An Internet of Things-based intelligent gas pipeline temperature control method and system

Abstract

An embodiment of this specification provides an intelligent gas pipeline temperature control method and system based on the Internet of Things. This method is implemented based on an intelligent gas pipeline temperature control system. The method includes obtaining pipeline information of the gas pipeline and basic sensing data collected and uploaded by the gas equipment object platform based on the gas company management platform, and obtaining candidate parameters from the government safety supervision and management platform. Through at least one round of iterative interaction with the government safety supervision and management platform, the transmission parameters are determined, and based on the transmission parameters, the air compressor equipment of the gas equipment object platform is controlled to adjust the gas transmission temperature. By introducing an intelligent Internet of Things system, temperature monitoring technology, and emergency response measures, real-time and accurate monitoring of the gas pipeline temperature is achieved, and effective measures are taken to intervene and regulate the source of the problem, thereby ensuring the safe and stable operation of the natural gas pipeline and guaranteeing the continuity and reliability of natural gas supply.

Description

Technical Field

[0001] This specification relates to the field of gas pipelines, and particularly to an intelligent gas pipeline temperature control method and system based on the Internet of Things. Background Art

[0002] As an important infrastructure for modern energy transportation, natural gas pipelines bear the heavy responsibility of safely and efficiently transporting natural gas. Maintaining an appropriate temperature is crucial for them. Too high or too low a temperature is not conducive to transportation. If the temperature in the natural gas pipeline is too low, the moisture in the natural gas may form hydrates, further accumulate liquid and freeze, resulting in pipeline blockage and reducing the transportation efficiency of natural gas. High temperature is particularly challenging, as it is likely to cause the pipeline to expand and deform under pressure, causing the pipeline to lose its load-bearing capacity, shortening its lifespan, and even posing a risk of rupture, threatening the stability and safety of energy supply.

[0003] CN113124327B discloses a monitoring device for natural gas pipelines. By using sensors in the natural gas pipeline to monitor temperature and pressure data, it evaluates the leakage risk based on temperature-pressure combination criteria, and establishes a pipeline coordinate system to locate and alarm the leakage point. However, this solution does not consider adjusting the pipeline through means such as pipeline refrigeration and gas flow regulation to reduce the leakage risk. Summary of the Invention

[0004] Some embodiments of this specification provide an intelligent gas pipeline temperature control method and system based on the Internet of Things to solve various problems caused by too high or too low temperatures in gas pipelines, thereby ensuring the safe and stable operation of natural gas pipelines and guaranteeing the continuity and reliability of natural gas supply.

[0005] One or more embodiments of this specification provide an Internet of Things-based intelligent gas pipeline temperature control method, which is implemented based on an intelligent gas pipeline temperature control system. The method includes: obtaining pipeline information of a gas pipeline and basic sensing data collected and uploaded by a gas equipment object platform based on a gas company management platform, and obtaining candidate parameters from a government safety supervision and management platform. Through at least one round of iterative interaction with the government safety supervision and management platform, determine the transmission parameters; and based on the transmission parameters, control an air compressor device of the gas equipment object platform to adjust the gas transmission temperature; wherein, one round of the iterative interaction includes: the gas company management platform determines the temperature impact of the gas pipeline based on the candidate parameters, the pipeline information and environmental information through a first model; the first model is a machine learning model; sending the temperature impact of the gas pipeline to the government safety supervision and management platform; the government safety supervision and management platform determines the deformation evaluation of the gas pipeline based on the temperature impact of the gas pipeline, the candidate parameters, the pipeline information and the basic sensing data; updating the candidate parameters based on the deformation evaluation of the gas pipeline to obtain updated candidate parameters; and in response to the deformation evaluation of the gas pipeline meeting a preset deformation condition, determining the updated candidate parameters as the transmission parameters.

[0006] One or more embodiments of this specification provide an Internet of Things-based intelligent gas pipeline temperature control system, characterized in that the system includes a management platform, a sensing network platform, and a gas equipment object platform respectively configured on different servers; the management platform includes a gas company management platform and a government safety supervision management platform, and data exchange is carried out between the gas company management platform and the government safety supervision management platform through the sensing network platform; the sensing network platform includes a gas company sensing network platform and a government safety supervision sensing network platform, and the sensing network platform operates based on data communication devices; the gas company management platform is configured to: obtain pipeline information of the gas pipeline and basic perception data collected and uploaded by the gas equipment object platform, and obtain candidate parameters from the government safety supervision management platform, and determine transmission parameters through at least one round of iterative interaction with the government safety supervision management platform; and based on the transmission parameters, control the air compressor equipment of the gas equipment object platform to adjust the gas transmission temperature; wherein, one round of the iterative interaction includes: determining the temperature influence of the gas pipeline through a first model based on the candidate parameters, the pipeline information, and environmental information; the first model is a machine learning model; sending the temperature influence of the gas pipeline to the government safety supervision management platform; the government safety supervision management platform is configured to: determine the deformation evaluation of the gas pipeline based on the temperature influence of the gas pipeline, the candidate parameters, the pipeline information, and the basic perception data; update the candidate parameters based on the deformation evaluation of the gas pipeline to obtain updated candidate parameters; and in response to the deformation evaluation of the gas pipeline meeting a preset deformation condition, determine the updated candidate parameters as the transmission parameters.

[0007] In some embodiments of this specification, through the iterative interaction between the gas company management platform and the government safety supervision management platform, the government safety supervision management platform can realize real-time supervision of the gas company and the gas pipeline. And, since the gas temperature in the gas pipeline will change during the gas transmission process, considering sending the temperature influence of the gas pipeline to the government safety supervision management platform is beneficial for the government safety supervision management platform to determine more accurate transmission parameters. The gas company management platform then controls the air compressor equipment to adjust the gas transmission temperature based on the transmission parameters, which can effectively avoid gas pipeline safety problems caused by too high or too low temperature, and is also beneficial for ensuring gas transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0009] Figure 1is an exemplary schematic diagram of the intelligent gas pipeline temperature control Internet of Things system shown in some embodiments of this specification;

[0010] Figure 2 is an exemplary module diagram of the management platform shown in some embodiments of this specification;

[0011] Figure 3 is an exemplary schematic diagram of the Internet of Things-based intelligent gas pipeline temperature control method shown in some embodiments of this specification;

[0012] Figure 4 is an exemplary flowchart of the method for determining the transportation parameters shown in some embodiments of this specification;

[0013] Figure 5 is an exemplary schematic diagram of the first model shown in some embodiments of this specification;

[0014] Figure 6 is an exemplary schematic diagram of the second model shown in some embodiments of this specification;

[0015] Figure 7 is an exemplary schematic diagram of the method for adjusting the deformation evaluation of each pipeline segment shown in some embodiments of this specification;

[0016] Figure 8 is an exemplary flowchart of the method for adjusting the deformation evaluation of each pipeline segment shown in some other embodiments of this specification;

[0017] Figure 9 is an exemplary flowchart of the method for updating candidate parameters shown in some embodiments of this specification;

[0018] Figure 10 is an exemplary flowchart of the method for adjusting the transportation parameters shown in some embodiments of this specification. Detailed implementation manners

[0019] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios 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.

[0020] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the previous or subsequent operations do not necessarily need to be executed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Also, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0021] Figure 1 is an exemplary schematic diagram of the intelligent gas pipeline temperature control Internet of Things system shown in some embodiments of this specification.

[0022] The data communication device refers to a device used to achieve data exchange and transmission between different platforms in the control system. Exemplary data communication devices can include, but are not limited to, gateways, etc. In some embodiments, the data communication device supports data communication between the gas company management platform and the government safety supervision management platform, and between the gas company management platform and the gas equipment object platform, ensuring real-time sharing and processing of information.

[0023] The management platform is a platform configured to overall coordinate the connection and cooperation between each functional platform. The gas company management platform refers to a platform used for data exchange with the government safety supervision management platform and the gas equipment object platform to jointly achieve intelligent monitoring and management of gas pipelines. In some embodiments, the gas company management platform is configured to: obtain the pipeline information of the gas pipeline and the basic perception data collected and uploaded by the gas equipment object platform, and obtain candidate parameters from the government safety supervision management platform, and determine the transmission parameters through at least one round of iterative interaction with the government safety supervision management platform; and based on the transmission parameters, control the air pressure equipment of the gas equipment object platform to adjust the gas transmission temperature. The gas company management platform can achieve collaborative operations with government regulatory departments through data exchange with the government safety supervision management platform and the gas equipment object platform, ensuring the safe, efficient, and intelligent operation of gas pipelines.

[0024] The government safety supervision and management platform refers to a platform used for the safety supervision of gas pipelines and gas companies. That is to say, the object platform of the government safety supervision and management platform (abbreviated as the government safety supervision object platform) can include the gas company management platform. In some embodiments, the government safety supervision and management platform is configured to: determine the deformation assessment of the gas pipeline based on the temperature influence, candidate parameters, pipeline information, and basic sensing data of the gas pipeline; update the candidate parameters based on the deformation assessment of the gas pipeline to obtain the updated candidate parameters; and in response to the deformation assessment of the gas pipeline meeting the preset deformation condition, determine the updated candidate parameters as the transmission parameters. The government safety supervision and management platform and the gas company management platform can be respectively configured on different servers to process the data and / or information obtained by each and execute relevant program instructions. The government safety supervision and management platform exchanges data with the gas company management platform through the sensing network platform, enabling the safety supervision and intelligent management of gas pipelines, ensuring the safe operation of gas pipelines and compliance with government supervision requirements.

[0025] The sensing network platform is configured as a communication network and a gateway. In some embodiments, the sensing network platform includes the gas company sensing network platform and the government safety supervision sensing network platform. The gas company sensing network platform refers to a platform used for data exchange with the gas company management platform and the gas equipment object platform. In some embodiments, the gas company sensing network platform can receive the basic sensing data uploaded by the gas equipment object platform and transmit it to the gas company management platform. The government safety supervision sensing network platform refers to a platform used for data exchange with the government safety supervision and management platform and the gas company management platform. In some embodiments, the government safety supervision sensing network platform can receive the temperature influence of the gas pipeline determined by the gas company management platform and transmit it to the government safety supervision and management platform. In some embodiments, the government safety supervision sensing network platform can also receive the transmission parameters determined by the government safety supervision and management platform and send them to the gas company management platform, so that the gas company management platform can control the air compressor equipment of the gas equipment object platform to adjust the gas transmission temperature based on the transmission parameters.

