Pipeline drying treatment method based on intelligent gas safety supervision and Internet of Things system

Abstract

The invention provides a pipeline drying processing method based on intelligent fuel gas safety supervision and an Internet of Things system, the system comprises a fuel gas company management platform, a government fuel gas supervision management platform, a fuel gas company object platform and the like, and the method comprises the following steps: obtaining drying medium information of at least one fuel gas pipeline outlet; determining an initial drying value of the gas pipeline based on the drying medium information; in response to the situation that the initial drying value is lower than a drying threshold value, the gas pipeline serves as a target gas pipeline, and advanced drying parameters are determined based on the initial drying value of the target gas pipeline; generating a first control instruction based on the advanced drying parameter and sending the first control instruction to the gas company object platform to perform advanced drying on the target gas pipeline; based on detection data during advanced drying, the confidence coefficient of the initial drying value is evaluated; based on the confidence coefficient of the initial drying value, generating a threshold adjustment instruction, and updating the drying threshold; and generating a performance adjustment instruction based on the confidence coefficient of the initial drying value. The gas pipeline cleaning device can improve the cleaning quality and effect of the gas pipeline.

Description

Technical Field

[0001] The present invention relates to the technical field of gas pipeline drying, and in particular to a pipeline drying processing method and an Internet of Things system based on intelligent gas safety supervision. Background Art

[0002] After the gas pipeline is put into use, impurities will accumulate in the pipeline. In order to ensure the normal use of gas, the gas pipeline needs to be cleaned and dried regularly or irregularly. The operation of ordinary gas pipeline cleaning devices is complicated and inefficient, and it is difficult to complete the steps of quickly cleaning and effectively drying the inside of the pipeline. Therefore, how to simplify the operation and quickly and efficiently clean and dry the inside of the gas pipeline is an urgent problem to be solved today.

[0003] In order to solve the problem of complicated operation of gas pipeline cleaning devices, CN112692011A proposes a gas pipeline cleaning and maintenance device, which optimizes the overall structural design of the gas pipeline cleaning device so that it can quickly clean the internal debris of the pipeline and is easy to operate. However, it still does not solve the problems of water accumulation in low-lying areas after pipeline cleaning, and residual water in the form of gas attached to the pipe wall, which is difficult to remove. This requires evaluation and further processing of the drying effect inside the pipeline.

[0004] Therefore, a pipeline drying treatment method and an Internet of Things system based on intelligent gas safety supervision are provided to solve the problem of natural gas quality being affected by incomplete drying of the inside of the gas pipeline, thereby improving the cleaning quality and effect of the gas pipeline. Summary of the invention

[0005] The invention content includes a pipeline drying processing method based on smart gas safety supervision, which is executed by a pipeline drying processing Internet of Things system based on smart gas safety supervision, and the method includes: obtaining drying medium information of at least one gas pipeline outlet through the gas company management platform; determining an initial drying value of the gas pipeline based on the drying medium information; in response to the initial drying value of at least one gas pipeline being lower than a drying threshold, taking the at least one gas pipeline as a target gas pipeline, and determining an advanced drying parameter based on the initial drying value of the target gas pipeline; generating a first control instruction based on the advanced drying parameter, and sending the first control instruction to the gas company management platform; The target gas pipeline is sent to the gas company object platform, and the gas company object platform performs advanced drying on the target gas pipeline based on the first control instruction; the detection data of the target gas pipeline during advanced drying is obtained, and sent to the government gas supervision and management platform; through the government gas supervision and management platform: based on the detection data during the advanced drying, the confidence of the initial drying value is evaluated; based on the confidence of the initial drying value, a threshold adjustment instruction is generated, and the threshold adjustment instruction is sent to the gas company management platform, so that the gas company management platform updates the drying threshold; based on the confidence of the initial drying value, a performance adjustment instruction is generated.

[0006] The invention content includes a pipeline drying processing Internet of Things system based on smart gas safety supervision, including a government gas supervision management platform, a government gas supervision sensor network platform, a government supervision object platform, a gas company sensor network platform and a gas company object platform, wherein the government supervision object platform includes a gas company management platform; the gas company management platform is configured to: obtain drying medium information of at least one gas pipeline outlet; determine an initial drying value of the gas pipeline based on the drying medium information; in response to the initial drying value of at least one gas pipeline being lower than a drying threshold, take the at least one gas pipeline as a target gas pipeline, and determine advanced drying parameters based on the initial drying value of the target gas pipeline; generate an advanced drying parameter based on the advanced drying parameter A first control instruction is generated, and the first control instruction is sent to the gas company object platform. The gas company object platform performs advanced drying on the target gas pipeline based on the first control instruction; the detection data of the target gas pipeline during advanced drying is obtained, and the data is sent to the government gas supervision and management platform; the government gas supervision and management platform is configured to: evaluate the confidence of the initial drying value based on the detection data during advanced drying; generate a threshold adjustment instruction based on the confidence of the initial drying value, and send the threshold adjustment instruction to the gas company management platform so that the gas company management platform updates the drying threshold; generate a performance adjustment instruction based on the confidence of the initial drying value.

[0007] The present invention includes but is not limited to the following beneficial effects: (1) by analyzing the initial drying value, the gas pipeline that is not completely dried can be evaluated, and according to different initial drying values, different advanced drying parameters are provided to further perform advanced drying on the pipeline that is not completely dried, thereby improving the overall drying effect of the gas pipeline; (2) by adjusting the drying threshold according to the confidence level of the initial drying value, the gas pipeline that is not completely dried can be further screened out as the target gas pipeline, thereby performing advanced drying. The lower the confidence level of a gas company, the more likely it is that the final drying will be incomplete, which will affect the quality and safety of gas use. The processor needs to process the detection data obtained by the crawling robot at a higher frequency to improve the accuracy of data processing and the timeliness of judgment; (3) Based on the actual detection data of the crawling robot in the target pipeline, the correction coefficient is determined to correct the initial drying value of the candidate gas pipeline, which can further screen out the target pipeline that meets the conditions and avoid missing the target pipeline; (4) The drying position whose natural drying time is less than the preset time threshold is deleted from the advanced drying parameters, so that the crawling robot does not need to stay in the pipeline section that has been naturally dried, thereby improving efficiency and safety, while saving resources and costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The present invention will be further described in the form of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is a schematic diagram of the platform structure of the pipeline drying treatment Internet of Things system based on smart gas safety supervision shown in some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a pipeline drying treatment method based on smart gas safety supervision according to some embodiments of this specification;

[0011] Figure 3 is an exemplary schematic diagram of determining a sub-drying value according to some embodiments of the present specification;

[0012] Figure 4 is an exemplary flow chart for adjusting advanced drying parameters according to some embodiments of the present specification;

[0013] Figure 5 is an exemplary schematic diagram of a natural drying model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present invention. For ordinary technicians in this field, the present invention can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] The present invention uses a flow chart to illustrate the operations performed by the system according to an embodiment of the present invention. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, the various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] After the gas pipeline is put into use, it needs to be cleaned regularly to prevent a large amount of impurities from accumulating in the pipeline. CN112692011A only focuses on the goal of quickly cleaning the internal debris of the gas pipeline and simple operation through the design of a reasonable device structure, but does not solve the problem of evaluating the drying effect in the pipeline and dealing with the problem of not drying. Therefore, some embodiments of the present invention preliminarily judge the distribution of the drying situation based on cleaning parameters, drying parameters, pipeline characteristics, ambient temperature, etc., and determine the actual degree of drying in combination with internal monitoring data. During this period, according to the distribution of the drying situation, a first drying instruction is generated to control the robot to reach the corresponding position, and then the advanced drying parameters are determined in combination with the actual degree of drying, and the robot is controlled to use the advanced drying parameters to process the incompletely dried pipeline area. In this way, the drying situation inside the gas pipeline can be better judged, and the incompletely dried area can be further processed, thereby ensuring the drying efficiency and improving the cleaning quality and effect of the gas pipeline.

[0019] Figure 1 It is a schematic diagram of the platform structure of a pipeline drying treatment Internet of Things system based on smart gas safety supervision shown in some embodiments of this specification.

