Gas recovery system and method based on smart gas monitoring Internet of Things

Abstract

The present invention provides a gas recovery system and method based on a smart gas supervision Internet of Things, the system includes a government supervision management platform, a government supervision sensor network platform, a government supervision object platform, a gas company sensor network platform, and a gas equipment object platform, the government supervision object platform includes a gas company management platform; the method includes: obtaining target detection data and target flow data of a pipeline to be recovered from the gas equipment object platform; determining a gas pollution value based on the target detection data and the target flow data; determining purification parameters of a purification device based on the gas pollution value and the target flow data; determining a recovery instruction, and sending it to at least one user interaction device through the gas equipment object platform; and, in response to obtaining a recovery completion instruction, sending the purification parameters to the gas equipment object platform. Measuring the situation of gas passing through the pipeline by the gas pollution value and then determining the purification parameters can ensure the safety of gas recovery.

Description

Technical Field

[0001] This specification relates to the technical field of gas recovery, and particularly to a gas recovery system and method based on the intelligent gas supervision Internet of Things. Background Art

[0002] Before the pipeline is repaired, replaced or its operation is adjusted, it is necessary to first recover the gas in the pipeline to ensure safety and reduce waste. However, the gas in the pipeline may be contaminated. For example, dust and particulate matter outside the pipeline may enter the pipeline interior, and moisture in the air may condense on the inner wall of the pipeline to form moisture, etc., thus affecting the quality of the gas.

[0003] Therefore, it is necessary to provide a gas recovery system and method based on the intelligent gas supervision Internet of Things, which helps to detect and purify the gas to be recovered, and at the same time improves the safety and economic benefits of the recovery process. Summary of the Invention

[0004] The present invention provides a gas recovery system based on the intelligent gas supervision Internet of Things, including a government supervision management platform, a government supervision sensor network platform, a government supervision object platform, a gas company sensor network platform, and a gas equipment object platform. The government supervision object platform includes a gas company management platform. Among them, the government supervision management platform, the government supervision sensor network platform, and the government supervision object platform interact in sequence, and the gas company management platform, the gas company sensor network platform, and the gas equipment object platform interact in sequence. The gas equipment object platform includes a purification device, a gas storage tank group, and a temporary storage tank group. The temporary storage tank group includes at least one temporary storage tank, and the temporary storage tank is used to store the gas to be recovered. The purification device is used to extract the gas to be recovered from the temporary storage tank group, purify the gas to be recovered, and store the purified clean gas into the gas storage tank group. The gas storage tank group includes at least one gas storage tank, and the gas storage tank is used to store the clean gas. The gas equipment object platform includes at least one user interaction device. The gas company management platform is configured to: obtain the target detection data and target flow data of the pipeline to be recovered from the gas equipment object platform; determine the gas pollution value based on the target detection data and the target flow data; determine the purification parameters of the purification device based on the gas pollution value and the target flow data; determine a recovery instruction, and send the recovery instruction to the at least one user interaction device through the gas equipment object platform, and the recovery instruction is used to instruct the staff to store the gas in the pipeline to be recovered into the temporary storage tank group; and, in response to obtaining a recovery completion instruction, send the purification parameters to the gas equipment object platform, and the gas equipment object platform is configured to: generate a control instruction based on the purification parameters, and send the control instruction to the purification device to control the purification device to operate according to the purification parameters.

[0005] The present invention provides a gas recovery method based on the intelligent gas supervision Internet of Things. The method is implemented based on an intelligent gas recovery Internet of Things system, which includes a government supervision management platform, a government supervision sensor network platform, a government supervision object platform, a gas company sensor network platform, and a gas equipment object platform. The gas equipment object platform includes at least one user interaction device. The method includes: obtaining target detection data and target flow data of a pipeline to be recovered from the gas equipment object platform; determining a gas pollution value based on the target detection data and the target flow data; determining purification parameters of the purification equipment based on the gas pollution value and the target flow data; determining a recovery instruction, and sending the recovery instruction to the at least one user interaction device through the gas equipment object platform. The recovery instruction is used to instruct the staff to store the gas in the pipeline to be recovered into a temporary storage tank group; and, in response to obtaining a recovery completion instruction, sending the purification parameters to the gas equipment object platform, which is configured to: generate a control instruction based on the purification parameters and send the control instruction to the purification equipment to control the purification equipment to operate according to the purification parameters.

[0006] The embodiments of the present specification at least include the following beneficial effects: When performing maintenance, replacement, or operation adjustment on a pipeline, it is necessary to first recover the gas in the pipeline. However, the gas may be polluted during transmission through the pipeline and cannot be directly recovered. By measuring the gas pollution value, the situation of the gas passing through the pipeline is measured, and then the purification parameters are determined, thereby ensuring the safety of gas recovery and reducing waste of gas resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] This specification will be further described in the form of exemplary embodiments, which will be described in detail through the accompanying drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0008] Figure 1 is a schematic structural diagram of a gas recovery system based on the intelligent gas supervision Internet of Things according to some embodiments of this specification;

[0009] Figure 2 is an exemplary flowchart of a gas recovery method based on the intelligent gas supervision Internet of Things according to some embodiments of this specification;

[0010] Figure 3 is an exemplary schematic diagram of a pollution value determination model according to some embodiments of this specification;

[0011] Figure 4 is an exemplary schematic diagram of an effect determination model according to some embodiments of this specification. Detailed implementation manners

[0012] To more clearly illustrate the technical solutions of the embodiments of this specification, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0013] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0014] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the operations before or after may not necessarily be executed precisely in sequence. On the contrary, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0016] A smart gas recovery Internet of Things system and a gas recovery method provided by some embodiments of this specification can be applied to multiple scenarios, such as gas management, environmental protection, resource recovery, etc. For example, in industrial production, especially in industries such as chemical engineering and metallurgy, a large amount of gas containing impurities is generated. The smart gas recovery Internet of Things system is integrated into the gas treatment systems of these enterprises to effectively recover and purify the gas in industrial production and achieve the reuse of resources; for another example, when the gas pipeline needs to be maintained, repaired or replaced, the smart gas recovery Internet of Things system can recover and purify the gas in the pipeline to be recovered to ensure that the gas meets the re-emission standards.

[0017] Figure 1 is a schematic structural diagram of a gas recovery system based on the smart gas supervision Internet of Things shown in some embodiments of this specification.

[0018] As Figure 1As shown, the gas recovery system 100 based on the intelligent gas supervision Internet of Things may include a government supervision management platform 110, a government supervision sensing network platform 120, a government supervision object platform 130, a gas company sensing network platform 140, and a gas equipment object platform 150.

[0019] The government supervision management platform 110 is a platform for the government to conduct supervision and management.

[0020] In some embodiments, the government supervision management platform 110 may be configured as a single server or a server group. The server group may be centralized or distributed (for example, the servers may be a distributed system). In some embodiments, the server may be local or remote.

[0021] In some embodiments, the government supervision management platform 110 may include a government safety supervision management platform 111. The government safety supervision management platform 111 may be a platform for the government to conduct safety supervision and management. For example, the government safety supervision management platform 111 may receive information related to gas safety (such as gas safety incident alarm data, gas equipment operation status data, gas pipeline maintenance data) to conduct supervision and management of gas safety. In some embodiments, the government safety supervision management platform 111 may be configured as a processor, such as a combination of one or more of a microcontroller (MCU), an embedded processor, and a graphics processing unit (GPU).

[0022] The government supervision sensing network platform 120 is a platform for sensing communication of supervision-related information and control information sensing communication. For example, the government supervision sensing network platform 120 may be configured as a communication base station, a router, a wireless device, etc.

[0023] In some embodiments, the government supervision sensing network platform 120 may include a government safety supervision sensing network platform 121. The government safety supervision sensing network platform 121 may be a functional platform for managing safety supervision-related information.

[0024] In some embodiments, the government supervision sensing network platform 120 may perform data interaction with the government supervision management platform 110 and the government supervision object platform 130.

[0025] The government supervision object platform 130 is a platform for providing relevant data such as gas use, operation, and safety, and for executing control information.

[0026] In some embodiments, the government regulatory object platform 130 may include a gas company management platform 131 and a key gas-using enterprise platform 132.