[0026] The gas equipment object platform refers to a platform used to obtain data and / or information related to gas pipeline equipment. For example, the gas equipment object platform can be used to obtain various data such as the actual temperature of the inspection point and basic sensing data.

[0027] The gas equipment object platform can be composed of multiple sensing devices, including but not limited to temperature sensors, flow meters, etc. In some embodiments, the gas equipment object platform can also include other devices such as interactive devices.

[0028] For more information about the intelligent gas pipeline temperature control system based on the Internet of Things, please refer to the relevant descriptions in the following text.

[0029] Figure 2 It is an exemplary module diagram of the management platform shown according to some embodiments of this specification. As Figure 2 shown, the management platform is configured with a parameter acquisition module 210, a temperature impact determination module 220, a deformation evaluation determination module 230, a candidate parameter update module 240, a conveying parameter determination module 250, and a conveying temperature adjustment module 260. In some embodiments, the parameter acquisition module 210, the temperature impact determination module 220, the deformation evaluation determination module 230, the candidate parameter update module 240, the conveying parameter determination module 250, and the conveying temperature adjustment module 260 are all communicatively connected. Exemplary communication connection methods include but are not limited to Bluetooth, WIFI, 5G, etc. In some embodiments, the parameter acquisition module 210, the temperature impact determination module 220, the deformation evaluation determination module 230, the candidate parameter update module 240, the conveying parameter determination module 250, and the conveying temperature adjustment module 260 may each have their own processors, or they may share a single processor.

[0030] The processor can process data and / or information obtained from other devices or system components. The processor can execute program instructions based on this data, information, and / or processing results to perform one or more functions described in this application. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-chip processing device). By way of example only, the processor may include a central processing unit (CPU), a controller, a microprocessor, etc., or any combination thereof.

[0031] In some embodiments, the parameter acquisition module 210 may be configured to acquire basic sensing data, candidate parameters, and pipeline information. In some embodiments, the parameter acquisition module 210 may include sensing devices. Exemplary sensing devices may include but are not limited to temperature sensors, speed sensors, flow meters, etc. In some embodiments, the temperature sensor and the flow meter may be disposed at different positions of the gas pipeline (such as a delivery station, etc.) to respectively collect the ambient temperature and the gas delivery rate at different positions of the gas pipeline. In some embodiments, the parameter acquisition module 210 may further include an interaction device. For example, electronic components with interaction functions such as an operation console, a desktop computer, etc. In some embodiments, the management personnel may input candidate parameters and pipeline information through the interaction device.

[0032] In some embodiments, the temperature impact determination module 220 may be configured to determine the temperature impact of the gas pipeline based on the candidate parameters, pipeline information, and environmental information through a first model.

[0033] In some embodiments, the deformation evaluation determination module 230 may be configured to determine the deformation evaluation of the gas pipeline based on the temperature influence of the gas pipeline, candidate parameters, pipeline information, and basic sensing data. In some embodiments, the gas pipeline includes a plurality of pipeline segments. The deformation evaluation determination module 230 may further be configured to determine the deformation evaluation of the gas pipeline through a second model based on the temperature influence of the gas pipeline, candidate parameters, pipeline information, and basic sensing data; the second model is a machine learning model. Wherein, the second model includes a plurality of deformation layers, and each deformation layer is configured to determine the deformation evaluation of one pipeline segment among the plurality of pipeline segments.

[0034] In some embodiments, the candidate parameter update module 240 may be configured to update the candidate parameters based on the deformation evaluation of the gas pipeline to obtain updated candidate parameters. In some embodiments, the candidate parameter update module 240 may further be configured to determine the first amplitude of the candidate parameters based on the deformation evaluation corresponding to the candidate parameters; determine the second amplitude of the candidate parameters based on the consistency between the deformation evaluation and the gas flow direction; and update the candidate parameters based on the first amplitude and the second amplitude.

[0035] In some embodiments, the delivery parameter determination module 250 may be configured to determine the updated candidate parameters as delivery parameters in response to the deformation evaluation of the gas pipeline satisfying a preset deformation condition.

[0036] In some embodiments, the delivery temperature adjustment module 260 may be configured to control the air pressure equipment of the gas equipment object platform to adjust the gas delivery temperature based on the delivery parameters.

[0037] In some embodiments, the intelligent gas pipeline temperature control system 200 based on the Internet of Things further includes a deformation evaluation adjustment module 270 and a delivery parameter adjustment module 280. The deformation evaluation adjustment module 270 and the delivery parameter adjustment module 280 are both communicatively connected to the foregoing modules. In some embodiments, the deformation evaluation adjustment module 270 and the delivery parameter adjustment module 280 may also have their own processors, or share a processor with other modules.

[0038] In some embodiments, the deformation evaluation adjustment module 270 may be configured to determine a first confidence level for each pipeline segment based on pipeline information, environmental information, conveying parameters, inlet data for each pipeline segment, and historical pipeline leakage information; and adjust the deformation evaluation for each pipeline segment based on the first confidence level of each pipeline segment. In some embodiments, a plurality of checkpoints are provided on the gas pipeline. The deformation evaluation adjustment module 270 may further be configured to obtain the actual temperature of the plurality of checkpoints; determine a second confidence level for each pipeline segment based on the actual temperature of the plurality of checkpoints and historical predictions; and adjust the deformation evaluation for each pipeline segment based on the first confidence level and the second confidence level.

[0039] In some embodiments, a plurality of checkpoints are provided on the gas pipeline, and the plurality of checkpoints correspond to at least one transfer station. The conveying parameter adjustment module 280 may be configured to obtain the actual temperature of the plurality of checkpoints; determine the confidence level of at least one transfer station corresponding to the plurality of checkpoints based on the actual temperature of the plurality of checkpoints and historical predictions; and adjust the conveying parameters based on the confidence level of at least one transfer station.

[0040] It should be noted that the above description of the management platform and its modules is only for convenience of description and does not limit this specification to the scope of the examples given. It can be understood that for those skilled in the art, after understanding the principle of the intelligent gas pipeline temperature control system based on the Internet of Things, they may, without departing from this principle, make any combination of the various modules, or form a subsystem and connect it with other modules.

[0041] Some embodiments of this specification provide an intelligent gas pipeline temperature control method based on the Internet of Things, and this method is implemented based on the intelligent gas pipeline temperature control system. For more content about the intelligent gas pipeline temperature control system, reference can be made to Figure 1 - Figure 2 and its related descriptions.

[0042] Figure 3 is an exemplary schematic diagram of the intelligent gas pipeline temperature control method shown in some embodiments of this specification. As Figure 3 shown, the intelligent gas pipeline temperature control method based on the Internet of Things includes: based on the gas company management platform 350, obtaining the pipeline information 310 of the gas pipeline and the basic perception data 320 collected and uploaded by the gas equipment object platform 340, and obtaining the candidate parameters 330 from the government safety supervision management platform 360, and determining the conveying parameters 370 through iterative interaction with the government safety supervision management platform 360; and based on the conveying parameters 370, controlling the air compressor equipment of the gas equipment object platform 340 to adjust the gas conveying temperature 380.

[0043] The pipeline information of a gas pipeline refers to various data and / or information related to the gas pipeline. In some embodiments, the pipeline information of a gas pipeline may include at least one of the topological structure, length, pipe diameter, degree of bending, material, and thickness of the gas pipeline. In some embodiments, the pipeline information of a gas pipeline may further include the setting information of the bellows compensator. The setting information of the bellows compensator refers to the information related to the setting position of the bellows compensator. A bellows compensator is a compensating element used in a pipeline system, mainly used to compensate for dimensional changes caused by factors such as temperature changes, mechanical displacement, and vibration, thereby ensuring the safe and stable operation of the pipeline system. The working principle of the bellows compensator is mainly based on the "bellows effect", that is, by forming a corrugated shape on the pipe blank through hydraulic or mechanical means, the pipe blank is made to have telescopic and compensating capabilities. In some embodiments, the gas company management platform can directly retrieve the pipeline information of the gas pipeline from the database. In some embodiments, the pipeline information of the gas pipeline can also be obtained by input from management personnel.

[0044] The basic perception data refers to the information related to the gas pipeline and gas transmission. In some embodiments, as Figure 3 shown, the basic perception data 320 may include at least one of the environmental information 321 and the flow information 322. In some embodiments, the basic perception data can be collected by sensing devices (such as temperature sensors, flow meters, etc.) located at different gas pipeline or valve positions, and then uploaded by the sensing devices to the gas equipment object platform for aggregation and storage. The gas equipment object platform reports the basic perception data to the gas company management platform according to a preset reporting rule. Among them, the preset reporting rule can be determined based on manual input or prior experience. For example, the preset reporting rule can be to report the basic perception data to the gas company management platform at a preset time interval (such as 30s, 1min). For more content on how to obtain the basic perception data, reference can be made to Figure 1 and its related descriptions.

[0045] The environmental information refers to the gas temperature information and the external environmental information of the gas pipeline at different positions. In some embodiments, the external environmental information may include at least one of the soil layer thickness and the external temperature related to a specific position. Among them, the specific position refers to the position in the gas pipeline where the environmental information needs to be focused on, and the specific position can be determined artificially. The soil layer thickness refers to the depth at which the gas pipeline is buried in the soil layer, and can be determined through the pipeline installation information. The pipeline installation information includes the relevant installation information (such as the soil layer thickness and installation position of the gas pipeline) during the initial installation of the gas pipeline. In some embodiments, the pipeline installation information can be obtained by manual input. The external temperature can be obtained by real-time collection by a temperature sensor. The gas temperature information refers to the gas temperature inside the gas pipeline. In some embodiments, the gas temperature information can also be obtained by real-time collection by a temperature sensor.

[0046] Flow information refers to information related to gas transmission in a gas pipeline. In some embodiments, the flow information may include at least one of inlet flow and outlet flow. In some embodiments, the flow information can be obtained by a flow meter.

