit thickness in a gas pipeline area reaches a preset threshold (e.g., 3 mm), the gas pipeline area is determined to require pigging and is designated as a pigging area.

[0096] For example, a gas company management platform can generate an estimated pipeline cleaning time based on the results of two inspections and the time interval between them. For example, the gas company management platform can calculate the accumulation rate by dividing the difference in the amount of debris in the pipeline from the two inspections by the time interval between the inspections. The platform then divides the accumulation rate by a preset threshold and subtracts the time interval to calculate the cleaning time.

[0097] Step 250: Receive the pigging confirmation data returned by the government safety supervision management platform, generate a pigging instruction based on the pigging confirmation data, and perform pigging operations on part of the gas pipeline according to the pigging instruction.

[0098] The pigging confirmation data refers to the confirmation information related to pigging data sent by the government safety supervision and management platform. For example, the pigging confirmation data may include whether pigging is required, the pigging area of the pipeline, the pigging time, and the pigging sequence. For example, (AB, Y, 1.3, 1; CD, Y, 3, 37) may indicate that the gas pipeline areas numbered AB and CD need to be pigged (Y indicates that pigging is required, N indicates that pigging is not required), the pigging time for pipeline AB is after 1.3 days, and the pigging sequence is the 1st; the pigging time for pipeline BC is after 3 days, and the pigging sequence is the 37th.

[0099] In some embodiments, the government safety supervision and management platform can sort based on the sequence of pigging times to determine the pigging sequence. In some embodiments, if the pigging times of different gas pipelines are the same or similar, the pigging sequence can be determined according to the pipeline type (reflecting the importance of the pipeline, such as main pipelines, branch pipelines, etc.) or the accumulation rate of attachments. For example, the pigging times of two gas pipeline areas numbered AB and BC are both after 1 day, but the type of pipeline AB is a main pipeline, and the type of pipeline BC is a branch pipeline. Since pipeline AB is more important than pipeline BC, the pigging sequence of pipeline AB is more forward than that of pipeline BC.

[0100] In some embodiments, the gas company management platform can also generate a fan control instruction based on the pigging confirmation data returned by the government safety supervision and management platform, send it to the gas pipeline network maintenance object platform, and based on the fan control instruction, control the fan to operate with preset working parameters through the gas pipeline network maintenance object platform.

[0101] The fan control instruction refers to the instruction related to controlling the fan communicated between the platforms and devices in the intelligent gas pipeline attachment monitoring system. For example, the fan control instruction may include the preset working parameters generated by the gas company management platform. The gas pipeline network maintenance object platform can send the fan control instruction to different fans to control different fans to operate with preset working parameters.

[0102] The fan refers to a device used to regulate the gas flow in the gas pipeline. In some embodiments, the fan can, without affecting the normal transportation of gas in the pipeline, cause the impurities in the gas not to naturally deposit due to gravity but to be transported forward with the gas. In some embodiments, a impurity removal device for collecting impurities can be deployed at a specific position in the gas pipeline (such as the downstream position of the fan).

[0103] In some embodiments, the fan can stir the gaseous or liquid gas in the pipeline to affect the gas flow direction, thereby reducing the attachment accumulation rate. For more descriptions of the attachment accumulation rate, see Figure 2 Other parts of the content.

[0104] The preset operating parameters refer to the preset operating parameters of the fan, such as power, fan blade rotation speed, etc.

[0105] In some embodiments, the preset operating parameters can be pre - input by the user into the gas company management platform.

[0106] In some embodiments, the gas equipment object platform can send control instructions through wireless communication to set or adjust the preset operating parameters of the fan.

[0107] In some embodiments, the gas company management platform can obtain the preset gas transmission parameters through the government safety supervision management platform, and adjust the preset operating parameters according to the basic perception data and the preset gas transmission parameters. For more descriptions about the basic perception data and the preset gas transmission parameters, see Figure 2 the content of other parts.

[0108] In some embodiments, the gas company management platform can adjust the preset operating parameters through various methods.

[0109] For example, the gas company management platform can adjust the preset operating parameters according to the difference between the basic perception data and the preset gas transmission parameters (such as the median value of the parameter range). For example, the gas company management platform can determine the stability based on the difference between the basic perception data and the preset gas transmission parameters. If the stability is lower than 0.9, it will re - use the prediction model to determine the adjusted preset operating parameters. For more descriptions about the prediction model, see Figure 5 and related descriptions.

[0110] The stability refers to the stability degree of the gas transmission process. For example, the stability can include the gas pressure stability and the gas flow rate stability. The gas pressure stability and the gas flow rate stability refer to the values reflecting the stability degrees of the gas pressure and the gas flow rate. The larger the gas pressure stability and the gas flow rate stability are, the more stable the gas pressure and the gas flow rate are. The gas pressure stability and the gas flow rate stability can be values between 0 and 1.

