Pipeline cleaning method and system based on intelligent fuel gas supervision internet of things and medium

Abstract

The invention provides a pipeline cleaning method and system based on an intelligent gas supervision internet of things, and a medium, and relates to the technical field of internet of things. The method comprises the steps of obtaining pollution discharge working data and gas monitoring data, determining pipeline cleaning parameters based on the pollution discharge working data and the gas monitoring data, generating a cleaning regulation and control instruction based on the pipeline cleaning parameters, and issuing the cleaning regulation and control instruction to an intelligent gas equipment object platform, and controlling the target pollution discharge equipment to clean according to the cleaning working parameters. The Internet of Things system comprises an intelligent gas government safety supervision management platform, an intelligent gas government safety supervision sensing network platform, an intelligent gas government safety supervision object platform, an intelligent gas company sensing network platform and an intelligent gas equipment object platform. The method can also be operated after a computer instruction stored in a computer readable storage medium is read. According to the method, the accurate target pollution discharge equipment and the corresponding cleaning working parameters can be determined.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things technology, and in particular to a pipeline cleaning method, system and medium based on a smart gas monitoring Internet of Things. Background Art

[0002] When the urban gas pipeline system transports gas to gas users, it will filter the gas through the sewage discharge equipment. The filtered impurities will accumulate in the sewage pipe of the sewage discharge equipment. After a period of time, too many impurities will accumulate in the sewage pipe, affecting the subsequent gas filtering effect and the quality of downstream gas.

[0003] In order to realize automatic cleaning of gas filter devices, the Chinese patent application with announcement number CN111359333B proposes an automatic filter cleaning and sewage discharge system suitable for gas. The system uses the pressure difference data collected by the electric control cabinet. When the pressure difference reaches the specified value, it starts the automatic cleaning operation and switches the connection of the pipeline from the gas outlet to the gas inlet to avoid affecting the downstream gas quality. However, this prior art only sets the specified value based on experience to determine whether sewage cleaning is required, and fails to systematically evaluate whether sewage cleaning is needed from data from all parties, and the impact of sewage cleaning on downstream pipelines is unknown.

[0004] Therefore, it is necessary to provide a pipeline cleaning method, system and medium based on the smart gas supervision Internet of Things, so as to determine the accurate target sewage discharge equipment and its corresponding cleaning work parameters. Summary of the invention

[0005] In order to solve the problem of how to accurately determine the target sewage discharge equipment and its corresponding cleaning work parameters, this specification provides a pipeline cleaning method, system and medium based on a smart gas monitoring Internet of Things.

[0006] The invention content includes a pipeline cleaning method based on a smart gas supervision Internet of Things, characterized in that the method is executed by a smart gas supervision Internet of Things system, the Internet of Things system includes a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a smart gas gas company sensor network platform and a smart gas equipment object platform; the smart gas government safety supervision object platform includes a smart gas gas company management platform, the smart gas gas company management platform includes a gas database, and the gas database is configured as a storage device; the smart gas government safety supervision management platform and the smart gas gas company management platform are configured as servers; the smart gas government safety supervision sensor network platform and the smart gas gas company sensor network platform are configured as a communication network, and the smart gas equipment object platform is configured as sewage equipment and gas monitoring equipment, and the sewage equipment includes filtering equipment, sewage pipelines in At least one gas monitoring device is arranged on the gas pipeline; the method comprises: the smart gas gas company management platform obtains the sewage discharge work data and gas monitoring data collected by the smart gas equipment object platform through the smart gas gas company sensor network platform, and stores the sewage discharge work data and gas monitoring data in the gas database; the smart gas gas company management platform determines the pipeline cleaning parameters based on the sewage discharge work data and the gas monitoring data, and uploads the pipeline cleaning parameters to the smart gas government safety supervision management platform, the pipeline cleaning parameters include the target sewage discharge equipment and its corresponding cleaning work parameters, the cleaning work parameters include the sewage discharge valve opening level, the monitoring level and the intelligent working parameters of the cleaning crawling robot; and the smart gas government safety supervision management platform generates the cleaning control instruction based on the pipeline cleaning parameters, and sends the cleaning control instruction to the smart gas equipment object platform to control the target sewage discharge equipment to clean with the cleaning work parameters.

[0007] The invention content includes a smart gas supervision Internet of Things system, which is characterized in that the Internet of Things system includes a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a smart gas gas company sensor network platform and a smart gas equipment object platform; the smart gas government safety supervision object platform includes a smart gas gas company management platform, the smart gas gas company management platform includes a gas database, and the gas database is configured as a storage device; the smart gas government safety supervision management platform and the smart gas gas company management platform are configured as servers; the smart gas government safety supervision sensor network platform and the smart gas gas company sensor network platform are configured as a communication network, the smart gas equipment object platform is configured as sewage equipment and gas monitoring equipment, the sewage equipment includes at least one of filtering equipment and sewage pipelines, and the gas monitoring equipment is arranged at On the gas pipeline; the Internet of Things system is configured as follows: the smart gas gas company management platform obtains the sewage work data and gas monitoring data collected by the smart gas equipment object platform through the smart gas gas company sensor network platform, and stores the sewage work data and gas monitoring data in the gas database; the smart gas gas company management platform determines the pipeline cleaning parameters based on the sewage work data and gas monitoring data, and uploads the pipeline cleaning parameters to the smart gas government safety supervision and management platform. The pipeline cleaning parameters include the target sewage equipment and its corresponding cleaning work parameters. The cleaning work parameters include the sewage valve opening level, monitoring level and intelligent working parameters of the cleaning crawler robot; and the smart gas government safety supervision and management platform generates cleaning control instructions based on the pipeline cleaning parameters, and sends the cleaning control instructions to the smart gas equipment object platform to control the target sewage equipment to clean with the cleaning work parameters.

[0008] The invention content includes a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the above-mentioned pipeline cleaning method based on the smart gas supervision Internet of Things.

[0009] The beneficial effects brought about by the above invention content include but are not limited to: through the collaborative work of the smart gas gas company management platform and the smart gas gas company sensor network platform, the sewage discharge work data and gas monitoring data collected by the smart gas equipment object platform can be effectively acquired and stored in the gas database. In addition, the smart gas gas company management platform can determine the pipeline cleaning parameters based on the sewage discharge work data and gas monitoring data, and upload the pipeline cleaning parameters to the smart gas government safety supervision and management platform. Furthermore, the smart gas government safety supervision and management platform can use the pipeline cleaning parameters to generate cleaning control instructions, and send them to the smart gas equipment object platform to accurately control the target sewage discharge equipment to operate according to the established cleaning work parameters, ensuring the timeliness, efficiency, safety and compliance of the pipeline cleaning operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein: Figure 1 It is a platform structure diagram of the smart gas supervision Internet of Things system shown in some embodiments of this specification; Figure 2 is an exemplary flow chart of a pipeline cleaning method based on a smart gas supervision Internet of Things according to some embodiments of this specification; Figure 3 is a schematic diagram of a process for determining a target sewage discharge device according to some embodiments of this specification; Figure 4 is a schematic diagram of a process for determining a target sewage discharge device according to other embodiments of this specification; Figure 5 is an exemplary flow chart for determining cleaning operation parameters according to some embodiments of the present specification. DETAILED DESCRIPTION

[0011] The following is a brief introduction to the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0012] The "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0013] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0014] When the operations performed in the embodiments of this specification are described in steps, unless otherwise specified, the order of the steps is interchangeable, steps may be omitted, and other steps may be included in the operation process.

[0015] Figure 1 This is a platform structure diagram of the smart gas monitoring Internet of Things system shown in some embodiments of this specification. The smart gas monitoring Internet of Things system involved in the embodiments of this specification will be described in detail below. It should be noted that the following embodiments are only used to explain this specification and do not constitute a limitation on this specification.

[0016] In some embodiments, Figure 1 As shown, the smart gas supervision Internet of Things system 100 includes a smart gas government safety supervision management platform 110, a smart gas government safety supervision sensor network platform 120, a smart gas government safety supervision object platform 130, a smart gas gas company sensor network platform 150, and a smart gas equipment object platform 160.

[0017] Smart gas government safety supervision and management platform 110 refers to a platform that government users coordinate and coordinate the connection and collaboration between various functional platforms, and gather all the information of the Internet of Things to provide perception management and control management functions for the Internet of Things operation system.

[0018] In some embodiments, the smart gas government safety supervision management platform 110 is configured as a server.

[0019] The server can be used to process data related to the smart gas supervision Internet of Things system 100. In some embodiments, the server is a single server or a server group. In some embodiments, the server group is centralized or distributed.

[0020] The smart gas government safety supervision sensor network platform 120 refers to a functional platform for managing sensor communication. In some embodiments, the smart gas government safety supervision sensor network platform 120 has the functions of sensing information sensor communication and controlling information sensor communication.

[0021] In some embodiments, the smart gas government safety supervision sensor network platform 120 connects the smart gas government safety supervision management platform 110 and the smart gas government safety supervision object platform 130 to realize information interaction among the smart gas government safety supervision sensor network platform 120, the smart gas government safety supervision management platform 110 and the smart gas government safety supervision object platform 130.

[0022] In some embodiments, the smart gas government safety supervision sensor network platform 120 is configured as a communication network.

[0023] In some embodiments, the communication network includes any suitable network that can facilitate information and / or data exchange of the smart gas regulatory IoT system 100. In some embodiments, the smart gas government safety supervision management platform 110 obtains information and / or data from the smart gas government safety supervision object platform 130 through the communication network.