[0047] A candidate parameter refers to the temperature or rate of the gas when it is transmitted along the gas flow direction. For more information about the gas flow direction, reference can be made to Figure 9 and its related description. In some embodiments, the candidate parameter may include at least one of the candidate gas transmission temperature and the candidate gas transmission rate at each transfer station. For more information about the transfer station, reference can be made to the relevant description in the following text (such as Figure 10 etc.). In some embodiments, the candidate parameter can be obtained by input from a management personnel.

[0048] A transmission parameter refers to a relevant parameter during gas transmission in a gas pipeline. In some embodiments, the transmission parameter may include at least one of the gas transmission temperature and the gas transmission rate at each transfer station. Among them, the gas transmission temperature refers to the temperature of the transmitted gas. The gas transmission rate refers to the rate of the transmitted gas. In some embodiments, each transfer station can set its own gas transmission temperature and gas transmission rate, and the gas transmission temperature and gas transmission rate of each transfer station can be the same or different. In some embodiments, the gas company management platform can obtain the transmission parameter from the government safety supervision and management platform through at least one round of iterative interaction with the government safety supervision and management platform, so as to determine the transmission parameter. For the specific description of how the government safety supervision and management platform determines the transmission parameter, reference can be made to Figure 4 and its related description. Among them, one round of iterative interaction includes: determining the temperature impact of the gas pipeline through a first model based on the candidate parameter, pipeline information, and environmental information; and sending the temperature impact of the gas pipeline to the government safety supervision and management platform.

[0049] The temperature impact of a gas pipeline can reflect the temperature change of the gas pipeline. In some embodiments, the gas pipeline includes multiple pipeline segments, so the temperature impact of the gas pipeline includes the temperature impact of each pipeline segment among the multiple pipeline segments. In some embodiments, a transfer station can be used to control one or more gas pipelines or pipeline segments. When the transfer station controls multiple pipeline segments, since each pipeline segment is affected by various factors (such as ambient temperature, gas transmission rate, pipeline information, etc.), during the gas transmission process, the gas temperature in each pipeline segment may change. That is to say, the temperature impact of each pipeline segment may be the same or different. In some embodiments, the splitting point of the pipeline segment can be the position where a flowmeter and a temperature sensor are simultaneously installed in the gas pipeline. In some embodiments, the gas pipeline can also be split in any other feasible way to form multiple pipeline segments. For example, random splitting, etc. For more information about pipeline segments and their splitting points, reference can be made to the relevant descriptions in the following text (such as Figure 5 )

[0050] In some embodiments, the temperature impact of the gas pipeline can be represented by an array. For example, the temperature impact of the gas pipeline can be represented as ((a1, b1, m11), (a1, b2, m12), …, (a2, b1, m21), …). Among them, a1 and a2 respectively represent pipeline segment 1 and pipeline segment 2; b1 and b2 respectively represent candidate parameter 1 and candidate parameter 2; m11 represents the temperature impact of pipeline segment 1 under candidate parameter 1, m12 represents the temperature impact of pipeline segment 1 under candidate parameter 2, and m21 represents the temperature impact of pipeline segment 2 under candidate parameter 1. Only as an example, if m11 is +2°C or -5°C, it means that under candidate parameter 1, the outlet temperature of pipeline segment 1 is 2°C higher or 5°C lower than the inlet temperature, that is, the temperature impact of candidate parameter 1 on pipeline segment 1 is +2°C or -5°C. Among them, the outlet temperature refers to the gas temperature when the gas flows out of each pipeline segment along the gas flow direction. The inlet temperature refers to the gas temperature when the gas enters each pipeline segment. In some embodiments, the outlet temperature of the previous segment is the inlet temperature of the current segment. Among them, the current segment refers to the current pipeline segment; the previous segment refers to the pipeline segment located in the previous section relative to the current segment. In some embodiments, the gas flows from the previous segment to the current segment.

[0051] In some embodiments, the first model can process candidate parameters, pipeline information, and environmental information to determine the temperature impact of the gas pipeline. The first model refers to a model used to determine the temperature impact of the gas pipeline. In some embodiments, the first model can be a machine learning model. For example, the first model can include a combination of one or more of a Deep Neural Networks (DNN) model, a Neural Network (NN) model, and a Recurrent Neural Network (RNN) model. For more descriptions on how the first model determines the temperature impact of the gas pipeline, reference can be made to Figure 5 and its related descriptions.

[0052] In some embodiments, the gas company management platform can also determine the temperature impact of the gas pipeline based on the pipeline information and environmental information in the following manner:

[0053] S1: Based on the candidate parameters, pipeline information, and environmental information, methods such as Fourier's Law, Newton's Law of Cooling, and Stefan-Boltzmann Law are used to calculate the theoretical outlet temperature of the first pipeline segment, and then the theoretical inlet temperature and theoretical outlet temperature of each pipeline segment are obtained. As mentioned above, the outlet temperature of the previous segment is the inlet temperature of the current segment. Therefore, for other pipeline segments, based on the theoretical outlet temperature of the previous segment, the pipeline information, and environmental information of the current segment, methods such as Fourier's Law, Newton's Law of Cooling, and Stefan-Boltzmann Law are used to calculate the theoretical outlet temperature of other pipeline segments. Combining the theoretical outlet temperature of the first pipeline segment and the theoretical outlet temperatures of other pipeline segments, the theoretical inlet temperature and theoretical outlet temperature of each pipeline segment can be obtained.

[0054] S2: Based on the theoretical inlet temperature and theoretical outlet temperature of each pipeline segment, the theoretical temperature difference of each pipeline segment is calculated. For example, the theoretical temperature difference = |theoretical outlet temperature - theoretical inlet temperature|.

[0055] S3: Based on the environmental information, the measured inlet temperature and measured outlet temperature of each pipeline segment are determined. As mentioned above, the environmental information includes the external temperature, and the splitting points of the pipeline segments are the positions where flow meters and temperature sensors are simultaneously installed in the gas pipeline. Therefore, the measured inlet temperature and measured outlet temperature of each pipeline segment can be obtained based on the environmental information.

[0056] S4: Based on the measured inlet temperature and the measured outlet temperature of each pipeline segment, calculate the actual temperature difference of each pipeline segment. For example, the actual temperature difference = |measured outlet temperature - measured inlet temperature|.

[0057] S5: Based on the theoretical temperature difference and the actual temperature difference, determine the temperature impact of each pipeline segment. For example, the temperature impact = [theoretical temperature difference + actual temperature difference] / 2.

[0058] In some embodiments, the gas company management platform can send the temperature impact of the gas pipeline to the government safety supervision and management platform based on the sensing network platform.

[0059] In some embodiments, the gas company management platform can control the operation of the air compression equipment based on the conveying parameters to adjust the gas conveying temperature. Only as an example, if the gas temperature at the current conveying station is higher than the gas conveying temperature in the conveying parameters, the gas company management platform can control the air compression equipment to refrigerate and reduce the gas temperature at the current conveying station so that the conveying station conveys gas according to the conveying parameters. Among them, the temperature reduction range can be the difference between the gas temperature at the current conveying station and the gas conveying temperature in the conveying parameters. For example, the gas conveying temperature in the conveying parameters is 20°C, and the gas temperature at the current conveying station is 25°C, then the temperature reduction range is 5°C. Among them, the air compression equipment is also called an air compressor, which mainly uses the compression and expansion of air to achieve the refrigeration effect. In some embodiments, the air compression equipment can be set in each conveying station and is communicatively connected to the gas company management platform so as to be able to timely adjust the gas conveying temperature under the control of the gas company management platform.

[0060] In some embodiments of this specification, through the iterative interaction between the gas company management platform and the government safety supervision and management platform, the government safety supervision and management platform can achieve real-time supervision of the gas company and the gas pipeline. And, since the gas temperature in the gas pipeline will change during the gas conveying process, considering sending the temperature impact of the gas pipeline to the government safety supervision and management platform is beneficial for the government safety supervision and management platform to determine more accurate conveying parameters. The gas company management platform then controls the air compression equipment to adjust the gas conveying temperature based on the conveying parameters, which can effectively avoid gas pipeline safety problems caused by too high or too low temperature, and is also beneficial for ensuring the gas conveying efficiency.

[0061] Figure 4 is an exemplary flowchart of a method for determining conveying parameters shown in some embodiments of this specification. As Figure 4 shown, process 400 may include the following steps. In some embodiments, process 400 may be executed by the government safety supervision and management platform.

[0062] Step S410: Determine the deformation evaluation of the gas pipeline based on the temperature impact of the gas pipeline, candidate parameters, pipeline information, and basic sensing data. In some embodiments, step 410 may be executed by the deformation evaluation determination module 230. For more information on the temperature impact, candidate parameters, pipeline information, and basic sensing data, reference can be made to Figure 3 and its related descriptions.

[0063] The deformation evaluation of the gas pipeline refers to the data of possible deformations at different positions of the gas pipeline due to excessive or low temperature. In some embodiments, the deformation evaluation of the gas pipeline may include at least one of the amount of deformation and the probability of deformation of the gas pipeline. The probability of deformation refers to the probability that the amount of deformation exceeds the deformation threshold. Herein, the deformation threshold refers to the maximum value that the amount of deformation can reach, and the deformation threshold can be determined based on historical data, etc. In some embodiments, the amount of deformation and the probability of deformation can be converted into each other. For example, the probability of deformation can be the ratio of the amount of deformation to the deformation threshold. Also for example, the amount of deformation can be the product of the probability of deformation and the deformation threshold. As mentioned above, the gas pipeline includes multiple pipeline segments, so the deformation evaluation of the gas pipeline includes the deformation evaluation of each pipeline segment among the multiple pipeline segments.