[0027] The gas company management platform 131 refers to a platform for managing gas-related data of gas companies.

[0028] In some embodiments, the gas company management platform 131 may interact with a gas company sensor network platform 140 and a government regulatory sensor network platform 120 for data. For example, the gas company management platform 131 may obtain gas regulatory information, target detection data of pipelines to be recycled, target flow data, etc. in different gas regulatory areas based on the gas company sensor network platform 140. In some embodiments, the gas company management platform 131 may be configured on a gas company management server.

[0029] In some embodiments, the gas company management platform 131 may obtain target detection data and target flow data of pipelines to be recycled from a gas equipment object platform. The target detection data includes impurity detection time, impurity type, and impurity location. The target flow data includes the pipeline area where gas flow exists. Based on the target detection data and target flow data, determine a gas pollution value. Based on the gas pollution value and target flow data, determine purification parameters for a purification device. Determine a recycling instruction and send it to at least one user interaction device through a gas user object platform. The recycling instruction is used to instruct staff to store the gas in the pipeline to be recycled into a temporary storage tank group. And, in response to obtaining a recycling completion instruction, send the purification parameters to the gas equipment object platform. For more content on this part, reference can be made to Figures 2 - 4 and its related description.

[0030] The key gas-using enterprise platform 132 refers to a platform for managing relevant information of key gas-using enterprises. For example, the government regulatory object platform 130 may obtain basic information of enterprises through the key gas-using enterprise platform 132.

[0031] The gas company sensor network platform 140 refers to a platform for sensing information sensing communication and control information sensing communication. For example, the gas company sensor network platform 140 may be configured as a communication base station, a router, a wireless device, etc.

[0032] In some embodiments, the gas company sensor network platform 140 may interact with the gas company management platform 131, the key gas-using enterprise platform 132, and a gas equipment object platform 150 for data.

[0033] The gas equipment object platform 150 may be a functional platform for generating sensing information and executing control information.

[0034] In some embodiments, the gas equipment object platform 150 includes at least one user interaction device 150-1. The user interaction device 150-1 is used for interacting with the user. In some embodiments, the user interaction device 150-1 can be used to receive a recovery instruction to instruct the user to store the gas in the pipeline to be recovered into the temporary storage tank group based on the recovery instruction. In some embodiments, the user interaction device 150-1 can obtain the input information of the user, etc. In some embodiments, the user interaction device 150-1 can include input components and output components such as buttons, touch sensors, joysticks, keypads, microphones, and display screens. In some embodiments, the user can issue a recovery completion instruction through the user interaction device 150-1 to indicate that the user has stored the gas in the pipeline to be recovered into the temporary storage tank group.

[0035] In some embodiments, the gas equipment object platform 150 includes a purification device 150-2, a gas storage tank group 150-3, and a temporary storage tank group 150-4.

[0036] The temporary storage tank group 150-4 is a container for containing gas or fluid. For example, the temporary storage tank group 150-4 can be used to temporarily store the unclean gas in the pipeline to be recovered. The unclean gas refers to the gas that is contaminated during the gas transmission process and contains impurities and pollutants (such as substances adsorbed or carried from the inner wall of the pipeline, such as rust and dust).

[0037] In some embodiments, the temporary storage tank group 150-4 includes one or more temporary storage tanks, and the temporary storage tanks are used to store the gas to be recovered. The gas to be recovered is the unclean gas before purification.

[0038] When maintenance, repair, or replacement of the gas pipeline is required, the unclean gas in the pipeline cannot be directly used or stored, as it may contain substances that affect the combustion efficiency or cause damage to the equipment. Therefore, purification treatment is required to remove the impurities and pollutants therein to meet the specified gas quality standards and become clean gas.

[0039] The purification device 150-2 is a device for purifying unclean gas. For example, the purification device can be a gas purification device, etc. The purification device 150-2 can remove the impurities and pollutants in the gas to be recovered through filtration, separation, and other treatment means, so as to achieve the purpose of purification and improve the gas quality.

[0040] In some embodiments, the purification device 150-2 can include a pipeline regulating valve, a pressure control unit, a temperature control unit, etc. (not shown in the figure).

[0041] The pipeline regulating valve is a valve for controlling the flow or flow rate of gas in the purification device.

[0042] The pressure control unit refers to a device used to regulate the pressure inside the purification equipment. For example, the pressure control unit can control the pressure control unit to increase or decrease the pressure according to the purification parameters to achieve the purpose of regulating the indoor pressure. Correspondingly, the pressure control unit can include: a compressor and a pressure relief valve.

[0043] The temperature control unit refers to a device used to regulate the temperature inside the purification equipment. For example, the temperature control unit can control the heating or cooling of the temperature control unit according to the purification parameters to achieve the purpose of regulating the temperature. Correspondingly, the temperature control unit can include: a heater and a cooler.

[0044] The gas storage tank group 150-3 is a container used to hold gas or fluid. For example, the gas storage tank group 150-3 can be used to store the purified clean gas.

[0045] In some embodiments, the gas storage tank group 150-3 can include one or more gas storage tanks, and the gas storage tanks are used to store the clean gas.

[0046] In some embodiments, the purification equipment 150-2 can be communicatively connected to the gas equipment object platform 150. The gas equipment object platform 150 is sequentially communicatively connected to the gas company sensing network platform 140, the government supervision object platform 130, the government supervision sensing network platform 120, and the government supervision management platform 110. The gas equipment object platform 150 can receive the purification parameters issued by the government supervision management platform, generate corresponding control instructions based on the purification parameters, and send the control instructions to the purification equipment 150-2; the purification equipment 150-2 can, based on the control instructions, extract the gas to be recycled from the temporary storage tank group, purify the gas to be recycled, and store the purified clean gas in the gas storage tank group.

[0047] In some embodiments, the gas equipment object platform 150 can also include various gas pipeline network devices (such as outdoor gas pipelines, valve control devices, pressure regulating devices, etc.) and monitoring devices (such as temperature sensors, pressure sensors, gas detectors, inspection robots, etc.).

[0048] In some embodiments, the gas equipment object platform 150 can obtain the target detection data and target flow data of the pipeline to be recycled, and upload them to the government supervision management platform 110 via the gas company sensing network platform 140, etc. For more content about the target detection data and target flow data, reference can be made to Figure 2 the relevant description.

[0049] For more content about the above part, reference can be made to Figure 2 and its relevant description.

[0050] In some embodiments of this specification, through the gas recovery system 100 based on the intelligent gas supervision Internet of Things, it can operate coordinately and regularly under the unified management of the intelligent gas management platform, realizing the automatic monitoring of the internal facilities and equipment in the integrated pipe gallery.

[0051] In some embodiments, the platform in the gas recovery system 100 based on the intelligent gas supervision Internet of Things can be divided into the intelligent gas primary network and the intelligent gas secondary network. Among them, the intelligent gas primary network refers to the network for government users to supervise the operation of the gas pipeline network, and the intelligent gas secondary network includes the network for the operation of the gas pipeline network. In some embodiments, the same platform in the gas recovery system 100 based on the intelligent gas supervision Internet of Things can play different platform roles in the intelligent gas primary network and the intelligent gas secondary network.

[0052] In some embodiments, the intelligent gas primary network can include an intelligent gas primary network service platform, an intelligent gas primary network management platform, an intelligent gas primary network sensing network platform, and an intelligent gas primary network object platform. Among them, the intelligent gas primary network management platform can include a government supervision management platform 110, the intelligent gas primary network sensing network platform can include a government supervision sensing network platform 120, and the intelligent gas primary network object platform can include a government supervision object platform 130.

[0053] In some embodiments, the intelligent gas secondary network can include an intelligent gas secondary network management platform, an intelligent gas secondary network sensing network platform, and an intelligent gas secondary network object platform. Among them, the intelligent gas secondary network management platform can include a gas company management platform 131, the intelligent gas secondary network sensing network platform can include a gas company sensing network platform 140, and the intelligent gas secondary network object platform can include a gas equipment object platform 152.

[0054] It should be noted that the above description of the intelligent gas recovery Internet of Things system is only for convenience of description and does not limit this specification within the scope of the exemplified embodiments.

[0055] Figure 2 It is an exemplary flowchart of the gas recovery method based on the intelligent gas supervision Internet of Things shown in some embodiments of this specification.

