Intelligent gas pipe network particulate matter safety monitoring method, internet of things system and medium

Abstract

The present invention provides a smart gas pipeline network particulate matter safety monitoring method, Internet of Things system, and medium, relating to the field of particulate matter monitoring. The method comprises: obtaining concentration data for at least one pipeline area; generating a concentration level for at least one pipeline area based on the concentration data, and generating a concentration level marker in a preset display system; determining a concentration level difference based on the concentration level of at least one pipeline area; determining a pipeline to be inspected based on the concentration level difference, and generating a pipeline marker for the pipeline to be inspected in a preset display system; generating a pipeline inspection instruction based on the pipeline to be inspected; generating a pipeline inspection work order; and regulating operating parameters of pipeline ancillary equipment in at least one pipeline area based on the execution result of the pipeline inspection work order and / or the concentration level difference. This method improves the efficiency of particulate matter concentration monitoring and gas pipeline network operation and maintenance by visually displaying the particulate matter concentration within the pipeline, while also generating a pipeline inspection work order specifically for the pipeline to be inspected.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of particulate matter monitoring, in particular to a smart gas pipeline network particulate matter safety monitoring method, an Internet of Things system and a medium. BACKGROUND

[0002] Gas transmission is usually accompanied by particulate matter flow. Generally, high particulate matter concentration indicates that the gas pipeline has hidden dangers and will increase the resistance of gas transmission, accelerate the erosion of the pipe wall, and corrode the pipeline and equipment. In order to avoid the failure of the gas pipeline, it is necessary to monitor the particulate matter content in the gas pipeline network.

[0003] Therefore, the present application provides a smart gas pipeline network particulate matter safety monitoring method, an Internet of Things system and a medium, which can visually display the concentration level of particulate matter in the pipeline, improve the efficiency of particulate matter concentration monitoring and gas pipeline network operation and maintenance, and timely adjust the relevant equipment to ensure the efficiency of gas pipeline transmission. SUMMARY

[0004] The present application provides a smart gas pipeline network particulate matter safety monitoring method, an Internet of Things system and a medium, which can visually display the concentration level of particulate matter in the pipeline, improve the efficiency of particulate matter concentration monitoring and gas pipeline network operation and maintenance, and timely adjust the relevant equipment to ensure the efficiency of gas pipeline transmission.

[0005] The summary of the application comprises a smart gas pipeline network particulate matter safety monitoring Internet of Things system, the Internet of Things system comprises a government regulatory object platform, a gas company sensing network platform and a gas equipment object platform, the government regulatory object platform comprises a gas company management platform, the gas company management platform is configured to: obtain concentration data of particulate matter of at least one pipeline area from a monitoring device of the gas equipment object platform through the gas company sensing network platform; generate a concentration level of the at least one pipeline area based on the concentration data, and generate a concentration level mark in a preset display system; determine a concentration level difference based on the concentration level of the at least one pipeline area; determine a pipeline to be inspected based on the concentration level difference, and generate a pipeline to be inspected mark in the preset display system; generate a pipeline inspection instruction based on the pipeline to be inspected; generate a pipeline inspection work order based on the pipeline inspection instruction; and based on an execution result of the pipeline inspection work order and / or the concentration level difference, regulate operation parameters of pipeline auxiliary equipment of the at least one pipeline area through the gas equipment object platform.

[0006] The summary of the application comprises a computer readable storage medium, the storage medium stores computer instructions, when a computer reads the computer instructions in the storage medium, the computer executes the method described in the above embodiment.

[0007] The beneficial effects of the application include but are not limited to: (1) based on the smart gas pipeline network particulate matter safety monitoring Internet of Things system, an information operation closed loop can be formed between each functional platform, coordinated and regularly operated, realizing the informatization and smartization of gas pipeline particulate matter monitoring. (2) through the concentration level difference of adjacent pipeline areas, the pipeline to be inspected can be quickly determined, and the concentration level of the particulate matter in the pipeline can be visually displayed, which can improve the efficiency of particulate matter concentration monitoring. At the same time, the pipeline inspection work order is generated based on the pipeline to be inspected, and then the pipeline to be inspected is checked in time, which can quickly respond when the concentration data in the gas pipeline is abnormal, so as to ensure the efficiency of gas pipeline transportation. (3) by distinguishing the monitoring priority of different pipeline areas, some pipeline areas prone to hazards caused by particulate matter concentration can be focused on and processed, improving the efficiency of gas pipeline operation and maintenance. BRIEF DESCRIPTION OF DRAWINGS

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

[0009] Figure 1 is a platform structure schematic diagram of the smart gas pipeline network particulate matter safety monitoring Internet of Things system according to some embodiments of the present specification;

[0010] Figure 2 is an example flowchart of a method for monitoring particulate matter safety of a smart gas pipeline network according to some embodiments of the present specification;

[0011] Figure 3 is an example flowchart of determining a pipeline to be inspected according to some embodiments of the present specification;

[0012] Figure 4 is an example schematic diagram of a particulate matter model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings required to be used in the embodiment description will be briefly introduced as follows. The drawings do not represent all the embodiments.

[0014] In the embodiments of the present specification, when the operations performed in steps are described, the order of the steps is exchangeable unless otherwise specified, the steps can be omitted, and other steps can be included in the operation process.

[0015] Figure 1 is a schematic diagram of a platform structure of an Internet of Things system for monitoring particulate matter safety of a smart gas pipeline network according to some embodiments of the present specification.

[0016] In some embodiments, as shown in Figure 1 , the Internet of Things system for monitoring particulate matter safety of a smart gas pipeline network 100 can include a government regulatory object platform 110, a gas company sensor network platform 120, and a gas equipment object platform 130.

[0017] The government regulatory object platform refers to a platform for generating government regulatory information and executing control information. In some embodiments, the government regulatory object platform includes a gas company management platform 111.

[0018] The gas company management platform refers to a comprehensive management platform for gas company information. In some embodiments, the gas company management platform is configured to process and store data of the Internet of Things system for monitoring particulate matter safety of a smart gas pipeline network 100. The gas company management platform includes a processor and a storage device, etc. The processor includes a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), a graphics processor (GPU), etc. or any combination thereof.

[0019] The gas company sensor network platform refers to a platform for comprehensively managing sensor information of a gas company. In some embodiments, the gas company sensor network platform is configured as a communication network or a gateway, etc. The gas company sensor network platform interacts with the gas company management platform and the gas equipment object platform.

[0020] The gas equipment object platform refers to a functional platform for generating sensing information and executing control information. In some embodiments, the gas equipment object platform includes a monitoring device and a pipeline auxiliary equipment, etc. The pipeline auxiliary equipment includes at least one of a filter, a pressure regulating cabinet, and a flow rate regulating valve, etc.

[0021] The monitoring device refers to a device for monitoring the concentration of particulate matter mixed in the gas, such as a particulate matter monitor, etc.

[0022] The filter is used to filter particulate matter in the gas. The pressure regulating cabinet is used to control the pressure of the gas in the gas pipeline. The flow rate regulating valve is used to control the flow rate of the gas in the gas pipeline.