[0064] In some embodiments, the deformation evaluation of the gas pipeline can be represented by an array. For example, the deformation evaluation can be expressed as ((a1, b1, d11), (a1, b2, d12), …, (a2, b1, d21), …). Wherein, a1 and a2 respectively represent pipeline segment 1 and pipeline segment 2; b1 and b2 respectively represent candidate parameter 1 and candidate parameter 2; d11 represents the amount of deformation (or probability of deformation) of pipeline segment 1 under candidate parameter 1, d12 represents the amount of deformation (or probability of deformation) of pipeline segment 1 under candidate parameter 2, and d21 represents the amount of deformation (or probability of deformation) of pipeline segment 2 under candidate parameter 1. Only as an example, if d11 is +1 mm or -0.5 mm, it means that the amount of deformation of pipeline segment 1 under candidate parameter 1 is +1 mm or -0.5 mm, that is, the gas may cause the pipe diameter of pipeline segment 1 to increase by 1 mm or the pipe diameter to shrink by 0.5 mm. If d11 is 90%, it means that the probability of deformation of pipeline segment 1 under candidate parameter 1 is 90%.

[0065] In some embodiments, the government safety supervision and management platform can determine the deformation evaluation of the gas pipeline based on the temperature impact of the gas pipeline, candidate parameters, pipeline information, and basic sensing data in various ways. For example:

[0066] S411: Based on the temperature impact of the gas pipeline and the pipeline information, calculate the pipeline expansion or pipeline contraction caused by temperature change for each pipeline segment. Exemplary calculation formulas may include: . Wherein, is the amount by which the diameter of a pipeline segment increases or shrinks due to temperature changes; is the coefficient of thermal expansion of the pipeline segment material; is the original diameter of the pipeline segment at the initial temperature; is the temperature change.

[0067] S412: Based on the basic perception data, determine the measured inlet flow rate and the measured outlet flow rate of each pipeline segment. As mentioned above, the basic perception data includes flow rate information, and the segmentation points of the pipeline segments are the positions where flow meters are installed in the gas pipeline. Therefore, the measured inlet flow rate and the measured outlet flow rate of each pipeline segment can be obtained based on the basic perception data.

[0068] S413: Based on the measured inlet flow rate and the measured outlet flow rate of each pipeline segment, calculate the flow rate change of each pipeline segment. For example, the flow rate change = |measured outlet flow rate - measured inlet flow rate|.

[0069] S414: Based on the flow rate change of each pipeline segment, the pipeline information, and the environmental information in the basic perception data, according to the geometric characteristics of the pipeline segment and the relevant formulas of fluid mechanics, calculate the pressure change caused by the flow rate change of each pipeline segment.

[0070] S415: Based on the above pressure change, according to the thin-walled cylinder strength calculation formula, calculate the deformation caused by the above pressure change of each pipeline segment.

[0071] S416: Based on the pipeline expansion or pipeline contraction caused by temperature change and the deformation caused by pressure change of each pipeline segment, obtain the deformation amount of each pipeline segment (i.e., deformation evaluation) through weighted summation. It should be noted that the weight coefficients during the weighted summation of the two can be determined based on past experience and other methods.

[0072] For more content on how to determine the deformation evaluation of the gas pipeline, reference can be made to Figure 6 and its related descriptions.

[0073] Step S420, update the candidate parameters based on the deformation evaluation of the gas pipeline to obtain the updated candidate parameters. In some embodiments, step 420 can be executed by the candidate parameter update module 240.

[0074] The updated candidate parameters refer to the candidate parameters adjusted according to the deformation evaluation of the gas pipeline. In some embodiments, the government safety supervision and management platform may update the candidate parameters based on the deformation evaluation corresponding to the candidate parameters through a preset rule to obtain the updated candidate parameters. Among them, the preset rule may include that in response to the deformation evaluation exceeding the deformation threshold, the gas transmission temperature in the candidate parameters is reduced by a preset reduction amplitude. The preset reduction amplitude may be set in advance manually or determined based on a first preset table. For example, if the average value of the deformation evaluations (such as the amount of deformation) of multiple gas pipeline segments exceeds twice the deformation threshold, the gas transmission temperature in the candidate parameters is reduced by 5°C. Another example is that if the average value of the deformation evaluations (such as the amount of deformation) of multiple gas pipeline segments is between 1 and 2 times the deformation threshold, the gas transmission temperature in the candidate parameters is reduced by 2°C. In some embodiments, the first preset table may be constructed based on historical data.

[0075] For more content on how to update candidate parameters based on the deformation evaluation of the gas pipeline, reference can be made to Figure 9 and its related descriptions.

[0076] Step S430, in response to the deformation evaluation of the gas pipeline satisfying the preset deformation condition, determine the updated candidate parameters as the transmission parameters. In some embodiments, step 430 may be executed by the transmission parameter determination module 250.

[0077] The preset deformation condition refers to a pre-set judgment condition. In some embodiments, the preset deformation condition may include that the average value (or maximum value) of the deformation evaluations of multiple pipeline segments is less than a preset value, etc. The preset value may be set in advance manually.

[0078] In some embodiments, when the average value (or maximum value) of the deformation evaluations of multiple pipeline segments is less than the preset value, the government safety supervision and management platform may determine the candidate parameters corresponding to the minimum average value (or maximum value) of the deformation evaluations of multiple pipeline segments as the transmission parameters. Only as an example, if there are 100 pipeline segments and 10 candidate parameters, then there are 1000 deformation evaluations. Among them, 100 deformation evaluations are the deformation evaluations of different pipeline segments under candidate parameter 1, 100 deformation evaluations are the deformation evaluations of different pipeline segments under candidate parameter 2,..., and there are also 100 deformation evaluations that are the deformation evaluations of different pipeline segments under candidate parameter 10. When determining the transmission parameters based on these 10 candidate parameters, for each candidate parameter, calculate the average value (or maximum value) of its corresponding 100 deformation evaluations, and select the candidate parameter (such as candidate parameter 2) corresponding to the minimum average value (or maximum value) of the 100 deformation evaluations as the transmission parameter.

[0079] In some embodiments, when the deformation assessment of the gas pipeline does not meet the preset deformation conditions (that is, when the mean (or maximum value) of the deformation assessments of multiple pipeline segments exceeds the preset value), the government safety supervision and management platform can reduce the gas transmission temperature in the candidate parameters based on the first amplitude, and synchronously update the deformation assessment of the gas pipeline based on the reduced candidate parameters until the deformation assessment of the gas pipeline meets the preset deformation conditions. At this time, the transmission parameter is the candidate parameter corresponding to when the deformation assessment of the gas pipeline meets the preset deformation conditions. Among them, the first amplitude can be a fixed value. For more information about the first amplitude, reference can be made to Figure 9 and its related descriptions.

[0080] In some embodiments of this specification, based on the temperature influence of the gas pipeline, candidate parameters, pipeline information, and basic perception data, the deformation assessment of the gas pipeline is determined, and the possibilities that can cause the deformation of the gas pipeline are analyzed from multiple perspectives, obtaining relatively comprehensive deformation assessment analysis data of the gas pipeline. Further, the candidate parameters are updated based on the deformation assessment until the deformation assessment meets the preset deformation conditions, and the updated candidate parameters are determined as the transmission parameters. By adjusting the gas transmission parameters within the allowable deformation amount or deformation probability range of the gas pipeline, not only the danger caused by the serious deformation of the gas pipeline is effectively avoided, but also the service life of the gas pipeline is extended and the maintenance or replacement cost is reduced.

[0081] Figure 5 is an exemplary schematic diagram of the first model shown in some embodiments of this specification.

[0082] In some embodiments, the gas pipeline includes multiple pipeline segments, and the first model includes multiple temperature layers. Each temperature layer is configured to determine the temperature influence and outlet data of one pipeline segment among the multiple pipeline segments. A pipeline segment refers to the multiple pipeline sections obtained by dividing the gas pipeline according to the cut-off points. In some embodiments, the temperature influence determination module 220 can segment the gas pipeline based on the pipeline length, delivery station, etc. For example, the gas pipeline is segmented according to a preset pipeline length. Among them, the preset pipeline length can be determined according to past experience or historical data, etc. For more information about how to segment the gas pipeline, reference can be made to the relevant descriptions in other parts of this specification.

[0083] The temperature layer can be used to determine the temperature influence and outlet data of the pipeline segment. In some embodiments, one temperature layer corresponds to one pipeline segment, and one temperature layer can be used to determine the temperature influence and outlet data of a corresponding pipeline segment. In some embodiments, each temperature layer is a neural network (NN) model.

[0084] The outlet data refers to the relevant data at the outlet of each pipeline segment. In some embodiments, the outlet data may include at least one of the outlet temperature and the outlet rate. In some embodiments, each pipeline segment corresponds to its own outlet data, and the outlet data of the previous segment is the inlet data of the current segment. For more information about the previous segment and the current segment, reference can be made to Figure 3 and its related description. The inlet data refers to the relevant data at the inlet of each pipeline segment. In some embodiments, the inlet data may include at least one of the inlet temperature and the inlet rate. In some embodiments, the input of each temperature layer may include the inlet data of the corresponding pipeline segment, pipeline information, and environmental information, and the output of each temperature layer may include the temperature impact of the corresponding pipeline segment and the outlet data.

[0085] As Figure 5 shown, for the first temperature layer (i.e., the temperature layer 510-1 corresponding to the first pipeline segment), its input may include the inlet data of the first pipeline segment (i.e., the candidate parameter 330), the first pipeline information (310-1), and the first environmental information (321-1), and its output may include the first temperature impact (520-1) and the first outlet data (530-1) of the first pipeline segment. For the Nth temperature layer (i.e., the temperature layer 510-n corresponding to other pipeline segments), its input may include the (N-1)th temperature impact (520-(n-1)) and the (N-1)th outlet data (530-(n-1)) of the previous segment, the Nth pipeline information (310-n) and the Nth environmental information (321-n) of the current segment, and its output may include the Nth temperature impact (520-n) and the Nth outlet data (530-n) of the current segment.

[0086] It should be noted that the subsequent segments are iteratively calculated according to the gas flow direction among multiple temperature layers. For example, the output of the previous segment temperature layer is used as the input of the subsequent segment temperature layer. However, when a sensing device (such as a temperature sensor, a flowmeter) is provided at the inlet position of the subsequent segment, the data (such as the gas transmission temperature, the gas transmission rate) obtained by the sensing device in real time needs to be used as the inlet data.

[0087] In some embodiments, the output of the first model may be a sequence composed of the outlet data and the temperature impacts output by all temperature layers. For example, ((the first outlet data, the first temperature impact), (the second outlet data, the second temperature impact),..., (the Nth outlet data, the Nth temperature impact)).