[0020] In some embodiments, Figure 1 As shown, the pipeline drying processing Internet of Things system 100 based on smart gas safety supervision may include a government gas supervision management platform 110, a government gas supervision sensor network platform 120, a government supervision object platform 130, a gas company sensor network platform 140 and a gas company object platform 150 connected in sequence.

[0021] The government gas regulation management platform 110 is a platform for processing data related to government gas regulation. In some embodiments, the government gas regulation management platform 110 can be configured as a processor. The government gas regulation related data can include the confidence of the initial dry value, threshold adjustment instructions, performance adjustment instructions, etc.

[0022] The government gas supervision sensor network platform 120 is a platform used by the government for sensor communication. In some embodiments, the government gas supervision sensor network platform 120 can be configured as a gateway device or a communication device, etc., to realize data interaction function.

[0023] In some embodiments, the government gas supervision sensor network platform 120 can be connected to the government gas supervision management platform 110 and the gas company management platform 131 of the government supervision object platform 130. For example, the government gas supervision sensor network platform 120 can obtain the detection data and initial drying value sent by the gas company management platform 131 and upload them to the government gas supervision management platform 110. For another example, the government gas supervision sensor network platform 120 can obtain the threshold adjustment instruction and performance adjustment instruction generated by the government gas supervision management platform 110 and send them to the gas company management platform 131.

[0024] The government regulatory object platform 130 is a direct source platform for government users to obtain regulatory information.

[0025] In some embodiments, the government regulatory object platform 130 may include a gas company management platform 131 .

[0026] The gas company management platform 131 is a platform for managing and analyzing data related to the gas company. In some embodiments, the gas company management platform 131 may include a data center and a detection database. The data center is used to store and manage data related to the gas pipeline drying process. In some embodiments, the data center can be configured as a memory. The detection database is a database for the detection data of the gas pipeline. In some embodiments, the detection database can be part of the data center or a separate memory. For more information about detection data, see Figure 2 And related instructions.

[0027] In some embodiments, the gas company management platform 131 is configured to obtain drying medium information of at least one gas pipeline outlet; determine the initial drying value of the gas pipeline based on the drying medium information; in response to the initial drying value of at least one gas pipeline being lower than the drying threshold, take at least one gas pipeline as a target gas pipeline, and determine advanced drying parameters based on the initial drying value of the target gas pipeline; generate a first control instruction based on the advanced drying parameters, and send the first control instruction to the gas company object platform 150, and the gas company object platform 150 performs advanced drying on the target gas pipeline based on the first control instruction; obtain detection data of the target gas pipeline during advanced drying, and send it to the government gas supervision and management platform 110.

[0028] In some embodiments, the drying medium information also includes a drying medium flow rate, and the gas company management platform 131 can be further configured to determine moisture discharge data in the gas pipeline based on the drying medium information; and determine an initial drying value based on the moisture discharge data.

[0029] In some embodiments, the gas pipeline includes at least one pipeline segment, the initial dryness value includes a sub-dryness value of at least one pipeline segment, and the gas company management platform 131 can be further configured to: segment the gas pipeline based on the gas pipeline information, and determine the location information of at least one pipeline segment; determine the sub-dryness value of at least one pipeline segment based on the location information and moisture discharge data of at least one pipeline segment.

[0030] In some embodiments, the gas company management platform is further configured to: determine the location of residual moisture in the gas pipeline based on the gas pipeline information; segment the gas pipeline based on the residual moisture location, and determine the location information of at least one pipeline segment. For more information about the residual moisture location, please refer to Figure 2 And related instructions.

[0031] In some embodiments, the gas company management platform 131 is further configured to: construct a moisture discharge map based on the location information and moisture discharge data of at least one pipeline segment, the moisture discharge map including nodes and edges, the nodes are pipeline segments, the node features of the nodes include the location information of the pipeline segments, gas pipeline information, drying medium information and moisture residual position, the direction of the edges is the flow direction of the drying medium, and the edge features of the edges include the diameter of the joints between the pipeline segments; based on the moisture discharge map, determine the sub-dryness value of at least one pipeline segment through a drying evaluation model, and the drying evaluation model is a graph neural network model.

[0032] In some embodiments, the gas company management platform 131 is further configured to: determine the actual dryness value of the target gas pipeline based on the detection data of the target gas pipeline; determine the correction value based on the actual dryness value and the initial dryness value; and correct the initial dryness value of the candidate gas pipeline based on the correction value.

[0033] In some embodiments, the gas company management platform 131 is further configured to: determine similar gas pipelines of the target gas pipeline based on the gas pipeline information; and correct the initial dryness value of the similar gas pipeline based on the correction value.

[0034] In some embodiments, the gas company management platform 131 is further configured to: determine the water content in the target gas pipeline based on the initial dryness value and the target gas pipeline information; determine the advanced drying parameters based on the water content; obtain the first detection data of the first position before advanced drying, and based on the first detection data, evaluate the first dryness value of the target gas pipeline at the first position; generate a parameter adjustment instruction based on the first dryness value; and adjust the advanced drying parameters of the second position based on the parameter adjustment instruction.

[0035] In some embodiments, the target gas pipeline includes multiple pipeline segments, and the gas company management platform can be further configured to: estimate the airflow drying effect of multiple pipeline segments at the second position based on the first drying value; determine the natural drying time of the target gas pipeline at the second position based on the airflow drying effect and the second drying value, and the second drying value refers to the drying value of the pipeline segment at the second position; and delete the drying positions whose natural drying time is less than a preset time threshold from the advanced drying parameters.

[0036] In some embodiments, the gas company management platform can be further configured to: determine the natural drying time through a natural drying model based on the airflow drying effect sequence, the second position information sequence, and the second drying value sequence, where the natural drying model is a machine learning model. For more information about the natural drying model, see Figure 5 And related instructions.

[0037] The gas company sensor network platform 140 is a functional platform used by the gas company to monitor and transmit gas pipeline drying process related data. In some embodiments, the gas company sensor network platform 140 can be configured as a gateway device or a communication device to realize data interaction function.

[0038] In some embodiments, the gas company sensor network platform 140 can be connected to the gas company management platform 131 of the government supervision object platform 130 and the gas company object platform 150 for communication. For example, the gas company sensor network platform 140 can obtain the drying medium information uploaded by the gas company object platform 150 and send it to the gas company management platform 131 of the government supervision object platform 130. For another example, the gas company sensor network platform 140 can obtain the first control instruction issued by the gas company management platform 131 of the government supervision object platform 130 and send it to the gas company object platform 150.

[0039] The gas company object platform 150 is a functional platform for sensing information generation and controlling information execution.

[0040] In some embodiments, the gas company object platform can be configured as a drying device, a blow-drying device, a detection device, a crawling robot, etc.

[0041] Drying equipment refers to equipment for preliminary drying of gas pipelines. For example, the drying equipment may include at least one of a pipe cleaner, an air compressor unit, a heating device, a nitrogen replacement device, and the like.

[0042] Blow-drying equipment refers to equipment for advanced drying of gas pipelines. Blow-drying equipment may include a blower and a heating wire. The blower blows out hot air through the heating wire, thereby performing advanced drying of the gas pipeline.

[0043] The detection equipment is a device that detects the relevant operating parameters of the gas pipeline. The detection equipment can be configured as a humidity sensor, a temperature sensor, a flow rate sensor, etc.

[0044] The crawling robot is an autonomous device that can move in a gas pipeline. In some embodiments, the crawling robot can be equipped with a drying device and a detection device. The crawling robot can move in the gas pipeline, perform advanced drying of different parts of the gas pipeline based on the drying device, and obtain detection data in the gas pipeline based on the detection device.

[0045] For more information on the above, see Figure 2-Figure 5 And related instructions.

[0046] Through the pipeline drying treatment Internet of Things system 100 based on smart gas safety supervision, an information operation closed loop can be formed between the gas company object platform 150 and the government gas supervision management platform 110, and coordinated and regularly operated under the unified management of the government supervision object platform 130, thereby realizing the informatization and intelligence of gas pipeline drying treatment.