[0023] In some embodiments, two channels are included in the filter, one is a filtering channel containing a filter element, and the other is a non-blocking channel without a filter element. The filter opening refers to opening the filtering channel and closing the non-blocking channel. The filter closing refers to closing the filtering channel and opening the non-blocking channel. The opening and closing state of the filter can be represented by a numerical value, etc., for example, 0 represents the filter closing, and 1 represents the filter opening.

[0024] In some embodiments, the monitoring device, the filter, the pressure regulating cabinet, and the flow rate regulating valve, etc. pipeline auxiliary equipment are deployed at the preset equipment site of the gas pipeline network. The preset equipment site is set in advance by the gas company personnel, for example, the common starting point of multiple downstream pipelines, the outlet of the gas gate station and / or the pressure regulating station, etc. The gas pipeline network refers to the pipeline network for transporting gas.

[0025] For detailed description of the foregoing, please refer to the related description of Figures 2 to 4 .

[0026] In some embodiments of the present specification, based on the intelligent gas pipeline network particulate matter safety monitoring Internet of Things system 100, an information running closed loop can be formed between each functional platform, coordinated and regularly run, and the informatization and intelligentization of gas pipeline particulate matter monitoring can be realized.

[0027] Figure 2 is an exemplary flowchart of the intelligent gas pipeline network particulate matter safety monitoring method according to some embodiments of the present specification. In some embodiments, the intelligent gas pipeline network particulate matter safety monitoring method flow 200 can be executed by the gas company management platform (hereinafter referred to as the company management platform) in the intelligent gas pipeline network particulate matter safety monitoring Internet of Things system. As Figure 2 shown, the intelligent gas pipeline network particulate matter safety monitoring method flow 200 includes the following steps:

[0028] Step 210, acquiring the concentration data of particulate matter of at least one pipeline area from the monitoring device of the gas equipment object platform through the gas company sensing network platform.

[0029] For details of the platforms of the smart gas pipeline network particulate matter safety monitoring Internet of Things system and the monitoring devices, see Figure 1 and the related description.

[0030] A pipeline area refers to an area in the gas pipeline network that contains at least one pipeline. In some embodiments, the company management platform divides one or more pipelines between two monitoring devices into one pipeline area.

[0031] In some embodiments, the company management platform pre-numbers all the pipelines in the gas pipeline network, and represents different pipeline areas by different sets of pipeline numbers in different pipeline areas.

[0032] Concentration data refers to data related to the concentration of particulate matter in gas. Concentration data is represented by numerical values and the like, and the unit of concentration data is milligrams per cubic meter. Particulate matter refers to particulate matter mixed in gas. Particulate matter includes at least one of rock particles, ferrous sulfide, etc.

[0033] In some embodiments, the company management platform obtains concentration data from the monitoring devices of the gas equipment object platform via the gas company sensing network platform. The monitoring devices collect concentration data based on collection parameters and the like and upload it to the gas company sensing network platform. For details of the collection parameters, see the related description of step 270.

[0034] In some embodiments, the particulate matter concentration of a pipeline area is represented by the average of the concentration data collected by the monitoring devices at both ends of the pipeline area.

[0035] Step 220: Based on the concentration data, generate the concentration level of at least one pipeline area, and generate a concentration level marker in the preset display system.

[0036] Concentration level refers to a level that characterizes the size of concentration data. For example, the higher the concentration level, the larger the concentration data, and the higher the particulate matter concentration of the corresponding pipeline area.

[0037] In some embodiments, the company management platform generates the concentration level of at least one pipeline area based on the concentration data. For example, the company management platform queries the preset level table for the reference concentration interval containing the concentration data based on the concentration data of the pipeline area, and takes the reference concentration level corresponding to the reference concentration interval as the concentration level of the pipeline area.

[0038] The preset level table is pre-set based on historical data, including a reference concentration interval of a preset number of levels and a reference concentration level corresponding to each reference concentration interval.

[0039] In some embodiments, the company management platform obtains a plurality of historical concentration data in the historical data, divides an interval between 0 and a maximum value of the plurality of historical concentration data into a plurality of concentration intervals, and calculates a frequency ratio of each concentration interval. The plurality of concentration intervals are merged based on a merging rule to obtain a preset number of reference concentration intervals. The number of concentration intervals and the preset number of levels are pre-set based on historical experience. The frequency ratio refers to a ratio of the number of occurrences of the plurality of historical concentration data in the concentration interval to the total number of historical concentration data.

[0040] The merging rule refers to a rule for merging concentration intervals. In some embodiments, the merging rule includes merging concentration intervals with the same frequency ratio into one reference concentration interval in order of concentration intervals from small to large based on the frequency ratio. For example, there are 50 concentration intervals. The company management platform screens them in order of concentration intervals from small to large. If the concentration intervals with a frequency ratio less than 0.05 are ranked 0 to 30, the company management platform divides the concentration intervals ranked 0 to 30 into reference concentration intervals corresponding to the reference concentration level 0. If the concentration intervals with a frequency ratio less than 0.1 and greater than 0.05 are ranked 31 to 35, the company management platform divides the concentration intervals ranked 31 to 35 into reference concentration intervals corresponding to the reference concentration level 1. Similarly, a preset number of reference concentration intervals and corresponding reference concentration levels are obtained. The frequency ratio (such as 0.05) for dividing a plurality of concentration intervals into a reference interval is pre-set by the user based on historical experience.

[0041] In some embodiments, the preset number of levels is determined by manual annotation or company management platform evaluation, etc. For example, the smart gas pipe network particulate matter safety monitoring Internet of Things system randomly generates different numbers of levels, and performs trial operation based on different numbers of levels. The effect of each trial operation is evaluated by manual annotation or company management platform, and the number of levels corresponding to the best trial operation effect is determined as the preset number of levels. The best trial operation effect includes at least one of the lowest failure rate of the gas pipe network during the trial operation, the highest hidden danger detection rate of the gas pipe network, and the lowest hardware operation load of the gas pipe network.

[0042] The preset display system refers to a system with the functions of displaying the gas pipe network and marking, etc. In some embodiments, the preset display system includes a gas GIS (Geographic Information System) system, etc. The preset display system is used to display the gas pipe network, gas gate stations, pressure regulating stations, etc. in the gas pipe network, and mark and display the pipelines, etc. The marking in the preset display system can include at least one of digital marking, color marking, and highlight marking, etc.

[0043] The concentration level mark refers to a mark indicating the concentration level of a pipeline area. In some embodiments, in response to the company management platform determining the concentration level of at least one pipeline area, the preset display system displays the concentration level mark on the corresponding pipeline area in the displayed gas pipeline network.

[0044] In step 230, a concentration level difference value is determined based on the concentration levels of the at least one pipeline area.

[0045] The concentration level difference value refers to a value used to represent the difference in concentration level between adjacent pipeline areas. The adjacent pipeline areas include an upstream pipeline area and a downstream pipeline area.

[0046] In some embodiments, the concentration level difference value of the adjacent pipeline areas is represented by the difference between the concentration level of the downstream pipeline area and the concentration level of the upstream pipeline area. For each group of adjacent pipeline areas, the company management platform calculates the difference between the concentration level of the downstream pipeline area and the concentration level of the upstream pipeline area, and confirms the difference as the concentration level difference value of the adjacent pipeline areas.