[0024] The smart gas government safety supervision object platform 130 is a functional platform for sensing information generation and controlling information execution.

[0025] In some embodiments, the smart gas government safety supervision object platform 130 includes a smart gas gas company management platform 140 .

[0026] In some embodiments, the smart gas company management platform 140 includes a gas database.

[0027] In some embodiments, the gas database is a storage device.

[0028] The gas database refers to a database storing information related to the smart gas monitoring IoT system 100. In some embodiments, the gas database is configured to store information such as sewage discharge data and gas monitoring data. For more information about sewage discharge data and gas monitoring data, please refer to Figure 2 and its related description.

[0029] Storage devices refer to devices that store data information. Storage devices can include various types of memories, such as random access memory (RAM), read-only memory (ROM), etc.

[0030] The smart gas company sensor network platform 150 refers to a functional platform for managing sensor communication. In some embodiments, the smart gas company sensor network platform 150 implements the functions of sensing information sensor communication and controlling information sensor communication.

[0031] In some embodiments, the smart gas government safety supervision object platform 130 obtains gas-related data from the smart gas equipment object platform 160 through the smart gas gas company sensor network platform 150 .

[0032] In some embodiments, the smart gas equipment object platform is configured as various types of gas pipe network equipment and monitoring equipment. For example, the smart gas equipment object platform is configured as sewage equipment and gas monitoring equipment.

[0033] The sewage discharge equipment refers to equipment for filtering and discharging sewage from the gas flowing through. In some embodiments, the sewage discharge equipment includes filtering equipment, sewage discharge pipes, and the like.

[0034] The filter device is a device for filtering the fuel gas. In some embodiments, the filter device includes a filter element, such as a metal filter, a fiber filter, and the like.

[0035] The sewage pipe refers to the pipe used to collect and discharge impurities generated during the filtration process.

[0036] In some embodiments, when the filter device filters the gas, the impurities filtered out will adhere to and accumulate in the sewage pipe. The more impurities accumulated in the sewage pipe, the easier it is to cause the sewage pipe to be blocked. At the same time, the worse the filtering effect of the filter device, the more impurities are carried by the gas delivered to the downstream pipeline. Therefore, the sewage pipe needs to be cleaned.

[0037] Gas monitoring equipment is a device used to monitor gas data, such as pressure sensors, temperature sensors, flow sensors, flow velocity sensors, gas composition monitors, etc.

[0038] In some embodiments, the gas monitoring device monitors the parameters of the gas in the gas pipeline. For example, the parameters of the gas in the gas pipeline include pressure data, temperature data, flow data, flow rate sensor, gas composition data, etc.

[0039] In some embodiments, the gas monitoring device is disposed on the gas pipeline.

[0040] In some embodiments of the present specification, based on the smart gas supervision Internet of Things system 100, an information operation closed loop can be formed between the smart gas government safety supervision management platform 110 and the smart gas equipment object platform 160, and coordinated and regular operation can be achieved under the unified management of the smart gas company management platform 140, thereby realizing the informatization and intelligence of pipeline cleaning management based on the smart gas supervision Internet of Things.

[0041] Figure 2 This is an exemplary flow chart of a pipeline cleaning method based on the smart gas monitoring Internet of Things according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 is executed by a smart gas monitoring IoT system.

[0042] Step S210, the smart gas company management platform obtains the sewage discharge work data and gas monitoring data collected by the smart gas equipment object platform through the smart gas company sensor network platform, and stores the sewage discharge work data and gas monitoring data in the gas database.

[0043] In some embodiments, step S210 is performed based on a smart gas company management platform.

[0044] Sewage discharge working data refers to the working parameters related to the operation of sewage discharge equipment. For example, sewage discharge working data includes but is not limited to the working time, pressure drop, filtration accuracy, and working temperature of sewage discharge equipment.

[0045] Working time refers to the total time since the sewage treatment equipment was last cleaned. Pressure drop refers to the pressure loss when the fluid (such as gas, etc.) flows in the sewage treatment equipment. Filtration accuracy refers to the size of solid particles in the fluid that the sewage treatment equipment can filter out. Working temperature refers to the temperature of the sewage treatment equipment during operation. For more information about sewage treatment equipment, please refer to Figure 1 and its related description.

[0046] In some embodiments, the smart gas company management platform obtains the sewage discharge working data of the sewage discharge equipment based on the smart gas equipment object platform (such as sensors, monitoring equipment, etc.). For example, the smart gas company management platform obtains the working time of the sewage discharge equipment through a timer, etc. For another example, the smart gas company management platform obtains the pressure drop of the sewage discharge equipment through a pressure sensor. For another example, the smart gas company management platform directly obtains the filtration accuracy of the sewage discharge equipment through the smart gas equipment object platform, and the filtration accuracy is regulated by the smart gas equipment object platform. For another example, the smart gas company management platform obtains the working temperature of the sewage discharge equipment through a temperature sensor.

[0047] Gas monitoring data refers to data related to gas collected by gas monitoring equipment. For example, gas monitoring data includes but is not limited to pressure data, temperature data, flow data, flow rate data, and gas composition data. Among them, flow data refers to the flow within a unit time period (for example, 0.5h, 1h, 2h, etc.).

[0048] For more information about gas monitoring equipment, please refer to Figure 1 and its related description.

[0049] In some embodiments, the smart gas company management platform collects sewage discharge data of sewage discharge equipment based on gas monitoring equipment installed on the gas pipeline.

[0050] In some embodiments, the smart gas company management platform stores sewage discharge data and gas monitoring data in the gas database of the smart gas company management platform.

[0051] Step S220: The smart gas company management platform determines the pipeline cleaning parameters based on the sewage discharge data and gas monitoring data, and uploads the pipeline cleaning parameters to the smart gas government safety supervision management platform.

[0052] In some embodiments, step S220 is performed based on a smart gas company management platform.

[0053] Pipeline cleaning parameters refer to relevant data when performing pipeline cleaning operations. For example, pipeline cleaning parameters include but are not limited to target sewage equipment and its corresponding cleaning work parameters.

[0054] The target sewage discharge equipment refers to the sewage discharge equipment that needs to be cleaned. For example, the target sewage discharge equipment is a filtering device that needs to be cleaned, a sewage discharge pipe that needs to be cleaned, etc.

[0055] Cleaning working parameters refer to parameters used to characterize the cleaning operation. For example, cleaning working parameters include but are not limited to the sewage valve opening level, monitoring level and intelligent working parameters of the crawling robot.

[0056] The sewage valve opening level refers to a numerical value or letter that can reflect the degree of opening of the sewage valve during the cleaning process. For example, the sewage valve opening level is expressed in a numerical value. The larger the numerical value, the greater the sewage valve opening level and the greater the degree of opening of the sewage valve.

[0057] The monitoring level refers to a numerical value or letter that can reflect the monitoring frequency and monitoring accuracy of the target sewage discharge equipment during the cleanup operation. For example, the monitoring level is expressed in a numerical value. The larger the numerical value, the higher the monitoring level, the greater the monitoring frequency, and the higher the monitoring accuracy.

[0058] In some embodiments, the monitoring level is positively correlated with the monitoring frequency and the monitoring accuracy.

[0059] The monitoring frequency refers to the frequency of monitoring the target sewage discharge equipment during the cleaning operation. For example, the monitoring frequency is to monitor the target sewage discharge equipment 10 times per hour, etc., which is not limited here.

[0060] Monitoring accuracy refers to the amount of data collected in each collection interval. As an example only, in response to the smart gas company management platform collecting data at intervals of 1 hour, and the monitoring accuracy is 5, it means that the smart gas company management platform collects data 5 times in a row per hour.

[0061] In some embodiments, different monitoring levels correspond to different monitoring frequencies and monitoring accuracies. For example, the higher the monitoring level, the greater the monitoring frequency of the target sewage discharge equipment and the higher the monitoring accuracy.

[0062] The cleaning crawler robot is an automated device equipped with cleaning tools.

[0063] In some embodiments, the cleaning crawler robot can select appropriate cleaning tools according to different degrees of contamination, such as a brush suitable for light contamination, capable of removing surface dust and light attachments. A scraper is suitable for heavier dirt or hard deposits. A high-pressure water gun is used to spray water to dissolve and flush impurities that are difficult to remove.

[0064] In some embodiments, the cleaning crawling robot can also selectively carry vacuum cleaners with different functions, and suck impurities into dust bags or containers through suction, which is convenient for later cleaning to meet the cleaning needs of various sewage discharge equipment. For example, in response to the cleaning crawling robot carrying a magnetic vacuum cleaner, the magnetic field is used to clean iron or magnetic materials in the sewage discharge equipment. For another example, in response to the cleaning crawling robot choosing to carry an ordinary vacuum cleaner, a strong airflow is generated to suck in dust, dirt and other small particles, and then the dirt is sucked into the dust bag or dust bucket through a suction nozzle or brush.

[0065] The intelligent working parameters refer to the working parameters of the cleaning crawler robot when performing cleaning operations. For example, the intelligent working parameters include but are not limited to the moving speed, cleaning intensity, and number of repeated cleaning times of the cleaning crawler robot.

[0066] The moving speed refers to the speed at which the cleaning crawler robot moves when cleaning the pipeline, for example, 1 m / s, etc., which is not limited here.

[0067] In some embodiments, the smart gas company management platform adjusts the moving speed based on the complexity and cleaning difficulty of the pipeline. As an example only, the greater the complexity of the pipeline and the higher the cleaning difficulty, the slower the moving speed of the cleaning crawler robot.