[0056] In some embodiments, the process 200 can be implemented based on the gas company management platform of the intelligent gas recovery Internet of Things system. As Figure 2 shown, the process 200 includes the following steps:

[0057] Step 210, obtaining the target detection data and target flow data of the pipeline to be recovered from the gas equipment object platform.

[0058] The pipeline to be recycled refers to the gas pipeline that needs to have its gas recycled. In some embodiments, a gas pipeline that requires maintenance, replacement, or management operations associated with operational adjustments can be determined as the pipeline to be recycled.

[0059] The target detection data refers to the impurity detection data of the pipeline to be recycled within a preset time period. For example, the preset time period can be the time period of the most recent monitoring by the monitoring device. The target detection data can include the impurity detection data obtained during the most recent monitoring of the pipeline to be recycled.

[0060] The impurity detection data refers to information related to impurities within the pipeline.

[0061] In some embodiments, the impurity detection data can include the impurity detection time, the impurity type, and the impurity location of different types of impurities.

[0062] Among them, the impurity detection time refers to the specific time point when the impurity is detected. The impurity type refers to the result of classifying and identifying the impurities within the pipeline. For example, the impurity type can include types such as water vapor, dust particles, sulfides, etc. The impurity location refers to the location of the impurity within the pipeline.

[0063] The target flow data refers to the gas flow data of the pipeline to be recycled within a preset time period. For example, the target flow data can include the gas flow data obtained during the most recent monitoring of the pipeline to be recycled.

[0064] The gas flow data refers to information related to the flow condition of the gas within the pipeline.

[0065] In some embodiments, the gas flow data can include the pipeline area where gas flow exists.

[0066] The pipeline area where gas flow exists refers to a certain pipeline section or area within the pipeline to be recycled where gas passes through. When there is no pipeline section or area within the pipeline to be recycled where gas passes through, the gas flow data can be 0.

[0067] In some embodiments, the target detection data and the target flow data are monitored and collected by the monitoring devices of the gas equipment object platform. For example, the monitoring devices are distributed inside the pipeline to be recycled for monitoring and collecting the impurity detection data and the gas flow data within the pipeline to be recycled.

[0068] In some embodiments, the gas company management platform can obtain the impurity detection data and the gas flow data collected by the monitoring devices from the gas equipment object platform via the gas company sensing network platform. The gas company management platform can screen out the target detection data and the target flow data from the collected impurity detection data and gas flow data.

[0069] For more information about the gas equipment object platform, the gas company sensor network platform, the government supervision object platform, the government supervision sensor network platform, and the monitoring equipment, please refer to Figure 1 for the relevant description.

[0070] Step 220: Determine the gas pollution value based on the target detection data and the target flow data.

[0071] The gas pollution value is used to measure the degree of gas pollution. The gas pollution value can be expressed in numerical form. The more severely the gas is polluted, the larger the gas pollution value.

[0072] In some embodiments, the gas company management platform can determine the gas pollution value in various ways based on the target detection data and the target flow data. For example, the gas company management platform can construct a first retrieval vector based on the target detection data and the target flow data; perform a retrieval in the first database based on the first retrieval vector to determine a first target vector that meets the matching conditions, and use the reference gas pollution value corresponding to the first target vector as the current gas pollution value.

[0073] The first database is a database for storing, indexing, and querying vectors. The first database can store multiple first reference vectors and the reference gas pollution value corresponding to each first reference vector. Among them, the first reference vector is constructed from historical target detection data and historical target flow data.

[0074] The historical target detection data and historical target flow data that make up the first reference vector can be data calculated or obtained at the same time point or time period.

[0075] In some embodiments, the gas company management platform can construct the first database based on historical data. For example, the historical impurity detection data, historical gas flow data during each historical detection of the recycled pipeline, and the historical measured gas pollution value corresponding to each detection time period are constructed into a clustering vector; clustering is performed based on the clustering vector to form at least one clustering set; the historical target detection data and historical target flow data in the clustering vector corresponding to the center of the clustering set are constructed into a first reference vector, and the historical measured gas pollution value corresponding to the center of the clustering set is associated and stored with the first reference vector. Further, the gas company management platform can construct the first database based on multiple first reference vectors and their corresponding reference gas pollution values.

[0076] The types of clustering algorithms can include various ones. For example, the clustering algorithm can include K-Means (K-means) clustering, density-based clustering method (DBSCAN), etc.

[0077] The measured gas pollution value refers to the degree of gas pollution obtained by actually detecting the gas to be recycled.

[0078] In some embodiments, in each historical detection performed on the recycled pipeline, the gas company management platform can use a gas detector to detect the gas to be recycled before purification, determine the concentration of various impurities; the concentration of various impurities is used to determine the measured gas pollution value by weighted summation.

[0079] The matching condition can refer to the judgment condition for determining the target vector. The matching condition can include that the vector distance from the retrieval vector is less than the first threshold, the vector distance is the smallest, etc. There are various methods for calculating the vector distance, such as Euclidean distance, cosine distance, etc. The first threshold can be a system preset value, a system default value, etc.

[0080] In some embodiments, the gas company management platform can determine the current impurity distribution based on the target detection data; and determine the gas pollution value based on the current impurity distribution and the target flow data.

[0081] The current impurity distribution refers to the impurity detection data at the current moment. For example, the current impurity distribution can include the current moment, the impurity type, and the impurity positions of different types of impurities.

[0082] Among them, the current moment is the moment when the purification parameters are calculated or evaluated. The current moment can be any time point, specifically depending on the time when the gas company management platform processes relevant instructions.

[0083] In some embodiments, the gas company management platform can perform screening based on historical data to determine historical impurity detection data that is the same as or similar to the target detection data of the pipeline to be recycled, and use the impurity type and impurity position in the next impurity detection data of the historical impurity detection data as the impurity type and impurity position in the current impurity distribution.

[0084] In some embodiments, the gas company management platform can determine the gas pollution value based on the current impurity distribution and the target flow data in various ways. For example, the gas company management platform can obtain an initial gas pollution value based on the target detection data and the target flow data; determine an adjustment coefficient based on the current impurity distribution, and adjust the initial gas pollution value based on the adjustment coefficient. Among them, the initial gas pollution value can be the gas pollution value determined through the first database based on the target detection data and the target flow data.

[0085] For example, the gas company management platform can determine the adjustment coefficient based on the impurity type in the current impurity distribution. Different impurity types correspond to different adjustment coefficients. For example, water vapor has a relatively small impact on the gas pollution value, and the adjustment coefficient is small, while dust particles or sulfides have a relatively large impact on the gas pollution value, and the adjustment coefficient is large.

[0086] For another example, the gas company management platform can determine an adjustment coefficient based on the impurity positions in the current impurity distribution. For example, when the impurity position is near the inlet of the pipeline, the adjustment coefficient is relatively large, indicating that the impurities are more likely to affect the quality of the gas.

[0087] In some embodiments, the gas company management platform can construct a retrieval vector based on the current impurity distribution and the target flow data, and perform vector matching in the first database based on this retrieval vector to determine the current gas pollution value. For more details, see step 220 and its related description.

[0088] In some embodiments, the gas pollution value is also related to the line data and gas inspection data on at least one gas line where the pipeline to be recycled is located. For more content of this embodiment, see Figure 3 the related description.

[0089] There may be a difference between the target detection data obtained from the most recent detection and the current impurity distribution obtained currently: if the time interval between the time of the most recent detection and the current time is small, the target detection data can reflect the impurity situation in the current pipeline; if the time interval between the time of the most recent detection and the current time is large, the target detection data cannot reflect the impurity situation in the current pipeline. In some embodiments of this specification, the current impurity distribution situation is estimated through the target detection data, and then the gas pollution value is determined based on the current impurity distribution, so that the determined gas pollution value is more in line with the current situation and its accuracy is improved.

[0090] Step 230, determine the purification parameters of the purification device based on the gas pollution value and the target flow data.

[0091] The purification parameters are a series of parameters used to control the operation of the purification device. For example, the purification parameters can include parameters such as gas flow rate, internal pressure, internal temperature, and washing liquid concentration.