[0047] In some embodiments, if the downstream pipeline area corresponds to multiple upstream pipeline areas, the company management platform calculates the difference between the concentration level of the downstream pipeline area and the concentration level of each of the multiple upstream pipeline areas, and takes the maximum value among the multiple differences as the concentration level difference value of the adjacent pipeline areas.

[0048] In step 240, a pipeline to be inspected is determined based on the concentration level difference value, and a pipeline to be inspected mark is generated in the preset display system.

[0049] The pipeline to be inspected refers to a pipeline that needs to be inspected.

[0050] In some embodiments, the company management platform determines the pipeline to be inspected in multiple ways. For example, the company management platform screens the adjacent pipeline areas whose concentration level difference values are not less than a first difference threshold value, and determines the pipelines in the downstream pipeline area of the adjacent pipeline areas as the pipeline to be inspected. The first difference threshold value is pre-set based on historical experience.

[0051] In some embodiments, the company management platform adjusts the first difference threshold value based on the execution result of the pipeline inspection work order. For example, the company management platform counts the number of negative results in the execution result, calculates the ratio of the number of negative results to the total number of execution results, and if the obtained ratio is less than an adjustment threshold value, the first difference threshold value is increased. The adjustment threshold value is pre-set based on historical experience. For the description of the execution result of the pipeline inspection work order, see step 270 and the related description.

[0052] In some embodiments, the company management platform determines the pipeline to be inspected based on the source confidence distribution. For details, see Figure 3 and the related description.

[0053] The to-be-inspected pipeline marker refers to a marker indicating the to-be-inspected pipeline.

[0054] In some embodiments, in response to the company management platform determining the to-be-inspected pipeline, the preset display system displays the to-be-inspected pipeline marker on the corresponding to-be-inspected pipeline in the displayed gas pipeline network.

[0055] Step 250: generating a pipeline inspection instruction based on the to-be-inspected pipeline.

[0056] The pipeline inspection instruction refers to a control instruction indicating the generation of a pipeline inspection work order.

[0057] In some embodiments, the company management platform generates the pipeline inspection instruction based on the to-be-inspected pipeline. For example, the company management platform generates the pipeline inspection instruction based on the number of the to-be-inspected pipeline and the concentration level difference.

[0058] Step 260: generating a pipeline inspection work order based on the pipeline inspection instruction.

[0059] The pipeline inspection work order refers to a work order for assigning a pipeline inspection task. In some embodiments, the pipeline inspection work order includes the number of the to-be-inspected pipeline and the pipeline inspection task to be performed, etc. The pipeline inspection task includes at least one of checking the thickness of the pipeline attachment, checking the aging condition of the pipeline, and maintaining the filter, etc.

[0060] In some embodiments, the company management platform generates the pipeline inspection work order based on the pipeline inspection instruction. For example, the company management platform queries the pipeline inspection task corresponding to the concentration level difference in the task reference table based on the pipeline inspection instruction, and generates the pipeline inspection work order based on the number of the to-be-inspected pipeline and the determined pipeline inspection task. The task reference table is pre-set based on historical experience and includes a plurality of concentration level differences and the pipeline inspection task corresponding to each concentration level difference.

[0061] In some embodiments, the company management platform sends the pipeline inspection work order to the terminal device of the pipeline maintenance personnel through wireless transmission or the like.

[0062] Step 270: based on the execution result of the pipeline inspection work order and / or the concentration level difference, adjusting the operating parameter of the pipeline accessory equipment of at least one pipeline area through the gas equipment object platform.

[0063] For the description of the pipeline accessory equipment, see Figure 1 and the related description.

[0064] The execution result of the pipeline inspection work order refers to the result of the pipeline inspection by the pipeline maintenance personnel based on the pipeline inspection work order. The execution result includes negative results and positive results. The negative results include the need to clean the pipeline, etc. The positive results include that the pipeline is normal, etc.

[0065] In some embodiments, the pipe network maintenance personnel uploads the execution result to the company management platform through the terminal device.

[0066] The operation parameter refers to a parameter related to the operation of the pipe auxiliary device. For example, at least one of whether a filter is turned on, a gas pressure adjusted by a pressure regulating cabinet, a gas flow rate limited by a flow rate regulating valve, and the like.

[0067] In some embodiments, the company management platform controls, through the gas equipment object platform, the operation parameter of the pipe auxiliary device of at least one pipe region based on the execution result of the pipe inspection work order and / or the concentration level difference. For example, when the inspection result is a negative result, the company management platform controls, through the gas equipment object platform, the filter of the pipe region upstream of the pipe to be inspected to be turned on, and controls the filter to be turned on when the cleaning of the pipe is completed. For another example, in response to the concentration level difference being greater than a second difference threshold value, the company management platform turns on the filter of the pipe region upstream of the pipe to be inspected in advance. The second difference threshold value is set in advance based on historical experience.

[0068] In some embodiments, the company management platform obtains, through the preset display system, a mark of at least one pipe region, and sets the collection parameter of the monitoring device based on the mark.

[0069] In some embodiments, the company management platform obtains, through the preset display system, a mark of at least one pipe region. The mark includes a concentration level mark, a pipe to be inspected mark, and a key pipe mark. For the key pipe mark, see the description thereof and the related description. Figure 3

[0070] In some embodiments, the company management platform determines the monitoring priority of at least one pipe region based on the mark. The monitoring priority is used to represent the priority of obtaining the concentration data.

[0071] In some embodiments, the detection priority of the pipe region corresponding to different marks is different. For example, the monitoring priority of the pipe region corresponding to the pipe to be inspected mark is greater than the monitoring priority of the pipe region corresponding to the key pipe mark, and the monitoring priority of the pipe region corresponding to the key pipe mark is greater than the monitoring priority of other pipes. The other pipes refer to the pipes in the pipe network except the pipe to be inspected and the key pipe.

[0072] In some embodiments of the present specification, by dividing the monitoring priority of different pipe regions, the pipe region which needs to obtain the concentration data more urgently can be determined, and more targeted particulate matter monitoring can be realized.

[0073] ​The collection parameter of the monitoring device refers to a parameter used to instruct the monitoring device to perform data collection. In some embodiments, the collection parameter includes a collection period and a collection time, etc. The collection period refers to the time interval at which the monitoring device collects data each time. The collection time refers to the time used by the monitoring device to collect data each time.

[0074] In some embodiments, the company management platform sets the collection parameter of the monitoring device in multiple ways. For example, the company management platform counts the concentration data of each pipeline area, sorts the concentration data according to the concentration data, and determines the collection parameter of the monitoring device corresponding to the pipeline area based on the sorting. Among them, the earlier the concentration data in the sorting, the shorter the collection period of the monitoring device corresponding to the concentration data, and the longer the collection time.

[0075] In some embodiments, the company management platform sets the collection parameter of the monitoring device based on the label. For example, the company management platform determines the monitoring priority of the pipeline area based on the label, sorts the multiple pipeline areas corresponding to each monitoring priority according to the concentration data, and determines the collection parameter of the monitoring device corresponding to the pipeline area based on the maximum data processing capacity and the minimum confirmation data volume, according to the sorting of the monitoring priority and the sorting of the multiple pipeline areas corresponding to each monitoring priority, until the company management platform reaches the maximum data processing capacity.