[0068] The cleaning intensity refers to the force applied by the cleaning tool or device of the cleaning crawler robot to the contaminant. For example, the cleaning intensity is expressed as a numerical value, and the larger the numerical value, the higher the cleaning intensity.

[0069] In some embodiments, the greater the cleaning force of the brush in the cleaning tool, the greater the cleaning force of the scraper, the greater the intensity of the jet water flow, and the greater the flow rate of the jet water flow, the higher the cleaning intensity of the cleaning crawling robot.

[0070] In some embodiments, the smart gas company management platform adjusts the moving speed based on the intensity of the cleaning task. As an example only, the higher the intensity of the cleaning task, the higher the cleaning intensity of the cleaning crawler robot.

[0071] The number of repeated cleaning times refers to the number of times the cleaning crawler robot repeatedly cleans the target sewage discharge equipment, for example, 5 times, etc., which is not limited here.

[0072] In some embodiments, the smart gas company management platform determines the target sewage pipeline in the pipeline cleaning parameters based on multiple methods. For example, the smart gas company management platform determines the sewage equipment whose working time of the current sewage equipment exceeds the time threshold, the total amount of gas filtered in a unit time period is lower than the filtering threshold, and the filtering score is lower than the score threshold as the target sewage equipment.

[0073] The duration threshold refers to a threshold used to determine whether the working time of the sewage discharge equipment is too long. In some embodiments, the duration threshold is set by professional technicians or by system default.

[0074] The total amount of gas filtered within a unit time period refers to the total amount of gas filtered and processed by the sewage discharge equipment within a unit time period (for example, 1 minute, 30 minutes, 60 minutes, etc.).

[0075] In some embodiments, the smart gas company management platform obtains the total amount of gas filtered in a unit time period corresponding to the sewage discharge equipment based on the flow data in the gas monitoring data.

[0076] The filtering threshold refers to a threshold used to determine whether the total amount of gas filtered by the sewage discharge equipment within a unit time period is too small. In some embodiments, the filtering threshold is set by professional technicians or by system default.

[0077] The filtration score refers to a quantitative evaluation of the filtration effect of sewage treatment equipment, which can reflect the current working status and performance of the sewage treatment equipment.

[0078] In some embodiments, the smart gas company management platform determines the filtration score based on the amount of impurities decreased before and after the discharge and the gas filtration flow rate through a first preset rule. The first preset rule includes a positive correlation between the filtration score and the amount of impurities decreased before and after the discharge and the gas filtration flow rate.

[0079] The scoring threshold refers to a threshold used to determine whether the filtering effect of the sewage discharge equipment has reached an acceptable level. In some embodiments, in response to the filtering score being lower than the scoring threshold, it may indicate that the sewage discharge equipment needs to be cleaned. In some embodiments, the scoring threshold is set by a professional technician or by system default.

[0080] In some embodiments, the smart gas company management platform determines the cleaning working parameters corresponding to the target sewage pipe in the pipeline cleaning parameters based on a variety of methods. For example, the smart gas company management platform determines the sewage valve opening level, monitoring level, and intelligent working parameters based on the gas flow data through the second preset rule. The second preset rule includes that the sewage valve opening level, monitoring level, and intelligent working parameters are positively correlated with the gas flow data.

[0081] For another example, the smart gas company management platform determines the sewage valve opening level, monitoring level, and intelligent working parameters based on the gas flow data and pipeline importance score through the third preset rule. The third preset rule includes that the sewage valve opening level, monitoring level, and intelligent working parameters are positively correlated with the gas flow data and pipeline importance score.

[0082] For more information on pipeline importance scores, see Figure 3Step S330 and its related description.

[0083] For other embodiments of determining pipeline cleaning parameters based on sewage discharge data and gas monitoring data, please refer to Figure 3 , Figure 4 , Figure 5 and its related description.

[0084] In some embodiments, the smart gas gas company management platform uploads the pipeline cleaning parameters to the smart gas government safety supervision management platform through the smart gas government safety supervision sensor network platform.

[0085] Step S230: The smart gas government safety supervision and management platform generates a cleaning control instruction based on the pipeline cleaning parameters, and sends the cleaning control instruction to the smart gas equipment object platform to control the target sewage equipment to clean according to the cleaning work parameters.

[0086] In some embodiments, step S230 is performed based on the smart gas government safety supervision and management platform.

[0087] Cleaning control instructions refer to instructions used to control the target sewage discharge equipment to clean according to pipeline cleaning parameters.

[0088] In some embodiments, the cleaning control instruction also includes an indirect control instruction, which is configured to increase the monitoring level of the monitoring equipment on the pipeline gas when cleaning the target sewage discharge equipment.

[0089] The affected pipeline refers to the pipeline related to the sewage pipeline corresponding to the target sewage equipment.

[0090] In some embodiments, the smart gas government safety supervision and management platform takes the distance between the downstream sewage pipeline and the target sewage equipment, and the downstream sewage pipeline within the distance threshold range as the affected pipeline.

[0091] The downstream sewage pipe refers to the sewage pipe following the sewage pipe corresponding to the target sewage discharge equipment along the direction of the gas flow. The gas flow direction refers to the direction of gas flow.

[0092] The distance threshold is used to determine whether the pipeline can be affected. For example, the distance threshold is 100 meters, etc., which is not limited here.

[0093] In some embodiments, the smart gas government safety supervision and management platform determines the distance threshold by querying a preset relationship table based on the flow of the sewage pipe corresponding to the target sewage discharge equipment.

[0094] In some embodiments, the preset relationship table includes flow data of the sewage pipe corresponding to the target sewage discharge equipment and the real distance threshold. As an example only, the distance threshold in the first preset relationship table is positively correlated with the flow of the sewage pipe corresponding to the target sewage discharge equipment.

[0095] In some embodiments of the present invention, switching of sewage pipes during the cleaning process may cause gas fluctuations (such as changes in flow and pressure). Therefore, it is necessary not only to adjust the monitoring level of the target sewage equipment, but also to increase the monitoring level of the gas monitoring equipment on the affected pipeline, so as to ensure real-time monitoring of all affected downstream sewage pipes, improve monitoring priority, and effectively prevent accidents.

[0096] In some embodiments, the smart gas government safety supervision and management platform generates cleaning and control instructions based on pipeline cleaning parameters, and sends the cleaning and control instructions to the smart gas equipment object platform.

[0097] In some embodiments of the present specification, through the collaborative work of the smart gas gas company management platform and the smart gas gas company sensor network platform, the sewage discharge work data and gas monitoring data collected by the smart gas equipment object platform can be effectively acquired and stored in the gas database. In addition, the smart gas gas company management platform can determine the pipeline cleaning parameters based on the sewage discharge work data and gas monitoring data, and upload the pipeline cleaning parameters to the smart gas government safety supervision and management platform. Furthermore, the smart gas government safety supervision and management platform can use the pipeline cleaning parameters to generate cleaning control instructions, and send them to the smart gas equipment object platform to accurately control the target sewage discharge equipment to operate according to the established cleaning work parameters, ensuring the timeliness, efficiency, safety and compliance of the pipeline cleaning operation.

[0098] Figure 3 is a schematic diagram of a process for determining a target sewage discharge device according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 is executed by a smart gas company management platform.

[0099] Step S310, constructing a stacking characteristic diagram based on the sewage discharge work data and the gas monitoring data.

[0100] The stacking feature graph refers to a knowledge graph used to represent the distribution of sewage pipes and ordinary pipes and their attributes. In some embodiments, the stacking feature graph is composed of at least one node and at least one edge, the edge connects the nodes, and the nodes and the edges have attributes.

[0101] In some embodiments, the nodes of the stacking characteristic graph include sewage pipe nodes and ordinary pipe nodes.

[0102] In some embodiments, the sewage pipe node corresponds to a sewage pipe existing in a preset area.

[0103] In some embodiments, the attributes of the sewage pipeline node reflect the characteristics of the sewage node. For example, the attributes of the sewage pipeline node include but are not limited to at least one of the filter device type, sewage operation data, gas monitoring data, weather data, and pipeline physical characteristics. The preset area may include but is not limited to a city, a district, and a street.

[0104] The type of filtering equipment refers to the type of equipment installed on the sewage pipeline node to filter impurities in the fuel gas. For example, the type of filtering equipment includes but is not limited to bag filters and activated carbon filters.

[0105] In some embodiments, the sewage operation data includes current sewage data and historical sewage data.

[0106] Current sewage discharge data refers to the working parameters recorded during the current operation of the sewage discharge equipment. Historical sewage discharge data refers to the working parameters corresponding to the sewage discharge equipment during the historical preset time period.

[0107] For more information on sewage treatment work data, please refer to Figure 2 and its related description.

[0108] In some embodiments, the gas monitoring data includes current monitoring data and historical monitoring data.

[0109] The current monitoring data refers to the gas monitoring data collected during the current operation of the gas monitoring device, and the historical monitoring data refers to the gas monitoring data collected by the gas monitoring device within a historical preset time period.

[0110] For more information about gas monitoring data, see Figure 2 and its related description.

[0111] Weather data refers to climate condition data related to the area where the node in the stacked feature graph is located. For example, weather data includes but is not limited to temperature and humidity.

[0112] In some embodiments, the weather data includes historical weather data and current weather data.

[0113] In some embodiments, the smart gas company management platform obtains weather data based on the smart gas equipment object platform (such as temperature sensors, humidity sensors, etc.).

[0114] The physical characteristics of a pipeline refer to the physical properties of the pipeline. For example, the physical characteristics of a pipeline include the material data, shape and size, and length of the sewage pipeline.