[0111] In some embodiments, the stability can be determined based on the fluctuation conditions of the gas pressure and the gas flow rate. For example, the larger the fluctuation amplitude of the gas pressure and the gas flow rate is, the lower the stability is.

[0112] In some embodiments, the gas company management platform can determine the stability based on the basic perception data and the preset gas transmission parameters. For example, the gas company management platform can obtain the difference between the basic perception data and the preset gas transmission parameters, and divide the difference by the preset gas transmission parameters to determine the fluctuation value. If the fluctuation value is within 5%, the stability is determined to be 1; if the fluctuation value is between 5% - 15%, the stability is determined to be 0.9, and so on.

[0113] In some embodiments, the gas company management platform can adjust preset working parameters through a machine learning model. For example, the gas company management platform can analyze candidate working parameters through a prediction model to determine predicted working parameters, and then adjust the preset working parameters according to the predicted working parameters.

[0114] For more descriptions on how to adjust the preset working parameters and the prediction model, see Figure 5 and related descriptions.

[0115] In some embodiments of this specification, by dynamically adjusting working parameters of the fan such as power and blade rotation speed, etc., the risk of pipeline residue or formation of pipeline attachments can be reduced to a certain extent, as well as the accumulation rate of attachments, thereby reducing the workload of subsequent pigging and pipeline maintenance.

[0116] In some embodiments of this specification, by considering the difference between the basic sensing data obtained through monitoring and the preset pipeline operation parameters to adjust the operation parameters of the fan, since the change of the monitoring data can also indirectly reflect the accumulation rate of attachments in the pipeline, the risk of pipeline residue or formation of attachments can also be effectively reduced, as well as the accumulation rate of attachments.

[0117] The pigging instruction refers to the instruction related to pigging communicated between the platform and devices in the intelligent gas pipeline attachment monitoring system. For example, the gas company management platform can generate a pigging instruction and send it to the gas pipeline network maintenance object platform. The gas pipeline network maintenance object platform can, according to the pigging instruction, allocate the personnel, materials, and equipment required for pigging, and perform pigging operations.

[0118] The pigging operation refers to the operation related to cleaning the pipeline attachments on the inner wall of the gas pipeline.

[0119] In some embodiments of this specification, considering that there will be deposits of impurities carried by the gas in the gas pipeline and deposits of impurities generated by physical aggregation and chemical reactions during gas transportation, by reasonably determining the attachment risk area and the pipeline area to be detected according to the collected basic sensing data, the efficiency of on-site inspection can be guaranteed, and the pipeline inspection cost and subsequent pigging cost can be saved.

[0120] It should be noted that the above description of process 200 is only for illustration and example, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0121] Figure 3 is an exemplary flowchart for determining the attachment risk area shown in some embodiments of this specification. As Figure 3As shown, process 300 includes the following steps. In some embodiments, process 300 may be executed by a gas company management platform.

[0122] Step 310: Generate geographical location information of the gas pipeline area, geographical location information of the sensors, and gas flow information based on the basic perception data.

[0123] For more descriptions about the gas pipeline area, see Figure 2 and related descriptions.

[0124] The geographical location information may include information related to the geographical location where the gas pipeline area and / or the sensors are located. For example, the geographical location information may include the location coordinates of the geographical location where the gas pipeline area and / or the sensors are located. For another example, the geographical location information may be the relative position relationship between different gas pipelines and sensors. For instance, (AB, BC, -10) may indicate that pipeline AB is upstream of pipeline BC and is 10 meters away from pipeline BC.

[0125] In some embodiments, the gas company management platform may determine the number information (such as area number or sensor number) of the gas pipeline area or sensor corresponding to the basic perception data based on the basic perception data, and then may obtain the geographical location information corresponding to different gas pipeline areas or sensors from the government safety supervision management platform.

[0126] The gas flow information refers to data related to gas flow. For example, the gas flow information may include the gas flow direction, flow rate, etc.

[0127] In some embodiments, the gas company management platform may extract information such as gas flow rate and gas flow direction from the basic perception data, and then determine the gas flow information based on the gas flow rate. For another example, the gas company management platform may retrieve the gas flow information of the corresponding gas pipeline area from the database of the government safety supervision management platform.

[0128] For more descriptions about the basic perception data, see Figure 2 and related descriptions.

[0129] Step 320: Determine the influence degree of attachments based on the historical pigging data.

[0130] The historical pigging data refers to data related to pipeline pigging performed in the past. For example, the historical pigging data may include historical pigging time, the gas pipeline area corresponding to the pigging location, the cumulative number of pigging times, etc.