[0047] Figure 2200 is an exemplary flow chart of a pipeline drying treatment method based on smart gas safety supervision according to some embodiments of this specification. Flow 200 is an exemplary flow chart of a pipeline drying treatment method based on smart gas safety supervision, such as Figure 2 As shown, the process 200 includes the following steps 210 to 280.

[0048] In some embodiments, steps 210 to 250 may be performed by the gas company management platform 131 .

[0049] Step 210: Acquire drying medium information of at least one gas pipeline outlet.

[0050] The gas pipeline is a gas pipeline that has been preliminarily dried. The preliminarily drying can be achieved by using a drying device through a preset method, and the drying device can include at least one of a pipe cleaner, an air compressor unit, a heating device, a nitrogen replacement device, etc. The preset method can be at least one of a desiccant drying method, a dry air drying method, a nitrogen drying method, etc.

[0051] The gas pipeline outlet refers to the outlet of the drying medium in the gas pipeline. The drying medium is the medium that provides a dry environment or creates drying conditions. Different drying methods use different drying media, such as the desiccant (such as methanol desiccant) used in the desiccant drying method, the nitrogen used in the nitrogen drying method, and the dry air used in the dry air drying method.

[0052] The drying of the gas pipeline is generally long-distance pipeline station drying, that is, the drying medium enters from the inlet of one gas station and flows out from the gas pipeline of other gas stations. In some embodiments, the gas pipeline outlet may include one or more.

[0053] The drying medium information is information related to the drying medium. In some embodiments, the drying medium information may include the drying medium humidity at the outlet of the gas pipeline when the preliminary drying is completed.

[0054] In some embodiments, the gas company management platform 131 may obtain the drying medium information uploaded by the gas company object platform 150 through the gas company sensor network platform 140. The gas company object platform 150 may obtain the drying medium information through a sensor disposed at at least one gas pipeline outlet. For example, the drying medium humidity may be obtained through a humidity sensor disposed at at least one gas pipeline outlet.

[0055] Step 220: Determine the initial drying value of the gas pipeline based on the drying medium information.

[0056] The initial drying value is a numerical value used to characterize the dryness of the gas pipeline after preliminary drying. The larger the initial drying value, the drier the gas pipeline is and the better the initial drying effect is.

[0057] In some embodiments, the gas company management platform 131 can use the drying medium humidity at the end of the initial drying as the theoretical humidity in the gas pipeline to calculate the initial drying value of the gas pipeline. The initial drying value is negatively correlated with the theoretical humidity.

[0058] For example, the gas company management platform 131 can calculate the initial dryness value by formula (1). Formula (1) is as follows:

[0059] Initial drying value = 1 / theoretical humidity (1)

[0060] Among them, theoretical humidity refers to the theoretical humidity value in the gas pipeline after preliminary drying.

[0061] In some embodiments, the gas company management platform 131 may determine the moisture discharge data in the gas pipeline based on the drying medium information; and determine the initial drying value based on the moisture discharge data.

[0062] The moisture discharge data refers to the relevant data of the moisture discharged from the gas outlet of the gas pipeline during the preliminary drying process. In some embodiments, the moisture discharge data includes the moisture discharge speed, the moisture discharge amount, etc. The moisture discharge speed refers to the speed at which moisture is discharged from the gas outlet during the preliminary drying process. The moisture discharge amount refers to the amount of moisture contained in the drying medium discharged from the gas outlet during the preliminary drying process.

[0063] In some embodiments, the gas company management platform 131 can obtain the drying medium flow rate and the drying medium humidity at multiple consecutive moments in the preliminary drying process; based on the drying medium flow rate and the drying medium humidity between two adjacent moments, the sub-moisture discharge amount between the two adjacent moments is calculated, and the multiple consecutive sub-moisture discharge amounts are added to obtain the total moisture discharge amount of the gas pipeline; the sub-moisture discharge speed can be calculated based on the sub-moisture discharge amount and the time length between the two moments.

[0064] In some embodiments, the gas company management platform 131 can perform curve fitting on multiple sub-water discharge amounts and sub-water discharge speeds in the preliminary drying process to determine a water discharge change curve; integrate the water discharge data change curve to obtain the total moisture content in the gas pipeline; use the difference between the total moisture content in the gas pipeline and the water discharge amount as the residual moisture content in the gas pipeline; and determine the initial drying value based on the residual moisture content in the gas pipeline and the gas pipeline information. The water discharge change curve reflects the changes in the sub-water discharge amounts and sub-water discharge speeds in multiple time periods during the preliminary drying process, and the multiple time periods are time periods composed of multiple adjacent moments in the preliminary drying process.

[0065] The gas company management platform 131 can calculate the volume of the gas pipeline based on the diameter and length of the gas pipeline in the gas pipeline information, and use the ratio of the residual moisture content to the volume as the theoretical humidity to calculate the initial dry value based on formula (1). For formula (1), please refer to the above, and for the gas pipeline information, please refer to the following.

[0066] The initial drying value is determined by the moisture discharge data. The moisture discharge data can be calculated based on multiple detection data, and the total moisture content of the gas pipeline before preliminary drying can be fitted, thereby calculating the residual moisture content. The initial drying value based on the residual moisture content can make the initial drying value more accurate and reduce the error caused by directly measuring the humidity of the drying medium.

[0067] In some embodiments, the gas pipeline includes at least one pipeline segment, and the initial dryness value includes a sub-dryness value of the at least one pipeline segment.

[0068] Pipeline segmentation refers to dividing the same gas pipeline into at least one section of pipeline, each section is a pipeline segment. Different pipeline segments correspond to different sub-drying values.

[0069] In some embodiments, the gas company management platform 131 can segment the gas pipeline based on the gas pipeline information and determine the location information of at least one pipeline segment; based on the location information and moisture discharge data of at least one pipeline segment, determine the sub-dryness value of at least one pipeline segment.

[0070] Gas pipeline information refers to information related to the size and distribution of gas pipelines, etc. For example, the length, diameter, material, service life, branches, joints, elbows, etc. of the gas pipeline. In some embodiments, the gas company management platform 131 can obtain the gas pipeline information uploaded by the government gas supervision management platform 110 through the government gas supervision sensor network platform 120. Government users can upload gas pipeline information to the government gas supervision management platform 110 through user terminals.

[0071] In some embodiments, the gas company management platform 131 can segment the gas pipeline based on the gas pipeline information by various methods. For example, the gas company management platform 131 can segment different branch pipelines into different pipeline segments. For another example, the gas company management platform 131 can segment gas pipelines of different materials into different pipeline segments. For another example, the gas company management platform 131 can segment gas pipelines of different diameters into different pipeline segments.

[0072] In some embodiments, the gas company management platform 131 can determine the location of residual moisture in the gas pipeline based on the gas pipeline information; segment the gas pipeline based on the residual moisture location, and determine the location information of at least one pipeline segment.

[0073] The residual moisture location refers to the location in the gas pipeline where moisture is likely to remain, such as depressions, joints, branches, elbows, etc. of the pipeline.

[0074] In some embodiments, the moisture residual position can be determined based on prior experience. For example, based on prior experience, the position where water accumulation exists in historical data is set as the moisture residual position.

[0075] In some embodiments, the gas company management platform 131 may use the moisture residue position as the demarcation point for pipeline segmentation, and segment the gas pipeline according to the demarcation point to obtain multiple pipeline segments.

[0076] The presence of water at the moisture residual position will affect the drying value of the nearby pipes. Segmentation based on the moisture residual position can obtain more detailed and accurate drying values, providing accurate data reference for the subsequent determination of advanced drying parameters.

[0077] The position information of the pipeline segment is related information used to indicate the position of the pipeline segment in the gas pipeline. The position information of the pipeline segment can be indicated by the distance of the pipeline segment from the inlet and / or outlet of the gas pipeline.

[0078] In some embodiments, the gas company management platform 131 can construct a feature vector based on moisture discharge data and location information of pipeline segments, search in a vector database based on the feature vector, and use the reference dryness value corresponding to the reference vector with the highest similarity as the sub-dryness value of different gas pipeline segments.