[0115] In some embodiments, the common pipeline node corresponds to a common pipeline existing in a preset area.

[0116] In some embodiments, the attributes of a common pipeline node reflect the characteristics of the common node. For example, the attributes of a common pipeline node include but are not limited to at least one of gas monitoring data, weather data, and pipeline physical characteristics.

[0117] Among them, ordinary pipelines refer to gas transmission pipelines without filtering devices installed.

[0118] In some embodiments, when the pipelines corresponding to the two nodes are physically connected, the line between the two nodes constitutes an edge. In some embodiments, the edge is a directed edge, and the attributes of the edge include the direction of the gas flow.

[0119] In some embodiments, the smart gas company management platform constructs a stacking feature graph based on the above-mentioned nodes, edges, node attributes and edge attributes.

[0120] Step S320, based on the accumulation characteristic diagram, determine the current accumulation amount set through the accumulation amount determination model.

[0121] The current accumulation volume refers to the set consisting of the pipeline corresponding to each node in the accumulation feature graph and the impurity accumulation volume corresponding to the pipeline. For example, the current accumulation volume set is represented by {(A1, B1), (A2, B2), …, (A i , B i ),…,(A n , B n )}. Among them, A i represents the pipeline corresponding to the node in the stacked feature graph, B i Represents pipeline A i The amount of impurities accumulated.

[0122] The current impurity accumulation refers to the total weight of impurities formed by solid particles, sediments, etc. accumulated on the inner wall of the pipeline.

[0123] In some embodiments, the smart gas company management platform determines the current accumulation quantity set based on the accumulation characteristic diagram through an accumulation quantity determination model.

[0124] The accumulation amount determination model refers to a model used to determine the current accumulation amount set. In some embodiments, the accumulation amount determination model is a machine learning model. For example, the accumulation amount determination model is a graph neural network (GNN) model.

[0125] The input of the accumulation amount determination model may be an accumulation feature map, and the output may be a current accumulation amount set.

[0126] In some embodiments, the accumulation amount determination model is obtained based on the first sample training set training. The first sample training set includes multiple sample accumulation feature maps and their corresponding first labels. The first sample training set is input into the initial accumulation amount determination model, a loss function is constructed by the first label and the result of the initial determination model, and the parameters of the initial determination model are iteratively updated based on the loss function. When the loss function of the initial accumulation amount determination model meets the preset conditions, the model training is completed, and a trained accumulation amount determination model is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0127] In some embodiments, the first sample training set is a sample accumulation feature map. The smart gas company management platform constructs the sample accumulation feature map based on the first historical moment of the first sample training set and the historical sewage work data and historical gas monitoring data before the first historical moment.

[0128] In some embodiments, the first label may be the current accumulation amount of samples actually collected at the first historical moment corresponding to the first sample training set. For example, the smart gas company management platform is based on a cleaning crawling robot equipped with an ultrasonic sensor to detect the thickness of impurity accumulation. In response to the thicker the average thickness of the impurity accumulation, the higher the impurity accumulation amount.

[0129] In some embodiments, the smart gas company management platform uses the total impurity accumulation thickness of all impurities as the impurity accumulation amount. For another example, the smart gas company management platform cleans up the weight of impurities in the pipeline and obtains the impurity accumulation amount by weighing.

[0130] In some embodiments, the smart gas company management platform modifies the accumulation amount determination model based on the actual working parameters, or provides training samples for further strengthening the accumulation amount determination model. For example, the smart gas company management platform determines the actual impurity accumulation amount based on the actual impurity accumulation thickness, and in response to the actual impurity accumulation amount being different from the impurity accumulation amount output by the accumulation amount determination model, it indicates that the accumulation amount determination model has a deviation and may need to be corrected, such as adjusting the parameters of the accumulation amount determination model. In addition, the actual working parameters can provide training samples for the optimization of the accumulation amount determination model.

[0131] For details about the actual working parameters, see Figure 5 and its related description.

[0132] Step S330, determining the target sewage discharge equipment based on the current accumulation amount set and the cleaning threshold.

[0133] The cleanup threshold is a threshold used to determine whether the current accumulation amount is too high.

[0134] In some embodiments, the cleaning threshold is set by a professional technician or by system default. In some embodiments, the cleaning threshold is also determined based on pipeline physical characteristics, historical monitoring data, and pipeline importance scores. For more information about pipeline physical characteristics and historical monitoring data, see Figure 3 Step S310 and its related description.

[0135] The pipeline importance score refers to a numerical value used to characterize the importance of the pipeline. In some embodiments, the higher the numerical value, the higher the pipeline importance score.

[0136] In some embodiments, the smart gas company management platform determines the pipeline importance score by the following formula (1) based on the positive correlation between the pipeline importance score and the gas flow data, the number of associated pipelines, and the gas flow data of the associated pipelines.

[0137] (1) in, Score the pipeline importance, is the gas flow data, is the number of associated pipelines, It is the gas flow data of the associated pipeline. , , They are respectively the gas flow data, the number of associated pipelines, and the weight coefficient of the gas flow data of the associated pipelines, and can be obtained in advance.

[0138] For more information about traffic data, see Figure 2 and its related description.

[0139] An associated pipeline is a pipeline whose impurity accumulation is affected by the upstream sewage pipeline.

[0140] In some embodiments, the smart gas company management platform determines the associated pipeline based on a variety of methods. For example, the smart gas company management platform determines the associated pipeline based on historical data. As an example only, the smart gas company management platform responds to the sewage discharge equipment being cleaned, and the impurities in the gas composition data of the downstream pipeline decrease, then the pipeline is the associated pipeline of the sewage discharge equipment.

[0141] In some embodiments, for a pipeline, the smart gas company management platform adjusts the characteristics (e.g., sewage work data) of the node of the sewage pipeline corresponding to the pipeline in the accumulation feature map; then based on the adjusted accumulation feature map, the adjusted impurity accumulation amount set is determined through the accumulation amount determination model. Since the accumulation amount of impurities in the first associated pipeline is affected by the sewage pipeline upstream, by comparing the impurity accumulation amount set obtained before the adjustment (i.e., obtained using real data) and the adjusted impurity accumulation amount set, the pipeline in the downstream of the sewage pipeline that is different from the impurity accumulation amount set obtained before the adjustment and the adjusted impurity accumulation amount set is determined as the first associated pipeline of the sewage pipeline corresponding to the pipeline.

[0142] The number of associated pipes refers to the sum of the numbers of all associated pipes downstream of the sewage pipe.

[0143] In some embodiments, the smart gas company management platform determines the cleaning threshold through the following formula (2) based on the positive correlation between the cleaning threshold and the pipeline length and the filtering score, and the negative correlation between the cleaning threshold and the pipeline inner diameter and the pipeline importance score.

[0144] (2) in, To clean up the threshold, is the pipe length, is the inner diameter of the pipe, Score the pipeline importance, Rate the filter. , , , are respectively the weight coefficients of pipeline length, pipeline inner diameter, pipeline importance score, and filter score. In some embodiments, , is a positive number, , It is a negative number and can be obtained by default.

[0145] In some embodiments of the present specification, even if the amount of impurity accumulation is the same, the degree of impact on the pipeline may be different. Therefore, based on the physical characteristics of the pipeline, historical monitoring data and pipeline importance score, the pipeline situation can be more comprehensively evaluated, and more adaptive cleaning thresholds can be set for different sewage pipelines to clean the sewage pipeline more adaptively.

[0146] In some embodiments, in response to the amount of impurities accumulated in the sewage pipe being greater than a cleaning threshold, the smart gas company management platform identifies the sewage pipe as a target sewage equipment.

[0147] In some embodiments of the present specification, an accumulation characteristic map is constructed based on sewage discharge work data and gas monitoring data, and then based on the accumulation characteristic map, the current accumulation amount set is determined by the accumulation amount determination model. Constructing an accumulation characteristic map can provide rich information, enhance the reasoning ability and accuracy of the accumulation amount determination model, and help the accumulation amount determination model better understand and handle complex relationships. Determining the current accumulation amount set can accurately determine the pipeline and its corresponding impurity accumulation amount, which helps the system to detect and handle problems in a timely manner. Based on the current accumulation amount set and the cleaning threshold, the target sewage discharge equipment can be more effectively determined and the cleaning efficiency can be improved.

[0148] In some embodiments, the current accumulation amount set includes a sewage pipe corresponding to at least one sewage pipe node and its current impurity accumulation amount. For a sewage pipe corresponding to a sewage pipe node and its current impurity accumulation amount, in response to the current impurity accumulation amount being less than a cleaning threshold and greater than a concern threshold, the smart gas company management platform determines the sewage pipe corresponding to the current impurity accumulation amount as a concerned sewage pipe, generates a monitoring enhancement instruction, and sends the monitoring enhancement instruction to the smart gas equipment object platform to increase the monitoring level of the gas monitoring equipment of the concerned sewage pipe.

[0149] The concern threshold refers to the threshold used to determine whether the pipeline needs enhanced monitoring and attention.

[0150] In some embodiments, the smart gas company management platform determines the attention threshold through a fourth preset rule based on the gas flow data. The fourth preset rule includes that the attention threshold is negatively correlated with the gas flow data.

[0151] A sewage pipe of concern refers to a sewage pipe whose current impurity accumulation has not reached the cleaning threshold but has exceeded the concern threshold.

[0152] Monitoring enhancement orders are orders used to increase the level of monitoring of sewage pipes.

[0153] In some embodiments, the above-mentioned increased attention extent is obtained by professional technicians or system presets.