[0092] Among them, the gas flow rate is used to characterize the gas flow rate entering the purification device; the internal pressure is used to reflect the pressure value inside the purification device; the internal temperature is used to reflect the temperature value inside the purification device; the washing liquid concentration refers to the concentration of the active ingredient or solute in the washing liquid used during the purification process. The washing liquid can include alkaline washing liquid, acidic washing liquid, etc.

[0093] In some embodiments, the gas company management platform can determine the purification parameters in various ways based on the gas pollution value and the target flow data. For example, the gas company management platform can construct a preset table based on the historical data of the historical purification process, and determine the corresponding purification parameters by looking up the table. The preset table is used to reflect the corresponding relationship between different combinations of gas pollution values and historical gas flow data and different purification parameters.

[0094] In some embodiments, the control module may count, from the historical data of multiple historical purification processes, the purification parameter that is used most frequently during actual purification under the combination of different gas pollution values and historical gas flow data, and use it as the purification parameter corresponding to the combination of the gas pollution value and the historical gas flow data.

[0095] In some embodiments, the gas company management platform may obtain at least one candidate purification parameter and determine the purification parameter therefrom. For more content of this embodiment, reference can be made to Figure 4 the relevant description.

[0096] Step 240, determine a recovery instruction and send it to at least one user interaction device through the gas equipment object platform.

[0097] The recovery instruction is an order instructing the relevant staff of the gas company to perform a recovery operation. The recovery operation may include recovering the pipeline to be recovered and storing the gas to be recovered inside the pipeline to be recovered into a temporary storage tank group, etc. In some embodiments, the recovery instruction is used to instruct the staff to store the gas in the pipeline to be recovered into the temporary storage tank group.

[0098] In some embodiments, the gas company management platform may send the recovery instruction to the government supervision object platform through the government supervision sensing network platform simultaneously when determining the purification parameter, or after a specified time; the government supervision object platform may send the recovery instruction to the gas equipment object platform through the gas company sensing network platform; the gas equipment object platform may send the recovery instruction to at least one user interaction device; and the user interaction device may give an indication to the user based on the recovery instruction.

[0099] In some embodiments, the recovery instruction may be directly displayed and output on the interaction interface of the user interaction device. In some embodiments, the recovery instruction may be sent to the staff in the form of a message. For example, it is sent to the mobile phone number of the staff by text message. Or, for example, it is sent to the user interaction device through a prompt message. In some embodiments, the recovery instruction may be passed to a specific interface of the user interaction device, and the interface includes but is not limited to a program interface, a data interface, a transmission interface, etc.

[0100] In some embodiments, the staff (such as gas operation and maintenance personnel) may input a recovery completion instruction through the user interaction device after storing the gas in the pipeline to be recovered into the temporary storage tank group. For example, the user presses a keyboard key, clicks on a touch screen or issues relevant voice information so that the user interaction device receives the recovery completion instruction.

[0101] Step 250, in response to obtaining the recovery completion instruction, send the purification parameter to the gas equipment object platform.

[0102] The recycling completion instruction is a signal or command confirmed and sent by the staff to indicate that the staff has completed the relevant recycling operation.

[0103] In some embodiments, after receiving the interaction completion instruction from the staff, the user interaction device can sequentially send the interaction completion instruction to the gas company management platform through the gas equipment object platform and the gas company sensing network platform.

[0104] In some embodiments, in response to obtaining the recycling completion instruction, the gas company management platform can sequentially send the purification parameters to the gas equipment object platform through the gas company sensing network platform, the gas company management platform, and the government supervision sensing network platform. The gas equipment object platform can generate and send corresponding control instructions to the purification equipment based on the purification parameters to control pipeline regulating valves, pressure control units, temperature control units, etc. in the purification equipment to operate according to the purification parameters. For example, the purification equipment can extract gas from the temporary storage tank group based on the purification parameters, purify the gas to be recycled, and store the purified gas in the gas storage tank group.

[0105] In some embodiments of this specification, when overhauling, replacing, or adjusting the operation of a pipeline, it is necessary to first recycle the gas in the pipeline. However, the gas transmitted through the pipeline may be contaminated and cannot be directly recycled. The gas pollution value is used to measure the situation of the gas passing through the pipeline, and then the purification parameters are determined to ensure the safety of gas recycling and reduce the waste of gas resources.

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

[0107] Figure 3 It is an exemplary schematic diagram of the pollution value determination model shown in some embodiments of this specification.

[0108] In some embodiments, the gas equipment object platform further includes at least one sampling device. At least one sampling device is located at at least one preset position of the pipeline to be recycled, and the sampling device is configured to extract a preset amount of pipeline gas for inspection to obtain gas inspection data.

[0109] The sampling device is a device for automatically extracting gas in the pipeline for inspection. For example, the sampling device can be a pipeline sampling device, an on-line monitoring device, etc.

[0110] In some embodiments, one or more preset positions are arranged on the pipeline to be recycled, and one or more sampling devices can be installed at each preset position.

[0111] The preset position refers to a specific position pre-selected in the pipeline for placing the sampling device.

[0112] In some embodiments, the preset position may be the inlet, outlet of the pipeline or the intersection with other pipelines. In some embodiments, the preset position may be determined by the gas company management platform. For example, the pipeline position where anomalies have occurred many times in history (such as parts where impurities are likely to accumulate or the impurity content is relatively high, etc.) can be determined as the preset position. For another example, the pipelines in high-incidence areas can be determined as the preset positions. The high-incidence area refers to the pipeline area where anomalies have been detected many times in history, which can be determined according to historical statistical data.

[0113] In some embodiments, the sampling device may be configured to extract a preset amount of pipeline gas for inspection to obtain gas inspection data. The preset amount can be determined based on experiments or experience.

[0114] The gas inspection data refers to the data obtained after inspecting the preset amount of gas to be recycled extracted. For example, the gas inspection data may include gas concentration, gas components, etc.

[0115] Among them, the gas concentration refers to the proportion of gas in the mixed gas. The gas components refer to the proportion of various gas components in the gas, including but not limited to hydrocarbon gases such as methane, ethane, propane, butane, etc. and non-hydrocarbon gases such as carbon dioxide, nitrogen, etc.

[0116] In some embodiments, the gas pollution value is also related to the line data and gas inspection data on at least one gas line where the pipeline to be recycled is located. As Figure 3 shown, the gas company management platform is further configured to: construct an impurity map 320 based on the gas inspection data 310-1 at at least one preset position, the line data 310-2 on at least one gas line, the current impurity distribution 310-3, and the target flow data 310-4; process the impurity map through the pollution value determination model 330 to determine the gas pollution value 340.

[0117] For more content about the current impurity distribution and target flow data, reference can be made to Figure 2 the relevant description.

[0118] The gas line refers to the gas transmission route connected or related to the pipeline to be recycled.

[0119] In some embodiments, the pipeline to be recycled may be connected to at least one pipeline to form at least one gas line. A gas line may be composed of multiple pipelines and all include the pipeline to be recycled.

[0120] The line data refers to the relevant information of all pipelines on the gas line where the pipeline to be recycled is located.

[0121] In some embodiments, the pipeline data may include at least one of the pipeline temperature, pipeline gas pressure, and impurity detection data of all pipelines on the gas pipeline where the pipeline to be recycled is located.

[0122] For different gas pipelines, the corresponding pipeline data is different.

[0123] In some embodiments, monitoring devices may be respectively arranged on at least one pipeline of at least one gas pipeline to obtain the corresponding pipeline data. The pipelines constituting the gas pipeline may be a straight pipeline section that does not include any branch points or confluence points, or may also be composed of multiple connected pipeline sections.

[0124] In some embodiments, the gas company management platform may sequentially obtain the gas inspection data and pipeline data collected by the sampling devices and monitoring devices from the gas equipment object platform via the government supervision sensing network platform, the gas company management platform, and the gas company sensing network platform.

[0125] For more content about the gas equipment object platform and the gas company sensing network platform, reference can be made to Figure 1 the relevant description.

[0126] The impurity map can be a map used to characterize each pipeline and the relationship between them.

[0127] In some embodiments, the impurity map may be a data structure composed of nodes and edges. The edges connect the nodes, and the nodes and edges may have attributes. As Figure 3 shown, the nodes of the impurity map 320 may include A, B, C, D, and E, and the edges may include AB, BC, BD, and DE.