[0088] In some embodiments, the first temperature layer can be obtained through training based on a large number of first training samples with first sample labels. For example, multiple labeled training samples can be input into the initial first temperature layer, a loss function can be constructed based on the labels and the results of the initial first temperature layer, and the parameters of the initial first temperature layer can be iteratively updated based on the loss function through gradient descent or other methods. When a preset condition is met, the training of the first temperature layer is completed, and the trained first temperature layer is obtained. Among them, the preset condition can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0089] In some embodiments, the first training samples can include sample parameters, sample pipeline information of the first pipeline segment, and sample environmental information. The first sample label can be the actual temperature impact and actual outlet data of the first pipeline segment under the sample parameters, sample pipeline information of the first pipeline segment, and sample environmental information. Among them, the actual temperature impact of the first pipeline segment is the difference between the measured outlet temperature and the measured inlet temperature of the first pipeline segment. In some embodiments, the first training samples and the first sample labels can be obtained based on actual data.

[0090] In some embodiments, the Nth temperature layer can be obtained through training based on a large number of second training samples with second sample labels, using a training method similar to that of the first temperature layer, and the similarities will not be elaborated here. In some embodiments, the second training samples can include the sample outlet data and sample temperature impact of the previous segment, the sample pipeline information and sample environmental information of the current segment. The second sample label can be the actual temperature impact and actual outlet data of the current segment under the sample outlet data and sample temperature impact of the previous segment, the sample pipeline information and sample environmental information of the current segment. In some embodiments, the second training samples and the second sample labels can be obtained based on actual data.

[0091] In some embodiments of this specification, through the trained first model, the temperature impact and outlet data of different pipeline segments can be obtained more accurately and quickly, so as to lay a foundation for accurately determining deformation evaluation subsequently.

[0092] In some embodiments, since the diameter change, pipeline bifurcation, and pipeline intersection of the gas pipeline will affect the gas transmission rate, the splitting points of the pipeline segments can also include the diameter change positions, pipeline bifurcation positions, and pipeline intersection positions of the gas pipeline.

[0093] In some embodiments, the temperature impact determination module 220 can determine the inlet rate of the current segment based on the outlet rate and diameter of the previous segment. For example, the temperature impact determination module 220 can calculate the inlet rate of the current segment based on the outlet rate and diameter of the previous segment through fluid mechanics methods.

[0094] In some embodiments of the present specification, the splitting points of the gas pipeline are confirmed based on the diameter change positions, pipeline bifurcation positions, and pipeline intersection positions of the gas pipeline, which can make the diameters of each pipeline segment as the same as possible, thereby facilitating further improvement of the prediction accuracy of the first model.

[0095] In some embodiments, the deformation evaluation determination module 230 may determine the deformation evaluation of the gas pipeline through a second model based on the temperature influence, candidate parameters, pipeline information, and basic sensing data of the gas pipeline. For more content regarding the deformation evaluation of the gas pipeline, reference can be made to Figure 4 and its related descriptions.

[0096] In some embodiments, the second model is a machine learning model. For example, the second model may include any one or combination of various feasible models such as a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, etc.

[0097] In some embodiments, the second model may include multiple deformation layers, and each deformation layer is configured to determine the deformation evaluation of one pipeline segment among multiple pipeline segments. The deformation layer can be used to determine the deformation evaluation of the pipeline segment. In some embodiments, one deformation layer corresponds to one pipeline segment, and one deformation layer can be used to determine the deformation evaluation of a corresponding pipeline segment. In some embodiments, each deformation layer is a Neural Network (NN) model. In some embodiments, the input of each deformation layer may include candidate parameters, pipeline information of the corresponding pipeline segment, and environmental information, and the output of each deformation layer may include the deformation evaluation of the corresponding pipeline segment.

[0098] Figure 6 is an exemplary schematic diagram of the second model shown in some embodiments of the present specification. As Figure 6 shown, for the first deformation layer (i.e., the deformation layer 610-1 corresponding to the first pipeline segment), its input may include the inlet data of the first pipeline segment (i.e., candidate parameter 330), the first pipeline information (310-1), and the first environmental information (321-1), and its output may include the first deformation evaluation (620-1) of the first pipeline segment. For the Nth deformation layer (i.e., the deformation layer 610-n corresponding to other pipeline segments), its input may include the (N-1)th deformation evaluation (620-(n-1)) of the previous segment, the Nth pipeline information (310-n) of the current segment, the Nth environmental information (321-n), and the Nth temperature influence (520-n), and its output may include the Nth deformation evaluation (620-n) of the current segment.

[0099] Iterative calculations are performed for subsequent segments among multiple deformation layers according to the gas flow direction. For example, the output of the previous segmented deformation layer is used as the input of the subsequent segmented deformation layer. However, when a sensing device (such as a temperature sensor, a flowmeter) is provided at the inlet position of the subsequent segment, the data (such as the gas transmission temperature, the gas transmission rate) obtained by the sensing device in real time needs to be used as the inlet data. Moreover, since the corrugated compensator can compensate for the temperature difference deformation or other deformations between the device and the gas pipeline and has a great influence on the deformation evaluation of the gas pipeline, the pipeline information in the input of the deformation layer also needs to include the setting information of the corrugated compensator to further improve the prediction accuracy of the second model. For more content about the setting information of the corrugated compensator, reference can be made to Figure 3 and its related descriptions.

[0100] In some embodiments, the output of the second model can be a sequence composed of the deformation evaluations output by all deformation layers. For example, (the first deformation evaluation, the second deformation evaluation,..., the Nth deformation evaluation).

[0101] In some embodiments, the first deformation layer can be trained based on a large number of third training samples with third sample labels using a training method similar to that of the first temperature layer. For more content about the training method of the first temperature layer, reference can be made to Figure 5 and its related descriptions.

[0102] In some embodiments, the third training samples can include the sample candidate parameters of the first pipeline segment, the sample pipeline information, and the sample environmental information. In some embodiments, the third sample label can be the actual deformation evaluation of the first pipeline segment under the sample candidate parameters, the sample pipeline information, and the sample environmental information of the first pipeline segment. In some embodiments, the third training samples can be obtained based on historical data. The third sample label can be determined based on the actual deformation situation. For example, a deformation is labeled as 1, and no deformation is labeled as 0. Another example is that the actual deformation situation is a deformation amount of +1 mm, a deformation amount of +5 mm, a deformation amount of +0 mm, etc. In some embodiments, the actual deformation situation can be obtained based on historical pipeline leakage information and historical deformation data. Among them, the historical deformation data refers to the pipeline deformation situation found during pipeline maintenance and inspection. For more content about the historical pipeline leakage information, reference can be made to Figure 7 and its related descriptions.

[0103] In some embodiments, the Nth deformation layer can be obtained by training based on a large number of fourth training samples with fourth sample labels, using a training method similar to that of the first temperature layer. In some embodiments, the fourth training samples can include the sample deformation evaluation, sample pipeline information, and sample environment information of the previous segment, as well as the sample temperature impact, sample pipeline information, and sample environment information of the current segment. The fourth sample label can be the actual deformation evaluation of the current segment under the sample deformation evaluation, sample pipeline information, and sample environment information of the previous segment, as well as the sample temperature impact, sample pipeline information, and sample environment information of the current segment. In some embodiments, the fourth sample label can be determined based on the impact of the pipeline information and environment information of the current segment and the pipeline information and environment information of the previous segment on the deformation evaluation. For example, if the pipe diameter of the previous segment is large and the pipe diameter of the current segment is small, the pressure of the current segment increases and the deformation increases. At this time, the deformation evaluation of the current segment is the sum of the deformation amount of the deformation evaluation of the previous segment and the increased amplitude of the deformation. Another example is that if the temperature of the current segment drops (such as the temperature impact of the current segment or the external temperature where the current segment is located in the environment information drops), the deformation of the current segment weakens. At this time, the deformation evaluation of the current segment is the difference between the deformation probability of the deformation evaluation of the previous segment and the probability of deformation weakening.

[0104] In some embodiments, the training of the second model can further include determining different training sample sets and their corresponding labels based on the distribution of transfer stations; and alternately training different training sample sets according to their sizes; wherein, the learning rates of different training sample sets are different during the training process, and the learning rate is adjusted based on the training sample features.

[0105] The distribution of transfer stations can reflect the distribution of transfer stations in the pipeline system. In some embodiments, different training sample sets can be divided according to the distribution of transfer stations. For example, the data of several transfer stations within a preset distance threshold range can be used as a training sample set. Among them, the preset distance threshold can be set in advance manually.

[0106] The learning rate is a hyperparameter when updating weights during the gradient descent process in machine learning. The learning rate can control the convergence speed, ensure the stability and accuracy of the model, and affect the training efficiency of the model. The lower the learning rate, the slower the change speed of the loss function, and it is easy to overfit. If the learning rate is too high, gradient explosion is likely to occur, the amplitude of the loss vibration is large, and the model is difficult to converge.

[0107] The training sample features can reflect the characteristics of the training samples (including the third training sample and the fourth training sample) themselves. In some embodiments, the training sample features may include the source of the training sample and the reliability of the training sample. Among them, the source of the training sample may include the historical data of gas pipelines with different pressure levels. It can be understood that, compared with gas pipelines with different pressure levels, the similarity of gas pipelines with the same pressure level is higher. For example, the pipeline information, external temperature, pipeline maintenance conditions, etc. of high-pressure pipelines and low-pressure pipelines are usually different.

[0108] The reliability of a training sample refers to the consistency of its corresponding labels for the same or similar training samples. If multiple labels are consistent or mostly consistent, the reliability of the training sample is high and the training effect is good; if multiple labels are inconsistent (that is, for the same or similar training samples, the corresponding actual deformation evaluations are different), the reliability of the training sample is low, which will lead to a poor training effect. The similarity of training samples can be determined by various methods, such as feature extraction and representation, similarity measurement, multimodal integration, clustering and classification, etc.

[0109] In some embodiments, the deformation evaluation determination module 230 may determine the learning rate during the training process of different training sample sets by means of vector matching based on the training sample features. For example, the first vector database may include multiple candidate vectors and their corresponding candidate learning rates. Among them, the candidate vectors can be constructed based on the training sample source and the reliability of the training sample. The candidate learning rate corresponding to the candidate vector can be determined based on the actual learning rate corresponding to the training sample source and the reliability of the training sample.