[0154] In some embodiments, the smart gas company management platform determines the above-mentioned increased attention through a fifth preset rule based on the amount of impurities accumulated in the current sewage pipe of concern. The fifth preset rule includes that the increased attention is positively correlated to the amount of impurities accumulated in the current sewage pipe of concern.

[0155] In some embodiments of this specification, by increasing the monitoring level, it is possible to detect the current impurity accumulation before it approaches the cleaning threshold, so that it can be cleaned in time, reducing the risk of failure caused by impurity accumulation. In addition, by increasing the monitoring level of the sewage pipe of concern, it is possible to avoid the resources consumed by high-frequency monitoring of all pipes while strengthening monitoring, thereby achieving effective allocation of resources.

[0156] In some embodiments, after the target sewage discharge equipment is determined based on steps S310 to S330, the sewage discharge equipment that is not determined as the target sewage discharge equipment is determined as the first sewage discharge equipment. In response to the number of the first sewage discharge equipment being at least one, the smart gas company management platform obtains, for one first sewage discharge equipment, a first associated pipeline of the sewage discharge pipeline corresponding to the first sewage discharge equipment based on the gas monitoring data; and determines the target sewage discharge equipment based on the current accumulation amount set, the first associated pipeline and the associated threshold.

[0157] The first sewage discharge equipment refers to sewage discharge equipment that has not been determined as the target sewage discharge equipment.

[0158] The first associated pipeline refers to the associated pipeline of the sewage pipeline corresponding to the first sewage discharge equipment.

[0159] For more information about associated pipes, see Figure 3 Step S330 and its related description.

[0160] In some embodiments, the first associated pipeline is obtained in a manner similar to the associated pipeline, see Figure 3 Step S330 and its related description are not repeated here.

[0161] The associated threshold refers to a threshold used to determine whether the amount of impurity accumulation in the associated pipeline is too high.

[0162] In some embodiments, different first associated pipes correspond to different associated thresholds. Since different first associated pipes may have different physical characteristics, usage conditions, and importance, by setting different associated thresholds for different first associated pipes, the characteristics of each first associated pipe can be more accurately reflected, thereby helping to improve the accuracy of determining the first associated pipes.

[0163] In some embodiments, the associated threshold is negatively correlated to the pipe inner diameter size of the first associated pipe, and positively correlated to the pipe importance score of the first associated pipe.

[0164] In some embodiments, the smart gas company management platform determines the current impurity accumulation amount of the first associated pipeline based on the current accumulation amount set, and determines the amount by which the current impurity accumulation amount of the first associated pipeline exceeds the associated threshold, and determines the sewage discharge equipment whose amount exceeds the threshold as the target sewage discharge equipment.

[0165] The quantity threshold refers to a threshold used to determine whether there are too many first associated pipelines corresponding to the sewage discharge equipment. In some embodiments, the quantity threshold is set by professional technicians or by system default.

[0166] In some embodiments of the present specification, the first associated pipeline of the sewage pipe corresponding to each first sewage discharge device is obtained, and the target sewage discharge device is determined according to the current accumulation amount set, the first associated pipeline and the associated threshold value. On the basis of determining the target sewage discharge equipment in step S310-step S330, since some impurities may be carried when inputting gas to the downstream pipeline, further considering the downstream first associated pipeline helps to reduce the risk of failure of the downstream pipeline due to impurity accumulation, thereby improving the accuracy of determining the target sewage discharge equipment and further improving the sewage discharge efficiency.

[0167] Figure 4 is a schematic diagram of a process for determining a target sewage discharge device according to other embodiments of this specification. Figure 4 As shown, the process 400 includes the following steps. In some embodiments, the process 400 is executed by a smart gas company management platform.

[0168] Step S410, constructing an estimated characteristic diagram based on the sewage discharge work data and the gas monitoring data.

[0169] The definition and structure of the estimated feature map are similar to those of the stacked feature map and will not be described in detail here.

[0170] In some embodiments, the nodes of the estimated characteristic graph include sewage pipe nodes and ordinary pipe nodes.

[0171] The definition of sewage pipe nodes can be found in Figure 3 In some embodiments, the attributes of the sewage pipeline node include, but are not limited to, filter equipment type, sewage operation data, future sewage data, current accumulation volume set, historical accumulation volume sequence, future maintenance data, gas monitoring data, weather data, pipeline physical characteristics, and pipeline aging degree.

[0172] For more information on filter equipment types, sewage work data, current accumulation collection, gas monitoring data, and pipeline physical characteristics, please refer to Figure 3 And the related description will not be repeated here.

[0173] Future sewage discharge data refers to the data on the operation of sewage discharge equipment within a preset time period in the future.

[0174] In some embodiments, future pollution discharge data is obtained by background reading or manual input.

[0175] In some embodiments, future sewage discharge data can also be set by professional technicians or system defaults.

[0176] The historical accumulation sequence refers to the sequence consisting of the pipelines corresponding to each node at each historical time point and the impurity accumulation corresponding to the pipeline within the historical preset time period. For example, the historical accumulation sequence consists of {[(C1, D 11 ), (C2, D 12 )……(C i , D 1i )……(C n , D 1n )],[(C1,D 21 ), (C2, D 22 )……(C i , D 2i )……(C n , D 2n )]……[(C1,D j1 ), (C2, D j2 )……(C i , D ji )……(C n , D jn )]……[(C1,D m1 ), (C2, D m2 )……(C i , D mi )……(C n , D mn )]}. Among them, [(C1,D j1 ), (C2, D j2 )……(C i , D ji )……(C n , D jn )] represents the pipeline corresponding to each node at the jth historical time point, and the amount of impurity accumulation corresponding to the pipeline, C i represents the pipeline corresponding to the i-th node, D ji Represents pipeline C i The amount of impurity accumulation at the jth historical time point, the number of nodes is n, and the number of historical time points is m.

[0177] In some embodiments, the smart gas company management platform obtains the historical accumulation sequence based on the pipelines and impurity accumulation corresponding to each node at each historical time point in the historical preset time period in the historical data.

[0178] Future maintenance data refers to data related to the maintenance of the pipeline corresponding to the node. For example, future maintenance data includes but is not limited to future regular maintenance plans (such as regularly repaired and replaced pipeline parts and their replacement time).

[0179] In some embodiments, future maintenance data is set by professional technicians based on the current condition of the pipeline.

[0180] Definition and Figure 3 The weather data is similar to the mid-term weather data, but the difference is that the weather data can also include the temperature, humidity, etc. of the future weather.

[0181] In some embodiments, the smart gas company management platform obtains weather data based on a weather API (eg, an API such as Open WeatherMap).

[0182] The pipeline aging degree refers to letters or numerical values ​​used to characterize the aging status of the pipeline corresponding to the node.

[0183] In some embodiments, the degree of pipeline aging may affect the accumulation rate of pipeline impurities. For example, the higher the degree of pipeline aging, the more likely it is to generate impurities.

[0184] In some embodiments, the smart gas company management platform determines the pipeline aging degree through a sixth preset rule based on the actual use of the pipeline. The sixth preset rule includes that the pipeline aging degree is positively correlated with the use time of the pipeline.

[0185] In some embodiments, the smart gas company management platform determines the degree of pipeline aging based on the historical impurity accumulation of the gas pipeline, the physical characteristics of the pipeline, the historical weather data, and the historical gas composition data.

[0186] Historical gas composition data refers to the gas composition in the pipeline within a historical preset time period.

[0187] In some embodiments, the smart gas company management platform obtains historical gas composition data based on historical data.

[0188] In some embodiments, the smart gas company management platform constructs a first feature vector based on the historical impurity accumulation of the gas pipeline, the physical characteristics of the pipeline, the historical weather data, and the historical gas composition data, and then searches the first vector database based on the first feature vector to determine the degree of pipeline aging.

[0189] The first vector database is a database used to determine the degree of pipeline aging. In some embodiments, the first vector database includes a plurality of first reference vectors and a reference pipeline aging degree corresponding to each first reference vector.

[0190] In some embodiments, the smart gas company management platform constructs a first reference vector based on the historical impurity accumulation, historical pipeline physical characteristics, historical weather data, and historical gas composition data corresponding to the first reference data, and uses the historical actual pipeline aging degree corresponding to the first reference data as the reference pipeline aging degree. The first reference data refers to the historical data used to construct the first vector database.

[0191] In some embodiments, the reference pipeline aging degree is set by a professional technician or by system default.

[0192] In some embodiments, the smart gas company management platform calculates the similarity between the first reference vector and the first feature vector respectively, and determines the pipeline aging degree corresponding to the first feature vector. For example, the first reference vector with the greatest similarity is used as the target vector, and the reference pipeline aging degree corresponding to the target vector is used as the pipeline aging degree corresponding to the first feature vector. The similarity between the first reference vector and the first feature vector is negatively correlated to the vector distance between the first reference vector and the first feature vector, and the vector distance is determined based on the cosine distance, etc. For example, the similarity is the inverse of the vector distance.

[0193] In some embodiments of the present specification, based on the historical impurity accumulation of the gas pipeline, the physical characteristics of the pipeline, the historical weather data, and the historical gas composition data, the actual aging degree of the pipeline can be more accurately evaluated through the first vector database.

[0194] The definition of common pipeline nodes can be found in Figure 3 In some embodiments, the attributes of a common pipeline node include, but are not limited to, future maintenance data, gas monitoring data, weather data, pipeline physical characteristics, and pipeline aging degree.

[0195] In some embodiments, the edges and attributes of the estimated feature graph, and the construction method of the estimated feature graph are similar to those of the stacked feature graph, and will not be repeated here.