[0128] The nodes correspond to the pipelines on each gas pipeline.

[0129] The nodes may include the nodes to be recycled and other nodes. Among them, the nodes to be recycled correspond to the pipelines to be recycled, and the other nodes correspond to the other pipelines on at least one gas pipeline except the pipelines to be recycled.

[0130] The attributes of the nodes to be recycled may reflect the information related to the nodes to be recycled. For example, the attributes of the nodes to be recycled may include target detection data, whether gas flows through the pipeline, gas inspection data, and pipeline length. The attributes of the other nodes may reflect the information related to the other pipelines. The attributes of the other nodes may include pipeline data, whether gas flows through this pipeline, pipeline length, etc.

[0131] Whether gas flows through the pipeline refers to whether gas actually passes through this pipeline during the gas transportation process.

[0132] In some embodiments, the result of whether gas flows through a pipeline can be represented by 0 or 1. For example, when there is gas flowing in the pipeline, it is represented as 1; when there is no gas flowing in the pipeline, it is represented as 0.

[0133] In some embodiments, the gas company management platform can determine whether gas flows through a pipeline in various ways. For example, when the pipeline is a pipeline to be recycled, the gas company management platform can determine whether gas flows through the pipeline based on target flow data; for another example, when the pipeline is other pipelines, the gas company management platform can determine whether gas flows through the pipeline through devices such as flow meters or pressure gauges in the corresponding pipelines.

[0134] In some embodiments, the attributes of the nodes of the impurity map further include the pipeline in-degree.

[0135] The pipeline in-degree represents the number of pipeline branches of the gas flowing into the node.

[0136] In some embodiments, the gas company management platform can determine the pipeline in-degree of each node based on the gas pipeline network map.

[0137] The gas pipeline network map is a map used to display the structure of the gas pipeline network, the connection relationship between pipelines, and the attribute information of pipelines.

[0138] The gas pipeline network map can be pre-drawn by urban planning departments, gas companies, or professional surveying and mapping institutions, etc., and stored in the storage device of the gas company management platform. In some embodiments, the gas company management platform can obtain the gas pipeline network map based on the storage device of the gas company management platform.

[0139] The pipeline in-degree can provide information on the complexity of the gas pipeline network. Nodes with a higher pipeline in-degree usually represent more upstream pipeline connections and are more vulnerable to pollution. In some embodiments of this specification, taking the pipeline in-degree as a node attribute is beneficial to improving the accuracy of the predicted gas pollution value when predicting the gas pollution value based on the impurity map.

[0140] The edge between two nodes represents the direct connection of the pipelines corresponding to the two nodes. The attributes of the edge include the upstream and downstream relationships between the pipelines.

[0141] The upstream and downstream relationship between pipelines refers to the pipeline connection relationship formed according to the gas flow direction. The upstream pipeline is the pipeline that the gas first flows through, and the downstream pipeline is the subsequent pipeline that the gas flows through.

[0142] The attributes of nodes and edges can be determined by various methods based on the input data. The methods can be the methods described in the above embodiments or other methods. The input data can include the current impurity distribution, target flow data, gas inspection data, pipeline data, etc., and can also include historical impurity distribution, historical flow data, historical gas inspection data, historical pipeline data, etc.

[0143] In some embodiments, the attribute of the edge of the impurity map further includes a pollution intensity value.

[0144] The pollution intensity value is used to characterize the pollution ability of impurities in the pipeline.

[0145] In some embodiments, the pollution intensity value is related to the impurity type. Different impurity types have different pollution abilities for the gas in the pipeline, and their corresponding relationships can be obtained based on experiments or experience. For example, the same volume of gas can be taken as a test sample; different types of impurities are added to multiple test samples respectively; the time when different impurity types are added to the test sample until the test sample reaches the "fully polluted" state is recorded; the corresponding relationship between the type of impurity and the ratio of the time corresponding to the "fully polluted" state to the volume is established.

[0146] In some embodiments, the gas company management platform can perform real-time detection through a gas detector to determine the impurity content in the test sample. When the impurity content exceeds the content threshold, it is determined that it reaches the "fully polluted" state. The content threshold can be determined based on experiments or experience.

[0147] It should be noted that during the test, the consistency of the test samples needs to be maintained, such as all test samples being the same batch of gas, having the same initial conditions (such as concentration, temperature, pressure, etc.), and the same rate of adding impurities.

[0148] In some embodiments of this specification, the pipeline impurity pollution intensity value measures the pollution ability of impurities. By correlating the pollution intensity values of pipeline impurities, the pollution conditions at different pipelines can be further characterized.

[0149] In some embodiments of this specification, by representing the connection relationship between pipelines based on a graph structure, the layout and structure of the pipeline system can be more intuitively reflected; the attributes of the nodes and edges of the impurity map provide rich information, which helps to conduct in-depth data analysis, such as identifying pipelines to be recycled and evaluating the pollution status of pipelines.

[0150] The pollution value determination model is a model for determining the gas pollution value. In some embodiments, the pollution value determination model can be a machine learning model. For example, the pollution value determination model can be a neural network model. Another example is that the pollution value determination model can be a graph neural network model (Graph Neural Network, GNN).

[0151] In some embodiments, the input of the pollution value determination model may include an impurity spectrum, and the output is the gas pollution value. Among them, the corresponding gas pollution value can be output by the nodes to be recycled in the impurity spectrum.

[0152] In some embodiments, the pollution value determination model can be trained based on a large number of first training samples with first labels through various feasible methods. For example, parameter updates can be based on the gradient descent method. An exemplary training process includes: obtaining a plurality of first training samples with first labels; inputting the plurality of first training samples with first labels into the initial pollution value determination model, constructing a loss function through the labels and the results of the initial pollution value determination model, and iteratively updating the parameters of the initial pollution value determination model based on the loss function through gradient descent or other methods. When the preset conditions are met, the model training is completed, and the trained pollution value determination model is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0153] In some embodiments, the first training samples may include sample impurity spectra, and the first labels may be the measured gas pollution values output by the sample nodes to be recycled. The nodes and their features, and the edges and their features of the sample impurity spectra are similar to the above description. The first training samples can be determined based on historical data, and the first labels can be determined by the gas company management platform or manually marked. The training of the pollution value determination model is similar to the training process of the effect determination model. For specific details, reference can be made to Figure 4 the relevant description.

[0154] For more content about the measured gas pollution value, reference can be made to Figure 2 the relevant description.

[0155] In some embodiments of the present specification, in the process of calculating the gas pollution value, through the pollution value model, the impurity spectrum can be analyzed efficiently and accurately, which is beneficial to improving the accuracy of the determined gas pollution value, and at the same time is beneficial to improving the accuracy of the subsequent determined purification parameters.

[0156] Figure 4 is an exemplary schematic diagram of the effect determination model shown according to some embodiments of the present specification.

[0157] In some embodiments, such as Figure 4As shown, the purification parameter 450 is also related to the total amount of gas 420-2 in the temporary storage tank group. The gas company management platform can obtain the reference purification parameter 411; based on the reference purification parameter 411, determine at least one candidate purification parameter 420-1; for each of the at least one candidate purification parameter, based on the gas pollution value 340, the total amount of gas 420-2, and the candidate purification parameter 420-1, determine the purification effect 440; based on the purification effect 440 of the at least one candidate purification parameter, determine the purification parameter 450.

[0158] For more information about the gas pollution value and the purification parameter, please refer to Figure 2 the relevant description.

[0159] The total amount of gas refers to the total volume or total mass of the gas stored in the temporary storage tank group.

[0160] In some embodiments, the gas company management platform can determine the volume of gas stored in each temporary storage tank through a flow meter or other measuring devices; sum up the volumes of gas stored in all temporary storage tanks to determine the total amount of gas in the temporary storage tank group.

[0161] The reference purification parameter is a pre-set parameter that can be used to control the operation of the purification equipment.

[0162] In some embodiments, the gas company management platform can obtain the reference purification parameter based on a storage device or manual input.

[0163] The candidate purification parameter is a series of parameters to be determined as the purification parameter.

[0164] In some embodiments, the gas company management platform can determine at least one candidate purification parameter based on one reference purification parameter in various ways. For example, for each reference purification parameter, the gas company management platform can select one or more parameters from the reference purification parameter for data offset to obtain at least one candidate purification parameter.