[0076] The maximum data processing capacity refers to the maximum data volume that the company management platform can process within a unit time without affecting the operation of the gas. The unit time includes 1 second, etc. The minimum confirmation data volume refers to the minimum data volume required to determine the collection parameter of a monitoring device.

[0077] The minimum confirmation data volume is determined based on historical data. For example, the company management platform screens the historical similar data in the historical data (such as the similar pipeline area to the current pipeline area and the particulate matter concentration, gas flow rate, and gas pressure of the similar pipeline area, etc.), and if the ratio of the number of historical similar data in which the particulate matter source is consistent with the actual detection result to the total number of historical similar data is greater than the proportion threshold, the average value of the data volume required to determine the collection parameter in this batch of historical similar data is taken as the minimum confirmation data volume. The proportion threshold is set based on historical experience in advance.

[0078] In some embodiments, the company management platform constructs a region feature vector based on a region feature of a current pipeline region, constructs a historical feature vector based on a historical region feature of a historical pipeline region in historical data, matches the region feature vector with the historical feature vector, selects a historical feature vector satisfying a matching condition, and takes a pipeline region corresponding to the historical feature vector and data such as particulate matter concentration, gas flow rate, and gas pressure of the pipeline region as historical similar data. The region feature includes the size of the pipeline region, the number of pipelines contained, and the like. The region feature is obtained through a preset display system.

[0079] In some embodiments of the present specification, by distinguishing the monitoring priorities of different pipeline regions, some pipeline regions prone to hazards caused by particulate matter concentration can be focused on and processed, thereby improving the efficiency of gas pipeline network operation and maintenance.

[0080] In some embodiments of the present specification, by the concentration level difference of adjacent pipeline regions, the pipeline to be inspected can be quickly determined, and the concentration level of particulate matter in the pipeline can be visually displayed, thereby improving the efficiency of particulate matter concentration monitoring. Meanwhile, a pipeline inspection work order is generated based on the pipeline to be inspected, and the pipeline to be inspected is inspected in a timely manner, so that a quick response can be made when the concentration data in the gas pipeline is abnormal, thereby ensuring the efficiency of gas pipeline transportation.

[0081] Figure 3 is an exemplary flowchart for determining a pipeline to be inspected according to some embodiments of the present specification. In some embodiments, the flowchart 300 for determining a pipeline to be inspected can be executed by a company management platform. As shown in Figure 3 The flowchart 300 for determining a pipeline to be inspected includes the following steps:

[0082] In some embodiments, the company management platform generates an estimated concentration level of at least one pipeline region based on first concentration data, determines a key monitoring pipeline based on the estimated concentration level, generates a source confidence distribution based on second concentration data and a concentration level difference corresponding to the second concentration data, and determines a pipeline to be inspected based on the source confidence distribution.

[0083] Step 310: generating an estimated concentration level of at least one pipeline region based on first concentration data.

[0084] The first concentration data refers to concentration data at a first time point. In some embodiments, the first concentration data includes particulate matter concentration data of at least one pipeline region at a first time point.

[0085] The first time point refers to a time point before the current time point at which the monitoring device last collected concentration data. The first time point corresponding to each pipeline region is the same or different.

[0086] In some embodiments, the company management platform obtains the first concentration data from historical concentration data. The historical concentration data is concentration data in historical data. The company management platform obtains the historical concentration data from the storage device, and takes concentration data of at least one pipeline area at the first time point in the historical concentration data as the first concentration data.

[0087] The estimated concentration level refers to an estimated concentration level of the pipeline area. For the concentration level, refer to the description of step 220.

[0088] In some embodiments, the company management platform determines the estimated concentration level in multiple ways. For example, for each pipeline area, the company management platform calculates the product of the first concentration data of the pipeline area and the pollution value ratio, determines the obtained product as the estimated concentration of the pipeline area, and determines the concentration level corresponding to the estimated concentration as the estimated concentration level through the method of determining the concentration level based on the concentration data in step 220 and querying the preset level table.

[0089] The pollution value ratio refers to the ratio of the gas pollution value of the gas transported by the pipeline area at the current time point to the gas pollution value at the first time point.

[0090] The gas pollution value refers to data related to the degree of pollution of the gas. In some embodiments, the gas pollution value is related to the concentration data of the outbound gas, such as the gas pollution value being positively related to the concentration data of the outbound gas. For example, the company management platform calculates the gas pollution value by the following formula (1):

[0091] (1)

[0092] Wherein, is the gas pollution value, is the concentration data of the outbound gas. The outbound gas refers to the gas at the outlet of the gas gate station or pressure regulating station upstream of the pipeline area. The concentration data of the outbound gas is obtained by the monitoring device deployed at the outlet of the gas gate station or pressure regulating station.

[0093] In some embodiments, the company management platform generates the estimated concentration level of at least one pipeline area by the particulate matter model. For details, refer to the description of Figure 4 and the related description.

[0094] In some embodiments, the first concentration data further includes concentration sequence data of particulate matter of at least one pipeline area at a plurality of third time points. The company management platform generates concentration variation amplitudes of at least one pipeline area at a plurality of third time points based on the concentration sequence data, and generates the estimated concentration level of at least one pipeline area based on the concentration variation amplitudes.

[0095] The third time point refers to one of a plurality of historical time points before the current time point. In some embodiments, the plurality of third time points and the number of third time points are pre-set based on historical experience, and the last time point in the plurality of third time points is the first time point. The third time points of different pipeline regions are the same or different.

[0096] In some embodiments, the company management platform determines a starting time point of the third time point based on a plurality of manners. The starting time point refers to the first time point with the earliest time in the plurality of third time points. For example, if there is a filter in the upstream pipeline region within the preset neighborhood degree of the current pipeline region, the time point of the last adjustment of the filter is taken as the starting time point. The neighborhood degree is used to represent the number of pipeline regions or the number of pipelines between two pipeline regions or pipelines. The preset neighborhood degree is pre-set based on historical experience.

[0097] For another example, if there is no filter in the upstream pipeline region within the preset neighborhood degree of the current pipeline region, the concentration mutation point in the historical time is taken as the starting time point or the starting time point is pre-set by the user. The concentration mutation point refers to the time point at which the direction of the change amplitude of the concentration data changes (such as rising or falling).

[0098] The concentration sequence data refers to a sequence composed of concentration data corresponding to the plurality of third time points. In some embodiments, the concentration data in the concentration sequence data can be arranged in chronological order.

[0099] The concentration change amplitude refers to the change amplitude of the concentration data in the concentration sequence data. In some embodiments, the concentration change amplitude includes a plurality of data, each data corresponding to the change amplitude of the concentration data of one third time point and the previous third time point or the reference time point. The reference time point can be the third time point ranked first (the earliest time) in the concentration sequence data.

[0100] In some embodiments, the company management platform calculates the change amplitude of the concentration data of the third time point and the previous third time point or the reference time point based on the concentration sequence data. The change amplitude is represented by the ratio between the third time point and the previous third time point or the reference time point.

[0101] In some embodiments, the company management platform determines the estimated concentration based on the concentration change amplitude, and generates the estimated concentration level of at least one pipeline region based on the estimated concentration. For example, the company management platform determines the estimated concentration based on the concentration change amplitude by the following formula (2):

[0102] (2)

[0103] Wherein, is the estimated concentration, is the average value of the plurality of data in the concentration variation amplitude. is the average value of the plurality of data in the concentration variation amplitude.