[0196] Step S420, based on the estimated characteristic graph, determine the future accumulation amount sequence through the future estimation model.

[0197] The future accumulation sequence refers to a set of pipelines corresponding to each node at multiple future time points and the impurity accumulation of the pipelines. The form of the future accumulation sequence is similar to that of the historical accumulation sequence, and will not be repeated here.

[0198] In some embodiments, the smart gas company management platform determines the future accumulation quantity sequence based on the estimated characteristic graph through a future prediction model.

[0199] The future prediction model refers to a model used to determine the future accumulation amount sequence. In some embodiments, the future prediction model is a machine learning model. For example, the future prediction model is a GNN model.

[0200] The input of the future prediction model can be the prediction feature map, and the output can be the future accumulation amount sequence.

[0201] In some embodiments, the future prediction model is obtained based on the training of the sample training set; the sample training set includes multiple sample prediction feature graphs and their corresponding labels; each sample prediction feature graph is constructed and obtained based on the sample filtering equipment type, sample sewage discharge working data, sample gas monitoring data, sample weather data, sample pipeline physical characteristics, sample pipeline aging degree, sample future maintenance data, sample current accumulation amount set, sample historical accumulation amount sequence and sample future sewage discharge data; the label is the sample future accumulation amount sequence, and the collection time point of the sample future accumulation amount sequence is after the collection time point of the sample current accumulation amount set. Among them, the collection time point refers to the time point of collecting the impurity accumulation amount.

[0202] In some embodiments, the future prediction model is trained in a manner similar to the training of the accumulation determination model, see Figure 3 The related descriptions will not be repeated here.

[0203] In some embodiments, the sample training set is a historical sample estimation feature map. The smart gas company management platform constructs a historical sample estimation feature map based on the first historical moment of the sample training set and the historical sewage discharge work data and historical gas monitoring data before the first historical moment. The label is the future accumulation sequence actually collected at multiple second historical moments corresponding to the sample training set. The first historical moment is before the second historical moment. That is, the collection time points of the sample future accumulation sequence are multiple second historical moments, the collection time point of the sample current accumulation set is the first historical moment, and the collection time point of the sample future accumulation sequence is after the collection time point of the sample current accumulation set.

[0204] In some embodiments, among multiple sample estimation feature graphs and their corresponding labels, the sample collection accuracy of the sewage pipe corresponding to the sewage pipe node is greater than the sample collection accuracy of the pipe corresponding to the ordinary node; and the sample collection accuracy of the pipe corresponding to the node is related to the importance score of the pipe corresponding to the node.

[0205] In some embodiments, the label of each node has the same time interval. For example, for the sewage pipe node, if the data is collected every hour in the future, the label of the sewage pipe node is the sewage pipe, and its actual hourly impurity accumulation. For the ordinary pipeline node, if the data is collected every two hours in the future, the label of the ordinary pipeline node is the ordinary pipeline, and its actual hourly corresponding impurity accumulation, and the corresponding impurity accumulation between two hours is the mean of the corresponding collected data. Just as an example, in response to the ordinary node collecting the impurity accumulation at 10:00 and 12:00 in the future, the label corresponding to the ordinary node is the ordinary pipeline, and the impurity accumulation at 10:00, 11:00 and 12:00. The impurity accumulation at 11:00 is the average of the impurity accumulation at 10:00 and 12:00.

[0206] Collection accuracy refers to the degree of data accuracy during the data collection process.

[0207] In some embodiments, the higher the acquisition accuracy, the greater the number of acquisition time points of the future accumulation amount sequence of samples in the same time period, that is, the smaller the time interval between the acquisition time points of the future accumulation amount sequence of samples. For example, for nodes with high importance scores (such as key sewage pipeline nodes), the time interval of their labels may be once every hour; while for ordinary nodes, the time interval may be once every two hours or every three hours, without limitation here. For another example, in response to the acquisition accuracy of node 1 being greater than the acquisition accuracy of node 2, the future time points corresponding to the label of node 1 may be 10:00, 11:00, 12:00, etc., and the future time points corresponding to the label of node 2 may be 10:00, 12:00, etc., without limitation here.

[0208] In some embodiments of the present specification, in the sample training set, the collection accuracy of important nodes is ensured to be higher than that of ordinary nodes, so as to improve the prediction accuracy of the future prediction model at key nodes. Specifically, the time intervals of the collection time points of the future accumulation amount sequence of samples of important nodes are shorter, and the collected data are richer, so that the future prediction model can more accurately capture the changing trend of impurity accumulation. Not only does it enhance the robustness of the future prediction model, but it also ensures that the prediction of key nodes is more accurate, thereby more effectively guiding future maintenance and cleaning work. In addition, this differentiated way of resource allocation can more efficiently utilize limited monitoring resources and optimize the monitoring strategy.

[0209] Step S430, determining the target sewage discharge equipment based on the future accumulation amount sequence and the future threshold value.

[0210] The future threshold refers to a threshold used to determine whether the average increase in the amount of impurity accumulation in the future is too large.

[0211] In some embodiments, the smart gas company management platform determines the future threshold value through the seventh preset rule based on the flow data and the important score of the pipeline. The seventh preset rule includes that the future threshold value is negatively correlated with the flow data and the important score of the pipeline.

[0212] For more information about pipeline flow data and important scores, see Figure 2 and its related description.

[0213] In some embodiments, in response to the average of the increase in the amount of impurities accumulated in the future time of the sewage discharge equipment being greater than the future threshold, the smart gas company management platform determines the sewage discharge equipment as the target sewage discharge equipment. The increase in the amount of impurities accumulated in the future time refers to the rate of change of the amount of impurities accumulated in the future time relative to the initial value or a previous time point.

[0214] In some embodiments, the smart gas company management platform identifies a time point in the future when the amount of impurity accumulation exceeds a cleaning threshold, and in response to the time interval between this time point and the current time point being less than the time threshold, the sewage discharge equipment is the target sewage discharge equipment.

[0215] For more information about the cleanup threshold, see Figure 3 Step S330 and its related description.

[0216] In some embodiments, the smart gas company management platform determines the cleaning threshold through an eighth preset rule based on the pipeline importance score and the pipeline flow data. The eighth preset rule reflects that the time threshold is negatively correlated with the pipeline importance score and the pipeline flow data.

[0217] In some embodiments of the present specification, an estimated feature map is constructed based on sewage work data and gas monitoring data, which helps to more accurately predict the future accumulation sequence. Based on the estimated feature map, the future accumulation is predicted through the future estimation model, which can better reflect the complex relationship between the data and improve the accuracy and reliability of the prediction. Based on the future accumulation sequence and future threshold, the target sewage equipment is determined, and the system can more accurately determine the sewage equipment that needs to be cleaned first, which helps to improve the efficiency of the cleaning work and reduce resource waste.

[0218] In some embodiments, after the target sewage discharge equipment is determined based on step S410-step S430, the sewage discharge equipment that is not determined as the target sewage discharge equipment is determined as the second sewage discharge equipment. In response to the number of the second sewage discharge equipment being at least one, the smart gas company management platform obtains, for one second sewage discharge equipment, a second associated pipeline of the sewage discharge pipeline corresponding to the second sewage discharge equipment based on the gas monitoring data; and determines the target sewage discharge equipment based on the future accumulation amount sequence, the second associated pipeline and the associated threshold.

[0219] The second sewage discharge device, the second associated pipeline, and the method of obtaining the second associated pipeline are similar to the first sewage discharge device, the first associated pipeline, and the method of obtaining the first associated pipeline. Figure 3 The related descriptions will not be repeated here.

[0220] In some embodiments, the smart gas company management platform determines the sewage equipment whose increase in the amount of impurities accumulated in the second associated pipeline of the second sewage equipment exceeds the associated threshold and the quantity exceeds the quantity threshold as the target sewage equipment.

[0221] In some embodiments, within a preset time period in the future, if the smart gas company management platform determines that the second associated pipeline with impurity accumulation exceeding the associated threshold is greater than the quantity threshold, the sewage discharge equipment is determined as the target sewage discharge equipment.

[0222] In some embodiments of the present specification, by obtaining the second associated pipeline of the sewage pipe corresponding to the second sewage discharge equipment, the influence of the second associated pipeline on the second sewage discharge equipment can be evaluated, providing more dimensional information for determining the target sewage discharge equipment. At the same time, the target sewage discharge equipment can be determined more accurately in combination with the future accumulation sequence, the second associated pipeline and the associated threshold. Not only the situation of the second sewage discharge equipment itself is considered, but also the influence of its associated pipeline is considered, thereby improving the efficiency of the cleaning work. In addition, since some impurities may be carried when inputting gas to the downstream pipeline, further considering the downstream second associated pipeline can also help reduce the risk of failure of the downstream pipeline due to impurity accumulation, thereby improving the accuracy of determining the target sewage discharge equipment.

[0223] Figure 5 FIG. 1 is an exemplary flow chart for determining cleaning parameters according to some embodiments of this specification. Figure 5 As shown, the process 500 includes the following steps. In some embodiments, the process 500 can be executed by a smart gas company management platform.

[0224] Step S510: obtaining at least one candidate working parameter.

[0225] The candidate working parameters refer to one or more parameters that can be used for pipeline cleaning. The content of the candidate working parameters is similar to that of the cleaning working parameters. For example, the candidate working parameters include the sewage valve opening level, the monitoring level, and the intelligent working parameters of the cleaning crawler robot.