[0110] In some embodiments, the deformation evaluation determination module 230 may construct a vector to be matched based on the current training sample source and the reliability of the training sample, calculate the distances between the vector to be matched and multiple candidate vectors respectively, determine the candidate vectors with distances less than the distance threshold from the vector to be matched as target vectors, and determine the candidate learning rate corresponding to the target vector as the current learning rate. Among them, the distance threshold can be set in advance manually according to past experience.

[0111] In some embodiments of this specification, through the trained second model, the deformation evaluations of different pipeline segments can be obtained more accurately and quickly. And based on the distribution of transfer stations in the gas pipeline, different training sample sets and their corresponding labels are alternately trained according to the scale, and the deformation evaluation results can be obtained quickly and accurately. At the same time, determining the learning rate according to the training sample features can effectively reduce the training time and improve the training stability of the model.

[0112] Figure 7 is an exemplary schematic diagram of the method for adjusting the deformation evaluation of each pipeline segment shown in some embodiments of this specification. As Figure 7As shown, for each pipeline segment among multiple pipeline segments, the deformation evaluation adjustment module 270 can determine a first confidence level 730 for each pipeline segment based on pipeline information 310, environmental information 321, transportation parameters 370, the inlet data 710 of each pipeline segment, and historical pipeline leakage information 720; and adjust the deformation evaluation 740 of each pipeline segment based on the first confidence level 730 of each pipeline segment. For more information about pipeline information, environmental information, transportation parameters, pipeline segments, and the inlet data of pipeline segments, reference can be made to the relevant descriptions in the foregoing text.

[0113] Historical pipeline leakage information refers to the relevant information on past pipeline leaks. For example, historical pipeline leakage information may include the historical pipeline leakage location, etc. In some embodiments, the deformation evaluation adjustment module 270 can obtain historical pipeline leakage information based on historical data.

[0114] The first confidence level is one of the indicators used to evaluate the adjustment range or amplitude of deformation evaluation. In some embodiments, the deformation evaluation adjustment module 270 can determine the first confidence level based on the similarity between the deformation evaluation (such as the deformation probability) of the current segment output by the second model and the target deformation probability. For example, the higher the similarity, the higher the first confidence level. In some embodiments, the target deformation probability can be determined in various ways. For example, the deformation evaluation adjustment module 270 can construct a second vector database based on historical data, and retrieve the corresponding target deformation probability based on the matching vector. Among them, the second vector database can include multiple reference vectors and their corresponding reference deformation probabilities. The reference vectors can be constructed based on the transportation parameters, pipeline information, and environmental information of the current segment, as well as historical pipeline leakage information. The reference deformation probability corresponding to the reference vector can be the actual deformation probability corresponding to the transportation parameters, pipeline information, and environmental information of the current segment, as well as historical pipeline leakage information.

[0115] In some embodiments, the deformation evaluation adjustment module 270 can construct a vector to be matched based on the inlet data (gas transportation temperature, gas transportation rate) of the current segment, pipeline information, and environmental information, calculate the distances between the vector to be matched and multiple reference vectors respectively, determine the reference vector with a distance less than the distance threshold from the vector to be matched as the target vector, and determine the reference deformation probability corresponding to the target vector as the current target deformation probability. Among them, the distance threshold can be set in advance manually according to past experience. In some embodiments, the reference deformation probability can be labeled according to historical pipeline leakage information. For example, if the current segment has leaked multiple times (such as more than 5 times), the reference deformation probability is 1; if the number of leaks is moderate (such as no more than 3 times), the reference deformation probability is 0.5; if there has never been a leak, the reference deformation probability is 0.

[0116] In some embodiments, the deformation evaluation adjustment module 270 may determine a first magnification factor corresponding to each pipeline segment based on the first confidence level of each pipeline segment; and adjust the deformation evaluation of each pipeline segment based on the first magnification factor.

[0117] The first magnification factor refers to the factor used to adjust the deformation evaluation. The first magnification factors corresponding to each pipeline segment may be the same or different. In some embodiments, the first magnification factor corresponding to each pipeline segment may be negatively correlated with the first confidence level of each pipeline segment. For example, the smaller the first confidence level, the larger the corresponding first magnification factor.

[0118] In some embodiments, the deformation evaluation adjustment module 270 may calculate the adjusted deformation evaluation of each pipeline segment based on the first magnification factor corresponding to each pipeline segment to adjust the deformation evaluation of each pipeline segment. For example, the adjusted deformation evaluation = the current deformation evaluation × the corresponding first magnification factor. For more information on how to adjust the deformation evaluation of each pipeline segment, reference can be made to Figure 8 and its related description.

[0119] In some embodiments of this specification, by determining the first confidence level of each pipeline segment, on the basis of the deformation evaluation output by the second model, the deformation evaluation of each pipeline segment is adjusted to obtain a more accurate deformation probability.

[0120] In some embodiments, a plurality of inspection points are provided in the gas pipeline. An inspection point refers to a position point provided on the gas pipeline for temperature inspection. In some embodiments, the number of inspection points may be a fixed value. In some embodiments, the positions of the inspection points may be randomly generated. It should be noted that the number and positions of the inspection points may also be determined by any other feasible method. For more information on how to determine the number and positions of the inspection points, reference can be made to Figure 10 and its related description.

[0121] In some embodiments, the deformation evaluation adjustment module 270 may adjust the deformation evaluation of each pipeline segment through the steps described in process 800 based on the first confidence level of each pipeline segment.

[0122] Figure 8 is an exemplary flowchart of a method for adjusting the deformation evaluation of each pipeline segment according to some other embodiments of this specification. As Figure 8 shown, process 800 may include the following steps. In some embodiments, process 800 may be executed by the deformation evaluation adjustment module 270.

[0123] Step S810, obtain the actual temperatures of a plurality of inspection points.

[0124] In some embodiments, the deformation evaluation and adjustment module 270 may obtain the actual temperatures of multiple checkpoints through a sensing device. For example, a management personnel may set multiple temperature sensors at multiple checkpoints, and each temperature sensor may obtain the actual temperature of each checkpoint in real time and upload it to the deformation evaluation and adjustment module 270. In some embodiments, the temperature sensors may be integrated into a mobile measuring instrument, and the deformation evaluation and adjustment module 270 may control the mobile measuring instrument to move to each checkpoint in turn to obtain the actual temperatures of multiple checkpoints.

[0125] Step S820: Determine the second confidence level of each pipeline segment based on the actual temperatures of multiple checkpoints and historical predictions.

[0126] The historical prediction refers to the predicted value of the temperature impact corresponding to the transportation parameters reported by the transportation station before determining the current transportation plan. In other words, it is the temperature impact output by the first model corresponding to the transportation parameters when the deformation evaluation meets the preset conditions. For more information about the temperature impact output by the first model, reference can be made to Figure 5 And its related descriptions.

[0127] The second confidence level is another index used to evaluate the adjustment range or amplitude of the deformation evaluation. In some embodiments, the second confidence level of each pipeline segment may be represented based on the temperature difference of the checkpoints on each pipeline segment. In some embodiments, the deformation evaluation and adjustment module 270 may determine the second confidence level of each pipeline segment (i.e., the temperature difference of the checkpoints on each pipeline segment) based on the actual temperatures of multiple checkpoints and historical predictions through the following method.

[0128] S821: Determine the pipeline segment where each checkpoint is located and its position on the corresponding pipeline segment. Among them, the position of each checkpoint on the pipeline segment can be represented by the distance of each checkpoint from the entrance or exit of the pipeline segment where it is located. In some embodiments, the pipeline segment where each checkpoint is located and its position on the corresponding pipeline segment can be obtained by input from the management personnel.

[0129] S822: Obtain the inlet temperature of the pipeline segment where each checkpoint is located and the predicted outlet temperature of the corresponding pipeline segment output by the first model (hereinafter referred to as the predicted outlet temperature), and determine the estimated temperature of each checkpoint through linear difference fitting. Among them, the inlet temperature of the pipeline segment where each checkpoint is located is the outlet temperature of the previous pipeline segment of the corresponding pipeline segment, which is also obtained by the first model.

[0130] S823: Based on the actual temperature and estimated temperature of each checkpoint, calculate the temperature difference of each checkpoint, and then obtain the second confidence level of each pipeline segment. An exemplary calculation formula may include temperature difference = |actual temperature - estimated temperature|.

[0131] It should be noted that for a pipeline segment without a checkpoint, its second confidence level can be obtained based on the nearest checkpoint. For example, the second confidence level of a pipeline segment without a checkpoint = the temperature difference from the nearest checkpoint ÷ the distance between the checkpoint and the inlet or outlet of the pipeline segment.

[0132] Step S830, based on the first confidence level and the second confidence level, adjust the deformation evaluation of each pipeline segment.

[0133] In some embodiments, the deformation evaluation adjustment module 270 can determine a second magnification factor corresponding to each pipeline segment based on the first confidence level and the second confidence level; and adjust the deformation evaluation of each pipeline segment based on the second magnification factor.

[0134] In some embodiments, the second magnification factor corresponding to each pipeline segment can be negatively correlated with the weighted sum of the first confidence level and the second confidence level of each pipeline segment. For example, the smaller the weighted sum of the first confidence level and the second confidence level, the larger the corresponding second magnification factor. Among them, the weighted sum of the first confidence level and the second confidence level refers to the value obtained by weighted summation of the first confidence level and the second confidence level. Since the second confidence level is related to the actual temperature of the checkpoint on the pipeline segment and has a higher reliability compared to the first confidence level, the weight coefficient of the second confidence level is greater than the weight coefficient of the first confidence level when performing weighted summation. For the convenience of calculation, the first confidence level and the second confidence level need to be normalized.

[0135] In some embodiments, the deformation evaluation adjustment module 270 can calculate the adjusted deformation evaluation of each pipeline segment based on the second magnification factor corresponding to each pipeline segment to adjust the deformation evaluation of each pipeline segment. For example, the adjusted deformation evaluation = the current deformation evaluation × the corresponding second magnification factor.