[0104] In some embodiments, the company management platform determines the estimated concentration level based on the estimated concentration by the method of determining the concentration level in step 220.

[0105] In some embodiments of the present specification, the estimated concentration level is determined according to the variation amplitude of the concentration data at a plurality of third time points, which can take into account the variation of the concentration data and improve the accuracy of determining the estimated concentration level.

[0106] In some embodiments, the company management platform issues an adjustment instruction to the gas equipment object platform based on the concentration variation amplitude to regulate the operating parameters. For a description of the operating parameters, see the related description of step 260.

[0107] The adjustment instruction refers to a control instruction for adjusting the operating parameters. In some embodiments, the adjustment instruction includes changing the parameters of the flow rate regulating valve to adjust the flow rate of the gas.

[0108] In some embodiments, the adjusted gas flow rate is related to the average value of the plurality of data in the concentration variation amplitude, for example, the adjusted gas flow rate is negatively related to the average value of the plurality of data in the concentration variation amplitude. For example, the company management platform determines the adjusted gas flow rate by the following formula (3):

[0109] (3)

[0110] wherein, is the adjusted gas flow rate of the pipeline area, is the gas flow rate of the pipeline area before adjustment, is the average value of the plurality of data in the concentration variation amplitude corresponding to the pipeline area.

[0111] In some embodiments, the adjusted gas flow rate can also be related to the source confidence distribution. For the content of the source confidence distribution, see step 330.

[0112] In some embodiments, in response to the particulate matter source of the current pipeline area being the most upstream associated upstream pipeline, the company management platform adjusts the gas flow rate of the associated upstream pipeline based on the source confidence distribution. For example, the company management platform determines the adjusted gas flow rate of the associated upstream pipeline by formula (4):

[0113] (4)

[0114] wherein, is the adjusted gas flow rate of the associated upstream pipeline, is the gas flow rate of the associated upstream pipeline before adjustment, is an average of a plurality of data in the concentration variation amplitude corresponding to the pipeline region, is a confidence of the particulate matter source. For the description of the associated upstream pipeline of the most upstream, see step 330.

[0115] In some embodiments of the present specification, since the gas flow rate also affects the concentration data in the pipeline region, the change of the concentration data is determined according to the concentration variation amplitude, so as to adjust the gas flow rate of the pipeline region to avoid more and more particulate matter accumulation in the pipeline region. At the same time, in combination with the source confidence distribution, the gas flow rate of each pipeline region is adjusted to avoid affecting the stability of the entire gas pipeline network when adjusting the gas flow rate.

[0116] Step 320, based on the estimated concentration level, determine the key monitoring pipeline, and generate key pipeline markers in the preset display system.

[0117] The key monitoring pipeline refers to the pipeline that needs to be monitored.

[0118] In some embodiments, the company management platform determines the key monitoring pipeline based on the estimated concentration level of the pipeline region through various ways. For example, the company management platform can determine the pipeline in the pipeline region with an estimated concentration level greater than or equal to the level threshold as the key monitoring pipeline.

[0119] In some embodiments, the company management platform counts the historical concentration level corresponding to the pipeline region with negative results or the operating parameters of the pipeline accessory equipment that need to be regulated in the execution results in the historical data, and confirms the minimum value in the historical concentration level as the level threshold.

[0120] In some embodiments, the company management platform calculates the difference between the estimated concentration level and the actual concentration level of the pipeline region at the first time point based on the estimated concentration level of the pipeline region and the actual concentration level of the pipeline region at the first time point, and determines the pipeline in the pipeline region with a difference not less than the first difference threshold as the key monitoring pipeline. The actual concentration level of the pipeline region at the first time point is obtained through historical data. For the description of the first difference threshold, see step 240 and the related description.

[0121] The key pipeline marker refers to a marker indicating the key monitoring pipeline.

[0122] In some embodiments, in response to the company management platform determining the key monitoring pipeline, the preset display system displays the key pipeline marker on the corresponding key monitoring pipeline in the displayed gas pipeline network. For more description of the preset display system, see Figure 2 and the related description.

[0123] Step 330, based on the second concentration data and the concentration level difference corresponding to the second concentration data, generate a source confidence distribution.

[0124] The second concentration data refers to the concentration data of the second time point.

[0125] In some embodiments, the second concentration data comprises the concentration data of the particulate matter of the key monitoring pipeline at a plurality of second time points.

[0126] The plurality of second time points refers to a plurality of future time points after the current time point. In some embodiments, the plurality of second time points of each pipeline region is the same or different. The plurality of second time points is pre-set based on historical experience.

[0127] In some embodiments, the second concentration data is obtained by the monitoring device corresponding to the key monitoring pipeline. After the company management platform determines the key monitoring pipeline, each second time point is taken as a time point for collecting concentration data.

[0128] The source confidence distribution refers to data for characterizing the source of particulate matter of the gas in at least one pipeline region and the confidence of the source of particulate matter. In some embodiments, the source confidence distribution is represented by a sequence or the like, and a sequence comprises a pipeline region and the source of particulate matter of the gas in the pipeline region and the confidence of the source of particulate matter. The source of particulate matter includes particulate matter from the gas itself and / or from the pipeline. Wherein, the pipeline region in the sequence is represented by numbering or the like. The particulate matter from the gas itself refers to the particulate matter that is self-brought by the gas when the gas is output from the gas gate station, pressure regulating station or the like. The particulate matter from the pipeline refers to the particulate matter generated when the gas is transported from the upstream pipeline to the downstream pipeline.

[0129] In some embodiments, the company management platform generates the source confidence distribution based on the second concentration data and the concentration level difference corresponding to the second concentration data. For example, the company management platform determines the associated pipeline group of the key monitoring pipeline based on the second concentration data and the concentration level difference corresponding to the second concentration data, determines the source of particulate matter of the associated pipeline group, and determines the source confidence distribution based on the source of particulate matter of the associated pipeline group.

[0130] The concentration level difference corresponding to the second concentration data refers to the difference between the concentration level of the key monitoring pipeline and the concentration level of the upstream pipeline of the key monitoring pipeline. The company management platform determines the concentration level of the key monitoring pipeline by the method for determining the concentration level in step 220 based on the mean value or the median value of the second concentration data or the like. The company management platform determines the concentration level of the upstream pipeline by the method for determining the concentration level in step 220 based on the concentration data corresponding to the upstream pipeline.

[0131] The associated pipeline group refers to a set of multiple pipelines that have an upstream association. In some embodiments, the company management platform determines the associated pipeline group by multiple methods. For example, the key monitoring pipeline is taken as an associated pipeline group, and the associated upstream pipelines of the key monitoring pipeline are added to the associated pipeline group in which the key monitoring pipeline is located. The associated upstream pipeline refers to an upstream pipeline whose concentration level difference corresponding to the second concentration data is not greater than the first difference threshold. For the description of the first difference threshold, see Figure 2 and the related description.