[0131] In some embodiments, the gas company management platform may determine the historical pigging data based on the pigging logs stored in the gas pipeline network maintenance object platform. The pigging log refers to data that records and statistics all pigging operations.

[0132] The degree of influence of attachments refers to the numerical value of the influence on adjacent and connected other gas pipeline areas when there are pipeline attachments in the current gas pipeline area. The larger the numerical value of the degree of influence of attachments, the more likely it is that there are similar pipeline attachments in other gas pipeline areas when there are pipeline attachments in the current gas pipeline area.

[0133] For more descriptions about pipeline attachments, see Figure 2 and related descriptions.

[0134] In some embodiments, the degree of influence of attachments may refer to the degree of influence of the upstream gas pipeline area on the downstream gas pipeline area.

[0135] In some embodiments, the gas company management platform can determine the degree of influence of attachments through various methods based on historical pigging data. For example, there are three adjacent gas pipeline areas AB, BC, and CD, and AB, BC, and CD are all attachment risk areas, and the attachment thickness AB≥BC≥CD. Then, it can be considered that the degree of influence of attachments at BC is equal to the ratio of the attachment content at BC to the attachment content at AB, and the degree of influence of attachments at CD is equal to the ratio of the attachment content at CD to the attachment content at BC.

[0136] In some embodiments, the gas company management platform can construct a data group to be screened based on historical pigging data and relevant historical basic perception data. The data group to be screened includes multiple sets, and each set is composed of historical pigging data of at least 2 adjacent gas pipeline areas. The gas company management platform can determine the ratio of the number of sets in the data group to be screened where both the gas pipeline area AB and its upstream gas pipeline area are detected to have attachments, and the attachment thickness of the upstream gas pipeline area is greater than that of the downstream gas pipeline area, to the total number of sets in the data group to be screened that contain the gas pipeline area AB. Furthermore, this ratio can be determined as the degree of influence of attachments of the gas pipeline area AB.

[0137] Step 330, determine the attachment risk level of the gas pipeline area according to the geographical location information, gas flow information, and the degree of influence of attachments.

[0138] The attachment risk level refers to the data reflecting the risk magnitude of the existence of attachments in different gas pipeline areas. The higher the attachment risk level, the greater the possibility that there are attachments in the gas pipeline area. For example, the attachment risk level can be represented by Arabic numerals, such as 0 - 10 levels, and level 10 is the highest.

[0139] In some embodiments, the gas company management platform can determine the risk level of attachments through various methods. For example, the gas company management platform can determine the difference between the basic perception data at different locations and the preset gas transmission parameters, and determine the risk level of attachments based on the ratio of the difference to the preset transmission difference threshold. For example, if the ratio of the difference to the preset transmission difference threshold is less than 1, the risk level of attachments is determined to be level 1-5 according to the ratio size (indicating a relatively low risk of attachments). If it is equal to 1, the risk level of attachments is level 5 (indicating a certain risk). If it is greater than 1, the risk level of attachments is determined to be level 6-10 according to the ratio size. For example, when the ratio reaches 2 or more, the level is 10, reaching the maximum.

[0140] In some embodiments, the gas company management platform can determine the risk level of attachments in other gas pipeline areas based on the attachment influence degree. For example, if the risk level of attachments in the current gas pipeline area is level 10 and the attachment influence degree is 0.8, the risk level of attachments in the adjacent downstream gas pipeline area can be level 8.

[0141] For more descriptions about the preset transmission difference threshold, see Figure 2 and related descriptions.

[0142] Step 340, determine the attachment risk area based on the attachment risk level.

[0143] The attachment risk area refers to the gas pipeline area in the gas pipeline where pipeline attachments may exist. For more descriptions about the attachment risk area, see Figure 2 and related descriptions.

[0144] In some embodiments, in response to the attachment risk level meeting the preset risk condition, the gas company management platform can determine the gas pipeline area corresponding to the attachment risk level as the attachment risk area, where the preset risk condition can be determined according to historical inspection results.

[0145] The preset risk condition refers to the judgment rule preset by the gas company management platform for determining whether it is an attachment risk area. For example, the preset risk condition can be a preset risk threshold, such as the attachment risk level is not lower than level 6.

[0146] In some embodiments, the gas company management platform can determine and adjust the preset risk condition according to historical inspection results and historical pigging data.

[0147] For example, the gas company management platform can adjust the preset risk condition according to a preset algorithm and historical inspection results. For example, the gas company management platform can adjust the preset risk condition through formula (2):

[0148] T = Y - Q2 / Q1 (2)

[0149] Among them, T is the adjusted preset risk threshold, Y is the original risk threshold, Q2 is the number of times of pigging required in the historical inspection results of pipelines with the attachment risk level equal to the original risk threshold, and Q1 is the total number of historical inspection results.