[0079] The vector database includes multiple reference vectors and corresponding reference dryness values. The vector database can be constructed based on the actual dryness values ​​and their corresponding pipeline segment location information and moisture discharge data. For more information about the actual dryness values, see Figure 2 Related instructions are given below.

[0080] In some embodiments, the feature vector also includes a moisture residual position. For details about the moisture residual position, see above.

[0081] The gas pipeline between gas plants is not a single pipeline, and may have branches and different shapes. During the initial drying process, the drying conditions of each pipeline segment may be different, and the residual moisture during drying may be different. At the same time, the desiccant absorbs a large amount of moisture in the early stage of entering the pipeline, resulting in moisture absorption saturation. In the later stage, it is difficult to absorb more moisture, resulting in a lower dryness value for the pipeline segment close to the pipeline outlet. Therefore, by determining the sub-dryness value of the pipeline segment, the obtained dryness value can be made more accurate.

[0082] In some embodiments, the gas company management platform 131 can determine the actual dryness value of the target gas pipeline based on the detection data of the target gas pipeline; determine the correction value based on the actual dryness value and the initial dryness value; and correct the initial dryness value of the candidate gas pipeline based on the correction value.

[0083] The target gas pipeline refers to the gas pipeline that needs to be dried in an advanced manner. For more information about the target gas pipeline, please refer to the following text. For the initial drying value, please refer to the relevant instructions in the previous text.

[0084] The candidate gas pipeline refers to all gas pipelines except the target gas pipeline. The initial dryness value of the candidate gas pipeline is greater than or equal to the dryness threshold.

[0085] The actual dryness value is used to characterize the actual dryness level in the target gas pipeline.

[0086] In some embodiments, the gas company management platform 131 can obtain the actual moisture content detected by the crawling robot in different pipeline segments, determine the sub-dryness values ​​corresponding to the different pipeline segments based on the actual moisture content through formula (1), and use the statistical value of the sub-dryness values ​​of the different pipeline segments as the actual dryness value. Formula (1) can be found in the above text. The statistical value can be a mean value.

[0087] The corrected value refers to the corrected initial drying value.

[0088] In some embodiments, the gas company management platform 131 may determine at least one correction coefficient corresponding to at least one target gas pipeline based on the actual dryness value and the initial dryness value of at least one target gas pipeline; multiply the statistical value of the correction coefficient by the initial dryness value of the candidate gas pipeline as the correction value; and adjust the initial dryness value of the candidate gas pipeline to the correction value. The statistical value of the correction coefficient may be an average value of the correction coefficient.

[0089] The correction coefficient is positively correlated with the actual dryness value of the target gas pipeline and negatively correlated with the initial dryness value of the target gas pipeline. For example, the gas company management platform 131 can determine the correction coefficient by formula (2), which is as follows:

[0090] Correction factor = actual drying value / initial drying value (2)

[0091] In some embodiments, the gas company management platform 131 can re-judge the candidate gas pipelines based on the corrected initial dryness value, and use the candidate gas pipelines whose corrected initial dryness value is lower than the dryness threshold as target gas pipelines for advanced drying.

[0092] The initial dryness value is calculated based on the humidity of the drying medium at the outlet of the gas pipeline. It is an estimated value and may deviate from the actual humidity in the pipeline. Based on the actual detection data of the crawling robot in the target pipeline, the correction coefficient is determined and the initial dryness value of the candidate gas pipeline is corrected. This can further screen out the target pipelines that meet the conditions and avoid missing the target pipelines.

[0093] In some embodiments, the gas company management platform 131 can determine similar gas pipelines of the target gas pipeline based on the gas pipeline information, and correct the initial dryness value of the similar gas pipeline based on the correction value. For gas pipeline information, please refer to the above related description.

[0094] A similar gas pipeline refers to a gas pipeline in a candidate gas pipeline that is similar to a target gas pipeline. In some embodiments, the gas company management platform 131 can construct a first feature vector based on the gas pipeline information, calculate the similarity between the first feature vector of the target gas pipeline and the first feature vector of the candidate gas pipeline, and use the candidate gas pipeline with a similarity greater than a similarity threshold as a similar gas pipeline of the target gas pipeline. The similarity is negatively correlated with the vector distance, and the vector distance can be a Euclidean distance, a cosine distance, etc. For the candidate gas pipelines, please refer to the relevant description above.

[0095] In some embodiments, the gas company management platform 131 can obtain a correction coefficient of a target gas pipeline corresponding to a similar gas pipeline; use the product of the correction coefficient and the initial dry value of the similar gas pipeline as a correction value; and adjust the initial dry value of the similar gas pipeline to the correction value.

[0096] Since the gas pipeline is long, when comparing the entire section of the gas pipeline, there may be large differences between different gas pipelines, and it may be that fewer similar gas pipelines that meet the conditions are screened out.

[0097] In some embodiments, for a certain pipeline segment of the target gas pipeline, the gas company management platform 131 can construct a second feature vector based on the gas pipeline information, pipeline segment location information, and moisture residual location information of the pipeline segment, search for reference feature vectors with a similarity greater than a similarity threshold in the segment vector database, calculate the second feature vectors of different pipeline segments of the target gas pipeline, and the similarity with the second feature vectors of pipeline segments of the candidate gas pipeline, and take the pipeline segments with a similarity greater than the similarity threshold as similar pipeline segments. The vector database includes multiple gas pipeline segments of all candidate gas pipelines and corresponding reference feature vectors, and the reference feature vectors are constructed based on the gas pipeline information, location information, and moisture residual location of the pipeline segments of the candidate gas pipeline.

[0098] In some embodiments, the gas company management platform 131 can calculate the correction coefficient of the pipeline segment of the target gas pipeline based on the actual dryness value and sub-dryness value of the pipeline segment of the target gas pipeline by formula (2), and use the product of the correction coefficient and the sub-dryness value of the similar gas pipeline segment as the correction value of the similar pipeline segment, and adjust the sub-dryness value of the similar pipeline segment to the correction value. For the actual dryness value and sub-dryness value, please refer to the relevant description above.

[0099] In some embodiments, if the similar pipeline segment corresponds to pipeline segments of multiple target gas pipelines, a weighted value of the correction values ​​of the pipeline segments of the multiple target gas pipelines is calculated, and the weighted value is used as the final correction value of the pipeline segment. The weight can be determined based on the similarity between the reference feature vector of the pipeline segment and the second feature vectors of the pipeline segments of the multiple target gas pipelines, and the weight is positively correlated with the similarity.

[0100] Only making corrections to similar gas pipelines can ensure the accuracy of the correction operation and avoid invalid operations.

[0101] Step 230: In response to the initial dryness value of at least one gas pipeline being lower than a dryness threshold, taking at least one gas pipeline as a target gas pipeline, and determining an advanced drying parameter based on the initial dryness value of the target gas pipeline.

[0102] The dryness threshold refers to the critical value of the initial dryness value of the gas pipeline. The dryness threshold can be set based on experience or demand.

[0103] For details about the target gas pipeline, please refer to the relevant description above.

[0104] Advanced drying refers to further drying of the gas pipeline. Water accumulation in low-lying areas of the pipeline and residual water in liquid form attached to the pipe wall are difficult to completely remove through preliminary drying, and further advanced drying is required. Advanced drying can be carried out by entering the gas pipeline through a crawling robot. The drying equipment equipped with the crawling robot can blow out hot air through a fan and an electric heating wire to dry low-lying areas in the pipeline and other places with high humidity. For more information about crawling robots and drying equipment, please refer to Figure 1 .

[0105] Advanced drying parameters are related parameters for advanced drying of the target gas pipeline. For example, the drying position, the drying wind speed and drying time of the fan on the drying equipment, the heating power of the heating wire on the drying equipment, etc. The drying position is the position of the crawling robot when performing advanced drying on the target gas pipeline. For a target gas pipeline, the pipeline may be long and have many low-lying areas. The crawling robot can stay at multiple locations of the target gas pipeline to ensure the advanced drying effect.

[0106] In some embodiments, the gas company management platform 131 can evenly set multiple drying positions based on the length of the gas pipeline; the spacing between adjacent drying positions can be determined based on the initial drying value, and the smaller the initial drying value, the smaller the spacing.