[0132] In some embodiments, if the associated upstream pipeline also has an upstream pipeline, and the concentration level difference between the associated upstream pipeline and its upstream pipeline is not greater than the first difference threshold, the company management platform adds the upstream pipeline of the associated upstream pipeline to the associated pipeline group as an associated upstream pipeline. In this way, an associated pipeline group including the key monitoring pipeline and multiple associated upstream pipelines is obtained. If the concentration level difference between the associated upstream pipeline and its upstream pipeline is greater than the first difference threshold, the upstream pipeline of the associated upstream pipeline is no longer added to the associated pipeline group as an associated upstream pipeline, and the determination is stopped.

[0133] In some embodiments, if the most upstream associated upstream pipeline in the associated pipeline group still has an upstream pipeline, the company management platform determines the particulate matter source of the associated pipeline group as coming from the most upstream associated upstream pipeline in the associated pipeline group, and calculates the confidence of the particulate matter source. The confidence is used to represent the reliability of the particulate matter source. The confidence is related to the concentration data of the pipelines in the associated pipeline group. In some embodiments, the company management platform calculates the confidence of the particulate matter source by the following formula (5):

[0134] (5)

[0135] wherein, is the confidence, is the concentration data of the most upstream associated upstream pipeline in the associated pipeline group, is the average value of the concentration data of all pipelines in the associated pipeline group. The most upstream associated upstream pipeline refers to the first pipeline in the associated upstream pipelines of the associated pipeline group in the order of the gas delivery direction.

[0136] In some embodiments, if the most upstream associated upstream pipeline in the associated pipeline group does not have an upstream pipeline, the company management platform determines the particulate matter source of the associated pipeline group as the gas itself.

[0137] In some embodiments, the source confidence distribution is also related to the gas flow rate of the key monitoring pipeline.

[0138] In some embodiments, the company management platform calculates a plurality of correlation values of the key monitoring pipeline, determines that the key monitoring pipeline is a correlation pipeline group if the correlation values of the key monitoring pipeline are similar, calculates a plurality of correlation values of an upstream pipeline of the key monitoring pipeline, and adds the upstream pipeline to the correlation pipeline group if the correlation values of the upstream pipeline are similar. In this way, a correlation pipeline group is obtained until the upstream pipeline does not satisfy the condition of similar correlation values or there is no upstream pipeline.

[0139] The correlation value refers to the ratio of the concentration data of the pipeline at a single second time point to the flow rate of the gas at the second time point. The similar correlation values refer to the difference between any two correlation values in the plurality of correlation values being less than a correlation value threshold. The correlation value threshold is pre-set based on historical experience. The flow rate of the gas is obtained through a flow rate regulating valve. For a description of the flow rate regulating valve, see Figure 1 and related descriptions.

[0140] In some embodiments, if the upstream pipeline of the correlation pipeline group does not satisfy the condition of similar correlation values, the company management platform determines that the source of particulate matter is the upstream pipeline. If the correlation pipeline group has no upstream pipeline, the company management platform determines that the gas is self-borne.

[0141] In some embodiments, the company management platform determines the confidence degree that the source of particulate matter is the upstream pipeline based on the plurality of correlation values of the upstream pipeline and the plurality of correlation values of all pipelines in the correlation pipeline group. In some embodiments, the company management platform calculates the confidence degree that the source of particulate matter is the upstream pipeline through the following formula (6):

[0142] (6)

[0143] Wherein, is the confidence degree that the source of particulate matter is the upstream pipeline, is the average value of the plurality of correlation values of the upstream pipeline, is the average value of the correlation values of all pipelines in the correlation pipeline group.

[0144] In some embodiments of the present specification, the flow rate of the gas can affect the concentration data of the particulate matter, so considering the flow rate of the gas when determining the source confidence distribution can improve the accuracy of the source confidence distribution, which is conducive to subsequent accurate determination of the to-be-inspected pipeline.

[0145] Step 340, based on the source confidence distribution, determining the to-be-inspected pipeline, and generating a to-be-inspected pipeline marker in a preset display system.

[0146] In some embodiments, the company management platform selects the associated pipeline group with a confidence greater than a confidence threshold, confirms the most upstream associated upstream pipeline in the associated pipeline group as the to-be-inspected pipeline, and generates a to-be-inspected pipeline mark in a preset display system. The confidence threshold is pre-set based on historical experience. For descriptions of the preset display system and the to-be-inspected pipeline mark, see Figure 1 and related descriptions.

[0147] In some embodiments, if the confidence of the particle source is greater than the confidence threshold, the company management platform confirms the upstream pipeline as the to-be-inspected pipeline.

[0148] It can be understood that if the pipeline upstream is the first pipeline connected to the gas gate station or the pressure regulating station, the particles in the gas are generated by the gas gate station or the pressure regulating station, and are processed by the control system of the gas gate station or the pressure regulating station.

[0149] In some embodiments of the present specification, by using the first concentration data to estimate the estimated concentration level of different pipeline areas, the pre-control of the gas pipeline network can be realized, the key monitoring pipeline with high particle concentration can be reasonably determined, the accuracy of determining the to-be-inspected pipeline can be improved, and then the to-be-inspected pipeline can be timely inspected, and the gas hidden danger can be prevented in advance. At the same time, by using the second concentration data to determine the source confidence distribution, the key monitoring pipeline with high confidence can be determined as the to-be-inspected pipeline, the information processing amount of the company management platform can be reduced, the data processing efficiency can be improved, and then the accuracy of determining the to-be-inspected pipeline can be improved.

[0150] It should be noted that the above description of the intelligent gas pipeline network particle safety monitoring method process 200 and the process 300 for determining the to-be-inspected pipeline is only for example and illustration, and does not limit the scope of the present specification. Those skilled in the art can make various modifications and changes to the intelligent gas pipeline network particle safety monitoring method process 200 and the process 300 for determining the to-be-inspected pipeline under the guidance of the present specification. However, these modifications and changes are still within the scope of the present specification.

[0151] In some embodiments, the company management platform determines the position of the newly added equipment based on the source confidence distribution, and adjusts the operating parameters of the gas equipment object platform based on the source confidence distribution.

[0152] The newly added equipment refers to the newly added pipeline auxiliary equipment. The newly added equipment includes filters or monitoring equipment, etc. The position of the newly added equipment refers to the installation position of the newly added pipeline auxiliary equipment.

[0153] In some embodiments, the company management platform determines the new device location in multiple ways based on the source confidence distribution. For example, in response to the particulate source of the associated pipeline group being the most upstream associated upstream pipeline in the associated pipeline group and the confidence of the particulate source being greater than the confidence threshold, the company management platform confirms that the new device location is the end point of the most upstream associated upstream pipeline. For another example, in response to the particulate source of the associated pipeline group being gas self-borne, the company management platform confirms that the new device location is the start point of the key monitoring pipeline without a filter installed.

[0154] The installation work order refers to a work order for allocating installation of the new device. In some embodiments, the installation work order includes the new device location, etc. In some embodiments, the company management platform generates the installation work order based on the new device location and sends it to the pipeline maintenance personnel to enable the pipeline maintenance personnel to perform installation of the new device.