[0150] In some embodiments, the gas company management platform can determine the original risk threshold according to the same preset algorithm. Exemplarily, the original risk threshold can be the preset risk threshold after the last adjustment.

[0151] In some embodiments, the original risk threshold can be a preset value determined and input by the user to the gas company management platform. For example, if the user stipulates that further inspection of the gas pipeline is required when the attachment risk level is 5 or above, the preset risk threshold can be level 5. In some embodiments, the gas company management platform can determine the attachment risk level of the pipeline to be inspected corresponding to the minimum attachment thickness requiring pigging based on the inspection results of the pipeline to be inspected as the original risk threshold.

[0152] For example, the gas company management platform has determined 800 areas of pipelines to be detected, among which the risk levels of 60 areas to be detected are exactly equal to or approximately equal to the preset risk threshold (e.g., level 5). Approximately equal can be within a certain range of a certain value (e.g., within ±0.5 of 5). The gas company management platform inspects these 60 areas of pipelines to be detected and finds that 30 areas of pipelines to be detected require pigging. Then the gas company management platform can adjust the preset risk threshold = 5 - 30 / 60 = 4.5.

[0153] In some embodiments, if the proportion of inspection results equal to or approximately equal to the preset risk threshold that do not require pigging continuously occurs and is greater than the preset proportion (e.g., 0.9), and the continuous occurrence times are greater than or equal to the preset times (e.g., 5 times), then the adjusted preset risk threshold can be the original risk threshold plus 0.5.

[0154] In some embodiments, the preset times can be determined by the gas company management platform according to the historical inspection results. For example, in the historical inspection results, if the proportion of inspection results equal to or approximately equal to the preset risk threshold that do not require pigging continuously occurs N times and is greater than the preset proportion (e.g., 0.9), and all subsequent inspection results of this pipeline are those that do not require pigging, then the gas company management platform can determine N as the preset times. The preset proportion can be a preset value determined and input by the user to the gas company management platform.

[0155] The historical inspection results refer to the pipeline inspection data that has occurred historically. For more descriptions of the historical inspection results, see Figure 2 and related descriptions.

[0156] In some embodiments of the present specification, by determining the influence degree of the attachment, the influence relationship between different gas pipeline areas that conforms to the actual situation can be determined, thereby providing reliable data support for subsequent classification of the attachment influence level and determination of the attachment influence area.

[0157] In some embodiments of the present specification, by dynamically setting and adjusting the preset risk threshold according to historical inspection results, the pigging efficiency and pigging quality can be effectively guaranteed, and the pigging cost can be reduced to a certain extent.

[0158] It should be noted that the above description of process 300 is only for illustration and explanation, and does not limit the scope of application of the present specification. Those skilled in the art can make various modifications and changes to process 300 under the guidance of the present specification. However, these modifications and changes are still within the scope of the present specification.

[0159] Figure 4 It is an exemplary schematic diagram for determining the attachment risk level shown in some embodiments of the present specification.

[0160] As Figure 4 shown, the gas company management platform can be further configured to construct a pipeline network simulation map 410; based on the pipeline network simulation map 410, through the attachment analysis model 420, generate the attachment risk levels 430 of one or more edges 412 (such as Figure 4 430-1 and 430-n shown).

[0161] The pipeline network simulation map 410 refers to a knowledge map used to reflect the actual positional relationship between sensors and gas pipelines. Among them, the knowledge map refers to a data structure composed of nodes 411 and edges 412.

[0162] In some embodiments, the nodes 411 of the pipeline network simulation map 410 can represent sensors, and the edges 412 of the pipeline network simulation map 410 can represent the gas pipelines between sensors. In some embodiments, in the pipeline network simulation map 410, the node attributes of the nodes 411 can include the attachment influence degree, basic perception data, pipeline location information, etc., and the attributes of the edges can include the attachment risk level. In some embodiments, the edges 412 of the pipeline network simulation map 410 can be directed edges, and the direction of the edges 412 represents the gas flow direction in the gas pipeline. For more content about basic perception data, attachment influence degree, and attachment risk level, reference can be made to Figure 2 、 Figure 3 for relevant descriptions.

[0163] The pipeline location information refers to the geographical location of the gas pipeline where the sensor is located.

[0164] In some embodiments, the gas company management platform may construct a pipe network simulation graph 410 by using sensors and the gas pipelines between the sensors, taking the attachment impact degree, basic sensing data, and pipeline location information as node attributes, and taking the attachment risk level as an edge attribute. For example, the gas company management platform may set each sensor as each node of the pipe network simulation graph 410. For another example, if there is a gas pipeline between sensors, the nodes 411 corresponding to the sensors at both ends of the gas pipeline are connected to form an edge 412 of the pipe network simulation graph 410.