[0165] Data offset means adjusting one or more parameters in the given reference purification parameter based on a preset value. For example, adding or subtracting a preset value to / from one or more parameters respectively to obtain the corresponding parameters in the reference purification parameter.

[0166] In some embodiments, as Figure 4 shown, the gas company management platform can construct a frequent item database 412, based on the frequent item database 412, determine at least one adjustment item 413; based on the at least one adjustment item 413 and the reference purification parameter 411, determine at least one candidate purification parameter 420-1.

[0167] The frequent item database is a database for storing frequent items and their corresponding support degrees. A frequent item is a combination of parameter items whose support degree meets the preset requirements.

[0168] The combination of parameter items can include a single parameter item or a set composed of multiple parameter items. For example, the combination of parameter items can include three parameter items A, B, and C, where A, B, and C can each correspond to a single parameter item.

[0169] The support degree refers to the frequency of occurrence of a parameter item or a combination of parameter items in the dataset.

[0170] The preset requirements are the judgment conditions for determining frequent items. For example, the preset requirements can be that the support degree is greater than the support degree threshold. The support degree threshold can be the system default value or the system preset value.

[0171] In some embodiments, the support degree threshold is related to the historical purification effect.

[0172] The historical purification effect is used to measure the purification effect corresponding to the historical purification parameters.

[0173] For more content regarding the purification effect, reference can be made to Figure 4 the relevant description below.

[0174] In some embodiments, the gas company management platform can determine the corresponding historical purification effect based on each historical purification parameter, and determine the corresponding statistical value based on each historical purification effect. For example, the statistical value can be the variance; the gas company management platform can determine the support degree threshold based on the statistical values corresponding to each historical purification effect through a preset rule. Exemplarily, the preset rule is: the larger the variance, the lower the support degree threshold.

[0175] In some embodiments of this specification, by considering the degree of change in the historical purification effect to dynamically adjust the support degree threshold, the system can more flexibly and accurately determine candidate purification parameters: when the variance is large, it means that the historical purification effect fluctuates greatly, and reducing the support degree threshold can avoid the mis-exclusion of effective purification parameters due to fluctuations; when the variance is small, it means that the historical purification effect fluctuates little, and increasing the support degree threshold can obtain more accurate purification parameters.

[0176] A parameter item is one of the parameters that make up the purification parameter. For example, the parameter item can be one of the gas flow rate, internal pressure, internal temperature, and washing liquid concentration.

[0177] In some embodiments, the gas company management platform can determine the frequent item database in various ways. For example, the gas company management platform can determine the frequent item database based on the frequent item algorithm.

[0178] By way of example only, the frequent item algorithm includes the following steps: randomly select a parameter item combination from the test database as the target parameter item combination, and based on the character matching algorithm, match the target parameter item combination with the parameter item combinations in the test database to obtain the matching parameter item combination; determine the number of the matching parameter item combinations as the support degree of the target parameter item combination. The matching requirement can be related to the preset item number ratio. For example, the matching requirement can be that at least two or more parameter items in two parameter item combinations are the same. The preset item number ratio can be the system default value, the system preset value, etc.

[0179] Among them, the test database can be pre-constructed based on historical data. For example, the gas company management platform can statistically analyze the historical data and use one or more parameters in the purification parameters of the historical purification process that are different from the reference purification parameters as the parameter item combination.

[0180] Repeat the above steps to determine the support degree corresponding to each parameter item combination in the test database. Determine the parameter item combinations with the support degree greater than the support degree threshold as the frequent items, and then construct the frequent item database based on the frequent items and their corresponding support degrees.

[0181] Exemplarily, the gas company management platform matches the parameter item combination 1 (including parameter items: ABCD) with the parameter item combination 2 (including parameter items: ABE), and the parameter item combination 3 (including parameter items: BEG). Since both the parameter item combination 1 and the parameter item combination 2 contain the parameter items AB and meet the preset item number ratio (for example, at least two or more parameter items match), while both the parameter item combination 1 and the parameter item combination 3 contain the parameter item B but do not meet the preset item number ratio. At this time, only the parameter item combination 2 and the parameter item combination 1 meet the matching requirement, so the support degree of the parameter item combination 1 is 1. Repeat the above steps to obtain the support degree of the parameter item combination 2 as 2 and the support degree of the parameter item combination 3 as 1.

[0182] In some embodiments, when determining whether two parameter item combinations meet the matching requirement, it can be implemented based on a character matching algorithm or the like. The character matching algorithm refers to an algorithm for calculating the matching degree of two strings of characters. In some embodiments, the character matching algorithm can be the KMP algorithm or the BM algorithm. When the matching degree of two strings of characters meets the preset item number ratio, it is determined that the two strings of characters meet the matching requirement.

[0183] The adjustment item is the parameter item that needs to be adjusted. For example, the adjustment item can be one of the gas flow rate, the internal pressure, the internal temperature, the washing liquid concentration, or any combination thereof.

[0184] In some embodiments, the gas company management platform can use the parameters or parameter combinations selected from the frequent item database as the adjustment items.

[0185] In some embodiments, the gas company management platform may sort the frequent items in the frequent item database in descending order of support, that is, the frequent items with higher support are ranked earlier; select a preset number of frequent items ranked at the front as adjustment items. The preset number can be determined by experiments or experience.

[0186] In some embodiments, the gas company management platform may adjust the corresponding parameters in the reference purification parameters based on the adjustment items to obtain at least one candidate purification parameter. For example, each parameter in the adjustment items is used to replace the corresponding parameter in the reference purification parameters to determine the candidate purification parameter.

[0187] In some embodiments of this specification, by constructing a frequent database, determining adjustment items to adjust the reference purification parameters, and thus generating candidate purification parameters, it helps to optimize the purification process based on historical data and experience, and ensure the reliability and accuracy of subsequent purification.

[0188] The purification effect is a parameter for measuring the effective effect of purifying unclean gas. The purification effect can be in various forms such as a numerical value, a grade, etc.

[0189] In some embodiments, for each of the at least one candidate purification parameter, the gas company management platform may determine the purification effect in various ways based on the gas pollution value, the total gas volume, and the candidate purification parameter. For example, the gas company management platform may construct a second retrieval vector based on the gas pollution value, the total gas volume, and the candidate purification parameter; perform a retrieval in the second database based on the second retrieval vector to determine the first target vector that meets the matching conditions, and use the reference purification effect corresponding to the first target vector as the current purification effect.

[0190] The second database is a database for storing, indexing, and querying vectors. The second database may store multiple second reference vectors and the reference purification effect corresponding to each second reference vector. Among them, the second reference vector is constructed from the historical gas pollution value, the historical total gas volume, and the historical purification parameter.

[0191] The historical gas pollution value, the historical total gas volume, and the historical purification parameter that make up the second reference vector may be data calculated or obtained at the same time point or within the same time period.

[0192] In some embodiments, the gas company management platform may construct a second database based on historical data. For example, historical gas pollution values, historical gas volumes, historical purification parameters, and reference purification effects in the historical data are constructed into a clustering vector; clustering is performed based on the clustering vector to form at least one clustering set; the historical gas pollution values, historical gas volumes, and historical purification parameters in the clustering vector corresponding to the center of the clustering set are constructed into a second reference vector, and the reference purification effect corresponding to the center of the clustering set is associated with the second reference vector. Further, the gas company management platform may construct a second database based on multiple second reference vectors and their corresponding reference purification effects.

[0193] For more content on matching and clustering, reference can be made to Figure 2 the relevant description.

[0194] In some embodiments, the gas company management platform may obtain the reference purification effect in various ways. For example, the gas company management platform may detect the purified clean gas based on historical purification parameters, obtain the gas pollution value after purification, calculate the difference between the gas pollution value before purification and the gas pollution value after purification, and use the ratio of this difference to the gas pollution value before purification as the reference purification effect.

[0195] In some embodiments, as Figure 4 shown, the gas company management platform may determine the purification effect 440 of the candidate purification parameter through the effect determination model 430 based on the gas pollution value 340, the gas volume 420 - 2, and the candidate purification parameter 420 - 1.

[0196] The effect determination model is a model used to determine the purification effect of the candidate purification parameter.