[0155] In some embodiments, the company management platform dynamically regulates the operating parameters through the gas equipment object platform based on the source confidence distribution. For example, in response to the particulate source of the associated pipeline group being the most upstream associated upstream pipeline in the associated pipeline group and the confidence of the particulate source being greater than the confidence threshold, the company management platform controls, through the gas equipment object platform, the filters of all downstream pipeline regions corresponding to the associated upstream pipeline to be turned on and turned off when the maintenance cleaning of the associated upstream pipeline is completed. Among the all downstream pipeline regions corresponding to the associated upstream pipeline, only some of the downstream pipeline regions are provided with filters.

[0156] For another example, in response to the particulate source of the associated pipeline group being gas self-borne, the company management platform queries, based on the pressure regulation requirement, the pressure influence table for the number of filters corresponding to the associated pipeline group that can meet the number of filters to be turned on to meet the pressure regulation requirement. The pressure regulation requirement is pre-set based on historical data, for example, the pressure regulation requirement is the gas pressure in the pipeline during normal operation of the gas pipeline network. Since turning on the filter will affect the gas pressure in the pipeline, the pressure regulation requirement can be represented by the gas pressure. The multiple filters corresponding to the associated pipeline group refer to the filters of all downstream pipeline regions corresponding to the associated upstream pipeline.

[0157] In some embodiments, the company management platform preferentially turns on the filters in the upstream pipeline among the multiple filters corresponding to the associated pipeline group until the number of filters to be turned on is met.

[0158] The pressure influence table is pre-set based on historical data and includes multiple numbers of filters to be turned on and the corresponding drop in gas pressure in the pipeline. The company management platform takes the number of filters to be turned on and the drop in gas pressure in the pipeline in a single filter turning-on operation in the historical data as a piece of data and adds it to the pressure influence table. The gas pressure is obtained through the pressure regulating cabinet. For a description of the pressure regulating cabinet, see Figure 1and related descriptions.

[0159] In some embodiments of the present specification, when the existing filter cannot meet the filtering requirement, a new filter is added in the pipeline to improve the filtering effect. Considering that the filter filtering will affect the gas pressure, the number of filters is dynamically controlled according to the actual demand, so as to ensure the filtering effect, avoid the insufficient gas pressure affecting the use of downstream gas or increasing the working load of the upstream pressure regulating station, and improve the stability of gas transmission.

[0160] In some embodiments, the company management platform controls the operating parameters of the gas equipment object platform based on the estimated concentration level. For example, the company management platform controls the operating parameters of the filter through the gas equipment object platform based on the estimated concentration level. The operating parameters include the automatic cleaning period and the blowdown period of the filter. The automatic cleaning period refers to the period during which the filter is automatically cleaned and generates impurities. The blowdown period refers to the period during which the filter automatically discharges the impurities generated by cleaning to the outside of the filter.

[0161] In some embodiments, the company management platform determines the maximum value of the estimated concentration level of at least one upstream pipeline area of a single filter, and determines the reference operating parameters corresponding to the maximum value in the filter parameter table as the operating parameters of the filter by querying the filter parameter table.

[0162] The filter parameter table is pre-set based on historical experience and includes a plurality of concentration levels and corresponding reference operating parameters. Among them, the company management platform counts the historical operating parameters of the filter corresponding to the pipeline area meeting the pressure regulating demand in the historical data and the average value of the historical operating parameters and the concentration level corresponding to the pipeline area into the filter parameter table. The average value of the historical operating parameters includes the average value of the historical automatic cleaning period and the average value of the historical blowdown period.

[0163] In some embodiments of the present specification, by estimating the concentration level, the operating parameters of the filter can be controlled in advance, avoiding the simultaneous overloading of a large number of filters, causing the centralized accumulation of operation and maintenance tasks, improving the intelligent degree of gas pipeline network transmission, and reducing the influence of particulate matter in the gas on the quality of gas transmission.

[0164] Figure 4 is an exemplary schematic diagram of a particulate matter model according to some embodiments of the present specification.

[0165] In some embodiments, the company management platform constructs a pipeline area atlas 420 based on the first concentration data 411 and the pipeline characteristics 412 of at least one pipeline area, and generates the estimated concentration level 440 of at least one pipeline area through the particulate matter model 430 based on the pipeline area atlas 420.

[0166] For the description of the first concentration data and the estimated concentration level, refer to Figure 3 and the related description.

[0167] The pipeline region graph refers to a graph structure for reflecting the relative positions of the monitoring devices. The pipeline region graph comprises at least one node and at least one edge.

[0168] In some embodiments, the node of the pipeline region graph comprises a node representing a monitoring device (e.g., node 421). The features of the node comprise at least one of the first concentration data and the gas flow rate of the adjacent pipeline region upstream of the monitoring device, the filter installation condition, and the on-off state. The filter installation condition comprises whether a filter is installed in the adjacent pipeline region upstream of the monitoring device. For the description of the monitoring device, the filter, and the gas flow rate, refer to the related description of Figure 1 .

[0169] In some embodiments, the edge (e.g., edge 422) of the pipeline region graph is used to represent the pipeline region between two nodes. The edge comprises a directed edge, and the direction of the edge represents the flow direction of the gas. The features of the edge comprise pipeline features. The pipeline features comprise the pipeline distance between the filter closest to the pipeline region and the pipeline region in the upstream pipeline region of the pipeline region. The pipeline distance refers to the length of the pipeline. The pipeline distance is obtained by the preset display system of the company management platform.

[0170] In some embodiments, the company management platform constructs the node of the pipeline region graph based on the positions of the monitoring devices, and takes the first concentration data and the gas flow rate of the adjacent pipeline region upstream of the monitoring device, the filter installation condition, and the on-off state as the features of the node. The company management platform takes the pipeline region between the monitoring devices as the edge between the nodes, and takes the pipeline features as the features of the edge, to obtain the pipeline region graph.

[0171] The particulate matter model refers to a model for determining the estimated concentration level. In some embodiments, the particulate matter model is a machine learning model, such as any one or combination of a graph neural network model (GNN) or other custom model structure.

[0172] In some embodiments, the input of the particulate matter model comprises the pipeline region graph. The output of the particulate matter model comprises the estimated concentration level corresponding to each edge of the pipeline region graph.

[0173] In some embodiments, the company management platform trains the particulate matter model based on a large number of training samples with labels by gradient descent method, etc. The first sample comprises a sample pipeline region graph, and the label comprises the actual concentration level corresponding to each edge of the sample pipeline region graph.

[0174] In some embodiments, the company management platform constructs a sample pipeline area map based on historical data, and uses the historical concentration level corresponding to each edge of the sample pipeline area map in the historical data as a label.

[0175] In some embodiments, a particle model can be trained by inputting a plurality of labeled training samples into an initial particle model, constructing a loss function based on the labels and the prediction results of the initial particle model, iteratively updating the initial particle model based on the loss function, and completing particle model training when the loss function of the initial particle model satisfies a preset condition. The preset condition may include convergence of the loss function and a set number of iterations.

[0176] In some embodiments, the company management platform adjusts the training samples used subsequently based on the difference between the output results of the initial particulate matter model and the labels. For example, the difference value of each edge in the output results of the initial particulate matter model is counted, and the first-class edges and the second-class edges are screened, and the difference value averages of the two-class edges are calculated to obtain the first-class mean and the second-class mean, and the training samples used subsequently are adjusted based on the first-class mean and the second-class mean. Among them, the difference value of the edge refers to the difference between the edge output and the label corresponding to the edge. The first-class mean refers to the mean of the difference values ​​of the first-class edges. The second-class mean refers to the mean of the difference values ​​of the second-class edges. The first-class edge refers to the edge with a filter in the upstream edge within a neighboring degree. The second-class edge refers to the edge without a filter in the upstream edge within a neighboring degree. For an explanation of the neighboring degree, see Figure 3 and its related descriptions.