[0107] In some embodiments, the gas company management platform 131 can set the heating power of the heating wire on the drying device based on the difference between the initial dryness value of the target gas pipeline and the dryness threshold. The larger the difference, the greater the heating power.

[0108] In some embodiments, the gas company management platform 131 can set the drying speed and drying time of the fan on the drying equipment based on the distance between the drying position and the gas pipeline outlet. The longer the distance, the greater the wind speed and the longer the drying time, so that moisture can be blown out of the gas pipeline.

[0109] Step 240: Generate a first control instruction based on the advanced drying parameter, and send the first control instruction to the gas company object platform. The gas company object platform performs advanced drying on the target gas pipeline based on the first control instruction.

[0110] The first control instruction is an operation command to control the drying device of the crawling robot to perform advanced drying. In some embodiments, the gas company object platform 150 can control the drying device on the crawling robot to perform advanced drying on the target gas pipeline based on the first control instruction. For more information about the crawling robot and the drying device, please refer to Figure 1 Related instructions.

[0111] Step 250, obtaining the detection data of the target gas pipeline during advanced drying, and sending it to the government gas supervision and management platform.

[0112] The detection data refers to the actual moisture data detected by the crawling robot in the gas pipeline. In some embodiments, the detection data includes air humidity and water accumulation in the gas pipeline, and the water accumulation includes water accumulation area and water accumulation depth.

[0113] In some embodiments, the gas company management platform 131 can obtain the detection data uploaded by the gas company object platform 150 through the gas company sensor network platform 140. The gas company object platform 150 can obtain the air humidity in the gas pipeline through the humidity sensor configured on the crawler robot; and obtain the water accumulation in the gas pipeline through the acoustic wave detector.

[0114] In some embodiments, steps 260 - 280 may be performed by the government gas regulatory management platform 110 .

[0115] Step 260 , based on the detection data during advanced drying, evaluate the confidence of the initial drying value.

[0116] The confidence level of the initial drying value is used to characterize the credibility of the initial drying value.

[0117] In some embodiments, the government gas regulatory management platform 110 can determine the theoretical moisture content in the gas pipeline based on theoretical humidity and gas pipeline size; determine the actual moisture content based on detection data; and determine the confidence level of the initial drying value based on the difference between the theoretical moisture content and the actual moisture content.

[0118] The gas pipeline size may be the volume inside the gas pipeline. The gas pipeline size may be calculated based on the length and diameter of the gas pipeline in the gas pipeline information.

[0119] The theoretical moisture content refers to the theoretical amount of moisture remaining in the gas pipeline after preliminary drying. In some embodiments, the government gas supervision and management platform 110 can use the product of theoretical humidity and gas pipeline size as the theoretical moisture content.

[0120] The actual moisture content refers to the moisture content actually detected in the gas pipeline after preliminary drying. The actual moisture content includes the moisture content in the air and the amount of accumulated water. In some embodiments, the actual moisture content is positively correlated with air humidity, gas pipeline size, accumulated water area and accumulated water depth. The government gas supervision and management platform 110 can calculate the actual moisture content using formula (3).

[0121] Actual moisture content = air humidity × gas pipeline size + water density × water accumulation area × water accumulation depth (3)

[0122] The confidence of the initial dryness value is positively correlated with the absolute value of the difference between the theoretical moisture content and the actual moisture content. For example, the government gas supervision management platform 110 can calculate the confidence of the initial dryness value by formula (4).

[0123] Confidence of initial drying value = 1-|AB| / B (4)

[0124] Among them, A is the initial drying value and B is the actual drying value.

[0125] Step 270: Generate a threshold adjustment instruction based on the confidence of the initial dryness value, and send the threshold adjustment instruction to the gas company management platform so that the gas company management platform updates the dryness threshold.

[0126] The threshold value adjustment instruction refers to an operation instruction for adjusting the drying threshold value.

[0127] In some embodiments, the government gas regulatory management platform 110 may generate a threshold adjustment instruction in response to the confidence level of the initial dryness value being less than a preset threshold.

[0128] In some embodiments, the adjusted dryness threshold is positively correlated with the confidence of the initial dryness value. The lower the confidence of the dryness value, the lower the adjusted dryness threshold.

[0129] In some embodiments, the gas company management platform 131 can judge the candidate gas pipelines based on steps 210 to 240, further screen out the newly added target gas pipelines whose initial dryness values ​​are lower than the adjusted dryness threshold, and perform advanced drying on the newly added target gas pipelines. In this way, the gas pipelines that have not been completely dried can be screened out as completely as possible as target gas pipelines for advanced drying to avoid omissions. For the candidate gas pipelines, please refer to the relevant description above.

[0130] Step 280 , generating a performance adjustment instruction based on the confidence level of the initial dryness value.

[0131] The performance adjustment instruction is instruction information for adjusting the frequency of the processor of the government gas supervision and management platform 110 acquiring and processing the data related to different gas companies. The gas company related data refers to the data related to the drying process of the gas pipeline of the gas company, such as the drying medium information, gas pipeline information, detection data, threshold adjustment instruction, etc. of the gas pipeline of the gas company.

[0132] In some embodiments, the government gas supervision management platform 110 can generate a performance adjustment instruction based on the inverse of the confidence of the initial dry values ​​of different gas companies and adjust the performance allocation strategy. The performance allocation strategy refers to the frequency with which the processor of the government gas supervision management platform 110 processes data related to different gas companies.

[0133] The government gas regulatory management platform 110 can use the ratio of the average values ​​of the inverses of the confidence levels of the initial dry values ​​of multiple gas pipelines of different gas companies as the ratio of the frequencies of the processor processing different gas companies, generate performance adjustment instructions, and adjust the performance allocation strategy.

[0134] By analyzing the initial drying value, it is possible to evaluate gas pipelines that are not completely dried initially, and provide different advanced drying parameters according to different initial drying values ​​to further dry the pipelines that are not completely dried, thereby improving the overall drying effect of the gas pipeline. By adjusting the drying threshold according to the confidence of the initial drying value, gas pipelines that are not completely dried can be further screened out as target gas pipelines for advanced drying. The lower the confidence of a gas company, the more likely it is that the final drying will be incomplete, resulting in poor gas quality and safety. The processor needs to process the detection data obtained by the crawling robot at a higher frequency, thereby improving the accuracy of data processing and the timeliness of judgment.

[0135] Figure 3is an exemplary schematic diagram of determining a sub-dryness value according to some embodiments of the present specification.

[0136] In some embodiments, Figure 3 As shown, the gas company management platform 131 can construct a moisture discharge map 320 based on at least one pipeline segment 311 and moisture discharge data 312 ; based on the moisture discharge map 320 , determine a sub-dryness value 340 of at least one pipeline segment through a dryness assessment model 330 .

[0137] The moisture discharge map is used to represent the discharge of moisture in different pipeline sections in the same gas pipeline. One gas pipeline corresponds to one moisture discharge map. In some embodiments, the moisture discharge map may include nodes, node features, edges and edge features, etc.

[0138] The nodes of the water discharge map are used to represent pipeline segments. The number of pipeline segments is the number of nodes. For example, Figure 3 As shown, the nodes may include node A, node B, node C, and node D, which respectively represent four pipeline segments of the gas pipeline.

[0139] The node features of the moisture discharge map reflect the characteristic information of the pipeline segment. In some embodiments, the node features may include the location information of the pipeline segment, the gas pipeline information, the drying medium information, and the moisture residual location. For more information about the location information of the pipeline segment, the gas pipeline information, the drying medium information, and the moisture residual location, please refer to Figure 3 And related instructions.

[0140] The edge of the moisture discharge graph is used to represent the connection relationship between two adjacent pipe segments. The direction of the edge can be the flow direction of the drying medium.

[0141] Edge features are used to describe the connection features between adjacent pipe segments. Edge features can include the diameter of the pipe segments where they meet.