[0136] In some embodiments of this specification, based on the actual temperature and historical prediction of multiple checkpoints, determine the second confidence level of each pipeline segment, and determine the magnification factor based on the weighted sum of the first confidence level and the second confidence level to adjust the deformation evaluation of each pipeline segment, so as to obtain a more accurate deformation evaluation.

[0137] Figure 9 is an exemplary flowchart of a method for updating candidate parameters shown in some embodiments of this specification. As Figure 9 shown, process 900 can include the following steps. In some embodiments, process 900 can be executed by the candidate parameter update module 240.

[0138] Step S910, based on the deformation evaluation corresponding to the candidate parameter, determine the first amplitude of the candidate parameter.

[0139] The deformation evaluation corresponding to a candidate parameter refers to the deformation evaluation of each pipeline segment when a certain candidate parameter is used as the conveying parameter. In some embodiments, the deformation evaluations corresponding to a candidate parameter may be the same or different. For more information about candidate parameters and deformation evaluations, reference can be made to Figure 4 and the relevant descriptions. In some embodiments, the candidate parameter update module 240 may determine the deformation evaluation corresponding to a candidate parameter through a second preset table. Among them, the second preset table can be used to characterize the correlation between candidate parameters and the deformation evaluations of pipeline segments. Each candidate parameter has a corresponding deformation evaluation under different pipeline segments. In some embodiments, the second preset table may be constructed based on historical candidate parameters and historical deformation evaluations of each pipeline segment.

[0140] The first amplitude of a candidate parameter refers to the adjustment amplitude of the candidate parameter determined according to the deformation evaluation corresponding to the candidate parameter. In some embodiments, the candidate parameter update module 240 may determine the first amplitude of the candidate parameter based on the deformation evaluations corresponding to at least one candidate parameter through the principle of positive correlation. For example, the greater the deformation evaluation corresponding to a candidate parameter, the greater the first amplitude of the corresponding candidate parameter.

[0141] Step S920, determine the second amplitude of the candidate parameter based on the consistency between the deformation evaluation and the gas flow direction.

[0142] The gas flow direction refers to the flow direction of gas in the gas pipeline. For example, the gas flow direction is from the starting point (such as the gas source) to the ending point (such as the user end). The consistency between the deformation evaluation and the gas flow direction means that for the same candidate parameter, the degree of deformation of the pipeline segment caused by it is consistent with the distribution of this degree of deformation in the direction of the gas flow. For example, if the change of a candidate parameter causes the same or similar degrees of deformation in multiple pipeline segments on the gas pipeline, and these pipeline segments are physically close or continuous, then it can be considered that the deformation evaluation corresponding to this candidate parameter has a high consistency with the gas flow direction. In some embodiments, the candidate parameter update module 240 may determine the consistency between the deformation evaluation and the gas flow direction through graphical analysis based on the deformation evaluation corresponding to the candidate parameter and the gas flow direction. The specific steps are as follows:

[0143] S921, establish a two-dimensional coordinate system. Among them, the X-axis represents the number of pipeline segments according to the gas flow direction, and the Y-axis represents the deformation evaluation value corresponding to the pipeline segment. Each pipeline segment has a corresponding point in this two-dimensional coordinate system.

[0144] S922, draw a deformation curve. Plot the deformation evaluation values of all pipeline segments corresponding to the candidate parameter in the two-dimensional coordinate system and connect them in sequence to form a curve. This curve reflects the distribution of the deformation degrees of each pipeline segment along the gas flow direction under the same candidate parameter.

[0145] S923. Analyze the peak situation. When there is only one peak in the curve, and the pipeline segments corresponding to this peak are adjacent (such as pipeline segments 2, 3, and 4), and their deformation evaluation values are all the maximum or close to the maximum of this section of the curve, then it can be considered that under this candidate parameter, the consistency between the deformation evaluation and the gas flow direction is high. This indicates that the deformation is mainly concentrated on these adjacent pipeline segments. At this time, reducing the gas transmission temperature can solve the pipeline deformation problem. On the contrary, if there are multiple peaks in the curve (such as three peaks), and the pipeline segments corresponding to these peaks are far apart on the X-axis (such as pipeline segments 1, 50, and 100), then it can be considered that under this candidate parameter, the consistency between the deformation evaluation and the gas flow direction is poor. This indicates that there are more uncontrollable factors causing pipeline deformation. At this time, it is necessary to increase the reduction range of the candidate parameter so that the deformation can be reduced at multiple positions finally.

[0146] In some embodiments, the candidate parameter update module 240 can also screen out multiple pipeline segments with relatively high deformation evaluation values (such as the top 10) based on the deformation evaluation corresponding to the candidate parameter and the gas flow direction, and determine the consistency between the deformation evaluation and the gas flow direction by comparing the relative position relationships (such as distances) between these pipeline segments. For example, if the total distance of multiple pipeline segments with relatively high deformation evaluation values (such as the top 10) does not exceed the distance threshold, then it can be considered that the consistency between the deformation evaluation and the gas flow direction is high. Among them, the distance threshold can be set in advance manually.

[0147] The second amplitude refers to the adjustment amplitude determined according to the consistency degree between the gas flow direction and the deformation evaluation corresponding to the candidate parameter. In some embodiments, the candidate parameter update module 240 can determine the second amplitude of the candidate parameter based on the consistency between the deformation evaluation and the gas flow direction through the negative correlation principle. For example, the higher the consistency between the deformation evaluation and the gas flow direction, the smaller the second amplitude of the candidate parameter. When analyzing the influence of a certain candidate parameter on pipeline deformation, if it is found that the deformation evaluation results show a high degree of consistency in the pipeline segments along the gas flow direction, it indicates that the influence of this candidate parameter on pipeline deformation is local and concentrated. At this time, in order to control or reduce this deformation, a relatively small adjustment of the candidate parameter is required. On the contrary, if the deformation evaluation results show a low degree of consistency, it indicates that the influence of the candidate parameter on pipeline deformation may be more complex and dispersed. At this time, it is necessary to expand the adjustment of the second amplitude to ensure that multiple deformation points can be effectively controlled.

[0148] Step S930. Update the candidate parameter based on the first amplitude and the second amplitude.

[0149] In some embodiments, the candidate parameter update module 240 may calculate the maximum value or average value of the first amplitude and the second amplitude, and use it as the final adjustment amplitude (such as the temperature reduction amplitude), and then adjust or update the current candidate parameter based on the final adjustment amplitude. Merely by way of example, the updated candidate parameter = the current candidate parameter - |the final adjustment amplitude|.

[0150] In some embodiments of this specification, by respectively determining the first amplitude and the second amplitude of the candidate parameter, the candidate parameter update module can comprehensively consider the impact of the change of the candidate parameter itself on the pipeline deformation, as well as the consistency between this change and the gas flow direction. This dual consideration can make the adjustment more accurate, can more accurately reflect the actual situation, and reduce unnecessary adjustment errors.

[0151] In some embodiments, a plurality of inspection points are provided on the gas pipeline, and the plurality of inspection points correspond to at least one delivery station. A delivery station refers to a station in the gas pipeline that is responsible for multiple functions such as gas transmission, pressurization, distribution, metering, and monitoring. In some embodiments, one or more delivery stations may be provided on the gas pipeline, wherein one delivery station may correspond to one or more inspection points. For more content about the delivery station, reference can be made to the relevant description in the foregoing (such as Figure 3 ). In some embodiments, the number of inspection points is related to the deformation evaluation output by the second model. The government safety supervision and management platform can quantify and identify those pipeline segments whose deformation degree exceeds the preset safety threshold by statistically analyzing the deformation evaluation results output by the second model. In some embodiments, there is a significant positive correlation between the number of inspection points and the number of pipeline segments exceeding the safety threshold. That is, the more the number of pipeline segments exceeding the safety threshold, the more the number of inspection points. For more content about the second model and the deformation evaluation, reference can be made to the relevant description in the foregoing (such as Figure 4 、 Figure 6 ).

[0152] In some embodiments of this specification, determining the deformation evaluation of the gas pipeline based on the second model can identify possible weak links or high-risk pipeline segments in the gas pipeline. Based on these evaluation results, the system can dynamically adjust the number of inspection points, increasing the inspection points in the pipeline segments with larger deformation or higher risk, and appropriately reducing the inspection points in the relatively stable pipeline segments. This can not only ensure close monitoring of key pipeline segments, but also effectively avoid waste of resources, and improve the pertinence and monitoring effect of monitoring.

[0153] In some embodiments, the number of inspection points is also related to the temperature impact on the gas pipeline. In some embodiments, there is a significant positive correlation between the number of inspection points and the temperature impact value. That is, the larger the temperature impact value, the more the number of inspection points.

[0154] In some embodiments of this specification, by combining the number of checkpoints with the temperature impact on gas pipelines, the monitoring system can capture the changes in gas pipelines under different temperature conditions more accurately. Increasing the number of checkpoints in areas with large temperature fluctuations can more frequently monitor the impact of temperature on pipeline materials, stress states, etc., thereby detecting potential safety hazards earlier.

[0155] In some embodiments, the number of checkpoints is also related to the number of pipeline segments. In some embodiments, the more the number of gas pipeline segments, the more checkpoints should be set to ensure the accuracy and comprehensiveness of inspections.

[0156] In some embodiments of this specification, by dividing the gas pipeline into multiple pipeline segments and determining the distribution of checkpoints according to the number of pipeline segments, it can be ensured that each pipeline segment can be fully monitored. This helps to timely detect possible problems within each segment, such as leaks, deformations, etc., and thus take targeted measures for treatment to prevent the spread of problems.

[0157] In some embodiments, the location of the checkpoints is related to the temperature impact on the gas pipeline. In some embodiments, the location of the checkpoints needs to cover at least the pipeline segments with relatively high temperature impact values. For example, to determine the optimal location of the checkpoints, the government safety supervision and management platform can rank the pipeline segments based on the temperature impact, specifically involving temperature impact parameters m11, m12,..., m21, etc. Select the pipeline segments with the top-ranked (such as the top 5%) temperature impact among these pipeline segments, and set the checkpoints on these pipeline segments. If it is not feasible to directly set them on the pipeline segments, then select the checkpoint locations closest to these pipeline segments to ensure that the checkpoints can cover with the minimum number and effectively monitor the pipeline segments with the most significant temperature impact.