[0177] For example, the company management platform calculates the sum of the first-category mean and the second-category mean. If the ratio of the first-category mean to the sum is greater than a preset adjustment threshold, then subsequent training samples used are those containing more first-category edges. If the ratio of the first-category mean to the sum is not greater than the preset adjustment threshold, then subsequent training samples used are those containing more second-category edges. The preset adjustment threshold is pre-set based on historical experience.

[0178] It can be understood that if the ratio of the first-class mean to the sum is greater than the preset adjustment threshold, it indicates that the output of the initial particle model when processing training samples containing the first-class edge is significantly different from the label. Subsequent training of the initial particle model with training samples containing more first-class edges can obtain a more accurate particle model. If the ratio of the first-class mean to the sum is not greater than the preset adjustment threshold, it indicates that the output of the initial particle model when processing training samples containing the second-class edge is significantly different from the label. Subsequent training of the initial particle model with training samples containing more second-class edges can obtain a more accurate particle model.

[0179] In some embodiments of the present specification, the particle model is used to automatically determine the estimated concentration level, and the efficiency and accuracy of the determined estimated concentration level are improved. At the same time, when determining the estimated concentration level, the influence of the pipe distance between the pipe area and the nearest filter on the concentration data is considered, thereby improving the accuracy of the determined estimated concentration level.

[0180] In some embodiments of the present specification, a computer readable storage medium is also provided, and the storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the method of any one of the above embodiments.

[0181] In addition, some features, structures or characteristics in one or more embodiments of the present specification can be appropriately combined.

[0182] In some embodiments, the numerical parameters used in the specification and claims are approximations that can vary depending on the desired properties sought to be obtained by the particular embodiments. In some embodiments, the numerical parameters should be considered in the context of the number of significant digits and errors inherent to measurement techniques. Although the numerical ranges and parameters setting forth the broad scope of the embodiments of the present specification are approximations, the numerical values set forth in the specific embodiments are reported as precisely as possible. The numerical values set forth in the specific embodiments are provided to be as precise as reasonably possible. However, some variations can occur depending on the desired properties sought to be obtained by the particular embodiments.

[0183] If the description, definitions and / or the use of terms in the materials cited in the present specification are inconsistent or conflict with the description, definitions and / or the use of terms in the present specification, the description, definitions and / or the use of terms in the present specification shall prevail.

Claims

1. A smart gas network particulate matter safety monitoring method, characterized in that: The method is executed by a gas company management platform in a smart gas network particulate matter safety monitoring IoT system, and the method includes: Obtaining particulate matter concentration data of at least one pipeline area from a monitoring device of a gas equipment object platform via a gas company sensor network platform; generating a concentration level for the at least one pipeline region based on the concentration data, and generating a concentration level mark in a preset display system; determining a concentration level difference based on the concentration level of the at least one pipeline region; Based on the concentration level difference, determining the pipeline to be inspected, and generating a mark of the pipeline to be inspected in the preset display system; generating a pipeline inspection instruction based on the pipeline to be inspected; generating a pipeline inspection work order based on the pipeline inspection instruction; and, Based on the execution result of the pipeline inspection work order and / or the concentration level difference, regulating the operating parameters of the pipeline auxiliary equipment in the at least one pipeline area through the gas equipment object platform; The method further comprises: generating an estimated concentration level for the at least one pipeline region based on first concentration data, the first concentration data comprising concentration data of particulate matter for the at least one pipeline region at a first time point; Based on the estimated concentration level, determining key monitoring pipelines and generating key pipeline marks in the preset display system; generating a source confidence distribution based on second concentration data and a concentration level difference corresponding to the second concentration data, the second concentration data including concentration data of particulate matter in the key monitoring pipeline at a plurality of second time points, the second time points being later than the first time points; and Based on the source confidence distribution, the pipeline to be inspected is determined, and a label of the pipeline to be inspected is generated in the preset display system.

2. The method according to claim 1, wherein The first concentration data further includes concentration sequence data of particulate matter in the at least one pipeline region at a plurality of third time points. Generating an estimated concentration level of the at least one pipeline region based on the first concentration data includes: generating, based on the concentration series data, a concentration variation amplitude of the at least one pipeline region at the plurality of third time points; The estimated concentration level of the at least one pipeline region is generated based on the concentration variation magnitude.

3. The method according to claim 1, wherein The method further comprises: Obtaining a mark of the at least one pipeline area through the preset display system; Based on the marker, acquisition parameters of the monitoring device are set.

4. The method according to claim 3, wherein The method further comprises: Based on the marking, a monitoring priority of the at least one pipeline region is determined.

5. A smart gas pipeline network particulate matter safety monitoring Internet of Things system, characterized by: The Internet of Things system includes a government supervision object platform, a gas company sensor network platform, and a gas equipment object platform. The government supervision object platform includes a gas company management platform, and the gas company management platform is configured as follows: Obtaining, via the gas company sensor network platform, particulate matter concentration data for at least one pipeline area from a monitoring device of the gas equipment object platform; generating a concentration level for the at least one pipeline region based on the concentration data, and generating a concentration level mark in a preset display system; determining a concentration level difference based on the concentration level of the at least one pipeline region; Based on the concentration level difference, determining the pipeline to be inspected, and generating a mark of the pipeline to be inspected in the preset display system; generating a pipeline inspection instruction based on the pipeline to be inspected; generating a pipeline inspection work order based on the pipeline inspection instruction; as well as, Based on the execution result of the pipeline inspection work order and / or the concentration level difference, regulating the operating parameters of the pipeline auxiliary equipment in the at least one pipeline area through the gas equipment object platform; The gas company management platform is further configured to: generating an estimated concentration level for the at least one pipeline region based on first concentration data, the first concentration data comprising concentration data of particulate matter for the at least one pipeline region at a first time point; Based on the estimated concentration level, determining key monitoring pipelines and generating key pipeline marks in the preset display system; generating a source confidence distribution based on second concentration data and a concentration level difference corresponding to the second concentration data, the second concentration data including concentration data of particulate matter in the key monitoring pipeline at a plurality of second time points, the second time points being later than the first time points; and Based on the source confidence distribution, the pipeline to be inspected is determined, and a label of the pipeline to be inspected is generated in the preset display system.

6. The system according to claim 5, wherein: The first concentration data further includes concentration sequence data of particulate matter in the at least one pipeline area at a plurality of third time points. The gas company management platform is further configured to: generating, based on the concentration series data, a concentration variation amplitude of the at least one pipeline region at the plurality of third time points; The estimated concentration level of the at least one pipeline region is generated based on the concentration variation magnitude.

7. The system according to claim 5, wherein: The gas company management platform is further configured to: Obtaining a mark of the at least one pipeline area through the preset display system; Based on the marker, acquisition parameters of the monitoring device are set.

8. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to claim 1.

Images