[0142] In some embodiments, the gas company management platform 131 can construct a moisture discharge map based on at least one pipeline segment and moisture discharge data. For example, the gas company management platform 131 can determine at least one node and edge based on the location information of at least one pipeline segment and the gas pipeline information; use the location information of at least one pipeline segment, the gas pipeline information, the drying medium information and the residual moisture position as the node features of the node in the moisture discharge map; and use the moisture discharge direction in the moisture discharge data as the direction of the edge. Based on the location information in the node feature, the preset table is searched to determine the diameter of the junction of the pipeline segments, and it is used as the edge feature. The preset table includes pipeline diameters at different locations, and the preset table can be constructed based on the gas pipeline information. For information about gas pipeline information, please refer to Figure 1 Related instructions.

[0143] The dryness assessment model 330 is a model for determining a sub-dryness value 340 of at least one pipeline segment. The input of the dryness assessment model 330 may be the moisture discharge map 320, and the output may be a sub-dryness value 340 of at least one pipeline segment. In some embodiments, the dryness assessment model 330 may be a graph neural network (GNN) model.

[0144] In some embodiments, the dryness assessment model may be trained using a large number of first training samples and first labels corresponding to the first training samples.

[0145] In some embodiments, the first training sample includes a historical moisture discharge map of a sample pipeline constructed based on historical data of multiple gas companies. The first label is an actual dryness value corresponding to each pipeline segment in the first training sample. The actual dryness value refers to the actual dryness in the sample pipeline. For more information about the actual dryness value and its determination method, please refer to Figure 2 and related instructions.

[0146] In some embodiments, the drying assessment model can be trained by the following steps:

[0147] Step 1: Obtain a training data set, wherein the training data set includes a plurality of first training samples and a first label corresponding to each first training sample, wherein the training data set is a collection of training data from a plurality of gas companies.

[0148] Step 2, perform multiple rounds of iterations. At least one round of iterations includes: selecting one or more training samples from the training data set, inputting the one or more training samples into the drying assessment model, and obtaining the model prediction output corresponding to the one or more training samples; substituting the model prediction output corresponding to the one or more training samples and the labels of the one or more training samples into the formula of a predefined loss function to calculate the value of the loss function; and reversely updating the model parameters in the drying assessment model according to the value of the loss function, for example, the update can be performed based on the gradient descent method.

[0149] Step 3: When the iteration end condition is met, the iteration is ended to obtain a trained dryness evaluation model. The iteration end condition may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0150] The moisture discharge map can present the characteristics and connection relationship of each pipeline segment. The sub-dryness value of the pipeline segment is determined by the drying evaluation model based on the moisture discharge map, which helps to improve the accuracy and efficiency of predicting the sub-dryness value.

[0151] In some embodiments, for a gas company, the gas company management platform 131 can obtain detection data from the gas company management platform in response to the confidence of the initial dryness value being lower than the confidence threshold; determine a supplementary training data set for the dryness assessment model based on the detection data; and train the dryness assessment model based on the supplementary training data set to obtain the dryness assessment model of the gas company.

[0152] In some embodiments, the gas company management platform 131 may obtain detection data from the detection database of the gas company management platform in response to the initial dryness confidence of the gas company being lower than the confidence threshold. Figure 2 And related instructions.

[0153] The supplementary training data set refers to an extended training data set of a single gas company supplemented on the basis of the initial model training data set. The supplementary training data set includes multiple second training samples and a second label for each second training sample. For a gas company, the corresponding second training sample includes multiple historical moisture discharge maps constructed from multiple pipeline segments and moisture discharge data in the historical data obtained from the gas company, and the second label can be the actual dryness value of each pipeline segment corresponding to the second training sample.

[0154] The dryness assessment model of a gas company refers to a specific dryness assessment model of a gas company. When the gas company management platform 131 obtains the data of the gas company, the sub-dryness value of at least one pipeline segment can be determined through the dryness assessment model of the gas company based on the moisture discharge map.

[0155] In some embodiments, the gas company management platform 131 can train a dryness assessment model for the gas company based on a plurality of second training samples and a plurality of second labels in the supplementary training data set. For the specific training process, please refer to the above related description.

[0156] The amount of data for a single gas company is insufficient, so a general dryness assessment model is obtained through preliminary training of multiple gas companies. When the confidence of the initial dryness value of a gas company is insufficient, further training can be performed on the basis of the existing dryness assessment model by further obtaining a supplementary training data set for the gas company to obtain a model that is better suited to the situation of the gas company. This makes the sub-dryness value determined by the dryness assessment model more accurate.

[0157] Figure 4 is an exemplary flow chart for adjusting advanced drying parameters according to some embodiments of this specification. Figure 4 As shown, the process 400 includes steps 410 to 450. Steps 410 to 450 can be executed by the gas company management platform 131.

[0158] Step 410: Determine the water content in the target gas pipeline based on the initial dry value and the target gas pipeline information. Figure 2 And related instructions.

[0159] The target gas pipeline information is relevant information of the target gas pipeline. For example, the target gas pipeline information may include the length, diameter, material, service life, branches, joints, elbows, etc. of the target gas pipeline.

[0160] The water content in the target gas pipeline refers to the water content in multiple pipeline sections of the target gas pipeline, which is used to determine the required drying wind speed of the fan and the heating power of the heating wire.

[0161] In some embodiments, the gas company management platform 131 can calculate the pipeline volume of the target gas pipeline based on the diameter and length in the target gas pipeline information, and calculate the water content in the target gas pipeline based on the theoretical humidity and corresponding to the pipeline volume and initial dry value.

[0162] In some embodiments, the gas company management platform 131 may also calculate the water content of different pipeline sections of the target gas pipeline respectively.

[0163] Step 420: Determine the advanced drying parameters based on the moisture content. For a description of the advanced drying parameters, see Figure 1 .

[0164] In some embodiments, the gas company management platform 131 can determine the advanced drying parameters by the following methods: setting different pipeline segment starting points as the starting positions of advanced drying; setting the heating power of the heating wire in the blowing device according to the water content, the higher the water content, the higher the heating power; setting the drying wind speed and drying time of the fan in the blowing device according to the water content and the position of the pipeline segment, the higher the water content and the farther the position of the pipeline segment is from the pipeline outlet, the higher the drying wind speed and the longer the drying time. Among them, the pipeline segment starting point refers to the starting position of the flow direction of the drying medium.

[0165] Step 430 , obtaining first detection data at a first position before advanced drying, and evaluating a first dryness value of the target gas pipeline at the first position based on the first detection data.

[0166] The first position refers to the real-time position of the crawling robot at a certain pipeline segment of the target gas pipeline and the pipeline segment has not been dried. The first position can be represented by the position information of the pipeline segment where the crawling robot is located. For the position information of the pipeline segment, please refer to Figure 2 Related description: On the crawling route of the crawling robot, the pipeline segment before the first position has completed advanced drying.

[0167] The first detection data refers to the actual moisture data obtained by the crawling robot at the first position in the gas pipeline. For example, the first detection data may include air humidity, water accumulation, etc. of the pipeline segment at the first position.

[0168] In some embodiments, the first detection data can be obtained by a humidity sensor or an acoustic wave detector configured by the crawling robot.

[0169] The first dryness value refers to the sub-dryness value of the pipeline segment at the first position. The first dryness value may change due to the advanced drying process of the upstream pipeline segment. For example, if the air flow temperature blowing from the upstream pipeline segment is high during drying, it may take away the moisture at the first position, thereby increasing the first dryness value. The upstream pipeline segment may be the upstream (i.e., the starting point) of the drying medium flow sequence.

[0170] In some embodiments, the gas company management platform 131 can use the air humidity in the first detection data as the theoretical humidity and calculate the first dryness value using formula (1). For formula (1), see Figure 2 And related instructions.

[0171] Step 440: Generate a parameter adjustment instruction based on the first drying value.

[0172] The parameter adjustment instruction refers to instruction information for adjusting the advanced drying parameters. For example, the parameter adjustment instruction may include reducing and / or increasing the drying wind speed and heating power.

[0173] In some embodiments, the gas company management platform 131 can determine the first dryness value of different positions based on the first detection data, compare the first dryness value with the initial dryness value, and thus determine the adjustment instruction. For example, when the first dryness value is higher than the initial dryness value, the drying wind speed and heating power are reduced; when the first dryness value is lower than the initial dryness value, the drying wind speed and heating power are increased.