[0165] In some embodiments, the gas company management platform may construct a pipe network simulation graph 410 based on the distribution of the gas pipeline network where the gas pipelines are located. For example, the gas company management platform may extract information such as the location coordinates, pipeline diameters, and connection relationships of all gas pipelines in the target area through a GIS system (Geographic Information System). Subsequently, the location coordinates of each sensor in the gas pipeline network are extracted and matched with the gas pipelines in the GIS system; for each sensor, the gas company management platform may extract information such as the basic sensing data of each sensor; finally, the gas company management platform may draw corresponding edges 412 in the pipe network simulation graph 410 according to the actual connection relationships of the gas pipelines between the sensors.

[0166] The attachment analysis model 420 refers to a model for generating an attachment risk level 430. In some embodiments, the attachment analysis model 420 may be a machine learning model, such as a graph neural network model (Graph Neural Network, GNN), etc.

[0167] In some embodiments, the input of the attachment analysis model 420 may include the pipe network simulation graph 410. In some embodiments, the output of the attachment analysis model 420 may include the attachment risk level 430. For example, the attachment risk level 430 corresponding to each edge 412 in the pipe network simulation graph 410.

[0168] In some embodiments, the gas company management platform may train the attachment analysis model 420 based on a large number of first training samples with first tags. In some embodiments, the first training samples include sample pipeline network simulation diagrams. In some embodiments, the first tags may be the historical attachment risk levels corresponding to each edge 412 in the sample pipeline network simulation diagram. In some embodiments, the gas company management platform inputs the first training samples into the initial attachment analysis model 420 to obtain the model prediction output corresponding to the first training samples. The gas company management platform constructs a loss function based on the model prediction output corresponding to the first training samples and the first tags corresponding to the first training samples. The gas company management platform updates the model parameters in the initial attachment analysis model 420 in the reverse direction according to the value of the loss function, based on optimization algorithms such as the gradient descent method. When the iteration end condition is satisfied (for example, the loss function converges, the number of iterations reaches a preset iteration threshold, etc.), the gas company management platform ends the iteration and obtains the trained attachment analysis model 420.

[0169] In some embodiments, the gas company management platform may construct the first training samples based on the historical attachment influence degree, historical basic perception data, historical pipeline location information, and the historical attachment risk level 430 determined according to historical time. In some embodiments, the historical attachment risk level may be determined according to the actually measured attachment thickness in the historical pigging data. For example, the gas company management platform may preset different attachment risk levels 430 for them respectively according to the size of the actually detected attachment thickness. For example, if the attachment thickness is 3 mm, then the corresponding attachment risk level 430 is level 5. In some embodiments, the different attachment risk levels 430 corresponding to the thickness of each attachment may be preset based on manual experience. For example, the greater the actually measured attachment thickness of the gas pipeline, the higher the attachment risk level 430 corresponding to the gas pipeline, that is, the higher the attribute value (such as level, etc.) of the edge corresponding to the gas pipeline in the pipeline network simulation diagram 410. In some embodiments, the gas company management platform may construct the first tags based on the historical attachment risk level determined according to historical time.

[0170] In some embodiments of this specification, by using sensors as nodes and gas pipelines as edges to construct a pipeline network simulation diagram, the spatial relationships of each gas pipeline in the gas pipeline network can be simulated, so that the attachment analysis model can learn the location characteristics of the gas pipelines; by using the attachment analysis model to predict the attachment influence degree of each gas pipeline based on the pipeline network simulation diagram, the attachment risk levels of different gas pipelines can be evaluated more accurately.

[0171] Figure 5 It is an exemplary diagram of the prediction model shown in some embodiments of this specification.

[0172] In some embodiments, such as Figure 5 shown, the gas company management platform can be further configured to determine candidate operating parameters 520 of the fan based on the attachment risk level of the gas pipeline area and the inspection results; determine the predicted operating parameters 550 corresponding to the candidate operating parameters 520 through the prediction model 540 based on the candidate operating parameters 520, the pipeline diameter 510, and the basic sensing data 530; and adjust the preset operating parameters based on the predicted operating parameters 550.

[0173] The candidate operating parameters 520 can be determined in various ways. In some embodiments, the gas company management platform can determine multiple candidate operating parameters 520 by querying the fan parameter table based on the attachment risk level of the gas pipeline area and the inspection results.

[0174] In some embodiments, the gas company management platform can construct a fan parameter table based on the historical attachment risk level and historical inspection results. For example, the gas company management platform can use different historical attachment risk levels and the fan operating parameters proven to be effective under different historical inspection results as corresponding reference candidate operating parameters for querying or use.