[0226] In some embodiments, the candidate operating parameters are set based on experience. In some embodiments, the smart gas company management platform randomly generates candidate operating parameters. For example, the sewage valve opening level, the monitoring level, and the intelligent operating parameters of the cleaning crawler robot are randomly generated within their respective working ranges. Among them, the working range can be preset, and illustratively, the working range is a safe working range, and the safe working range is determined according to the factory parameters.

[0227] Step S520, for a candidate working parameter, based on the candidate working parameter, the current accumulation amount set of the target sewage discharge equipment, the accumulation impurity composition and the physical characteristics of the pipeline, determine the cleaning effect score and cleaning time corresponding to the candidate working parameter.

[0228] The accumulated impurity components refer to the components of the accumulated impurities in the sewage pipe. For example, the accumulated impurity components may include sand, rust, water, water vapor, sulfide, carbon dioxide, grease, dust, etc. In some embodiments, the accumulated impurity components are obtained based on the gas composition data of the fuel gas before and after filtering. For example, the impurity components whose composition data decreases before and after filtering are the accumulated impurity components.

[0229] The cleaning effect score refers to the score of the cleaning effect of cleaning the sewage pipe based on the candidate work parameters. For example, the cleaning effect score can be set to a value of 0-1, 0 means no cleaning, 1 means very clean cleaning, and the higher the value, the better the cleaning effect.

[0230] The cleaning time refers to the time required to clean the sewage pipe based on the candidate working parameters. For example, it takes 1 hour to complete the cleaning using a certain candidate working parameter.

[0231] In some embodiments, the smart gas company management platform constructs a second feature vector based on candidate working parameters, the current accumulation set of target sewage equipment, the accumulation impurity composition and the physical characteristics of the pipeline, and then searches in the second vector database based on the second feature vector to determine the cleaning effect score and cleaning time corresponding to the candidate working parameters.

[0232] The second vector database is a database for determining the cleaning effect score and the cleaning time. In some embodiments, the second vector database includes a plurality of second reference vectors, and a reference cleaning effect score and a reference cleaning time corresponding to each second reference vector.

[0233] In some embodiments, the smart gas company management platform constructs a second reference vector based on the historical impurity accumulation, historical pipeline physical characteristics, historical weather data, and historical gas composition data corresponding to the second reference data, and uses the historical cleaning effect score and historical cleaning time corresponding to the second reference data as the reference cleaning effect score and reference cleaning time. The second reference data refers to the historical data used to construct the second vector database.

[0234] In some embodiments, the reference cleaning time is an actual cleaning time corresponding to the second reference data.

[0235] In some embodiments, the smart gas company management platform determines the reference cleaning effect score based on the difference in filtering scores before and after cleaning, the difference in flow data before and after cleaning, and the difference in filtering ratios before and after cleaning in the second reference data. The difference in filtering scores before and after cleaning, the difference in flow data before and after cleaning, and the difference in filtering ratios before and after cleaning are proportional to the reference cleaning effect score. For more information about filtering scores and flow data, please refer to Figure 2 and its related description.

[0236] The filtration ratio is equal to the flow rate data after filtration divided by the flow rate data before filtration. The flow rate data before filtration refers to the flow rate data on the front side of the sewage discharge device (the side entering the sewage discharge device), and the flow rate data after filtration refers to the flow rate data on the back side of the sewage discharge device (the side exiting the sewage discharge device).

[0237] In some embodiments, the smart gas company management platform ensures that the amount of data in the second vector database is sufficient by continuously updating the data in the second vector database. For example, each time cleaning is performed, data is recorded to form a second reference vector, and the cleaning effect is scored after cleaning, so that the second reference vector determined above and its corresponding reference cleaning effect score and reference cleaning time are stored in the second vector database.

[0238] The process of searching the second vector database is similar to the process of searching the first vector database, and will not be repeated here.

[0239] Step S530: determining a cleaning work parameter based on a cleaning effect score and a cleaning time of at least one candidate work parameter.

[0240] In some embodiments, the smart gas company management platform selects one with the highest comprehensive score among at least one candidate working parameter as the determined cleaning working parameter.

[0241] In some embodiments, the smart gas company management platform determines the comprehensive score by the following formula (3): (3) in, For comprehensive rating; is the cleaning effect score; t is the cleaning time, , They are and The coefficient of ; where is a positive number, Is a negative number.

[0242] In some embodiments, the smart gas company management platform determines the cleaning work parameters based on the cleaning effect score, cleaning time, and pipeline importance score of the target sewage discharge equipment. For example, the cleaning effect score in formula (3) The coefficient of Pipeline importance score related to the target sewage treatment equipment. Pipeline importance score and coefficient of the target sewage treatment equipment Directly proportional.

[0243] In some embodiments of the present specification, the pipeline importance score is considered when determining the cleaning work parameters. For pipelines with higher importance scores, more resources can be allocated to ensure the effectiveness of the cleaning work. By giving important pipelines with high pipeline importance scores a higher cleaning effect score weight, it can be ensured that these pipelines obtain the best cleaning effect, reduce the possibility of impurity residues, thereby extending the service life of the equipment and reducing the risk of failure.

[0244] In some embodiments of the present specification, cleaning work parameters are determined based on the cleaning effect score and the cleaning time, so that reasonable work parameters can be efficiently selected to reduce work time and improve cleaning work efficiency while achieving the cleaning purpose.

[0245] In some embodiments, in response to the accumulated impurity components meeting the additional cleaning conditions, the smart gas company management platform generates additional cleaning instructions based on the accumulated impurity components, and sends the additional cleaning instructions to the smart gas equipment object platform to control the cleaning crawling robot to carry additional cleaning components to clean the target sewage equipment.

[0246] Additional cleaning conditions refer to conditions for determining whether it is necessary to use other cleaning methods other than the basic cleaning method (for example, jetting water) for cleaning. In some embodiments, the additional cleaning conditions include that the content of a specific impurity component is greater than the corresponding condition threshold. Among them, the specific impurity component refers to impurities that cannot be removed by the basic cleaning method. The condition thresholds corresponding to specific impurity components are different, and the condition thresholds are pre-set thresholds. For example, the additional cleaning conditions include that the content of corrosive substances in the accumulated impurity components exceeds m%, the content of chemical deposits in the accumulated impurity components exceeds n%, the content of microorganisms in the accumulated impurity components exceeds v%, etc.

[0247] It is understandable that different specific impurity components correspond to different cleaning methods. For example, the additional cleaning conditions include that the content of corrosive substances in the accumulated impurity components exceeds m%, or the content of chemical deposits in the accumulated impurity components exceeds n%. At this time, ordinary cleaning methods cannot effectively remove the accumulated impurities. At this time, chemical cleaning agents or solvents can be used to assist in removal. For another example, if the content of microorganisms in the accumulated impurity components exceeds v%, biocides that will not cause damage to the pipeline (for example, bactericides or disinfectants with no side effects) can be used for cleaning.

[0248] Additional cleaning instructions refer to controlling the cleaning crawler robot to carry additional cleaning components to clean the target sewage discharge equipment. Among them, additional cleaning components refer to components other than the cleaning components used in the basic cleaning method. For example, additional cleaning instructions include instructions to instruct the robot to load a disinfectant sprayer, evenly spray disinfectant on the inner wall of the pipe, and stay for a period of time.

[0249] In some embodiments, the smart gas company management platform generates additional cleaning instructions based on the accumulated impurity components through the ninth preset rule. Among them, the ninth preset rule refers to different additional cleaning conditions and corresponding additional cleaning instructions, and the additional cleaning instructions are set by technicians. For example, the ninth preset rule includes that the content of microorganisms in the accumulated impurity components exceeds v%, and the additional cleaning instructions are instructions to instruct the robot to load the disinfectant sprayer, spray the disinfectant evenly on the inner wall of the pipeline, and stay for a period of time.

[0250] According to some embodiments of the present specification, for accumulated impurities that are difficult to clean, additional cleaning instructions are provided to control the cleaning crawling robot to perform additional cleaning operations on the accumulated impurities that are difficult to clean, so that the sewage pipe can be cleaned more comprehensively and the cleaning effect can be improved.

[0251] In some embodiments, the cleaning crawler robot further includes an ultrasonic sensor. Before cleaning, the cleaning crawler robot collects ultrasonic data based on the ultrasonic sensor and uploads the ultrasonic data to the smart gas company management platform through the smart gas equipment object platform; and the smart gas company management platform determines the actual pipeline information and the actual working parameters of the cleaning crawler robot based on the ultrasonic data.

[0252] Ultrasonic sensors are sensors that convert ultrasonic signals into other energy signals (usually electrical signals). Ultrasonic waves have a good penetrating effect on liquids and solids. When they hit impurities or interfaces, they will produce significant reflections to form reflected echoes. Therefore, they can be used to measure the actual thickness of the pipeline, the thickness of accumulated impurities, etc.

[0253] Ultrasonic data refers to data collected using ultrasonic sensors.

[0254] The actual pipeline information refers to the information of the real pipeline and the accumulated impurities. For example, the actual pipeline information may include the actual thickness of the pipeline, the thickness of the accumulated impurities, etc.

[0255] In some embodiments, the smart gas company management platform obtains actual pipeline information based on ultrasonic data. In some embodiments, ultrasonic data can be processed using a variety of methods to obtain actual pipeline information, such as pulse-echo method (PEM), through-transmission method (TTM) and other algorithms.

[0256] The actual working parameters refer to the parameters used by the cleaning crawler robot in actual cleaning work.

[0257] In some embodiments, the smart gas company management platform determines the actual working parameters based on the actual pipeline information through the tenth preset rule.