[0174] Step 450 , adjusting the advanced drying parameters of the second position based on the parameter adjustment instruction.

[0175] The second position refers to the gas pipeline section after the crawler robot is located in the running direction of the target gas pipeline. The second position is located after the first position. That is, the pipeline section located at the second position has not yet been advanced dried.

[0176] In some embodiments, the gas company management platform 131 may send a parameter adjustment instruction to the gas company object platform 150 , and the gas company object platform 150 adjusts the advanced drying parameters of the second location based on the parameter adjustment instruction.

[0177] The first drying value of the first position is determined according to the first detection data, and the drying effect of the advanced drying parameters is evaluated to adjust the advanced drying parameters of the second position. The influence of the advanced drying of the upstream pipeline on the downstream pipeline is taken into consideration, and the advanced drying parameters of the downstream pipeline to be advanced dried are adjusted in time according to the influence effect, so that the subsequent pipelines can present a better drying effect.

[0178] In some embodiments, the gas company management platform 131 can determine the natural drying time of the target gas pipeline at the second position based on the airflow drying effect and the second drying value; and delete the drying positions whose natural drying time is less than the preset time threshold from the advanced drying parameters.

[0179] The airflow drying effect refers to the drying effect of the airflow generated by the advanced drying on the downstream pipeline segment. For example, how much moisture can the airflow generated by the advanced drying remove from the downstream gas pipeline. The downstream pipeline segment can be the downstream of the drying medium flow sequence (i.e., the outlet).

[0180] In some embodiments, the gas company management platform 131 can determine the cumulative impact value of one or more pipeline segments on downstream pipeline segments during advanced drying based on the difference between the first drying value and the initial drying value of multiple upstream pipeline segments, and use the cumulative impact value as the airflow drying effect.

[0181] Cumulative impact refers to the cumulative impact of all the advanced drying operations in the upstream pipeline on the initial drying value of each pipeline segment. For example, from upstream to downstream, there are pipeline segments 1, 2, 3, 4, and 5. The cumulative impact of pipeline segment 2 is the initial drying value affected by the advanced drying of pipeline segment 1; the cumulative impact of pipeline segment 4 is the initial drying value affected by the cumulative impact of pipeline segments 1, 2, and 3 during advanced drying.

[0182] The cumulative impact value refers to the difference between the real-time dryness value after the cumulative impact and the dryness threshold. For more information about the dryness threshold, see Figure 2 Related instructions.

[0183] The second dry value refers to the sub-dry value of the pipeline segment at the second position. The sub-dry value refers to the initial dry value of the pipeline segment. For details, see Figure 2 Related instructions.

[0184] The natural drying time is used to reflect the time taken for the dryness value of the downstream pipeline segment to reach the dryness threshold value only due to the airflow generated by the advanced drying of the upstream pipeline segment. The natural drying time can be the time taken from the crawler robot entering the target gas pipeline to the dryness value of the downstream pipeline segment reaching the dryness threshold value due to the influence of the advanced drying of the upstream pipeline.

[0185] In some embodiments, the natural drying time can be determined by a variety of methods. For example, the gas company management platform 131 can determine the natural drying time of the second position by searching a preset table based on the airflow drying effect and the second drying value. The preset table includes a mapping relationship between the airflow drying effect, the second drying value, and the natural drying time. The preset table can be based on a historical data framework.

[0186] In some embodiments, the gas company management platform 131 can determine the natural drying time through the natural drying model based on the airflow drying effect, the location information of the multiple pipeline segments at the second location, and the second drying value. Figure 5 .

[0187] The preset time threshold is a critical value of the natural drying time. In some embodiments, the preset time threshold may be the time from when the crawling robot enters the target gas pipeline to when it reaches the pipeline segment. In some embodiments, the gas company management platform 131 may delete the drying position whose natural drying time is less than the preset time threshold from the advanced drying parameters. That is, the crawling robot does not dry the pipeline segment of the drying position whose natural drying time is less than the preset time threshold.

[0188] If the natural drying time is less than the preset time threshold, it means that the pipeline segment has completed natural drying before the crawling robot reaches the pipeline segment. The drying position where the natural drying time is less than the preset time threshold is deleted from the advanced drying parameters. The crawling robot does not need to stay in the pipeline segment that has completed natural drying, thereby improving efficiency and safety, while saving resources and costs.

[0189] Figure 5 is an exemplary schematic diagram of a natural drying model according to some embodiments of the present specification.

[0190] In some embodiments, Figure 5 As shown, the government gas supervision and management platform 110 can determine the natural drying time 530 through the natural drying model 520 based on the airflow drying effect sequence 511, the second position information sequence 512, and the second drying value sequence 513.

[0191] The airflow drying effect sequence 511 refers to a sequence of airflow drying effects corresponding to the plurality of pipeline segments at the second position. The second position information sequence 512 refers to a sequence of position information of the plurality of pipeline segments at the second position. For the position information of the pipeline segments, see Figure 2 Related description: The second dryness value sequence 513 refers to a sequence consisting of sub-dryness values ​​of multiple pipeline segments at the second position.

[0192] The natural drying model 520 is a model for predicting the natural drying time of the target gas pipeline at the second position. In some embodiments, the natural drying model is a machine learning model. For example, a deep neural network (DNN) model, etc. For details about the airflow drying effect, the second position, the second drying value, and the natural drying time, please refer to Figure 4 Related instructions; For information about the location of pipeline segments, see Figure 2 Related instructions.

[0193] In some embodiments, the natural drying model can be obtained by training a large number of third training samples and third labels corresponding to the third training samples. In some embodiments, a plurality of third training samples with third labels can be input into the initial natural drying model, and a loss function can be constructed by the third labels and the results of the initial natural drying model. The parameters of the initial natural drying model are iteratively updated based on the loss function by gradient descent or other methods. When the preset conditions are met, the model training is completed and a trained natural drying model is obtained. The preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0194] Each group of training samples in the third training samples may include a sample airflow drying effect sequence, a sample second position information sequence, and a sample second drying value sequence. The third training sample can be obtained through historical data, and the historical airflow drying effect sequence, historical second position information sequence, and historical second drying value sequence corresponding to the second position when the crawling robot is located in different pipeline segments of the target gas pipeline in the historical data are used as the third training sample. The third label corresponding to the third training sample is the sample natural drying time corresponding to each group of training samples. In some embodiments, the third label can be the actual natural drying time corresponding to the pipeline segment at the second position corresponding to the third training sample, which is subsequently measured and the real-time drying value is just greater than the drying threshold.

[0195] The actual natural drying time reflects the actual time taken by the pipeline segment to complete natural drying due to the advanced drying of the upstream pipeline. The actual natural drying time may be the time from the first moment to the second moment, where the first moment refers to the moment when the crawling robot enters the target gas pipeline, and the second moment refers to the moment when the real-time dryness value detected by the crawling robot in the pipeline segment is just greater than the dryness threshold. The second moment may be the moment when the crawling robot is in the process of performing advanced drying on the pipeline segment.

[0196] By predicting the natural drying time through the natural drying model, the accuracy of the prediction of the natural drying time of the downstream pipeline and the data processing speed can be improved.

[0197] In some embodiments, the training data set of the natural drying model includes training samples under various acquisition environments, and distribution parameters of the training samples under various acquisition environments are determined based on historical data.

[0198] The collection environment refers to the ambient temperature and humidity when the training samples are collected. The collection environment can be obtained based on the temperature sensors and humidity sensors arranged in the environment.

[0199] The distribution parameters of the training samples reflect the distribution of the training samples during collection. In some embodiments, the distribution parameters of the training samples include the coverage of the collection environment when the training samples were collected, and the proportion of the number of training samples collected under different collection environment steps.