[0158] In some embodiments of this specification, by setting the location of the checkpoints in areas with greater temperature impact, such as positions with large temperature change gradients, pipe joints, elbows, etc., the impact of temperature on pipeline performance can be captured more accurately. This helps to timely detect potential problems such as pipeline deformations and leaks caused by temperature changes, and improves the accuracy of monitoring. For more content about checkpoints, reference can be made to the relevant descriptions in the previous text (such as Figure 8 ).

[0159] Figure 10 is an exemplary flowchart of a method for adjusting delivery parameters according to some embodiments of this specification. As Figure 10 shown, process 1000 may include the following steps. In some embodiments, process 1000 may be executed by the delivery parameter adjustment module 280.

[0160] Step S1010, obtain the actual temperatures of multiple checkpoints. For specific descriptions on how to obtain the actual temperatures of multiple checkpoints, reference can be made to Figure 8 and related descriptions.

[0161] Step S1020, based on the actual temperatures and historical predictions of multiple checkpoints, determine the confidence levels of at least one delivery station corresponding to the multiple checkpoints.

[0162] The confidence level of a delivery station is used to evaluate the adjustment range or adjustment amplitude of the delivery parameters of the delivery station. In some embodiments, the confidence level of a delivery station can be represented by a vector composed of the temperature differences of one or more checkpoints corresponding to the delivery station. As mentioned above, a delivery station can control one or more pipeline segments. Therefore, when a delivery station controls only one pipeline segment, the confidence level of the delivery station is the same as the second confidence level of the pipeline segment it controls. For more information on the actual temperatures and historical predictions of multiple checkpoints and the calculation method of the temperature differences of checkpoints, reference can be made to Figure 8 and related descriptions.

[0163] Step S1030, based on the confidence levels of at least one delivery station, adjust the delivery parameters. For more information on the delivery parameters, reference can be made to the relevant descriptions in the foregoing (such as Figure 3 - Figure 4 ).

[0164] In some embodiments, the delivery parameter adjustment module 280 can, based on the confidence levels of at least one delivery station, determine multiple checkpoints whose temperature differences among the above-mentioned confidence levels are within the temperature difference range and their corresponding delivery stations, and adjust the delivery parameters (such as the gas delivery temperature) of the delivery stations corresponding to the multiple checkpoints in the following manner. Only as an example, the adjusted gas delivery temperature = the current gas delivery temperature + the temperature difference Adjustment coefficient. Wherein, the adjustment coefficient < 1. In some embodiments, the temperature difference range and the adjustment coefficient can be determined by means such as past experience, historical data, simulation experiments, etc.

[0165] In some embodiments of this specification, by obtaining the actual temperatures of multiple checkpoints in real time and comparing them with historical prediction data, the pipeline segments with abnormal temperatures can be quickly determined. Based on this abnormal information, the system can immediately calculate the confidence levels of the corresponding delivery stations and adjust the delivery parameters accordingly. This fast response mechanism helps to promptly correct the deviations in pipeline operation and prevent problems from expanding.

[0166] 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 of 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 suggested in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

Claims

1. A smart gas pipeline temperature control method based on the Internet of Things, implemented based on a smart gas pipeline temperature control system, characterized in that: The method comprises: Based on the gas company management platform, pipeline information, basic sensing data and candidate parameters of the gas pipeline are obtained, and the transportation parameters are determined through at least one round of iterative interaction with the government safety supervision management platform; the candidate parameters include candidate gas transportation temperatures and / or candidate gas transportation rates of each transportation station; Based on the delivery parameters, controlling the gas equipment object platform to adjust the gas delivery temperature; Among them, one round of iterative interaction includes: Based on the candidate parameters, the pipeline information and the environmental information, the temperature impact of the gas pipeline is determined by a first model and sent to the government safety supervision management platform; the temperature impact is used to reflect the temperature change of the gas pipeline; The first model is a machine learning model; the gas pipeline includes a plurality of pipeline segments, the first model includes a plurality of temperature layers, each temperature layer corresponds to one pipeline segment, the input of each temperature layer includes the inlet data of the corresponding pipeline segment, the pipeline information and the environmental information, and the output of each temperature layer includes the temperature impact and outlet data of the corresponding pipeline segment; the inlet data includes the inlet temperature and / or the inlet rate, and the inlet data of the first pipeline segment is the candidate parameter; the outlet data includes the outlet temperature and / or the outlet rate; The government safety supervision management platform determines a deformation assessment of the gas pipeline based on the temperature impact of the gas pipeline, the candidate parameters, the pipeline information and the basic sensing data; updating the candidate parameters based on the deformation evaluation to obtain updated candidate parameters; In response to the deformation evaluation satisfying a preset deformation condition, the updated candidate parameter is determined as the conveying parameter.

2. The smart gas pipeline temperature control method based on the Internet of Things as claimed in claim 1 is characterized in that: The cutting points of the pipeline segmentation include the position where the diameter of the gas pipeline changes, the pipeline bifurcation position and the pipeline intersection position; The method further comprises: The inlet velocity of the current segment is determined based on the outlet velocity and pipe diameter of the previous segment.

3. The smart gas pipeline temperature control method based on the Internet of Things as claimed in claim 1 is characterized in that: The updating of the candidate parameters based on the deformation assessment of the gas pipeline includes: determining a first magnitude of the candidate parameter based on a deformation assessment corresponding to the candidate parameter; determining a second magnitude of the candidate parameter based on the deformation assessment and consistency of the gas flow direction; and, The candidate parameters are updated based on the first amplitude and the second amplitude.

4. The smart gas pipeline temperature control method based on the Internet of Things as claimed in claim 1 is characterized in that: The gas pipeline is provided with a plurality of inspection points, and the plurality of inspection points correspond to at least one delivery station; The method further comprises: obtaining actual temperatures of the plurality of checkpoints; Determining the confidence of at least one delivery station corresponding to the plurality of checkpoints based on the actual temperatures of the plurality of checkpoints and historical predictions; and The delivery parameters are adjusted based on the confidence level of the at least one delivery station.

5. The smart gas pipeline temperature control method based on the Internet of Things as claimed in claim 4 is characterized in that: The number of the inspection points is related to the temperature influence of the gas pipeline.

6. A smart gas pipeline temperature control system based on the Internet of Things, characterized in that: The system includes a management platform, a sensor network platform and a gas equipment object platform respectively configured on different servers; the management platform includes a gas company management platform and a government safety supervision management platform; The gas company management platform is configured as follows: Obtain pipeline information, basic sensing data and candidate parameters of the gas pipeline, and determine the transportation parameters through at least one round of iterative interaction with the government safety supervision management platform; the candidate parameters include candidate gas transportation temperatures and / or candidate gas transportation rates of each transportation station; Based on the delivery parameters, controlling the gas equipment object platform to adjust the gas delivery temperature; Among them, one round of iterative interaction includes: Based on the candidate parameters, the pipeline information and the environmental information, the temperature impact of the gas pipeline is determined by a first model and sent to the government safety supervision management platform; the temperature impact is used to reflect the temperature change of the gas pipeline; The first model is a machine learning model; the gas pipeline includes a plurality of pipeline segments, the first model includes a plurality of temperature layers, each temperature layer corresponds to one pipeline segment, the input of each temperature layer includes the inlet data of the corresponding pipeline segment, the pipeline information and the environmental information, and the output of each temperature layer includes the temperature impact and outlet data of the corresponding pipeline segment; the inlet data includes the inlet temperature and / or the inlet rate, and the inlet data of the first pipeline segment is the candidate parameter; the outlet data includes the outlet temperature and / or the outlet rate; The government security supervision management platform is configured as follows: Determining a deformation assessment of the gas pipeline based on the temperature impact of the gas pipeline, the candidate parameters, the pipeline information, and the basic sensing data; updating the candidate parameters based on the deformation evaluation to obtain updated candidate parameters; and, In response to the deformation evaluation satisfying a preset deformation condition, the updated candidate parameter is determined as the conveying parameter.

7. The smart gas pipeline temperature control system based on the Internet of Things as claimed in claim 6 is characterized in that: The management platform is configured with: A parameter acquisition module, configured to acquire the basic perception data, the candidate parameters and the pipeline information; a temperature impact determination module, configured to determine the temperature impact of the gas pipeline through the first model based on the candidate parameters, the pipeline information and the environmental information; a deformation assessment determination module, configured to determine a deformation assessment of the gas pipeline based on the temperature impact of the gas pipeline, the candidate parameters, the pipeline information and the basic sensing data; A candidate parameter updating module, configured to update the candidate parameters based on the deformation evaluation of the gas pipeline to obtain updated candidate parameters; a transport parameter determination module, configured to determine the updated candidate parameter as the transport parameter in response to the deformation assessment of the gas pipeline satisfying a preset deformation condition; and The delivery temperature adjustment module is configured to control the air compressor of the gas equipment object platform to adjust the gas delivery temperature based on the delivery parameters.

8. The smart gas pipeline temperature control system based on the Internet of Things as claimed in claim 7 is characterized in that: The gas pipeline includes a plurality of pipeline sections; the government safety supervision management platform is further configured with: The deformation assessment and adjustment module is configured as follows: For each pipeline segment in the plurality of pipeline segments, Determining a first confidence level for each of the pipeline segments based on the pipeline information, the environmental information, the transport parameters, the inlet data of each of the pipeline segments, and historical pipeline leakage information; and, A deformation assessment of each of the pipe segments is adjusted based on the first confidence level of each of the pipe segments.

9. The smart gas pipeline temperature control system based on the Internet of Things as claimed in claim 7, characterized in that: The gas pipeline is provided with a plurality of inspection points, and the plurality of inspection points correspond to at least one delivery station; The government security supervision management platform is further configured with: The transport parameter adjustment module is configured as follows: obtaining actual temperatures of the plurality of checkpoints; Determining the confidence of at least one delivery station corresponding to the plurality of checkpoints based on the actual temperatures of the plurality of checkpoints and historical predictions; and The delivery parameters are adjusted based on the confidence level of the at least one delivery station.

Images