[0175] For example, if a certain fan operating parameter is applied to the gas pipeline area corresponding to the attachment risk level A and the inspection result M, and subsequently the attachment risk level corresponding to this gas pipeline area decreases or the attachment content in the inspection result decreases, the gas company management platform can set this fan operating parameter as the reference candidate fan parameter corresponding to the attachment risk level A and the inspection result M in the fan parameter table.

[0176] For more descriptions about the candidate operating parameters 520, reference can be made to Figure 3 and its related descriptions.

[0177] The pipeline diameter 510 refers to the inner diameter size of the gas pipeline area, that is, the diameter size of the internal space of the gas pipeline.

[0178] In some embodiments, the gas company management platform can determine the pipeline diameter 510 corresponding to each gas pipeline area based on querying the pipeline diameter table. The pipeline diameter table refers to a list used to store each gas pipeline area and its corresponding pipeline diameter.

[0179] In some embodiments, the gas company management platform can also determine the pipeline diameter 510 through distance sensors (such as laser rangefinders and / or ultrasonic sensors, etc.) deployed on the inspection robots.

[0180] For the description of the basic sensing data 530, reference can be made to Figure 3 and its related descriptions.

[0181] The prediction model 540 refers to a model used to determine the prediction working parameters 550. In some embodiments, the prediction model 540 can be a machine learning model, such as a Recurrent Neural Network (RNN), etc.

[0182] In some embodiments, the input of the prediction model 540 can include the candidate working parameters 520, the pipeline diameter 510, and the basic sensing data 530. In some embodiments, the output of the prediction model 540 can include the prediction working parameters 550.

[0183] In some embodiments, the prediction working parameters 550 can include at least one of an estimated impurity deposition amount, an estimated gas pressure stability, and / or an estimated gas flow rate stability.

[0184] The impurity deposition amount refers to the deposition amount (e.g., the thickness of the attachment) of the pipeline attachments (such as solid polymers, dust, etc.) in the gas pipeline. The estimated impurity deposition amount refers to the estimated impurity deposition amount.

[0185] The gas pressure stability is an index used to measure the pressure fluctuation in the gas pipeline. For example, the higher the gas pressure stability, the smoother the gas flow. The estimated gas pressure stability refers to the estimated gas pressure stability.

[0186] The gas flow rate stability is an index used to measure the flow rate fluctuation of the gas in the gas pipeline. For example, the higher the gas flow rate stability, the smoother the gas flow. The estimated gas flow rate stability refers to the estimated gas flow rate stability.

[0187] For more information about the prediction working parameters 550, reference can be made to Figure 2 、 Figure 3 and its related descriptions.

[0188] In some embodiments, the gas company management platform can train the prediction model 540 based on a large number of second training samples with second labels by means such as the gradient descent method.

[0189] In some embodiments, the second training samples can include the sample working parameters, the sample pipeline diameter, the sample basic sensing data, etc. at the first historical time. In some embodiments, the second label can be the impurity deposition amount, the gas pressure stability, and the gas flow rate stability at the second historical time corresponding to the second training samples. Among them, the first historical time is earlier than the second historical time.

[0190] In some embodiments, the gas company management platform may obtain the historical pipeline diameter, historical basic sensing data, and historical working parameters collected at the first historical time from the storage unit, and construct a second training sample. In some embodiments, the gas company management platform may, based on the impurity deposition amount, gas pressure stability, and gas flow rate stability corresponding to the second training sample obtained from actual monitoring at the second historical time, construct a second label. Based on the basic sensing data, candidate working parameters, and inspection results at the first historical time corresponding to the second training sample, determine the impurity deposition amount, gas pressure stability, and gas flow rate stability at the second historical time; wherein, the stability may be determined based on the fluctuation condition. For example, if the fluctuation is within 5%, the stability is 1; if the fluctuation is between 5% and 15%, the stability is 0.9.

[0191] In some embodiments, the gas company management platform may use different groups of training samples to cross-train the prediction model 540. In some embodiments, the gas company management platform may determine different groups of training data sets based on the impurity deposition amount, gas pressure stability, and / or gas flow rate at historical times.

[0192] For example, the gas company management platform may set the second training samples with a floating trend less than the floating threshold in the historical time in terms of the impurity deposition amount, gas pressure stability, and / or gas flow rate as the training samples of the same group, and set the second training samples with a floating trend not less than the floating threshold as the training samples of the same group, and cross-train the prediction model 540 based on the different groups of training samples. In some embodiments, the floating threshold may be preset based on manual experience.