[0200] The collection environment ladder can be set according to demand or experience. A collection environment ladder can be expressed as [(T1, T2), (W1, W2)], (T1, T2) represents the temperature range, and (W1, W2) represents the humidity range. Exemplarily, one step is set for temperature every 5°C and one step is set for humidity every 5%, and the collection environment ladder may include: [(10°C, 15°C), (50%, 55%)], [(10°C, 15°C), (55%, 60%)], [(10°C, 15°C), (65%, 70%)]... [(15°C, 20°C), (50%, 55%)], [(15°C, 20°C), (55%, 60%)], [(15°C, 20°C), (65%, 70%)]... [(20°C, 25°C), (50%, 55%)], [(20°C, 25°C), (55%, 60%)], [(20°C, 25°C), (65%, 70%)]...

[0201] In some embodiments, the gas company management platform 131 may use the range covered by the historical collection environment data during drying in the historical drying records as the collection environment coverage range.

[0202] In some embodiments, the collection environment gradient can be set based on the distribution density of the historical collection environment data in the historical drying record. For the environment data interval with low distribution density, a collection environment gradient with a larger span can be set. For example, conventionally, a temperature gradient is set every 5°C, but 0-20°C rarely appears in the historical collection environment, so the span of this environment data interval can be directly set to set a temperature gradient every 10°C.

[0203] In some embodiments, the data proportions of training samples collected in different collection environment stages can be set in equal proportion.

[0204] By collecting training samples from a variety of collection environments, the diversity of training data can be ensured to improve the universality of the model in different environments.

[0205] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present invention. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and corrections to the present invention. Such modifications, improvements and corrections are suggested in the present invention, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present invention.

[0206] At the same time, the present invention uses specific words to describe the embodiments of the present invention. For example, "some embodiments" means a certain feature, structure or characteristic related to at least one embodiment of the present invention. Therefore, it should be emphasized and noted that "some embodiments" mentioned twice or more in different positions in the present invention do not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present invention can be appropriately combined.

[0207] In addition, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in the present invention are not intended to limit the order of the processes and methods of the present invention. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0208] Similarly, it should be noted that in order to simplify the description of the present invention and thus facilitate the understanding of one or more embodiments of the invention, in the above description of the embodiments of the present invention, multiple features are sometimes combined into one embodiment, figure or description thereof. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above.

[0209] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the present invention are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present invention are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0210] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in the present invention are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the present invention, documents that limit the broadest scope of the present invention (currently or later attached to the present invention) are also excluded. It should be noted that if the description, definition, and / or use of terms in the accompanying materials of the present invention are inconsistent or conflicting with the contents of the present invention, the description, definition, and / or use of terms of the present invention shall prevail.

[0211] Finally, it should be understood that the embodiments described in the present invention are only used to illustrate the principles of the embodiments of the present invention. Other variations may also fall within the scope of the present invention. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present invention may be considered consistent with the teachings of the present invention. Accordingly, the embodiments of the present invention are not limited to the embodiments explicitly introduced and described in the present invention.

Claims

1. A pipeline drying method based on smart gas safety supervision, characterized in that: The method is performed by a pipeline drying processing Internet of Things system based on smart gas safety supervision, and the method includes: Through the gas company management platform: Obtaining drying medium information of at least one gas pipeline outlet; Based on the drying medium information, determining an initial drying value of the gas pipeline; In response to the initial dryness value of at least one gas pipeline being lower than a dryness threshold, taking the at least one gas pipeline as a target gas pipeline, and determining an advanced drying parameter based on the initial dryness value of the target gas pipeline; Generate a first control instruction based on the advanced drying parameter, and send the first control instruction to the gas company object platform, and the gas company object platform performs advanced drying on the target gas pipeline based on the first control instruction; Acquire the detection data of the target gas pipeline during advanced drying and send it to the government gas supervision and management platform; Through the government gas regulatory management platform: Based on the detection data during the advanced drying, evaluating the confidence of the initial drying value; Based on the confidence level of the initial dryness value, generating a threshold adjustment instruction, and sending the threshold adjustment instruction to the gas company management platform, so that the gas company management platform updates the dryness threshold; Based on the confidence level of the initial dryness value, a performance adjustment instruction is generated.

2. The method according to claim 1, characterized in that: The drying medium information further includes a drying medium flow rate. The determining of the initial drying value of the gas pipeline based on the drying medium information includes: Determining moisture discharge data in the gas pipeline based on the drying medium information; Based on the moisture removal data, the initial dryness value is determined.

3. The method according to claim 2, characterized in that: The gas pipeline includes at least one pipeline segment, the initial dryness value includes a sub-dryness value of the at least one pipeline segment, and the method further includes: Based on the gas pipeline information, the gas pipeline is segmented and the location information of at least one pipeline segment is determined; The sub-dryness value of the at least one pipeline segment is determined based on the position information of the at least one pipeline segment and the moisture discharge data.

4. The method according to claim 2, characterized in that: The method further comprises: Determining an actual dryness value of the target gas pipeline based on the detection data of the target gas pipeline; Determining a correction value based on the actual drying value and the initial drying value; The initial dryness value of the candidate gas pipeline is corrected based on the correction value.

5. The method according to claim 1, characterized in that: The step of determining the advanced drying parameter based on the initial drying value of the target gas pipeline includes: Determining the water content in the target gas pipeline based on the initial dry value and the target gas pipeline information; Based on the moisture content, determining the advanced drying parameter; Acquire first detection data of a first position before advanced drying, and evaluate a first drying value of the target gas pipeline at the first position based on the first detection data; generating a parameter adjustment instruction based on the first drying value; The advanced drying parameter of the second position is adjusted based on the parameter adjustment instruction.

6. A pipeline drying processing Internet of Things system based on smart gas safety supervision, characterized in that: It includes a government gas supervision management platform, a government gas supervision sensor network platform, a government supervision object platform, a gas company sensor network platform and a gas company object platform, wherein the government supervision object platform includes a gas company management platform; The gas company management platform is configured as follows: Obtaining drying medium information of at least one gas pipeline outlet; Based on the drying medium information, determining an initial drying value of the gas pipeline; In response to the initial dryness value of at least one gas pipeline being lower than a dryness threshold, taking the at least one gas pipeline as a target gas pipeline, and determining an advanced drying parameter based on the initial dryness value of the target gas pipeline; Generate a first control instruction based on the advanced drying parameter, and send the first control instruction to the gas company object platform, and the gas company object platform performs advanced drying on the target gas pipeline based on the first control instruction; Acquire the detection data of the target gas pipeline during advanced drying, and send it to the government gas supervision and management platform; The government gas supervision and management platform is configured as follows: Based on the detection data during the advanced drying, evaluating the confidence of the initial drying value; Based on the confidence level of the initial dryness value, generating a threshold adjustment instruction, and sending the threshold adjustment instruction to the gas company management platform, so that the gas company management platform updates the dryness threshold; Based on the confidence level of the initial dryness value, a performance adjustment instruction is generated.

7. The system according to claim 6, characterized in that: The drying medium information also includes a drying medium flow rate, and the gas company management platform is further configured as follows: Determining moisture discharge data in the gas pipeline based on the drying medium information; Based on the moisture removal data, the initial dryness value is determined.

8. The system according to claim 7, characterized in that: The gas pipeline includes at least one pipeline segment, the initial dry value includes a sub-dry value of the at least one pipeline segment, and the gas company management platform is further configured as follows: Based on the gas pipeline information, the gas pipeline is segmented and the location information of at least one pipeline segment is determined; The sub-dryness value of the at least one pipeline segment is determined based on the position information of the at least one pipeline segment and the moisture discharge data.

9. The system according to claim 7, characterized in that: The gas company management platform is further configured as follows: Determining an actual dryness value of the target gas pipeline based on the detection data of the target gas pipeline; Determining a correction value based on the actual drying value and the initial drying value; The initial dryness value of the candidate gas pipeline is corrected based on the correction value.

10. The system according to claim 6, characterized in that: The gas company management platform is further configured as follows: Determining the water content in the target gas pipeline based on the initial dry value and the target gas pipeline information; Based on the moisture content, determining the advanced drying parameter; Acquire first detection data of a first position before advanced drying, and evaluate a first drying value of the target gas pipeline at the first position based on the first detection data; generating a parameter adjustment instruction based on the first drying value; The advanced drying parameter of the second position is adjusted based on the parameter adjustment instruction.

Images