[0197] In some embodiments, the effect determination model is a machine learning model. For example, the effect determination model may include any one or a combination of a Convolutional Neural Networks (CNN) model, a Neural Networks (NN) model, or other custom model structures, etc.

[0198] In some embodiments, the input of the effect determination model includes the gas pollution value, the gas volume, and the candidate purification parameter, and the output may include the purification effect of the candidate purification parameter. The candidate purification parameter input into the effect determination model may be one, and in this case, the output of the effect determination model is the purification effect of this candidate purification parameter. The candidate purification parameters input into the effect determination model may be multiple, and in this case, the output of the effect determination model is the purification effect of each of the multiple candidate purification parameters.

[0199] In some embodiments, as Figure 4As shown, the input of the effect determination model 430 further includes at least one gas inspection data 310-1. For more information about the gas inspection data, reference can be made to Figure 2 the relevant description.

[0200] In some embodiments of the present specification, by adding gas inspection data as input, the accuracy of predicting the purification effect and the generalization ability of the model can be further improved, thereby optimizing the purification process, improving resource utilization rate, and ensuring the safety and effectiveness of the purification process.

[0201] In some embodiments, the effect determination model can be trained based on a large number of second training samples with second labels in various feasible ways. For example, parameter updates can be based on the gradient descent method. An exemplary training process includes: obtaining a plurality of second training samples with second labels; inputting the plurality of second training samples with second labels into the initial effect determination model, constructing a loss function through the labels and the results of the initial effect determination model, and iteratively updating the parameters of the initial effect determination model based on the loss function by gradient descent or other methods. When the preset conditions are met, the model training is completed, and a trained effect determination model is obtained. Among them, the preset conditions can be the convergence of the loss function, the number of iterations reaching a threshold, etc.

[0202] In some embodiments, the second training samples at least include the sample gas pollution value, the sample total gas volume, and the sample purification parameters of the sample pipeline. In some embodiments, when the input of the effect determination model includes multiple gas inspection data, the second training samples can also include multiple sample gas inspection data. The second training samples can be obtained based on historical data.

[0203] In some embodiments, the second label can include the reference purification effect corresponding to the sample purification parameters. The second label can be obtained through the gas company management platform or manual annotation. For example, under the environmental conditions corresponding to the second training samples, the gas to be purified is purified using the sample purification parameters to obtain clean gas; the clean gas is detected to obtain the gas pollution value after purification; the difference between the gas pollution value before purification and the gas pollution value after purification is calculated, and the ratio of the difference to the gas pollution value before purification is determined as the reference purification effect and used as the second label.

[0204] In some embodiments of the present specification, through the effect determination model, the purification effect corresponding to the candidate purification parameters can be predicted efficiently and accurately, and better effects than those determined based on experience can be obtained, which is beneficial to subsequent determination of the most suitable purification parameters.

[0205] In some embodiments, during the training process of the effect determination model, different second training samples have different learning rates, and the learning rate of each second training sample is related to the total amount of sample gas in that second training sample. In some embodiments, the learning rate of each second training sample is positively correlated with the total amount of sample gas in that second training sample, that is, the larger the total amount of sample gas in the second training sample, the larger the learning rate.

[0206] The learning rate is a parameter used to control the magnitude of weight updates in machine learning algorithms. In some embodiments, the learning rate is a configurable parameter used in neural network training, and its value is usually a small positive value. For example, the learning rate is in the range between 0.0 and 1.0. Among them, the weight is a parameter used to calculate and estimate the relationship between input samples and output samples in the neural network model.

[0207] In some embodiments, the gas company management platform can set an initial learning rate for the initial effect determination model. As the training progresses, the learning rate can be dynamically adjusted, such as using methods like learning rate decay or adaptive learning rate, to adapt to the learning needs of the model at different stages.

[0208] In some embodiments of this specification, adjusting the learning rate according to the total amount of sample gas in the second training sample can make the effect determination model more flexible and efficient during the training process. For example, for samples with a large total amount of sample gas, the learning rate can be appropriately increased to speed up the training; for samples with a small total amount of sample gas, the learning rate can be appropriately decreased to ensure that the effect determination model can fully learn.

[0209] In some embodiments, the training data of the effect determination model includes multiple sample sets, and each of the multiple sample sets includes multiple training samples (i.e., second training samples) with labels (i.e., second labels).

[0210] In some embodiments, the multiple sample sets include a training set, a validation set, and a test set.

[0211] The training set is a data set used to adjust the learning parameters of the model during the model training process. The learning parameters include parameters such as weights and biases.

[0212] The validation set is a data set used to adjust the hyperparameters of the model during the model training process. The hyperparameters include the number of network layers, the number of network nodes, the number of iterations, and the learning rate, etc.

[0213] The test set is a data set used to evaluate the performance of the final model.

[0214] In some embodiments, the number of training samples in the training set, the number of training samples in the validation set, and the number of training samples in the test set reach a preset quantity ratio. The preset quantity ratio can be set in advance, for example, 8:1:1, etc. In some embodiments, there is no data crossover among multiple second training samples in the training set, the test set, and the validation set. No data crossover means that the same piece of data (i.e., a second training sample) can only exist in one of the training set, the test set, and the validation set.

[0215] In some embodiments, the sample statistical difference of the training set is greater than a preset difference threshold. The sample statistical difference reflects the sample diversity of the training set. The greater the sample diversity, the greater the sample statistical difference.

[0216] In some embodiments, the gas company management platform can quantify the historical gas pollution value, the historical gas total amount, and the historical purification parameters in each second training sample in the training set into numbers and construct a feature vector; calculate the vector distance between every two feature vectors in the training set, such as the cosine distance, etc.; calculate the statistical value of multiple vector distances, such as variance, etc.; and finally determine the sample statistical difference of the training set according to the statistical value. For example, the greater the variance, the greater the sample statistical difference.

[0217] The preset difference threshold is a threshold used to limit the range of the sample statistical difference. In some embodiments, the preset difference threshold can be set in advance based on historical data or prior knowledge.

[0218] In some embodiments, the preset difference threshold is related to the statistical value of the historical purification effect. The statistical value can be the variance, the ratio of the mean to the variance. The greater the statistical value of the historical purification effect, the greater the preset difference threshold. Among them, the historical purification effect includes the purification effect after multiple historical purification treatments on the pipeline.

[0219] In some embodiments of this specification, by determining the sample statistical difference, the robustness of the model can be made stronger, and overfitting of the model can be prevented. The greater the variance of the historical purification effect, the more uncertain the quality of the historical purification parameters and the more potential impacts in all aspects are involved. Therefore, the preset difference threshold can be adjusted upwards, so that the effect determination model can learn from data samples with a wider distribution to more accurately learn the prediction of the target. Through the first training process, the stability and accuracy of the effect determination model can be improved.

[0220] In some embodiments, the gas company management platform can perform at least one round of iterative training on the effect determination model based on the training set. Through at least one round of iterative training, the learning parameters of the updated effect determination model can be obtained.

[0221] In some embodiments, the gas company management platform may verify the effect determination model after the first-stage training based on the validation set, and adjust the hyperparameters of the effect determination model according to the verification results.

[0222] In some embodiments, the gas company management platform may test the effect determination model with determined learning parameters and hyperparameters based on the test set to evaluate the generalization ability of the effect determination model.

[0223] The embodiments of this specification do not have special limitations on the method of model training using the training set, test set, and validation set, and the operations well-known to those skilled in the art can be adopted.

[0224] In some embodiments, the gas company management platform may select the candidate purification parameter with the maximum purification effect from at least one candidate purification parameter as the current purification parameter.

[0225] In some embodiments of this specification, by evaluating the purification effect and selecting the optimal purification parameter from the candidate purification parameters, the efficiency and effect of the purification process can be effectively improved, while optimizing resource utilization and reducing costs; by selecting the parameter with the best purification effect, the safety of the purification process can be ensured, and potential hazards to the pipeline system or the environment can be reduced.

[0226] One or more embodiments of this specification also provide an intelligent gas recovery Internet of Things device, including a processing device, and the processing device is used to execute a gas recovery method based on an intelligent gas recovery Internet of Things system as described in any of the above embodiments.