[0193] In some embodiments, the gas company management platform may train the initial prediction model 540 through multiple rounds of iteration. Among them, at least one round of iteration includes: the gas company management platform selects one or more groups of second training samples, inputs the one or more groups of second training samples into the initial prediction model 540, and obtains the model prediction outputs corresponding to the one or more groups of second training samples. The gas company management platform substitutes the model prediction outputs corresponding to the one or more groups of second training samples and the one or more groups of second labels corresponding to these one or more second training samples into the formula of the predefined loss function to calculate the value of the loss function. The gas company management platform updates the model parameters in the initial prediction model 540 in reverse based on the value of the loss function and an optimization algorithm such as the gradient descent method. When the iteration end condition is met (for example, the loss function converges, the number of iterations reaches the preset iteration threshold, etc.), the gas company management platform ends the iteration and obtains the trained prediction model 540.

[0194] In some embodiments, different groups of training samples have different corresponding learning rates during the training process. For example, the learning rate of the group of training samples with a larger number of training samples can be higher than that of the group of training samples with a lower number of training samples.

[0195] In some embodiments, the gas company management platform can evaluate the predicted working parameter 550 in various ways based on the predicted impurity deposition amount, the predicted gas pressure stability, and the predicted gas flow rate stability, so as to screen the matching predicted working parameter 550.

[0196] In some embodiments, there is a negative correlation between the predicted working parameter 550 and the predicted impurity deposition amount, and there are positive correlations between the predicted working parameter 550 and the predicted gas pressure stability and the predicted gas flow rate stability. For example, the gas company management platform can evaluate the predicted working parameter 550 based on the following formula (3):

[0197] (3)

[0198] where, represents the evaluation score of the preset working parameter, 、 and respectively represent the predicted impurity deposition amount, the predicted gas pressure stability, and the predicted gas flow rate stability, 、 and respectively represent the weight coefficient of the predicted impurity deposition amount, the weight coefficient of the predicted gas pressure stability, and the weight coefficient of the predicted gas flow rate stability.

[0199] In some embodiments, the gas company management platform can determine 、 and through various methods according to the historical gas supply data. For example, the gas company management platform can perform statistical analysis on the historical gas supply data. When the change ranges of the impurity deposition amount, the gas pressure, and the gas flow rate in the historical gas supply data all reach the amplitude threshold (for example, 20%, etc.), 、 and are determined according to the influence degree of the downstream gas usage situation.

[0200] In some embodiments, the gas company management platform adjusts 、 and according to the proportion of user complaint types. For example, if the user reports that the gas pressure is insufficient, the gas company management platform can appropriately increase , etc. In some embodiments, the amplitude threshold can be preset according to manual experience.

[0201] In some embodiments, can be negative, and can be positive.

[0202] In some embodiments, the gas company management platform can screen out appropriate prediction working parameters 550 from multiple groups of prediction working parameters 550, and use the corresponding preset working parameters as the preset working parameters of each fan. For example, the gas company management platform can evaluate the prediction working parameters 550 through the above formula (3), and set the preset working parameter corresponding to the prediction working parameter 550 with the highest evaluation score as the current preset working parameter of the target fan.

[0203] In some embodiments of this specification, by introducing a prediction model to predict the working parameters of the fan, the accuracy of the predicted working parameters of the fan can be improved, and thus the working performance of the fan can be improved. By using a large amount of historical data to train and optimize the prediction model, the prediction model can more accurately predict the in-pipe data of the gas pipeline in the future time period (for example, impurity deposition amount, gas pressure stability, gas flow rate stability, etc.), so as to select appropriate preset working parameters of the fan, and thus improve the cleaning effect of the fan.

[0204] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0205] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A pipeline attachment monitoring method based on the intelligent gas Internet of Things, characterized in that, The method is executed by the gas company management platform of the intelligent gas pipeline attachment monitoring system, and includes: Obtaining basic perception data, and determining the attachment risk area of the gas pipeline according to the basic perception data. The basic perception data is gas-related parameters collected by one or more sensors, including gas temperature, gas flow rate, and gas pressure; Generating geographical location information and gas flow information according to the attachment risk area; Determining the attachment influence degree according to the historical pigging data. The attachment influence degree is a numerical value representing the influence degree on adjacent or connected other gas pipeline areas when there are pipeline attachments in the gas pipeline area; Constructing a pipeline network simulation map according to the geographical location information, the gas flow information, and the attachment influence degree. The pipeline network simulation map is used to reflect the actual positional relationship between the sensors and the gas pipelines, and includes one or more nodes representing the sensors and one or more edges representing the gas pipelines between the sensors; Based on the pipeline network simulation map, determining the attachment risk level of the gas pipeline area through an attachment analysis model. The attachment analysis model is a machine learning model; Determining the pipeline area to be detected based on the attachment risk level; Receiving the inspection results of the inspection robot for the pipeline area to be detected, generating the pigging data of the gas pipeline, and sending it to the government safety supervision management platform; and, Receiving the pigging confirmation data returned by the government safety supervision management platform, generating a pigging instruction and a fan control instruction based on the pigging confirmation data, and instructing to perform pigging operations on some of the gas pipelines according to the pigging instruction; Controlling the fan to operate with preset working parameters according to the fan control instruction; the preset working parameters are determined based on the stability, and the stability is determined based on the difference between the basic perception data and the preset gas transmission parameters.