[0258] The tenth preset rule refers to the rules of actual working parameters corresponding to different actual pipeline information. The actual working parameters are set by technicians. For example, the tenth preset rule includes that the pipe thickness at a certain position in the pipeline is lower than the thickness threshold, and / or the thickness of the accumulated impurities is lower than the accumulation threshold. In order to avoid further damage to the pipeline wall, the cleaning crawling robot uses a brush and a jet of water for cleaning, and the cleaning intensity of the brush and the jet of water is positively correlated to the impurity accumulation thickness at that position. For another example, the tenth preset rule includes that the pipe thickness at a certain position in the pipeline is higher than the thickness threshold, and the thickness of the accumulated impurities is higher than the accumulation threshold. Then the cleaning crawling robot uses a scraper and a jet of water for cleaning, and the cleaning intensity of the brush and the jet of water is positively correlated to the impurity accumulation thickness at that position. Among them, the thickness threshold and the accumulation threshold are pre-set by technicians.

[0259] According to some embodiments of the present description, the actual thickness of the pipe wall and the thickness of the accumulated impurities can be determined using ultrasonic sensors, and more accurate actual working parameters can be determined to achieve a cleaning effect while protecting the pipe wall and preventing further damage to the pipe wall.

[0260] This specification provides a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the above-mentioned pipeline cleaning method based on the smart gas supervision Internet of Things.

[0261] The embodiments in this specification are only for illustration and description, and do not limit the scope of application of this specification. For those skilled in the art, various modifications and changes that can be made under the guidance of this specification are still within the scope of this specification.

[0262] Certain features, structures or characteristics of one or more embodiments of this specification may be appropriately combined.

[0263] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. A pipeline cleaning method based on smart gas monitoring Internet of Things, characterized in that: The method is performed by a smart gas supervision Internet of Things system, which includes a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a smart gas gas company sensor network platform and a smart gas equipment object platform; the smart gas government safety supervision object platform includes a smart gas gas company management platform, the smart gas gas company management platform includes a gas database, and the gas database is configured as a storage device; the smart gas government safety supervision management platform and the smart gas gas company management platform are configured as servers; the smart gas government safety supervision sensor network platform and the smart gas gas company sensor network platform are configured as a communication network, and the smart gas equipment object platform is configured as a sewage discharge device and a gas monitoring device, the sewage discharge device includes at least one of a filtering device and a sewage discharge pipeline, and the gas monitoring device is arranged on the gas pipeline; the method includes: The smart gas company management platform obtains the sewage discharge work data and gas monitoring data collected by the smart gas equipment object platform through the smart gas company sensor network platform, and stores the sewage discharge work data and the gas monitoring data in the gas database; The smart gas company management platform determines pipeline cleaning parameters based on the sewage work data and the gas monitoring data, and uploads the pipeline cleaning parameters to the smart gas government safety supervision management platform. The pipeline cleaning parameters include target sewage equipment and its corresponding cleaning work parameters. The cleaning work parameters include sewage valve opening level, monitoring level and intelligent working parameters of the cleaning crawler robot; and The smart gas government safety supervision and management platform generates a cleaning and control instruction based on the pipeline cleaning parameters, and sends the cleaning and control instruction to the smart gas equipment object platform to control the target sewage discharge equipment to clean with the cleaning work parameters.

2. The method according to claim 1, characterized in that The cleaning and control instructions also include indirect control instructions, which are configured to increase the monitoring level of the gas monitoring equipment on the affected pipeline when cleaning the target sewage discharge equipment. The affected pipeline refers to a pipeline related to the sewage pipe corresponding to the target sewage discharge equipment.

3. The method according to claim 1, characterized in that The determining of pipeline cleaning parameters based on the sewage discharge work data and the gas monitoring data includes: Based on the sewage discharge working data and the gas monitoring data, a stacking feature graph is constructed, wherein the stacking feature graph is composed of nodes and edges, wherein the nodes include sewage discharge pipeline nodes and common pipeline nodes, wherein the attributes of the sewage discharge pipeline nodes include the type of filtering equipment, the sewage discharge working data, the gas monitoring data, weather data, and physical characteristics of the pipeline, wherein the attributes of the common pipeline nodes include the gas monitoring data, the weather data, and physical characteristics of the pipeline, wherein the edges include the lines between two physically connected nodes, wherein the attributes of the edges include the direction of gas fluid, wherein the sewage discharge working data include current sewage discharge data and historical sewage discharge data, wherein the gas monitoring data include current monitoring data and historical monitoring data, and wherein the weather data include current weather data and historical weather data; Based on the accumulation feature graph, determining a current accumulation amount set by an accumulation amount determination model, wherein the accumulation amount determination model is a machine learning model; and The target sewage discharge equipment is determined based on the current accumulation amount set and the cleaning threshold.

4. The method according to claim 3, characterized in that The current accumulation amount set includes the sewage pipeline corresponding to at least one sewage pipeline node and its current impurity accumulation amount, and the method further includes: For the sewage pipe corresponding to a sewage pipe node and its current impurity accumulation amount, in response to the current impurity accumulation amount being less than the cleaning threshold and greater than the attention threshold, the smart gas company management platform determines the sewage pipe corresponding to the current impurity accumulation amount as a concerned sewage pipe, and generates a monitoring enhancement instruction, and sends the monitoring enhancement instruction to the smart gas equipment object platform to increase the monitoring level of the gas monitoring equipment of the concerned sewage pipe.

5. The method according to claim 3, characterized in that Determination of the cleaning threshold includes: The cleaning threshold is determined based on the pipeline physical characteristics, the historical monitoring data and the pipeline importance score.

6. The method according to claim 3, characterized in that In response to the number of the first sewage discharge equipment being at least one, the first sewage discharge equipment being the sewage discharge equipment that is not determined as the target sewage discharge equipment, the method further includes: For one of the first sewage treatment equipment, Based on the gas monitoring data, obtaining a first associated pipe of the sewage pipe corresponding to the first sewage discharge equipment; and The target sewage discharge equipment is determined based on the current accumulation amount set, the first associated pipeline and the associated threshold.

7. The method according to claim 1, characterized in that The determining of pipeline cleaning parameters based on the sewage discharge work data and the gas monitoring data includes: Based on the sewage discharge working data and the gas monitoring data, an estimated feature graph is constructed, the estimated feature graph is composed of nodes and edges, the nodes include sewage discharge pipeline nodes and common pipeline nodes, the attributes of the sewage discharge pipeline nodes include filtering equipment type, the sewage discharge working data, future sewage discharge data, current accumulation amount set, historical accumulation amount set, future maintenance data, the gas monitoring data, weather data, pipeline physical characteristics and pipeline aging degree, the attributes of the common pipeline nodes include the gas monitoring data, the weather data, the future maintenance data, the pipeline physical characteristics and the pipeline aging degree, the edges include the connection between two physically connected nodes, the attributes of the edges include gas fluid direction, the sewage discharge working data include current sewage discharge data and historical sewage discharge data, the gas monitoring data include current monitoring data and historical monitoring data, and the weather data include future weather data, current weather data and historical weather data; Based on the estimated feature graph, determining a future accumulation amount sequence through a future estimation model, wherein the future estimation model is a machine learning model; and The target sewage discharge equipment is determined based on the future accumulation amount sequence and the future threshold value.

8. The method according to claim 1, characterized in that In response to the target sewage discharge equipment being determined, the determining of pipeline cleaning parameters based on the sewage discharge work data and the gas monitoring data includes: obtaining at least one candidate working parameter; For one of the candidate operating parameters, based on the candidate operating parameter, the current accumulation amount set of the target sewage discharge equipment, the accumulation impurity composition and the physical characteristics of the pipeline, determine the cleaning effect score and cleaning time corresponding to the candidate operating parameter; and The cleaning operating parameter is determined based on the cleaning effect score and the cleaning time of the at least one candidate operating parameter.

9. A smart gas monitoring Internet of Things system, characterized in that: The Internet of Things system includes a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a smart gas gas company sensor network platform and a smart gas equipment object platform; the smart gas government safety supervision object platform includes a smart gas gas company management platform, the smart gas gas company management platform includes a gas database, and the gas database is configured as a storage device; the smart gas government safety supervision management platform and the smart gas gas company management platform are configured as servers; the smart gas government safety supervision sensor network platform and the smart gas gas company sensor network platform are configured as a communication network, and the smart gas equipment object platform is configured as a sewage discharge device and a gas monitoring device, the sewage discharge device includes at least one of a filtering device and a sewage discharge pipeline, and the gas monitoring device is arranged on the gas pipeline; the Internet of Things system is configured as: The smart gas company management platform obtains the sewage discharge work data and gas monitoring data collected by the smart gas equipment object platform through the smart gas company sensor network platform, and stores the sewage discharge work data and the gas monitoring data in the gas database; The smart gas company management platform determines pipeline cleaning parameters based on the sewage work data and the gas monitoring data, and uploads the pipeline cleaning parameters to the smart gas government safety supervision management platform. The pipeline cleaning parameters include target sewage equipment and its corresponding cleaning work parameters. The cleaning work parameters include sewage valve opening level, monitoring level and intelligent working parameters of the cleaning crawler robot; and The smart gas government safety supervision and management platform generates a cleaning and control instruction based on the pipeline cleaning parameters, and sends the cleaning and control instruction to the smart gas equipment object platform to control the target sewage discharge equipment to clean with the cleaning work parameters.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the pipeline cleaning method based on the smart gas supervision Internet of Things as described in claim 1.

Images