[0227] One or more embodiments of this specification also provide a computer-readable storage medium, and the storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs a gas recovery method based on an intelligent gas recovery Internet of Things as described in any of the above embodiments.

[0228] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0229] In the meantime, this specification uses specific terms to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0230] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numerical letters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0231] Similarly, it should be noted that, in order to simplify the expression of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, sometimes multiple features are grouped into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0232] In some embodiments, numbers describing the components and the quantity of attributes are used. It should be understood that such numbers used for the description of embodiments are modified by the modifiers "about", "approximate", or "substantially" in some examples. Unless otherwise stated, "about", "approximate", or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and these approximate values can change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their ranges are approximate values, in specific embodiments, such numerical settings are made as precise as possible within the feasible range.

[0233] For each patent, patent application, patent application publication, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated by reference into this specification. This excludes application history files that are inconsistent with or conflict with the content of this specification, as well as files that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0234] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A gas recovery system based on smart gas monitoring Internet of Things, characterized in that: It includes a government supervision management platform, a government supervision sensor network platform, a government supervision object platform, a gas company sensor network platform, and a gas equipment object platform, wherein the government supervision object platform includes a gas company management platform; wherein the government supervision management platform, the government supervision sensor network platform, and the government supervision object platform interact in sequence, and the gas company management platform, the gas company sensor network platform, and the gas equipment object platform interact in sequence; The gas equipment object platform includes purification equipment, a gas storage tank group, and a temporary storage tank group; the temporary storage tank group includes at least one temporary storage tank, and the temporary storage tank is used to store the gas to be recovered; the purification equipment is used to extract the gas to be recovered from the temporary storage tank group, purify the gas to be recovered, and store the purified clean gas in the gas storage tank group; the gas storage tank group includes at least one gas storage tank, and the gas storage tank is used to store the clean gas; The gas equipment object platform includes at least one user interaction device and at least one sampling device, wherein the at least one sampling device is located at at least one preset position of the pipeline to be recovered, and the sampling device is configured to extract a preset amount of pipeline gas for inspection to obtain gas inspection data, wherein the gas inspection data includes gas concentration and gas composition; The gas company management platform is configured as follows: Acquire target detection data and target flow data of the pipeline to be recovered from the gas equipment object platform, wherein the target detection data is impurity detection data of the pipeline to be recovered within a preset time period, and the target flow data is gas flow data of the pipeline to be recovered within the preset time period; Determine a gas pollution value based on the target detection data and the target flow data, wherein the gas pollution value is also related to line data on at least one gas line where the pipeline to be recovered is located and the gas inspection data, wherein the line data includes at least one of pipeline temperature, pipeline gas pressure and impurity detection data of all pipelines on the gas line where the pipeline to be recovered is located; Determining current impurity distribution based on the target detection data; Based on the gas inspection data of the at least one preset position, the line data on the at least one gas line, the current impurity distribution, and the target flow data, an impurity map is constructed; the attributes of the nodes of the impurity map include pipeline in-degree, which is the number of pipeline branches of the gas flowing into the node; the attributes of the edges of the impurity map include pollution intensity values, which are related to the impurity type; The impurity map is processed by a pollution value determination model to determine the gas pollution value, wherein the pollution value determination model is a machine learning model; Determining purification parameters of the purification equipment based on the gas pollution value and the target flow data; Determine a recovery instruction, and send the recovery instruction to the at least one user interaction device through the gas company object platform, wherein the recovery instruction is used to instruct the staff to store the gas in the pipeline to be recovered into a temporary storage tank group; and, In response to obtaining the recycling completion instruction, the purification parameters are sent to the gas equipment object platform, and the gas equipment object platform is configured to: generate control instructions based on the purification parameters, and send the control instructions to the purification equipment to control the purification equipment to operate according to the purification parameters.

2. The system according to claim 1, characterized in that The purification parameter is also related to the total amount of gas in the temporary storage tank group, and the government supervision management platform is further configured as follows: Acquiring reference purification parameters, where the reference purification parameters are pre-set parameters for controlling the operation of the purification equipment; Based on the reference purification parameters, determining at least one candidate purification parameter, the candidate purification parameter being a series of parameters to be determined as purification parameters; For each of the at least one candidate purification parameter, determining a purification effect based on the gas pollution value, the total amount of gas, and the candidate purification parameter; The purification parameter is determined based on the purification effect of the at least one candidate purification parameter.

3. The system according to claim 2, characterized in that The government supervision management platform is further configured to: Constructing a frequent item database, wherein the frequent item database is a database for storing frequent items and their corresponding support, wherein the frequent item is a parameter item combination whose support meets preset requirements, wherein the parameter item combination includes one parameter item or a set of multiple parameter items, wherein the parameter item includes one of the gas flow rate, internal pressure, internal temperature, and washing liquid concentration, or any combination thereof; Based on the frequent item database, determining at least one adjustment item, where the adjustment item is a parameter item that needs to be adjusted; Based on the at least one adjustment item and the reference purge parameter, the at least one candidate purge parameter is determined.

4. A gas recovery method based on smart gas monitoring Internet of Things, characterized in that: The method is implemented based on a smart gas recovery Internet of Things system, which includes a government supervision management platform, a government supervision sensor network platform, a government supervision object platform, a gas company sensor network platform, and a gas equipment object platform. The gas equipment object platform includes at least one user interaction device. The method includes: Acquire target detection data and target flow data of the pipeline to be recovered from the gas equipment object platform, wherein the target detection data is the impurity detection data of the pipeline to be recovered within a preset time period, and the target flow data is the gas flow data of the pipeline to be recovered within the preset time period; Based on the target detection data and the target flow data, a gas pollution value is determined, wherein the gas pollution value is also related to line data and gas inspection data on at least one gas line where the pipeline to be recovered is located, wherein the gas inspection data includes gas concentration and gas composition, and the line data includes at least one of pipeline temperature, pipeline gas pressure, and impurity detection data of all pipelines on the gas line where the pipeline to be recovered is located; Determining current impurity distribution based on the target detection data; Based on the gas inspection data of the at least one preset position, the line data on the at least one gas line, the current impurity distribution, and the target flow data, an impurity map is constructed; the attributes of the nodes of the impurity map include pipeline in-degree, which is the number of pipeline branches of the gas flowing into the node; the attributes of the edges of the impurity map include pollution intensity values, which are related to the impurity type; The impurity map is processed by a pollution value determination model to determine the gas pollution value, wherein the pollution value determination model is a machine learning model; Determining purification parameters of purification equipment based on the gas pollution value and the target flow data; Determine a recovery instruction, and send the recovery instruction to the at least one user interaction device through the gas equipment object platform, wherein the recovery instruction is used to instruct the staff to store the gas in the pipeline to be recovered into a temporary storage tank group; and, In response to obtaining the recycling completion instruction, the purification parameters are sent to the gas equipment object platform, and the gas equipment object platform is configured to: generate control instructions based on the purification parameters, and send the control instructions to the purification equipment to control the purification equipment to operate according to the purification parameters.

5. The method according to claim 4, characterized in that The purification parameters are also related to the total amount of gas in the temporary storage tank group. The step of determining the purification parameters of the purification equipment based on the gas pollution value and the target flow data includes: Acquiring reference purification parameters, where the reference purification parameters are pre-set parameters for controlling the operation of the purification equipment; Based on the reference purification parameters, determining at least one candidate purification parameter, the candidate purification parameter being a series of parameters to be determined as purification parameters; For each of the at least one candidate purification parameter, determining a purification effect based on the gas pollution value, the total amount of gas, and the candidate purification parameter; The purification parameter is determined based on the purification effect of the at least one candidate purification parameter.

6. The method according to claim 5, characterized in that Determining at least one candidate purification parameter comprises: Constructing a frequent item database, wherein the frequent item database is a database for storing frequent items and their corresponding support, wherein the frequent item is a parameter item combination whose support meets preset requirements, wherein the parameter item combination includes one parameter item or a set of multiple parameter items, wherein the parameter item includes one of the gas flow rate, internal pressure, internal temperature, and washing liquid concentration, or any combination thereof; Based on the frequent item database, determining at least one adjustment item, where the adjustment item is a parameter item that needs to be adjusted; Based on the at least one adjustment item and the reference purge parameter, the at least one candidate purge parameter is determined.

Images