2. The method according to claim 1, wherein The method further includes: Generating a pipeline inspection sequence based on the attachment risk level and the geographical location information of the gas pipeline area; Performing on-site inspection on the pipeline area to be detected through the inspection robot based on the pipeline inspection sequence, and obtaining the inspection results.

3. The method according to claim 2, characterized in that, The method further includes: Responding to the inspection result that the attachment content meets the preset content condition, adjusting the pipeline inspection sequence of the non-target pipeline; wherein, the non-target pipeline is associated with the gas pipeline area corresponding to the inspection result, and the non-target pipeline is determined based on the attachment influence degree.

4. The method according to claim 1, wherein The method further includes: Issuing a data collection instruction, controlling the sensors on the gas pipeline or gas valve to collect the basic perception data, and transmitting it to the gas equipment object platform for summary and storage. The gas equipment object platform uploads the basic perception data to the gas company management platform according to the preset reporting rules; Generate a pipeline inspection instruction according to the pipeline area to be detected and send it to the gas pipeline network maintenance object platform; based on the pipeline inspection instruction, the gas pipeline network maintenance object platform controls the inspection robot to inspect the pipeline area to be detected and collect the inspection results uploaded by the inspection robot.

5. A pipeline attachment monitoring system based on the intelligent gas Internet of Things, characterized in that, The pipeline attachment monitoring system based on the intelligent gas Internet of Things includes a gas company management platform, a gas equipment object platform, a gas pipeline network maintenance object platform, and a government safety supervision and management platform; The gas company management platform is configured to: Obtain basic sensing data, and based on the basic sensing data, determine the attachment risk area of the gas pipeline. The basic sensing data is gas-related parameters collected by one or more sensors, including gas temperature, gas flow rate, and gas pressure; Generate geographical location information and gas flow information according to the attachment risk area; Determine the attachment impact degree according to historical pigging data. The attachment impact degree is a numerical value representing the impact degree on adjacent or connected other gas pipeline areas when there are pipeline attachments in the gas pipeline area; Construct a pipeline network simulation map according to the geographical location information, the gas flow information, and the attachment impact degree. The pipeline network simulation map is used to reflect the actual positional relationship between sensors and gas pipelines, including one or more nodes representing the sensors and one or more edges representing the gas pipelines between the sensors; Based on the pipeline network simulation map, determine the attachment risk level of the gas pipeline area through an attachment analysis model. The attachment analysis model is a machine learning model; Determine the pipeline area to be detected based on the attachment risk level; Receive the inspection results of the inspection robot for the pipeline area to be detected, generate pigging data for the gas pipeline and send it to the government safety supervision and management platform; Receive the pigging confirmation data returned by the government safety supervision and management platform, generate a pigging instruction and a fan control instruction based on the pigging confirmation data, and instruct to perform pigging operations on part of the gas pipeline according to the pigging instruction; Control the fan to operate with preset working parameters according to the fan control instruction; the preset working parameters are determined based on stability, and the stability is determined based on the difference between the basic sensing data and the preset gas transmission parameters; The gas equipment object platform is configured to: Receive the basic sensing data, summarize and store it, and upload the basic sensing data to the gas company management platform according to a preset reporting rule; The gas pipeline network maintenance object platform is configured to: Receive the pipeline inspection instruction sent by the gas company management platform, control the inspection robot to inspect the pipeline area to be detected, and collect the inspection results uploaded by the inspection robot, and send the inspection results to the gas company management platform; The government safety supervision and management platform is configured to: Receive the pigging data sent by the gas company management platform, generate and send the pigging confirmation data to the gas company management platform.

6. The system according to claim 5, wherein The gas company management platform is further configured to: Generate a pipeline inspection sequence based on the risk level of the attached objects and the geographical location information of the gas pipeline area; Based on the pipeline inspection sequence, use the inspection robot to conduct on-site inspections of the pipeline area to be detected and obtain the inspection results.

7. The system according to claim 6, wherein The gas company management platform is further configured to: In response to the inspection result that the content of the attached objects meets the preset content condition, adjust the pipeline inspection sequence of the non-target pipelines; wherein, the non-target pipelines are associated with the gas pipeline area corresponding to the inspection result, and the non-target pipelines are determined based on the influence degree of the attached objects.

8. The system according to claim 5, characterized in that, The gas company management platform is further configured to: Issue a data collection instruction to control the sensors on the gas pipeline or gas valve to collect the basic perception data and transmit it to the gas equipment object platform for summarization and storage.

Images